Mobile Edge Computing (MEC) is a key technology for enabling energy-efficient and low-latency processing of computation-intensive applications through task offloading. However, current frameworks typically model dependent tasks using static Directed Acyclic Graphs (DAGs), which are poorly suited to dynamic edge environments characterized by fluctuating resources and diverse QoS demands. These fixed DAG structures often fail to adapt to runtime changes in bandwidth or node workload, leading to frequent task failures or inefficient resource usage. To overcome these limitations, we propose Dynamic Application Configuration, a paradigm that allows applications to switch between multiple predefined DAG variants at runtime. This enables the system to dynamically balance accuracy and resource efficiency at critical decision points by adapting to current network and computing conditions. Based on this concept, we design the Dynamic Application Configuration and Capacityaware task offloading System (DACCS), which employs a two-step offloading strategy: (i) a Dynamic Graph Selection (DGS) algorithm that adaptively adjusts application configurations during key subtask execution based on real-time resource states, and (ii) a dependency-aware offloading algorithm (DAP) that optimizes offloading assignments by jointly optimizing the application completion rate, processing delay and effective utilization rate. Experiments and real-system validations demonstrate that DGS improves the service performance across multiple strategies. Furthermore, the proposed DGS-DAP strategy outperforms other benchmark approaches under dynamic conditions.

As a prevalent field of study in machine learning, intelligent agents can perceive surroundings and make informed decisions. In many research areas such as autopilot systems, undersea explorations, and distributed robotics, researchers have traditionally employed unidirectional systems, which usually rely on perceptions from sensors to controllers, or end-to-end models, which generate actions directly from raw data. Nonetheless, in unidirectional systems, controller efficiency is intrinsically linked to sensor accuracy, which makes unidirectional systems lack a self-improving capability. Meanwhile, compared with functionally separated frameworks, end-to-end methods may have their own limitations in scalability, generality, interoperability, training costs, and so on. To fulfill this gap, we propose a new Coordinated Optimization Framework for Intelligent Agents (COIA). We introduce an inverted optimization channel from controllers to sensors in traditional functionally separated frameworks through communication between devices, enabling closed-loop online evolutive learning. To the best of our knowledge, this paper first presents a universal coordinated optimization framework among supervised learning and RL models, without human labels or intervention. Our method allows heterogeneous agents to autonomously adapt to some special situations in open environments, which forms a basis of networked Artificial General Intelligence (AGI). We design an experimental paradigm of COIA with concrete cases, which shows a significantly large performance margin over unidirectional and end-to-end models. The performance margin grows with task complexity.

The criticality of efficient traffic forecasting in Intelligent Transportation System (ITS) has garnered significant academic attention. This study addresses the prevalent issue of distribution shift in real-world datasets, which often degrades performance, and explores the effectiveness of the channel-independence (CI), a technique recently proposed to mitigate this issue. While Spatio-Temporal Graph Neural Networks (STGNNs) are noted for their flexibility to represent road structures, their designs typically lack the capability to integrate CI without disrupting the spatial relationships, potentially limiting the performance. We present a novel approach that successfully integrates CI into spatial-temporal forecasting by incorporating distinct temporal, spatial, and predefined graph structure information within each channel. Moreover, STGNNs frequently emphasize intricate designs, which result in increased computational demands while offering only marginal improvements in accuracy. This paper presents ST-MLP, a streamlined spatio-temporal model constructed exclusively from cascaded Multi-Layer Perceptron (MLP) modules and linear layers. Experimental results indicate that ST-MLP outperforms numerous existing STGNNs in both accuracy and computational efficiency. Our findings advocate for further investigation into more streamlined and effective neural network architectures within spatial-temporal forecasting research.

In open underwater environments, ensuring accurate positions of sensors while protecting private information of localization systems presents a significant challenge. The physical channel differences between terrestrial and underwater networks render most existing privacy protection schemes designed for terrestrial networks inapplicable underwater. Moreover, limited research on underwater privacy protection has led to high implementation complexity and communication expenses. In this paper, to reduce the complexity of privacy protection, a secure mobile localization scheme using autonomous underwater vehicles (AUVs) as anchors is proposed for underwater sensor networks, based on adversarial neural cryptography utilizing acoustic channel features. Depending on whether eavesdroppers show interest in keys, two adversarial cryptography models are proposed to protect transmission of legitimate localization information and to actively counter eavesdroppers with learning capabilities in real time. Furthermore, to obtain effective keys and minimize unnecessary key transmission, random physical layer channel features are dynamically utilized as real-time keys for the cryptography system, and a synchronous channel probing protocol is designed for key generation. Simulation and experimental results demonstrate that, compared to other approaches, the proposed secure localization scheme effectively prevents the leakage of position information and maintains localization accuracy while operating at lower implementation complexity and communication expenses.

Fountain codes with online adaptation (OFCs) are promising for underwater acoustic sensor networks (UASNs), since they exploit limited feedback to reduce transmission over head. Yet, the performance of conventional OFCs is severely degraded in UASNs due to high error rates, long propagation delays, and sparse feedback, resulting in poor recovery efficiency and high energy cost. To address these challenges, we propose an energy-aware dual-perception OFC framework driven by deep reinforcement learning (DRL-OFC). In this design, a DRL agent jointly perceives channel dynamics and feedback sparsity to learn an optimal degree distribution that suppresses redundant coding and enhances intermediate decoding. In addition, a feedback aware transmission strategy is developed to cope with the long delay characteristics of UASNs, further reducing unnecessary retransmissions. Simulation results show that DRL-OFC achieves significant gains over existing OFC schemes in terms of decoding efficiency, transmission overhead, recovery performance, and energy consumption, confirming its suitability for resource constrained underwater communications.

A persistent risk in many underwater localization solutions is the leakage of position information, since anchor positions are revealed to the sensors performing position estimation. While cryptography-based secure localization mechanisms for underwater acoustic sensor networks (UASNs) can protect the privacy of anchors, varying levels of privacy preservation impact localization accuracy. Therefore, it is necessary to derive a quantitative relationship between privacy preservation levels and localization accuracy. In this paper, we first model the probability density function (PDF) of anchor decoding errors under privacy preservation constraints when anchors adopt an encrypted system to safeguard position information. The model parameters are optimized using the expectation-maximization (EM) algorithm. Next, based on the ranging PDF and anchor decoding error PDF distribution, we derive the position error bound (PEB) function that links privacy preservation levels with target localization accuracy. Simulation and field experiment results validate the effectiveness of the theoretical model.

With the increasing deployment of Underwater Acoustic Sensor Networks (UASNs) in various marine applications, ensuring network security has become a significant concern. Trust models offer an adaptive security mechanism for such networks. This paper proposes a dual-layer trust model (DLtrust) based on digital twin (DT) architecture. First, a network framework is constructed using DTs, in which the Local DT employs an adaptive long short-term memory (LSTM) algorithm to detect conventional attacks, providing the primary defense mechanism. DLtrust further interacts with the Cloud DT in real time to obtain the optimal weighting of trust evidence, thereby accelerating model convergence. Additionally, a reinforcement learning scheme is integrated into the Cloud DT to optimize dynamic trust evaluation and refine the evidence aggregation strategy of the Local DT. By continuously perceiving the global network status and adjusting trust parameters, the Cloud DT effectively guides the Local DT to detect anomalous behavior, especially in cases of compromised models. To enhance resilience against Byzantine attacks, the model incorporates the multi-Krum algorithm, strengthening advanced defense capabilities. Simulation results demonstrate that DLtrust outperforms existing trust models in terms of average detection accuracy and error rate.

Accurate traffic flow prediction is crucial for intelligent transportation systems supporting emerging applications such as autonomous driving and vehicle-infrastructure cooperation. However, existing methods often struggle to effectively disentangle the inherent trend, seasonal, and noise components within traffic flow data, thereby limiting prediction accuracy. To address this issue, we propose MF-AttnBiLSTM, a novel hybrid framework combining signal processing and temporal attention-based deep learning model through a decompose-then-predict strategy. Our approach first employs moving average to extract the trend component and discrete Fourier transform to isolate dominant seasonal patterns from the residuals. Subsequently, a dual-stream architecture utilizes multi-head self-attention-enhanced bidirectional LSTMs to independently model the temporal dynamics of the decomposed trend and seasonal components. The final prediction aggregates the outputs from both streams. Extensive experiments on PeMS04 and PeMS07 datasets demonstrate that MF-AttnBiLSTM significantly outperforms state-of-the-art baselines and exhibits robustness across varying traffic conditions. Ablation studies further confirm the efficacy of each component, particularly highlighting the significant contribution of the signal decomposition stage to overall performance improvement.

Multi-agent collaborative perception enables a single agent to perceive the comprehensive scene by exchanging sensory information using vehicle-to-everything communication. However, the communication resources of real-world communication systems are often limited. It fails to satisfy the real-time transmission of extensive data, which restricts the deployment of collaborative perception. To address the issue, we propose ComSH, a Communication-efficient multi-agent collaborative perception method based on Spatio-temporal Heterogeneity to achieve a trade-off between performance and bandwidth. Specifically, we consider the spatio-temporal heterogeneity to perform feature filtering, thus reducing the redundancy of transmitted features. First, it introduces valuable temporal semantics to enhance the current representation of each agent. Secondly, we consider the spatial confidence of each agent at each location and the relative position to obtain high confidence and complementary features. Eventually, a foreground object adaptive activation module is designed to enrich the visual representation of fused features. Therefore, ComSH enables different agents to transmit their critical and complementary perception information, thus reducing bandwidth consumption. We conduct experiments on collaborative detection tasks on the two datasets. Experimental results demonstrate the ComSH’s superiority and effectiveness.

Underwater acoustic sensor networks (UASNs) constitute the primary infrastructure for the Internet of Underwater Things (IoUT), but they face constraints in high-rate reliable transmission due to the complex underwater acoustic (UWA) channel characteristics and the scarce pilot resources. Orthogonal frequency division multiple access (OFDMA) has been widely adopted in UASNs owing to its capability for multi-user parallel transmission and flexible resource allocation. However, the severely limited and non-uniformly distributed pilots pose significant challenges for multi-user channel estimation in OFDMA-based UASNs. To address these challenges, this paper establishes a compressed sensing (CS)-based multi-user channel estimation model for OFDMA-based UASNs. Considering the significant variations in channel conditions among different UWA links, we propose an adaptive pilot allocation method that dynamically optimizes the number of pilots assigned to each user. Building on this, we further propose a bi-objective joint pilot position and power optimization (BOJPO) algorithm, which simultaneously minimizes both the mutual coherence and total coherence of the measurement matrix to enhance estimation accuracy. Simulation and sea experiment results demonstrate that the proposed pilot optimization scheme exhibits superior performance, delivering stable and reliable channel estimation for OFDMA-based UASNs despite severely scarce pilot resources.

Adverse weather conditions significantly challenge scene understanding of autonomous vehicles by degrading perception system performance. Despite advancements, the impacts of such conditions still require further investigation. In this paper, we propose a novel approach that leverages the advantages of Radar sensors against various weather types to improve robustness under foggy weather. Our framework refines Radar measurements through the Bayesian Filtering algorithm to enhance data quality and sparsity, generating informative representations as probabilistic Occupancy Grid Maps (OGM). We address sensor synchronization challenges to ensure accurate fusion across different modalities. We evaluate our framework and the effectiveness of the OGMs fused with LiDAR data under various fog densities. The experimental results demonstrated improvements in robustness and reduced detection errors when compared with LiDAR-only object detection.

Autonomous driving (AD) systems requires multisensor collaboration to address challenges caused by complex weather scenarios. The recognition accuracy of autonomous driving system based on single resource, either on image only or Lidar only, becomes unreliable due to untested weather conditions, occlusions objects, and other factors. This paper proposes a decision-level fusion network based on an improved YOLOV7 and an improved CenterPoint network to build a multi-sensor-collaboration scheme. The overall accuracy of the proposed fusion algorithm is improved for small targets by adding multi-scale and multi-stage attention channel modules into the backbones of image recognition network and point cloud recognition network respectively. Moreover, the fusion algorithm introduces mixed distance constraints as the loss function for overlapping targets. The proposed fusion algorithm has been successfully tested on the public ONCE dataset mixed with a self-built dataset under various road conditions such as sunny, night, and rainy weather. The mAP of proposed decision-level fusion algorithm achieves$\mathbf{8 3. 5 \%}$in sunny daytime,$\mathbf{8 0 \%}$during nighttime and 79.1 % during rain time.

Underwater Wireless Sensor Networks (UWSNs) have attracted considerable attention due to their critical roles in ocean data acquisition, marine exploration, and disaster prevention. As diverse underwater applications continue to emerge, there has been a significant increase in both the volume and variety of sensed data. This necessitates reliable and efficient data transmission to data centers, particularly given the challenging underwater environment. To address these demands, this paper introduces EVAOR: an Efficient and Void-Avoidable Opportunistic Routing Protocol based on the Genetic Algorithm (GA). EVAOR incorporates four key strategies to optimize routing performance. First, it implements an Enhanced Local Topology Awareness Mechanism to generate a high-quality initial population, accelerating the convergence of the GA. Second, a novel crossover scheme and scaling function are employed to enhance the GA’s search efficiency. Third, a multi-factor fitness function is designed to leverage local topological information, ensuring high-quality chromosome generation. Finally, a multiarmed bandit-based depth adjustment algorithm is proposed to optimize void node positioning, effectively restoring nodes from void zones and improving overall network performance. Experimental results demonstrate that EVAOR surpasses existing routing protocols in terms of packet delivery ratio and end-to-end delay, with the depth adjustment algorithm showing superior efficiency compared to traditional depth adjustment techniques.

The growing demands for low-latency and secure communication in vehicular networks necessitate reliable mobility management protocols. In this paper, we propose a proactive, hierarchical mobility management protocol designed to enhance the security of vehicular networks during handover processes. Our protocol emphasizes early registration and pre-authentication to mitigate risks associated with rapid vehicle mobility, such as impersonation, replay attacks, and data breaches. We evaluate the protocol’s effectiveness against common security threats in mobility management using real-world mobility traces.

In Wireless Multimedia Sensor Networks (WMSNs), maximizing network lifetime is a critical challenge due to the high energy demands of video processing and communication. Key factors influencing energy consumption include source coding parameters, the reliability and capacity of communication links, and routing strategies. Since the size of compressed multimedia data—particularly video—is inversely related to its visual quality, a trade-off naturally emerges between data volume and user-perceived quality. This paper addresses the problem of determining optimal coding and routing parameters that extend the network’s operational lifespan while maintaining the required visual quality at the sink and adapting to the dynamic nature of wireless links (e.g., fluctuating capacity and reliability). We propose a fully distributed and adaptive solution tailored to WMSNs. Our approach dynamically adjusts link utilization based on real-time reliability assessments and the residual energy of intermediate nodes. This ensures energy-efficient routing under both stable and perturbed network conditions. Extensive simulations demonstrate that our solution can prolong network lifetime by up to 9.76 times in ideal conditions and by approximately 5 times in the presence of network perturbations, while incurring only 0.16% of total battery energy as overhead. Moreover, the approach is shown to be highly responsive to topology changes, confirming its suitability for real-world WMSN deployments.

Online Fountain Codes (OFCs) adapt their encoding strategy to decoder feedback, making them attractive for Underwater Acoustic Sensor Networks (UASNs) with stringent delay and energy constraints. Yet, conventional OFCs perform poorly under the harsh conditions of UASNs, where high error rates, long propagation delays, and limited feedback severely restrict efficiency. This work identifies two key challenges: balancing recovery efficiency with intermediate decoding, and reducing encoding and decoding complexity under sparse feedback. To address them, we propose a Dual-Perception Fountain Code framework based on Deep Reinforcement Learning (DRL-OFC). A DRL agent learns optimized degree distributions to reduce redundant packets and improve decoding, while a feedback-aware strategy adapts transmissions to UASNs conditions. Simulations show that DRL-OFC achieves lower overhead, stronger intermediate recovery, fewer coded packets, and better energy efficiency than existing OFC schemes, confirming its suitability for resource-constrained underwater networks.

To address the pressing demands of marine resource exploration, this paper investigates the problem of node localization in underwater acoustic wireless networks and proposes a two-stage progressive collaborative optimization framework to overcome the performance limitations of the traditional DV-Hop algorithm. Error sources of DV-Hop in underwater scenarios are systematically analyzed, and a quantitative localization model, NSGA-II-DV-Hop, is established to incorporate both hop count estimation errors and position calculation errors. Based on this analysis, a two-stage optimization strategy is developed. In the first stage, an adaptive particle swarm optimization model, PSO-DV-Hop, is designed, where a dynamic inertia weight adjustment mechanism enhances global search efficiency, thereby reducing localization error and energy consumption. In the second stage, a Pareto-Based evolutionary optimization model, NSGA-II-DV-Hop, is introduced to realize simultaneous optimization of localization accuracy and energy efficiency through Pareto frontier analysis. Experimental results demonstrate that PSO-DV-Hop improves localization performance by reducing the average error by 18.2% and lowering the number of convergence iterations by 61%. Building on this, NSGA-II-DV-Hop further extends the network lifetime by 26.9%, reduces average node energy consumption by 10.07%, and achieves an additional 8.67% energy optimization.

This study explores the integration of Machine Learning (ML) techniques for the classification of traffic signs within simulated vehicular environments. Specifically, the research investigates and compares two training paradigms: centralized learning, enhanced through Transfer Learning (TL) to leverage pre-trained knowledge and reduce training time, and Federated Learning (FL), a decentralized method that allows for collaborative training across distributed nodes. The work involves the implementation and evaluation of two deep learning (DL) models: a classical CNN architecture from existing literature (LeNet-5) and a custom-designed CNN model tailored for vehicular contexts. This study contributes to developing cooperative learning frameworks between vehicles and infrastructure, aiming to enhance traffic safety and efficiency.

In harsh underwater environments, the localization of network nodes faces severe challenges due to open deployment environments. Most existing underwater localization methods suffer from privacy leaks. However, privacy protection schemes applied in terrestrial networks are not viable for underwater acoustic networks due to stratification effects and multipath complexities. In this paper, we introduce a secure localization scheme for underwater wireless sensor networks (UWSNs) utilizing cooperative beamforming among mobile underwater anchor nodes. With this scheme, the underwater sensor communicates and ranges with mobile anchor nodes to perform self-localization via time difference of arrival (TDOA) algorithm. However, the presence of eavesdroppers poses a threat by intercepting information emitted by the anchors. To avoid localization information leakage, then we model the secure localization requirement as a multi-anchors multi-objective dual joint optimization problem to enhance both security and energy performance. The deep reinforcement learning (DRL)-based multi-agent deep deterministic policy gradient (MADDPG) algorithm is applied to solve the optimization problem. Both simulation and field experimental results robustly validate the efficiency and accuracy of the proposed secure localization scheme.

In the realm of underwater wireless communication, vast oceanic expanses often demand large-scale deployment of Underwater Wireless Sensor Networks (UWSNs). UWSNs rely on acoustic communication channels, presenting distinct challenges like prolonged propagation delays, restricted bandwidth, and dynamic topologies. Furthermore, the far-reaching and multi-path nature of acoustic signals results in significant hidden terminal problems and ubiquitous interference between neighboring nodes. Therefore, an efficient medium access control (MAC) protocol is crucial for optimizing UWSN performance. This article proposes IC-MAC, a MAC protocol tailored for UWSNs to avoid collisions and improve network performance. IC-MAC employs distributed clustering to group sensor nodes and the cluster head degree is defined for each node, which is a coefficient that accentuates nodes characterized by a higher incidence of collision associations. To identify interfering nodes and construct an interference-free graph, an interference identification algorithm is proposed. In addition, a heuristic graph coloring technique, guided by particle swarm optimization, allocates time slots efficiently to achieve collision-free transmission scheduling and enhanced spatial reuse. Simulations demonstrate the effectiveness of the IC-MAC protocol in enhancing throughput, reducing delay, and improving packet delivery ratio and energy efficiency. This is achieved through efficient spatial resource utilization and robust management of collisions and interference, specifically tailored for underwater acoustic channels, outperforming existing MAC protocols.

In most existing underwater localization solutions, the risk of position information leakage persists, as anchor positions are revealed to the sensors performing position estimation. Conventional privacy protection methods designed for terrestrial networks often fail underwater due to the unique characteristics of the physical channels. Moreover, solutions proposed for the limited research on underwater privacy protection introduce expensive equipment costs and communication expenses. To tackle these challenges and reduce costs, this paper proposes a novel secure localization scheme tailored for underwater acoustic sensor networks (UASNs) based on adversarial neural cryptography utilizing acoustic channel features. The proposed scheme introduces an adversarial cryptography model to safeguard the transmission of legitimate localization data and dynamically counter eavesdroppers with learning capabilities in real-time. Furthermore, to obtain effective keys and minimize unnecessary key transmission, the scheme strategically employs channel features as cryptographic keys. Simulation results validate the effectiveness of this approach, demonstrating its ability to prevent the leakage of positional data, maintain localization precision, and operate with reduced hardware expenses and communication overhead compared to conventional methods.

Autonomous driving technology has become increasingly important in recent years, with the potential to revolutionize transportation systems and improve road safety. Vision-based methods have long been used in this field, but the major challenges in object detection are efficiency and occlusion. To address this challenge, anchor-free collaborative detection has been proposed as a promising solution. Despite its potential, there has been limited research on this approach. This study proposes an efficient vision-based multi-view object detection and localization method that leverages anchor-free collaborative detection to improve the accuracy of pedestrian detection. The method first generates feature maps to extract the head and foot of pedestrians and then applies spatial aggregation to fuse information from different views. Additionally, the study examines the efficiency of different convolutional neural network architectures for the feature map extraction model and identifies ResNet18 and ResNet34 as the most efficient models for the task. The proposed method has the potential to significantly improve the accuracy of pedestrian detection and localization in autonomous driving scenarios, which is critical for ensuring safety. Overall, this work contributes to the development of vision-based methods for autonomous driving and has significant implications for the future of transportation technology.

Underwater Wireless Sensor Networks (UWSNs) are integral to marine exploration yet confront significant security concerns. In contrast to terrestrial WSNs, underwater acoustic channels are characterized by their constrained bandwidth, considerable propagation delays, and a higher bit error rate. These factors facilitate adversaries’ ability to intercept network transmissions and acquire sensitive data. Furthermore, the constraints of energy resources in UWSNs pose additional challenges in harmonizing privacy preservation with energy conservation. This study introduces a novel Privacy-Preserving Data Fusion Algorithm (DSPDA) tailored for UWSNs. The DSPDA circumvents the shortcomings of conventional privacy algorithms by employing dynamic sharding to minimize transmission demands and augment data fusion precision, which adjusts the size of data shards relative to nodal distances, thereby safeguarding confidentiality. Furthermore, it enhances network-wide energy optimization by aligning the energy consumption of cluster heads with their respective child nodes, thus averting disproportionate energy depletion and potential network dysfunction. Our simulation results demonstrate that the DSPDA algorithm notably diminishes communication overhead by approximately 37% in comparison to the SMART algorithm and delivers a further 20% efficiency improvement over the EEHA algorithm.

As one of the research objects in machine learning, agents are endowed with the ability to perceive and make decisions. In order to meet the needs of different applications, many researchers focus on algorithms for controlling agents. In most current paradigms, the control algorithms take the information of the surrounding environment as input and output actions. However, under the influence of this unidirectional data flow, the upper limit of the performance of control algorithms depends on the accuracy and fit measure of the environment information. Even though recent end-to-end control algorithms take the environmental raw data as input and reduce the influence of perception performance on it, the raw data acquisition method is still fixed, therefore, the performance of these control algorithms is still limited by the environmental information acquisition scheme. Meanwhile, although most control methods have the ability to update parameters online, they usually do not have the ability to optimize the acquisition of environmental information, and there may be unknown situations that are not in the data set used for pre-training. As a result, current methods cannot handle detection inaccuracies and unknown situations, and lack the ability to further improve their own performance online. In order to resolve the deficiency of the traditional control paradigms, we introduce the reverse optimization channel from the controller to the environmental information acquisition scheme to form a new algorithm through communication between devices. Experiments show that our method has significant performance margin and universal online evolutive learning ability, as compared to traditional paradigms.

This article investigates the influence of limited information on the efficacy of traffic signal control algorithms for supporting Intelligent Transportation Systems. Our project has collected several classic and trending intelligent traffic signal control schemes and evaluated algorithmic performance under constrained data conditions. In these simulating scenarios, access to certain traffic data is restricted. The findings reveal that although information scarcity generally degrades algorithm performance, algorithms that perform well with comprehensive data maintain their superiority even in data-limited environments. This underscores the necessity of designing resilient algorithms capable of adapting to varying levels of information availability, offering valuable insights for developing robust traffic control systems.

Underwater Acoustic Sensor Networks (UASNs) have garnered significant interest over recent decades, yet they continue to confront substantial challenges concerning security and privacy. The inherent openness of acoustic communication in such networks introduces profound risks to node privacy and overall network security. External attackers are capable of retracing data streams to identify the source node, thus jeopardizing the confidentiality of the data origin. Notably, the subtleties of passive attacks in UASNs render them more elusive compared to active attacks. Furthermore, conventional research often fails to reconcile security needs with energy efficiency. Addressing these concerns, this paper concentrates on mitigating passive attacks in UASNs while striving to harmonize security with network performance. We introduce a Source Location Privacy Scheme based on the Multi-Armed Bandit and Pseudo-packet Scheduling for UASNs (MP-SLP). The methodology commences with the sink node executing geographic data acquisition and neighbor node identification using a flood-based technique. Subsequently, through a Multi-Armed Bandit (MAB) framework, the source node designates an intermediate node for data packet transmission. The sink node then employs a location-aware opportunistic routing strategy to establish authentic routes that combine both randomness and reduced energy consumption for the transmission of actual packets. Alongside, branch nodes implement a pseudopacket scheduling tactic aimed at obstructing adversarial efforts to track source locations. Simulation results demonstrate that the proposed scheme proficiently moderates additional energy consumption, maintaining them within acceptable limits, while safeguarding location privacy.

As the realms of Connected Automated Vehicles (CAVs) and the Internet of Vehicles develop, the ability to accurately forecast vehicle motions takes center stage in shaping the future of intelligent transportation systems, integrating vehicles harmoniously into a connected, data-driven ecosystem. Never-theless, vehicle motion forecasting for CAVs faces considerable challenges, including handling multimodal behavior and effectively considering the complex interactions between surrounding agents. To mitigate these challenges, we design an innovative Transformer-based model for Motion Forecasting (TMF) that takes into account the uncertainty in human driving behavior and the complex interactions between agents. More specifically, we explic-itly integrate map constraints by extracting agent-lane temporal and spatial interrelated features. Our transformer-based encoder benefits from an attention mechanism to enable social interactions, effectively acquiring meaningful representations of these scene elements to attain precise predictions. The evaluation results over the extensive Argoverse Motion Forecasting dataset demonstrate that TMF achieves higher performance when compared to several state-of-the-art models.

The Internet of Drones (IoD) is expected to revolutionize the utilization of drones in urban environments. Drone delivery applications are expected to become commonplace in people's everyday lives. Such applications will establish a network where drones will have organized airspace access, with variations in network node density based on location and time. Within this environment, the IoD network may encounter communication gaps among drones. In scenarios like drone delivery, altering a drone's route solely for message delivery within the network is impractical. We aim to deploy an auxiliary drone network to support IoD applications, similar to using auxiliary networks in vehicular networks for message delivery. This study introduces the AuxIoD method, which utilizes a genetic algorithm to position auxiliary drones strategically, bridging communication gaps within the IoD network. Compared to other strategies, our approach facilitated the delivery of approximately 30% more messages in the evaluated scenario.

COVID-19 has become the most devastating infectious disease of the 21st century. Governments worldwide devised a range of policies to control the pandemic and reduce losses in multiple aspects. To make timely and wise decisions, a thorough analysis of policies with reliable statistical evidence is crucial. Obtaining these statistical references to policies would help decision-makers optimize intervention policies to the maximum. In this work, we designed a policy-aware time series forecasting model based on the transformer architecture and successfully estimated COVID-19 epidemic trends. Through incorporating temporal information from 16 policy indicators, we developed a policy-aware time series model that demonstrated high forecasting performance. We further quantify the causal effect of indicators by employing a counterfactual approach and propose two static metrics lag period and average effect. The empirical results demonstrate that our model causally verifies the effectiveness of all 16 policy indicators in controlling COVID-19 virus transmission in the US. From qualitative analysis, we conclude that frequent adjustments to the extent of policy actions may intensify epidemic spread. Our study provides insight into modeling government policies from a statistical angle, and it has practical applications when confronting potential influenza-like diseases in the future.

The first stage in the pipeline of self-driving cars is a system that enables the vehicle to understand its surroundings which becomes the base for every decision it takes and every maneuver it performs. Therefore, it is of high importance to design the perceptual system in a way that renders a scene and extracts accurate information about the present entities with little latency. Furthermore, driving is a complex task that should be safely performed at any time, especially, under different weather conditions which are not necessarily normal. Thus, perception models should be robust to different situations and weather conditions. In this paper, we evaluate the performance of various perception models designed to do object detection task. We critically analyze the structure of each model to identify the advantages and drawbacks. Our evaluation is done based on the NuScenes dataset which is an extensive dataset that covers different times of the day and weather conditions. Related metrics such as mAP, NDS, and learning curves are used to compare the performance of respective models as well as how robust they are to situations that are not considered normal.

Location-based services (LBSs) play a vital role in many Internet applications. Privacy is a mandatory aspect of these tasks, including protecting the user's sensitive information from malicious entities. Location privacy-preserving mechanisms (LPPMs) were designed to ensure privacy for LBS users, and several strategies have emerged, such as cloaking mechanisms. Likewise, several attacks appeared to threaten the user's privacy, being based on ground-related aspects. Therefore, we must investigate new strategies to enhance privacy protection mechanisms. Unmanned Aerial Vehicles (UAVs) can provide assisted coverage to ground users in different tasks, including the support of LPPMs. However, the existing strategies rely on some unfeasible premises, and this collaboration needs to be adequately explored. Therefore, in this study, we propose Sky Cloaking, which promotes the opportunistic connection between ground users and UAVs in such a way the UAVs manage the user's query, creating a cloaking region and hampering the success of an attacker. Through a comprehensive evaluation, we demonstrated that SkyCloaking can ensure high levels of location privacy to LBS users with a slight impact on the communication channel, overcoming existing strategies. In the best scenarios, SkyCloaking protected more than 80% of the user trajectory, mitigating the exploitation of users' sensitive information.

Intelligent Transportation Systems (ITS) have garnered considerable attention as a potential solution for addressing the conflict between the increasing demand for transportation and the constraints within transportation infrastructure. One pivotal facet of this field is the domain of traffic flow prediction. In this paper, we introduce an inventive methodology for traffic flow prediction, in which we employ CNN to capture the underlying traffic data trends, while Support Vector Regression (SVR) with the signature kernel is adapted to predict the residual components within the traffic data. We evaluated our approach through comprehensive experiments based on real world traffic data, and the results clearly demonstrate a significant improvement in prediction accuracy over both ablation models and alternative state-of-art baseline methods.

The burgeoning deployment of Underwater Acoustic Sensor Networks (UASNs) for maritime applications highlights the critical need for reliable trust models to defend against internal security threats. Existing trust models are often inadequate due to high packet error rates inherent in underwater communication and a lack of accounting for nodes' traffic behavior. Additionally, conventional UASN architectures suffer from significant latency in gathering and processing trust evidence, which delays the identification of adversarial nodes. Addressing these limitations, this paper proposes the Traffic-Aware and Edge Computing-Enabled Trust Model (TECTM), a solution expressly conceived for UASNs. TECTM integrates environmental models to assess the acoustic environment's impact on communication and employs network traffic analysis as a trustworthy metric for identifying attack patterns. Autonomous Underwater Vehicles (AUVs) serve as edge computing nodes, leveraging a machine learning algorithm to enhance trust assessments within node clusters. Moreover, TECTM introduces a refined trust update mechanism, designed to be responsive to the dynamic underwater environment and complex attack behaviors. Through comparative simulations, TECTM demonstrates enhanced accuracy in the detection of malicious nodes, outperforming other methods.

The ever-changing traffic dynamics make the traditional traffic signal control methods unable to adapt to the environment. Meanwhile, deep reinforcement learning (DRL) has the property of interacting with the environment and adapting to changes in the environment. Therefore, in recent years, researchers have usually solved traffic signal control (TSC) problems through DRL methods. They have not only improved the design of neural networks, but also improved the ability of models to understand traffic conditions and learn corresponding task requests by designing different states and rewards. However, although the existing TSC algorithms based on DRL have proposed many well-designed states and reward strategies, which combinations of states and rewards should be adopted in practice to achieve the performance margin of models remains a question that researchers are seeking the answer to. Therefore, we introduce a general simulation platform to test and compare experimental performance under different combinations of states and rewards. Specifically, we test and analyze the experimental effects under different combinations of multiple traffic states and rewards through various TSC methods with a set of unified model settings. We further design and test some new state representations and reward strategies based on more detailed traffic information. The test results show that when researchers design the state and reward, refining the traffic state like vehicle running condition and making the state and reward match can make the experimental performance better than other combinations in most cases. We hope these results have some implications for the state and reward choice when researchers conduct experiments on TSC problem or other traffic decision management problems.

Underwater Acoustic Sensor Networks (UASNs) have emerged as pivotal contributors to various domains. Never-theless, UASNs grapple with intrinsic challenges, notably propa-gation delays, heightened energy consumption, and inconsistent transmissions, which cumulatively impair the fidelity of under-water communication. Given these challenges, the exigency for a mechanism that assures both energy efficiency and reliable data collection becomes paramount. In this paper, we propose a data acquisition framework with the support of Autonomous Underwater Vehicles (AUVs), utilizing the Hybrid Clustering and Matrix Completion (AHMC) methodology, aiming to enhance the efficiency of data collection in UASNs. Initially, our approach har-nesses a novel hybrid clustering strategy, melding the virtues of the fuzzy c mean (FCM) algorithm with the Firefly Optimization Method (FA) to bolster network performance. The core strategy delineates the formation of energy-optimized clusters through FCM, post which the Elbow method ascertains the optimal K-value. Successively, the FA algorithm becomes instrumental in pinpointing the most suitable cluster head (CH) for each cluster. Furthermore, we introduce an ant colony algorithm tailored for the UASN s, encapsulating factors like energy, transmission latency, and the comprehensive trajectory span of AUV s during their operational phase. This strategic inclusion refines the pheromone update model, seamlessly amalgamating multifaceted elements to chart an optimally efficient AUV pathway. To cul-minate, the intra-cluster data aggregation is honed via a matrix completion methodology. Simulation results attest to the superior performance of our AHMC paradigm, showcasing commendable metrics in energy efficiency, latency, and network lifetime.

Unmanned aerial vehicles (UAVs)–also known as drones or Unmanned Aircraft–have found diverse applications in various fields owing to their significant advantages, including fast mobility and rapid deployment. UAVs are crucial in aerial networks, providing increased coverage and on-demand connectivity as mobile nodes. In recent years, UAVs have made room to leverage the Internet of Things (IoT) to the sky, enhancing air-to-ground communication and pointing toward the next generation of UAV networks. As this expansion is still in its early stages, there are several aerial network terminologies, each with similarities and differences, depending on the deployment domain and the services they offer. However, studies have yet to discuss these different terminologies consistently. Key aspects have yet to be thoroughly explored, such as the anticipated requirements for deploying these networks and how they relate to the various terminologies. This work systematically analyzes the existing terminologies of UAV networks, considering their requirements and applications, shedding light on their intersections and differences. Furthermore, we present the demands for the next generation of UAV networks and discuss how they impact the design of UAV-related applications, aiding in the design of new protocols, tools, and technologies for both industry and academia. Lastly, we highlight the emerging trends and challenges associated with deploying and integrating these networks.

The growing significance of marine information in the context of increased human oceanic activities has fostered interest in marine exploration. However, the specific nature of underwater acoustic communication, characterized by propagation delays and fluctuating link quality, presents multifaceted challenges to Internet of Underwater Things (IoUT). The vast openness of the underwater environment further amplifies security vulnerabilities, emphasizing the imperative for secure network routing. This paper introduces GHL-SAR, a fortified routing paradigm to address these challenges. Central to GHL-SAR’s design is its ability to evaluate node trustworthiness based on energy, communication, and node trust. Within this model, the Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) serves as a predictor of potential hidden state sequences, while the Long Short-Term Memory (LSTM) elucidates the relationship between these states and trust levels. Moreover, GHL-SAR deploys an adaptive routing mechanism rooted in the Particle Swarm Optimization Algorithm (PSOA), judiciously weighing link quality for routing decisions. The protocol further advances a density-based spatial clustering method for effective trust evidence aggregation. The simulation results demonstrate that GHL-SAR significantly reduces packet loss and energy consumption, while ensuring detection accuracy and network security compared to other existing routing protocols.

To reliably and safely navigate dynamic urban environments, connected automated vehicles should anticipate the future motion of surrounding traffic agents, which can have fundamental implications on road safety, traffic management, and network communications in vehicular networks. This requires considering the inherent uncertainty in agents' behavior, making motion prediction challenging. To tackle this issue, we propose conditioning the agents' future motions on both context information and potential multimodal goals. We design a novel Goal-based Motion Prediction approach (GMP) for multimodal motion prediction. By encoding both interactions between agents using temporal convolutions and dynamic and static context information using graph attention, our method estimates the distribution of target goals, efficiently takes the inherent uncertainty in the behavior of agents into account, and generates precise multimodal trajectories. Experimental results indicate that GMP outperforms several benchmarks on the Argoverse Motion Forecasting dataset.

Mobile edge computing (MEC) facilitates the development of compute-intensive and real-time applications on mobile devices by providing computing resources in proximity of users. To take full advantage of MEC, making optimal offloading decisions is critical. In this paper, we study the computation offloading of latency-constrained tasks from multiple users to an edge server under a stochastic environment with time-varying wireless channels and dynamically variable set of active users. To lower the mutual interference experienced by users while accessing a set of shared channels, we utilize game theory to formulate the decision-making process of users as a general-sum Markov game model. Then, we provide a mathematical proof to demonstrate the equivalency of the proposed game model to a weighed potential game, which guarantees the presence of at least one pure-strategy Nash Equilibrium (NE) point due to the finite improvement property. Next, we design multi-user computation offloading algorithms using a NE-based multi-agent reinforcement learning (MARL) technique to achieve the equilibrium solution of the game in a decentralized manner. Numerical results show that the proposed algorithms can effectively improve the convergence rate and greatly reduce the system-wide energy cost, outperforming the previously studied learning-based multi-agent algorithms.

Tunnels and bridges are installed as efficient context over the road network. Adding extra layers to an existing road network reduces the traffic congestion on that road. This is due to the distribution of traffic among the layers. However, bottleneck problems may appear at the entrance or exit points due to some driving behaviors. Moreover, the several exit points around these road contexts usually lead toward different trajectories. Taking a wrong exit leads to drastically expanding the trip traveling time, the fuel consumption, and the gas emission of any vehicle. This work aims to introduce an efficient driving assistance protocol that recommends drivers' optimal speed and behavior around tunnels and bridges. This mainly reduces the bottleneck constructions and enhances the movement's smooth-ness. Moreover, it accurately recommends the exit point there for each driver toward his/her targeted destination. The experimental study shows that the proposed protocol reduces the percentage of bottlenecks around the tackled road context. It also reduces vehicles' traveling time and distance during their trips toward the targeted destinations compared to the scenario of the absence of this protocol.

Underwater acoustic sensor networks (UASNs) have emerged as a promising technology for marine exploitation. However, due to the challenging characteristics of the underwater communication, including propagation delay and unstable link quality, UASNs face numerous issues. Furthermore, the open nature of the underwater environment poses significant security threats, making secure routing in UASNs a crucial requirement. In this paper, we propose a novel and secure routing approach, named GHL-SAR, to address these challenges. GHL-SAR models and measures the trust level of nodes by considering energy trust, communication trust, and node trust. Specifically, Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) is employed to predict the most likely hidden state sequence for a given observation sequence, and then Long Short-Term Memory (LSTM) is used to determine the relationship between the hidden state and the trust level. Moreover, GHL-SAR utilizes an adaptive routing method based on the Particle Swarm Optimization Algorithm (PSOA), which takes into account the accurate link quality to determine the routing strategy. The simulation results demonstrate that GHL-SAR significantly reduces packet loss and energy consumption while ensuring network security compared to other existing routing algorithms.

Forecasting the future paths of surrounding vehicles of a Connected Autonomous Vehicle (CAV) can enhance connectivity and efficiency of vehicular networks, and accurate motion forecasting of nearby vulnerable road users can advance road safety and urban mobility. This task needs a high-level situational awareness for the CAV. Early methods rely solely on vehicle kinematics and overlook the uncertainty within agents behavior and the effects of surrounding context on the behavior of nearby agents, resulting in lower performance or infeasible predictions. In the current work, we introduce a novel context-aware forecasting approach for CAVs that benefits from inverse reinforcement learning (IRL) to condition the future motions of nearby agents on scene-based state sequences defined using a Markov Decision Process. More precisely, we map the images of the surrounding context and the behavior history of agents into rewards and learn optimal expert behaviors using IRL. We validate the path forecasting efficiency of our model using two large motion prediction benchmarks with different scenes and achieve state-of-the-art results in terms of FDE and ADE metrics.

Shortly, the airspace will have different types of aerial networks due to the continuous growth of demands for aerial applications. As these networks compete for airspace, it is necessary to manage them efficiently. Also, these networks are expected to communicate with each other and with terrestrial networks forming hybrid aerial-terrestrial networks (HATNs). Efficient protocols for data packet delivery in HATNs are crucial for these networks to work together. In addition, cooperation between networks can be essential for different emergencies. However, communication in HATNs is challenging because of the plurality of node types. This work presents an altitude-based routing protocol for Hybrid Aerial-terrestrial Networks (ARAT). ARAT is a geocast and store-carry-forward protocol with promising performance in sparse scenarios. Simulation results show that ARAT outperforms two protocols (a baseline protocol and the GeoUAV protocol) by 50% for the packet delivery ratio metric. Also, to the best of our knowledge, ARAT is the first protocol to consider a collaboration between Aerial Networks and Internet of Drones (IoD) with the traffic of drones constantly.

Internet of things (IoT)-based cameras have been proposed for surveillance and mixed reality applications in different domains. IoT cameras stream video frames produced from the scenery within their coverage area. Video frames are then processed to determine, identify, classify, and track objects of interest. Traditionally, IoT video frames are offloaded to distant cloud servers and processed by computation-intensive algorithms for video analytics. However, this approach incurs increased latency and network overhead. Recent studies proposed edge computing for resource provisioning for IoT applications. Nevertheless, edge computing presents many daunting challenges, such as the efficient management and allocation of edge server resources to IoT cameras. We propose the collaborative work of IoT cameras for video analytics. Accordingly, idle resources on an IoT camera can be used to process video frames produced by neighboring cameras. In this regard, we devised a mathematical framework for collaborative cross-camera IoT video analytics, which allows engineers and practitioners to obtain useful insides for the further design of architectures for collaborative IoT video analytics. We conduct extensive numerical evaluations and the obtained results show that the resources' utilization, offloading latency, and offloading costs are sensitive to the neighborhood resources demand.

Conventional AI-based service flow remains a challenge for IoT-enabled devices since data collected by local clients is transferred to a centralized server, which contains a global machine learning (ML) model. However, this introduces privacy and security concerns for the clients, and federated Learning is positioned to overcome this problem where each client trains a local model with its local data and shares its model parameters with the centralized server instead of sharing data. Upon the receipt of all parameters, it aggregates these parameters and generates a new global model. Later this global model is distributed among the clients. Various aggregation methods have been published for increasing the global model's accuracy performance after aggregation. However, those new aggregation algorithms are not fully investigated under malicious and collaborated environments. A malicious environment is a scenario where malicious clients are present and can share parameters to degrade the aggregated model performance. On the other hand, the collaborative environment is another scenario in which some clients can share information with each other in order to collaborate. To tackle this issue, we investigate a new aggregation method called Score Based Aggregation (SBA) That aims to mitigate the impact of the model parameters from such malicious clients without keeping compromising the training accuracy. We compare our result to a baseline approach where the malicious client is varied from 20% to 50%. Numerical results suggest that the SBA aggregation helps the model maintain the convergence of accuracy at higher levels in comparison to the baseline approach.

Vehicular Edge Computing (VEC), as one of the major components of Intelligent Transportation Systems, improves road safety by providing computing services to safety-related applications on vehicles. Currently, the existing fine-grained computing scheduling algorithms are normally designed based on some simple scheduling policies. Due to the heterogeneous nature of tasks offloaded from various applications, they may not effectively satisfy various performance requirements of the real system, thereby leading to the problem that the short-term residual computing power cannot be effectively utilized when computing-costly tasks occupy the server. Therefore, improving the overall system performance and the efficiency of utilizing computing power is a critical issue. Accordingly, in this paper, we study the problem of computing scheduling inside edge servers in VEC, where multiple tasks can be offloaded to Road Side Units (RSUs). We analyze the role played by multiple evaluation metrics in the existing methods for ensuring the quality of service (QoS) and further design a novel online multi-factor aware task offloading algorithm with a hierarchical fine-grained computing scheduling scheme inside the edge server. We evaluate it by conducting intensive simulation tests and comparing the results with some state-of-the-art approaches. Numerical results show that the proposed algorithm outperforms the methods in the control group in different aspects and achieves the best overall performance.

With the rise of advanced applications based on Artificial Intelligence (AI) and Internet-of-Things (IoT), mobile devices have become more intelligent, introducing a novel concept, Mobile Edge Intelligence. But the limited on-board resources often hinder the capabilities of mobile devices. Mobile Edge Computing (MEC), regarded as an effective method to expand device capability, effectively overcomes this barrier. However, the dynamic networks driven by mobility and the dependency on applications pose significant challenges for offloading, which can degrade MEC’s overall performance. Therefore, how to effectively combine the above points to achieve a stable and effective sharing of computing resources between devices and servers is a critical issue. In this paper, we consider a multi-slot MEC system with device mobility and multiple applications of unknown arrival. To improve application completion rate while reducing task delay, we introduce a novel, robust distributed offloading algorithm, which calls the Multi-Attention Pointer network-based Reinforcement Learning algorithm (MAPRL), for the dynamic and unstable resource offloading scenario. Numerous experiments have been carried out to demonstrate that, compared with the existing methods, MAPRL exhibits robustness when facing the changing scenario, it can adapt to the unknown workload and dynamic network connections to enhance the offloading performance.

In this paper, we propose different strategies to efficiently deploy RSUs in a city with the ultimate goal of having an 802.11p-based infrastructure to deliver Internet services. Unlike most existing works, (i) our strategies' only prior information is the average density of vehicles in the studied area, and (ii) they rely on the forecast of a performance model of 802.11p to assist and guide their choices regarding the location of RSUs. With the help of two simulators, namely SUMO and ns-3, we investigate the behavior of each strategy in three scenarios inspired by the street map of real-life major cities. Our findings are twofold: (i) we demonstrate that any efficient RSUs deployment is tightly tied to the specifics of the considered city (namely, the arrangement of streets and the spatial density of vehicles); (ii) the best strategy is not to position RSUs where the traffic density is at its highest, nor at the street junctions where the traffic density is often at its highest but instead where they will be able to deliver the target QoS to a maximum number of vehicles.

Location Privacy Protection Mechanisms (LPPMs) have been designed to enhance privacy in the Internet of Drones (IoD), however, they present suitable privacy levels only in specific network conditions. Also, they can lead to a lack of Quality of Service (QoS) if applied in unfavorable conditions. Thus, the dynamic assignment of the most suitable LPPM, given the IoD conditions, is a significant challenge. Reinforcement Learning (RL) represents a useful concept to handle this problem, given its exploratory characteristics and being able to enhance the knowledge about network dynamics. In this study, we propose IoDAPM, an RL-based approach for the Dynamic Assignment of Protection Mechanisms in IoD. Through simulations, we extensively trained the RL-based model, exploring the possible IoD network conditions. With this model, we carried out a comparative evaluation of existing LPPMs. The results highlighted that IoDAPM outperforms the compared mechanisms considering the QoS, providing enhanced performance regarding location privacy, energy efficiency, and flight delay.

Accurate traffic flow forecasting is crucial for smart-cities and traffic management in modern society. With the rapid increase in traffic information’s nonlinearity and complexity, Neural Networks-based models have been introduced to traffic flow forecasting for spatial and temporal dependencies extraction. In this paper, we present the feature engineering model of spatial, temporal, and spatial-temporal dependency in the traffic flow prediction problem. We consider the solution with Graph Convolutional Neural Network (GCN) for the spatial dependency modeling, Gated Recurrent Unit(GRU) for the temporal feature construction, and the sequential feature extraction for Spatial-temporal dependency. To explain the effectiveness of the proposed idea, we evaluate the models using real-world datasets. Experiments show that the models capture comprehensive Spatio-temporal correlations with sequential feature extraction outperforming the sole spatial and temporal models.

In Unmanned Aerial Vehicles (UAVs), the real-time detection and identification of unauthorized UAVs is a significant challenge to be appropriately addressed. Currently, supervised-based learning models (e.g., Deep Neural Networks) can detect the presence of authorized UAVs with reasonable accuracy. Still, they can not handle properly the wide range of unknown signals in the airspace, mainly their categorization. Clustering techniques (e.g., DBSCAN) can be applied to identify and classify unfamiliar signals. However, the uncertainty regarding the nature of unknown sounds can lead to a large dimensional problem, hampering the performance of these techniques. Given these issues, we proposed DissIdent, a dissimilarity-based method for identifying unknown drones. Our approach takes advantage of the dissimilarity concept, in which a function of proximity maps extensive and multi-dimensional problems to a binary problem. DissIdent can identify patterns from different features through an intelligent workflow, mitigating the trade-off between the traceability and accuracy of massive multi-class problems. We carried out an extensive evaluation of DissIdent, comparing it with eight different approaches. The results pointed out DissIdent as a robust approach to detection and identification tasks, overcoming the compared methods. DissIdent addressed accuracy rates higher than 93% in all scenarios, presenting a concise detection and identification of unauthorized drones.

The price of virtual machine instances in the Amazon EC2 spot model is often much lower than in the on-demand counterpart. However, this price reduction comes with a decrease in the availability guarantees. Several mechanisms have been proposed to analyze the spot model in the last years, employing different strategies. To our knowledge, there is no work that accurately captures the trade-off between spot price and availability, for short term analysis, and does long term analysis for spot price tendencies, in favor of user decision making. In this work, we propose (a) a utility-based strategy, that balances cost and availability of spot instances and is targeted to short-term analysis, and (b) a LSTM (Long Short Term Memory) neural network framework for long term spot price tendency analysis. Our experiments show that, for r4.2xlarge, 90 percent of spot bid suggestions ensured at least 5.73 hours of availability in the second quarter of 2020, with a bid price of approximately 38 percent of the on-demand price. The LSTM experiments were able to predict spot prices tendencies for several instance types with very low error. Our LSTM framework predicted an average value of 0.19 USD/hour for the r5.2xlarge instance type (Mean Squared Error$<10^{-6}$) for a 7-day period of time, which is about 37 percent of the on-demand price. Finally, we used our combined mechanism on an application that compares thousands of SARS-CoV-2 DNA sequences and show that our approach is able to provide good choices of instances, with low bids and very good availability.

Vehicle trajectory data is paramount in many applications and research areas, such as vehicular networks and Intelligent Transportation Systems (ITS). However, data gathered from location acquisition devices generally contain positional errors that hinder its applicability, and therefore processing techniques are necessary to improve the quality of trajectory data. For instance, physical constraints of the road network that bounds the vehicles’ movement can be used to represent a trajectory better. Therefore, this paper proposes an efficient framework to reconstruct road-network constrained trajectories from GPS-based datasets. The framework employs novel processing algorithms and models to prepare even low sampled trajectories, which naturally present gaps, for real applications. Besides that, we present a novel real-world benchmark dataset to evaluate trajectory reconstruction and map-matching algorithms and perform extensive experimental evaluations using the new dataset and another one from the literature to compare the proposed framework to related work. The experimental results show that the proposed framework has a better time complexity and accuracy than the other methods in all evaluated scenarios.

In Mobile Crowdsensing (MCS), fake tasks can drain significant amount of resources. This paper proposes a new methodology to determine a proper time window for the training dataset and the impact of the accuracy of task legitimacy detection on the MCS campaign performance. To reach the desired performance, the task legitimacy detection is utilized in such a way that while legitimate tasks are kept, the fake tasks are eliminated as much as possible in the MCS platform through machine learning (ML) prediction. The proposed methodology is evaluated for legitimacy detection under multiple ML methods. Moreover, a knowledge-based fake task detection technique with effective feature selection is formulated to ensure fake tasks are filtered at the MCS servers. Detection accuracy is improved by using shorter time frame in training and longer time frame in prediction. The overall performance improvement based on profit, cost, legitimate tasks loss ratio, and fake tasks elimination ratio has been achieved under three different sizes of training datasets to verify the efficiency of the proposed methodology. Moreover, Prior Knowledge Input with Self-Organizing Feature Map outperforms the conventional legitimacy detection by 5.48%, 12.11% and 58.05% in terms of test accuracy, profit and cost under the small dataset, respectively.

This work proposes a novel vehicle-assisted data delivery algorithm called VDDTP. VDDTP creates an extended trajectory model and uses predicted road-network constrained trajectories to calculate packet delivery probabilities. Next, it applies the predicted trajectories and some proposed heuristics in a data forwarding strategy to improve the vehicular network's global metrics (i.e., delivery ratio, communication overhead, and delivery delay). We perform extensive experiments using a real-world and large-scale trajectory dataset for evaluating vehicular network applications. The results demonstrate the algorithm's ability to improve the global metrics compared to related work.

The Internet of Drones (IoD) is a network paradigm that allows drones to perform several services, gathering and sharing location-based information, representing a piece of the next generation of the Internet of Things (IoT). Location privacy is a paramount requirement in IoD. A few Location Privacy Protection Mechanisms (LPPMs) are designed for IoD. Unfortunately, they are not energy-aware approaches, essential for IoD protocols since drones have power limitations. We present the MixRide, an energy-aware LPPM for IoD to overcome these issues. It provides location privacy through the aerial-grounded vehicle collaboration, where the drones take a ride with grounded vehicles, changing their pseudonyms while saving energy. A comparative experimental evaluation pointed out that MixRide can provide location privacy to the IoD at the same level as the state-of-the-art LPPM while improving the drone's power consumption. Our results also provide new insights on the trade-off between the delay caused by the ride and the drone's energy power consumption.

As a potential solution to the growing conflict between the increasing demand for transportation and the limited capacity of transportation infrastructure, Intelligent Transportation Systems have gained considerable attention for their effectiveness in improving the efficiency of existing transportation infrastructure and enhancing traffic safety. Among various research areas, traffic flow prediction is a vital application, and researchers have devoted a lot of effort to designing accurate and fast algorithms. Currently, to satisfy various performance requirements, hybrid prediction methods that can take advantage of different sub-modules are beginning to emerge and show advantages in prediction accuracy and timeliness over other prediction algorithms that rely solely on machine learning. In this paper, we introduce a novel high precise traffic flow prediction method by utilizing the Fourier analysis (FA)-assisted denoising. Briefly, three sub-modules are introduced. Singular Spectrum Analysis (SSA) module is able to filter the noise of the original data, FA module is applied to extract periodic features of the traffic flow, and Long Short-Term Neural Networks (LSTM) is utilized to predict the future trend of time series residuals. We conducted simulation experiments. The corresponding test results demonstrate a substantial improvement in the accuracy compared to pure sub-models and other machine learning methods.

Reliably anticipating the future behavior of surrounding vehicles is critical for the safe operation of the Connected Automated Vehicles (CAV) and improves traffic safety. This task requires processing the history and current behavior of a target vehicle and its surrounding vehicles. Nevertheless, this level of situational awareness is challenging due to the limited observability of the ego CAV’s mounted sensors, particularly in unsignalized intersections as an example of a complex scenario. In the current study, we propose an interaction-aware behavior prediction framework for CAVs which takes advantage of vehicular communication technologies to improve the prediction performance at the time of occlusion. With the help of Vehicle-to-Vehicle (V2V) communications, connected vehicles can gain an enriched understanding of the current behavior of the nearby vehicles, leading to an enhanced prediction. We benefit from graph convolutional networks to model the connection between the vehicles. We further analyze the proposed model over a large real-world dataset containing 14867 vehicle trajectories. The results indicate the higher performance of the introduced model against several benchmarks.

Recently applications that use a single drone are evolved into an Internet of drones (IoD) ecosystem. The IoD has a complex control as it needs to coordinate the drones in the airspace, which involves mobility and communication between them. It facilitates the IoD control if drones frequently report their positions to the control base, use well-defined airways to fly, and are managed through Software-Defined Internet of Drones (SDIoD). In the shared airspace, drones are expected to exchange messages with each other. In this work, we propose PSDIoD, a Position-based routing protocol for SDIoD, which has two versions. The first, called PSDIoD-SP (Shortest Path), considers the shortest path in the airways to select the routes. The second, called PSDIoD-EA (Energy-Aware), examines the radio power consumption estimated to choose the route. Due to nodes having a limited battery, power is a crucial factor in IoD. Both of which consider the knowledge of the position of drones to route packets. This work advances the state of the art by proposing efficient routing solutions that were developed in a suitable way for the IoD environment. The results show that PSDIoD versions are better in power consumption, packet delivery ratio, delay, and overhead when compared to a baseline protocol. Furthermore, PSDIoD-EA is approximately 9% more economical in terms of power consumption when compared to PSDIoD-SP.

In this paper, we focus on two fundamental aspects in the design of Bus-based Vehicular Networks: the building of bus mobility scenarios for validating solutions and the dissemination of messages on the network. We present a methodology for generating bus mobility scenarios based on official data and simulation tools. In this regard, we consider the city’s road map and additional traffic infrastructure elements. In addition, traffic demand for different days of the week is generated based on GTFS data provided by the city’s transport agency. We validate our scenarios with official data, and through a comparative analysis, we show the relevance of this work compared to existing alternatives in the literature. We present a novel routing protocol named BR3C, which aims to forward messages between bus lines for data dissemination. BR3C (Bus Routing protocol based on Community and Centrality Characteristics) considers social metrics extracted from the contacts between bus lines for decision-making. As a result, our protocol significantly reduces delivery latency while keeping delivery ratio values similar to state-of-the-art.

In recent years, people have paid more and more attention to the operational efficiency of the transportation system and the corresponding traffic safety and energy consumption issues. As a possible solution, with the improvement of vehicle detection capabilities and the corresponding computing power of vehicle computing equipment, the development of autonomous driving technology as an important application of AI technology in the automotive industry has attracted considerable attention from academics and industry. Technically, we consider vehicles and pedestrians to be the two most important participants of the transportation system. Accordingly, efficient coordination of relative movement between on-road vehicles and pedestrians plays a critical role in improving road safety. The effective detection of pedestrians from the vehicles’ point of view is fundamental for achieving such coordination. Therefore, in this paper, we will first provide a comprehensive study of existing pedestrian detection methods, especially the occluded pedestrian detection method. Then, we will discuss the potential solution for designing a practical pedestrian detection method for supporting autonomous driving.

Mobile Crowdsensing (MCS) is a sensing paradigm that has transformed the way that various service providers collect, process, and analyze data. MCS offers novel processes where data is sensed and shared through mobile devices of the users to support various applications and services for cutting-edge technologies. However, various threats, such as data poisoning, clogging task attacks and fake sensing tasks adversely affect the performance of MCS systems, especially their sensing, and computational capacities. Since fake sensing task submissions aim at the successful completion of the legitimate tasks and mobile device resources, they also drain MCS platform resources. In this work, Self Organizing Feature Map (SOFM), an artificial neural network that is trained in an unsupervised manner, is utilized to pre-cluster the legitimate data in the dataset, thus fake tasks can be detected more effectively through less imbalanced data where legitimate/fake tasks ratio is lower in the new dataset. After pre-clustered legitimate tasks are separated from the original dataset, the remaining dataset is used to train a Deep Neural Network (DeepNN) to reach the ultimate performance goal. Pre-clustered legitimate tasks are appended to the positive prediction outputs of DeepNN to boost the performance of the proposed technique, which we refer to as pre-clustered DeepNN (PrecDeepNN). The results prove that the initial average accuracy to discriminate the legitimate and fake tasks obtained from DeepNN with the selected set of features can be improved up to an average accuracy of 0.9812 obtained from the proposed machine learning technique.

The recent advancement of drone technologies and communication protocols allows us to envision a robust and dynamic mobile vehicular network paradigm called the Internet of Drones (IoD). In this environment, drones will perform several location-based services (LBSs) for users, awakening the interest of malicious entities whose intention is to hamper the service. Hence, drones need high protection regarding their localization in LBSs. However, there is a lack of Location Privacy Protection Mechanisms (LPPMs) for an IoD scenario. Dummy-based LPPMs provide proper location privacy in traditional mobile networks, mainly for sparse configurations. The design of this mechanism for IoD can overcome this deficiency. This study proposes a novel dummy-based LPPM for the IoD, called TDG, that focuses on the IoD topology characteristics regardless of near drones being the first approach presented in this context. Through extensive experiments, we show that TDG can provide proper location privacy for drones in sparse configurations, reducing the use of the wireless communication channel. TDG can protect the real drone’s trajectory up to more than 90% of the time, leaking less than 25% of the drone’s real coordinates.

Mobile edge computing (MEC) has appeared as a promising solution to fill the gap between the growing computationally intensive applications and limited computation capability of mobile devices by providing powerful computing services at the edge of the wireless access network. To use the services provided by the MEC more effectively, making efficient and reasonable offloading decisions is crucial. In this paper, we study the computation offloading of tasks from multiple users to a single-cell edge server under a dynamic environment. We consider a practical case wherein a group of mobile users with random mobility patterns use a common set of time-varying stochastic transmission channels to perform computation offloading, and the number of active users in the system randomly changes. To reduce the mutual interference among users when accessing the wireless channels, we adopt game theory to formulate the users’ computation offloading decision process as a stochastic game model. Next, we prove the existence of the Nash Equilibrium (NE) for the proposed game model by showing its equivalency to a weighted potential game which has at least one pure-strategy NE point. Then, we present distributed computation offloading algorithms by adopting a payoff-based multi-agent reinforcement learning (MARL) approach to reach the NE of the game. Finally, through simulation, we validate the effectiveness of the proposed algorithms by comparing them with the results obtained from other previously studied multi-agent learning algorithms as well as conventional Q-learning and deep Q-learning algorithms.

How to effectively improve the traffic efficiency of the road network plays a crucial role in ensuring the regular operation of modern society. This is also a key concern in the field of intelligent transportation systems. As the basis for formulating traffic control strategies, efficient and accurate traffic flow forecasting is essential. Accordingly, various prediction methods have been proposed for addressing the traffic flow prediction issue. However, we notice that most researchers only take the accuracy performance as the primary evaluation criteria and do not consider the problem of time cost. Consequently, the timeliness of the prediction results cannot be guaranteed. In this case, no matter how high the accuracy of the prediction is, it cannot provide practical information for the formulation of traffic measures. Therefore, in this paper, by exploiting the dimension reduction ability of Auto-Encoder (AE), we proposed a time-efficient prediction method for a large-scale road network that significantly reduces the prediction processing time while ensuring prediction accuracy. We conducted simulation experiments, and the corresponding test results demonstrate a substantial improvement in the time efficiency of our method compared to the traditional methods.

Internet of Drones (IoD) is an architecture that aims to enable different drones to share the same airspace. This architecture can help coordinate drone access to airspace in urban environments. Considering that the IoD is a dynamic network, it is possible to have scenarios in which drone traffic is sparse when, for instance, the network has isolated drones. In this case, the drones’ communication range does not reach any other drone. Thus, store-carry-forward protocols may be suitable for maintaining network communication. Moreover, different networks can collaborate to fill these communication gaps. In this study, we explore the collaboration between IoD and Bus Networks. Our analysis shows that maintaining a hybrid communication between drones and buses can fill the gaps in the communication between drones. The main goal of this work is to present the IoDSCF – a store-carry-forward routing protocol for joint Bus Networks and the Internet of Drones (IoD). IoDSCF takes advantage of both networks to extend the communication reachability. Our results reveal that IoDSCF presents better results in the number of delivered packets and end-to-end delay than a solution based only on communication between drones. This is a promising strategy for data communication, mainly in smart cities.

In recent years, data-driven intelligent transportation systems (ITS) have developed rapidly and brought various AI-assisted applications to improve traffic efficiency. However, these applications are constrained by their inherent high computing demand and the limitation of vehicular computing power. Vehicular edge computing (VEC) has shown great potential to support these applications by providing computing and storage capacity in close proximity. For facing the heterogeneous nature of in-vehicle applications and the highly dynamic network topology in the Internet-of-Vehicle (IoV) environment, how to achieve efficient scheduling of computational tasks is a critical problem. Accordingly, we design a two-layer distributed online task scheduling framework to maximize the task acceptance ratio (TAR) under various QoS requirements when facing unbalanced task distribution. Briefly, we implement the computation offloading and transmission scheduling policies for the vehicles to optimize the onboard computational task scheduling. Meanwhile, in the edge computing layer, a new distributed task dispatching policy is developed to maximize the utilization of system computing power and minimize the data transmission delay caused by vehicle motion. Through single-vehicle and multi-vehicle simulations, we evaluate the performance of our framework, and the experimental results show that our method outperforms the state-of-the-art algorithms. Moreover, we conduct ablation experiments to validate the effectiveness of our core algorithms.

This paper considers the problem of mobile computation offloading under stochastic wireless channels while task completion times are subject to deadline constraints. Our objective is to conserve energy for the mobile device by making an optimal decision to execute the task either locally or remotely. In the case of computation offloading, we dynamically vary the data transmission rate, in response to channel conditions. The wireless transmission channel is modelled using a Finite-State Markov Chain (FSMC). We formulate the problem of computation offloading as a constrained optimization problem, and develop an online algorithm to derive the optimal offloading policy. Moreover, to reduce the complexity, we estimate a suboptimal solution of the proposed online algorithm by reducing the size of the FSMC with the help of Markovian aggregation. The numerical results indicate that by applying Markovian aggregation, the running time of the algorithm can be significantly reduced without suffering unreasonable performance degradation.

We consider an update-and-decide IoT-based wireless network, where information packets generated from dual sources are co-stored in the transmitter's buffer, while decisions are made at the destination. Two practical assumptions about the communications between the transmitter and destination are taken into account: the communications are operating with finite blocklength (FBL) codes, and truncated hybrid automatic repeat request (HARQ) schemes are exploited to improve the FBL reliability, i.e., the number of allowed rounds of (re)transmissions is finite. For the first time, this paper characterizes the timeliness of status updates, namely age upon decisions (AuD) (which highlights the timeliness of the information at decisions in comparison to the concept of age of information), for such truncated HARQ-assisted wireless network. First, we characterize the inter-arrival time between two adjacent successfully transmitted packets, while taking into consideration the preemption policy and the randomness of the number of preempted packets from the same source. In particular, the probability density function, statistical performance of such inter-arrival time are derived. Following these characterizations, we propose a new approach to determine the average AuD and obtain a closed-form expression accordingly. Via simulations, we evaluate the performance and conclude a set of guidelines for designs on the considered network.

How to effectively improve the efficiency of vehicle traffic in the road system will play an essential role in improving the operational efficiency of the traffic system while eliminating the energy consumption and environmental pollution problems caused in particular, and this is also a key concern in the field of intelligent transportation systems. Timely and accurate traffic flow prediction is regarded as the key to solve the above problems because it can effectively improve the efficiency of traffic flow management. Many prediction methods have been proposed and among them, Machine Learning (ML)-based forecasting methods have gradually become mainstream in recent years because of their inherent ability to learn and predict nonlinear features in traffic information. However, we notice that most of the existing ML-based traffic prediction methods were designed relying fully on historical data while ignoring the structure and the impacts of the whole road network. Therefore, in this paper, we proposed a mixed method to take both historical data and road networks into consideration. Based on the real-world dataset, we conducted simulation experiments. The corresponding test results demonstrate a substantial improvement in the prediction accuracy of our method compared to conventional ML-based methods.

As a powerful non-intrusive method, driver identification based on driving data analysis has recently gained attention as it is beneficial for providing security, privacy, and personalization for driver assistance systems. Fortunately, the considerable variety of available in-vehicle sensors and net-working technologies has contributed to collecting high-quality data for driver identification purposes. Nevertheless, the main challenge in this task is extracting and capturing unique driving-related features and behavior of each individual. In this study, we analyze and compare the effectiveness of benchmark deep learning-based approaches in terms of driver identification accuracy. More specifically, we design an encoder-based framework to compare the performance of temporal convolutional and recur-rent neural networks in capturing the underlying features within the driving sequence data. We also provide insights on their strengths and limitations. Our qualitative and quantitative results demonstrate that a temporal convolution-based network can outperform recurrent architectures while reducing computational complexity by a factor of 5.6.

Internet of things (IoT) and 5G network are fundamental building blocks for industrial IoT (IIoT). IoT has enabled real-time monitoring and actuation in industrial floors and machinery, aimed at improving the efficiency and safety of industrial activities and processes. On the other hand, 5G networks will provide ultra-reliable and low-latency communication for the wireless integration of autonomous industrial machinery, mobile vehicles, and robots, and management systems, aimed at the real-time control and management of industrial machinery toward smart factories. In IIoT, machine learning (ML) will also play a fundamental role in handling complex tasks at industrial machinery and 5G networks management, configuration, and control. However, ML suffers from the cold-start problem and needs a large amount of highly accurate data samples for model training, which is costly and difficult to obtain in IIoT applications. In this article, we shed light on the design of transfer learning (TL)-based systems for IIoT. We discuss how TL can overcome the demand for high-quality large data samples required to training ML models in IIoT. We also highlight the work principles and daunting challenges faced during the TL systems for IIoT. Furthermore, we categorize the TL systems for IIoT into TL for IIoT machinery level and for IIoT networking level and provide an in-depth discussion of the design building blocks and challenges of TL systems in each proposed class. Finally, we point out some future research directions for the design of novel TL-based systems for envisioned 5G-enabled IIoT applications.

The advancements in Internet of Things (IoT) and embedded systems, 5G networks and next-generation wireless systems, and embedded and distributed artificial intelligence are empowering Industry 4.0. In this new industrial era, smart autonomous and connected systems will improve efficiency, reduce cost and pollution, and increase productivity and safety in industrial 4.0 based applications. Nevertheless, the new generation technologies mentioned above have not been explored to improve safety in multiplant and industrial zones. In this article, we shed light on the design of unmanned aerial vehicles (UAVs)-assisted systems for emergence response in multiplant and industrial zones. We discuss the important contributions of UAV-mounted cloudlet systems to support SAR missions by providing computation, communication, and storage resources to first responders, surveillance of the affected area, real-time monitoring of SAR members and victims, and caching nodes to improve content delivery among SAR teams. Besides, we design an envisioned UAV-cloudlet reference system for emergency response in industrial areas. Moreover, we highlight the current challenges that are being addressed in the literature aimed at making possible the efficient use of the designed UAV-mounted cloudlet systems for emergency response. Finally, we point out some future research directions that require further investigation.

The advent of in-vehicle networking systems as well as state-of-the-art sensors and communication technologies have facilitated the collection of large volume and almost real-time data on vehicles and drivers, thus opening up future possibilities. Processing and analyzing this data provides unprecedented opportunities to offer remarkable insights and solutions for driving behavior analysis (DBA). Characterizing driving behavior plays a key role in a variety of research areas such as traffic safety, the development of automated vehicles, energy and fuel management, risk assessment, and driver identification and profiling. Advances in DBA-based driver inattention or drunk driver detection can help reduce fatal car crashes, and understanding the driving style (e.g. eco-friendly or aggressive) of drivers can contribute to fuel management and risk assessment of the drivers. These facts have led to a growing interest in addressing DBA challenges. This paper aims to present the state-of-the-art methodologies for DBA and provide a clear roadmap about the main current and future trends in DBA. To this end, we propose categorizing the current research on driving behavior based on the types of data employed for the analysis, the ultimate goals of the analysis, and the techniques based on which the driving data are modeled. We provide an overview of different data resources and available datasets for DBA. Moreover, we discuss the application of DBA along with the key research challenges in this field and potential future directions.

Driver identification has shown sustainable development in recent years in a wide variety of applications including but not limited to security, personalization, fleet management, insurance telematics, or ride-hailing. However, the current progress suffers from several challenges such as costly data collections and the need for a huge amount of data from each individual for both driver identification and impostor detection. Therefore, more novel and efficient solutions are required to mitigate the existing challenges. In this paper, we address driver identification and impostor detection tasks using driving behavior analysis of the drivers. We design a deep learning-based system architecture that analyzes windows of 30 seconds of driving data to capture the unique underlying characteristics of the individuals steering behavior based on which it further distinguishes the drivers. We also develop a novel strategy to tackle driver verification and impostor detection tasks based on the combination of the proposed system architecture and Siamese networks concepts. We map the steering behavior of the drivers into latent representations which can be later used to train a similarity function. The performance of the proposed systems is tested over a real-world dataset of 95 drivers. The evaluation results indicate that our system outperforms well-established benchmarks and baseline methodologies.

Accurate and reliable prediction of future motions of the nearby agents and effective environment understanding will contribute to high-quality and meticulous path planning for the automated vehicles under uncertainty and guarantee traffic safety for future real-world deployments. This task becomes more challenging in highly dynamic and complex scenarios such as unsignalized intersections where no lights exist to control vehicles behavior, or there are not multiple lines for the vehicles to anticipate drivers’ future intentions based on the lane in which they are driving. In this study, we introduce a novel deep learning-based methodology to anticipate vehicles path at unsignalized intersections. The method provides multimodal outputs to take into account the inherited uncertainty and multimodality nature of vehicles behavior. Our proposed model works based on dilated convolutional networks in combination with a mixture density layer. We then cluster various existing mixes into possible paths that are ranked based on probability. We assess the performance and generalization capability of our vehicle path prediction model using several metrics over a large naturalistic dataset containing more than 23800 vehicle trajectories. The obtained results reveal the higher performance of our path prediction approach compared with several baselines and benchmarks.

Vehicle Make and Model Recognition (VMMR) requires fast and accurate recognition of a vehicle’s information. Generally, the vision-based VMMR method recognizes different vehicle models that mainly rely on locating and extracting the discriminative part features of a vehicle. In this paper, we propose a Lightweight Recurrent Attention Unit (LRAU) to enhance the feature extraction ability of the standard Convolutional Neural Network (CNN) architectures for VMMR. The proposed LRAU extracts the discriminative part features by generating attention masks to locate the keypoints of a vehicle (e.g., logo, headlight). The attention mask is generated based on the feature maps received by the LRAU and the preceding attention state generated by the preceding LRAU. By adding LRAUs to receive the multi-scale feature maps generated by the standard CNN architecture, discriminative features of different scales can be efficiently extracted and combined. We conduct comprehensive experiments on three challenging VMMR datasets to evaluate the proposed VMMR models. Experimental results show our models have a stable performance under different environmental conditions. Our models achieve state-of-the-art results with 93.94% accuracy on the Stanford Cars dataset, 98.31% accuracy on the CompCars dataset, and 99.41% accuracy on the NTOU-MMR dataset. Moreover, we demonstrate that our models outperform the traditional machine learning-based VMMR models in terms of recognition accuracy and processing speed. In addition, we construct a one-stage Vehicle Detection and Fine-grained Recognition (VDFR) model by combining our LRAU with the general object detection model. Results show the proposed VDFR model can achieve excellent performance with real-time processing speed.

The next generation of sustainable vehicular networks are expected to have a wide range of access technologies, multi-homing capabilities, and traffic demand and pattern heterogeneity. In order to deliver massive data loads from various services and applications to end-users, network softwarization is a key contributor that mitigates challenges in heterogeneous networks by providing a shared interface platform. SDN-enabled vehicular network provides global snapshot of the network's status and connectivity. However, using a centralized control unit, brings many difficulties, including bottleneck problem and densification issues. A distributed control plane is an alternative, but it raises questions about where to deploy the control units and how many controllers are needed in a given network structure. In this article, we propose an energy-efficient adaptive controller management strategy for distributed software-defined vehicular networks using vehicles' mobility densities and communication latencies between switch-enabled access points. To reduce the number of controllers, the proposed method employs a split-and-merge clustering technique. The performance of the clustering solution was evaluated using realistic mobility traces and compared to several benchmark clustering solutions and variations. The results indicate the efficiency of the proposed scheme in terms of energy consumption, latency, and load on network entities.

For developing a sustainable wireless sensor network (WSN), wireless energy charging and mobile data collection are two promising techniques for enhancing energy efficiency and achieving semi-permanent operation time of WSNs. Currently, many energy-aware methods have been developed by adopting these two technologies. However, joint methods that can combine the advantages of both are still lacking. Technically, by reducing the transmission energy consumption of individual nodes while wirelessly charging low power nodes, the joint method can better extend the operating time of the nodes in the system, improving the overall system life. Therefore, we design a two-mode QoS-aware mobile chargers (MCs) scheduling method for implementing both energy charging and data collection tasks simultaneously. The proposed scheme is comprised of two parts: 1) A new clustering algorithm is designed for addressing the trade-off problem regarding the delay and load balancing of sensors, and the network topology construction. 2) Two heuristic MC scheduling algorithms are introduced for facing the different delay requirements of systems, i.e., the single-path scheduling scheme (SPSS) and the multiple-path scheduling scheme (MPSS). The simulation results show that our proposed method outperforms the existing state-of-the-art approaches in the control group regarding the average delay and the charging utility.

Vehicle fuel efficiency (VFE) has a pivotal role in solving energy shortage issue due to the increasing global demand for energy. The high frequency of go-stop movements and long waiting times at intersections significantly reduce the VFE. Such negative impacts are particularly severe when the traffic flows are regulated by poorly designed traffic signal control. Existing works have successfully applied deep reinforcement learning (DRL) techniques to improve the efficiency of traffic signal control. However, to the best of our knowledge, few studies have explored traffic signal control for VFE through eco-driving techniques. To fill the gap, we propose a DRL-based fuel-economic traffic signal control for improving vehicle fuel efficiency. Briefly, we adopt the DRL-technique to develop an agent that can efficiently control traffic signals based on real-time traffic information at intersections, and adjust speed profiles for approaching vehicles to smooth traffic flows. We tested our method on both synthetic traffic dataset and real-world traffic dataset from surveillance cameras in Toronto. Through comprehensive experiments, we demonstrate that our method surpassed the performance of both pure eco-driving and pure traffic signal control techniques by significantly reducing vehicle fuel consumption and improving the efficiency of traffic signal control.

The concept of Multi-access Edge Computing (MEC) extends the provisioning of computing and storage capabilities from remote Cloud Data Centers (DC) to the proximity of end users via heterogeneous networks. By augmenting User Equipment (UE) with external computing power under the local coverage, Cloudlet-based offloading performs as a critical enabler to boost application execution performance and to prolong battery lifespan in the mobile devices. However, the mobility of UEs introduces intra-Cloudlet intermittent connections and inter-Cloudlet unbalanced load distributions in the MEC environment, which consequently leads to offloading failures and service downgrading. In this paper, we propose a novel MEC-based mobility-aware offloading model to solve the intra-Cloudlet offloading scheduling issue and inter-Cloudlet load-aware heterogeneous resource allocation issue in terms of concerning the offloading execution efficiency, task processing time constraints, and energy efficiency. A priority-based queue model is designed to formulate the intra-Cloudlet mobility-aware offloading scheduling problem, resolved by the adoption of the Particle Swarm heuristic. The energy-aware inter-Cloudlet resource selection procedure is formalized in a mobility-aware multi-site resource allocation model, which is further solved by lightweight dynamic load balancing. The results of the experiment indicate that the proposed framework can effectively improve the overall offloading service provisioning quality in the intra-Cloudlet and inter-Cloudlet offloading scenarios, compared to the current works.

Fuel consumption and gas emissions of traveling vehicles have become of great consideration for green environmental researchers. Several technologies have been developed to enhance the efficiency of daily traveling vehicles in terms of fuel consumption. Moreover, many protocols have been developed to reduce the fuel consumption and emissions of traveling vehicles. However, most of these protocols were dedicated to downtown and urban areas, since they are considered more consuming scenarios. Drivers spend a long time traveling over highways toward a targeted destination. Small mistakes could lead to greater fuel consumption; the percentage of extra fuel consumption can be drastically increased when drivers repeatedly make the same efficiency mistakes during their trips. In this work, we aim to introduce a green protocol to assist drivers and self-driving vehicles to drive efficiently over highways in order to reduce the fuel economy and gas emission of their vehicles. This protocol is designed to keep the speed of the traveling gasoline vehicles steady as much as possible in order to save energy and enhance efficiency. It also smooths the acceleration and deceleration reactions of vehicles when required. The performance of the proposed protocol has been evaluated using an extensive set of experiments.

As the most serious global infectious disease in the past 100 years, it has caused severe loss of life and property to countries and their people worldwide in the past year. As the most powerful tool in the fight against the epidemic, how to quickly promote the COVID-19 vaccine administration plays a vital role in gradually establishing an immune barrier in the population as soon as possible and blocking the COVID-19 epidemic. In this paper, we provide a machine learning-based policy recommendation method on the vaccination campaign of COVID-19 by minimizing three different cost factors: the duration of the pandemic, the budget of the COVID-19 battle as well as the death toll. To generate a more efficient vaccination policy, we construct an Age-stratified Susceptible-Infected-Recovered (ASSIR) model. We validate our method based on the real-world dataset of India by comparing our simulated results with the government's vaccination plan from machine learning prediction. Our approach shows a 13% decrease in disease control time and government budget. At the same time, we find out that vaccination based on each province's population leads to a 12.4% decrease in the death toll than on infection cases. The model developed in this study has practical implications for COVID-19 vaccination campaigns and the infection control of other infectious diseases.

In recent years, with the continuously increasing number of vehicles, how to solve the frequent traffic accidents, the increasing traffic congestion, and the corresponding exhaust pollution in the transportation system is the problem that must be solved to ensure people's safe, efficient, and green travel needs. As one of the core components of future intelligent transportation systems (ITS), autonomous vehicles have become a common area of interest for academia and industry because they can strictly follow traffic laws and regulations while avoiding traffic accidents caused by improper driving behavior of human drivers. However, the current autonomous driving technology often relies on a single vehicle to independently detect its surrounding traffic environment. Under the impression of the detection range of the corresponding detector and the occlusion of different types of objects in the traffic system, a single vehicle often has a large detection blind spot. As a result, it may not be possible to develop an effective driving strategy in complex environments. For addressing this issue, in this article, we will introduce a collaborative object detection and warning method based on vehicular edge computing (VEC) to achieve a transparent traffic environment. In other words, by exploiting the computing power provided by the VEC, we will eliminate the detection blind spots of traffic system participants as much as possible. The efficiency of the proposed method will be evaluated through physical experiments.

As a major type of driver assistance technologies, automated warning systems provide drivers and vulnerable road users with safety. These systems, such as forward collision warnings, can detect potential risks nearby and alert the drivers. One shortcoming of such warning systems is that their effectiveness and capability depend on the information collected from sensors existing in a single vehicle, which can be highly limited in the presence of occlusion, leading to irreversible consequences. To overcome this shortcoming, in this paper, we benefit from the vehicular sensing and communication technologies to propose a novel Internet-of-vehicles (IoV) powered framework for defensive driving warning, in which a vehicle can take advantage of other vehicles sensing data through V2V communications. We further evaluate the introduced framework in cyclist protection system scenarios. Simulation results demonstrate how the proposed IoV-based framework can improve warning systems by providing increased situational awareness.

Software-defined vehicular networks (SDVNs) have been a vital addition to the design of intelligent vehicular networks. SDVNs elevate the constraints of static hardware network devices to programmable units, provide a global view of the network status, and standardize the interface between different wireless access technologies. However, the static deployment and assignment of switches to control units do not consider vehicles rapid mobility and diverse densities. In this paper, we propose a mobility-based switch migration scheme for software-defined vehicular networks. The proposed scheme utilizes the vehicles’ mobility between switch-enabled roadside units to efficiently migrate selected switches to different controllers. The proposed scheme has been evaluated using the network simulator and reported its performance under realistic mobility traces and environment.

In the last few years, new scenarios have emerged for drone applications including those of risk scenarios. In this case, it is essential to have communication among drones whenever they perform tasks that need some sort of coordination, management or synchronization, for instance. In this work, we propose IoDAGR – Internet of Drones Airway-based Geocast Routing, a geocast protocol to transmit messages, such as alerts, to a specific geographical region in a drone network. IoDAGR advances the state of the art of geocast protocols for drones by proposing an efficient solution to this scenario. Simulation results revealed that IoDAGR presents promising results when compared to a baseline protocol.

In recent years, we have witnessed the viability of applying cloud computing concepts to the domain of vehicular networks. A basic component of this infrastructure derived from the merge of cloud computing and vehicular networks is a Vehicular Micro Cloud (VMC), also known as vehicular cloudlets. A VMC is a cluster of connected vehicles that share computational resources. Despite being the focus of many studies in recent years, we still do not have a clear understanding of the characteristics of VMCs in large-scale urban scenarios. In this paper, we investigate some fundamental characteristics of stationary and mobile VMCs obtained from a realistic vehicular mobility trace. We characterize the dwell time and the inter-arrival time in stationary VMCs. Also, using statistical modeling, we identify theoretical distributions that best fit these metrics. For mobile VMCs, we reveal how they occur throughout the city along the day, discussing evolution and lifetime aspects.

With the explosive use of surveillance and onboard cameras, vision-based Vehicle Re-identification (VReID) has attracted widespread attention. The goal of VReID is to search and identify the target vehicle from a large number of images. An efficient VReID model can help the police make fast decisions and improve regional security. The major challenge of the VReID is to distinguish the subtle visual difference between different vehicles. In this work, we propose a Compact Attention Unit (CAU) that relies on a single attention map to extract the discriminative local features of the vehicle. We add two CAUs to the truncated ResNet to construct a small but efficient VReID model, ResNetT-CAU. The feature representation of the vehicle image is the concatenation of the extracted global and local features. Compared with the original ResNet, the model size of ResNetT-CAU is reduced by 60% and has excellent VReID performance. We conduct experiments on two benchmark datasets, VeRi and VehicleID. The results show the proposed model stably achieves excellent VReID performance with very fast processing speed.

Floods are the most frequent type of natural disaster, and it is crucial to search and track the objects transported by the water flows, such as humans, animals, vehicles, and debris. The use of Unmanned Aerial Vehicles (UAVs) is essential in disaster scenarios to help first responders in determining correct procedures in terms of searching, tracking, and rescuing the victims, as well as in defining the actions to minimize the risks in a sustainable and timely manner. However, the tracking of mobile objects for UAVs is challenging because it is necessary to change the UAVs’ topology frequently to organize them according to the target object’s new location and the rescue team’s position. It is also mandatory to assure the distribution of real-time video flows with a high-quality level and a minimal delay in mobile environments and save scarce energy power. This paper proposes a swarm-based and mobility prediction algorithm for UAVs, called SUAV, to efficiently orchestrate UAVs to track mobile objects in flooding scenarios while saving energy and delivering real-time videos with Quality of Service (QoS) and Quality of Experience (QoE) assurance to first responders. Simulation results present the impact and the benefits of our proposal in delivering videos with QoE and QoS support compared to state-of-the-art approaches.

This work tackles the closed peripheral coverage issue. Such circumferential surveillance is essential in numerous realistic applications where the goal is to ensure rapid detection of any unauthorized entry/exit of the monitored area. To respond to these requirements, peripheral WMSNs can be rapidly deployed around areas of interest (e.g., temporary military camps, natural or nuclear disasters, etc.). While it seems simple, this solution raises two major challenging issues. First, checking whether the deployed peripheral WMSN forms a closed shape around the monitored region. That is, any object trying to leave or access this area must be instantaneously detected by at least one multimedia sensor node. Second, instead of activating all the deployed redundant sensor nodes, and hence, vainly wasting their scarce resources, an efficient scheduling technique must be proposed. We remedied these problems by proposing and evaluating a distributed algorithm that was specifically designed to fit the peculiarities of WMSNs.

Traffic distribution over highways affects several applications and functionalities of traveling vehicles. The level of traffic congestion has been scaled over road networks based on the traffic density, traveling speed or estimated traveling time of the investigated road scenario. These measurements have been used individually or combined with other parameters to indicate the level of the traffic congestion on certain road scenario. In this paper, we propose a context-aware traffic prediction technique. It predicts the context of the highway scenarios in terms of the existence of obstacles, broken vehicles, or entrance/exit points based on the distribution of vehicles’ traveling speed. From the experimental study, we can see that the proposed protocol have succeeded to predict the context of the highway. Our results indicate that our propose scheme exhibit good performance based upon an extensive set of simulation experiments.

High-level scene understanding and situational awareness are fundamental for autonomous vehicles before being widely used on public roads in a thoroughly efficient and safe manner. These tasks involve not only perceiving the current surrounding states but also predicting the future behavior of nearby human-driven vehicles. A large amount of vehicular sensing data can be collected using sensors and networking systems in vehicles. Moreover, with the advent of Dedicated Short Range Communication, vehicles can further transfer intention information to surrounding vehicles. However, real-time intention inference of nearby drivers is still challenging. Our primary focus is to present a novel deep learning-based approach to predict drivers driving behavior at unsignalized T-junctions. We use temporal convolutional networks to analyze sequences of trajectory data for a vehicle approaching the T-junction and classify the maneuver seconds before actual maneuver occurrence. The cross-validation results demonstrate the efficiency of the proposed methodology.

The Internet of Drones (IoD) is a novel network paradigm that presents a unique mobile network scenario with particular characteristics. Hence, privacy is a mandatory aspect to be assured, but there is a lack of studies regarding location privacy protection in IoD. Mix Zones is a location privacy protection mechanism well explored in terrestrial mobile networks, however, its investigation in IoD is still missing. In this work, we propose a novel Mix Zones-based approach, called MixDrones, that changes the airway of a drone besides its pseudonym. Hence, we advance the state of the art of location privacy protection mechanisms for IoD, in which MixDrones is the first approach proposed in this context. We carried out experiments through simulations comparing our approach with the traditional mechanism regarding anonymization coverage and resilience. We also evaluate the possibility of drone collision occurrence. The results pointed out that MixDrones provided a better location privacy protection than the traditional mechanism, anonymizing a large number of drones and being resilient through a trajectory-based de-anonymization attack, with less than 25% of trajectories being de-anonymized in all scenarios. Moreover, MixDrones mitigated the side effects of airway change, presenting low rates of airways change competition situations.

In recent years, to improve the transportation system's efficiency, relying on the development of vehicular wireless communication technology and corresponding in-vehicle sensor technology, intelligent transportation systems have become the focus of attention in academia and industry. This is because, by improving the vehicle's ability to perceive the surrounding traffic environment through the exchange of information between vehicles, the vehicle's safety can be effectively improved, which reduces the occurrence of traffic accidents, in turn improving the efficiency of the transportation system. However, while data exchange brings convenience, similar to the other data communication applications, communication security issues inevitably enter the Internet-of-Vehicles environment since the vehicle is no longer an isolated individual. Accordingly, in this paper, we will propose a data transmission security improvement method based on accurate traffic flow prediction for addressing a specific data theft problem. Briefly, our method can detect the fraud vehicle that spread fake traffic information to increase the possibility that it may be selected as a relay node, thereby increasing its theft of the data of related users who use it as a relay node. Intensive simulation experiments are conducted to evaluate and prove the efficiency of our proposed work.

Driver identification plays a pivotal role in the design of advanced driver assistant systems. The continued development of in-vehicle networking systems, CAN-bus technology, and the ubiquitous presence of smartphones as well as the broad range of state-of-the-art sensors have paved the way to collect huge amount of data from both vehicles and drivers. This paper addresses the necessity of having a large volume of labeled data for driver identification and presents a novel methodology to identify drivers based on their driving behavior analysis. The proposed architecture benefits from triplet loss training for driving time series in an unsupervised approach. An encoder architecture based on exponentially dilated causal convolutions is employed to obtain the representations. An SVM classifier is then trained on top of the representations to predict the person behind the wheel. The experiment results demonstrated higher performance of the proposed methodology when compared to benchmark methods.

The Fifth Generation (5G) communication technology has paved the way for intelligent and diversified Internet of Connected Vehicles (IoCV) services that meet stringent Quality of Service (QoS) requirements. Both Artificial Intelligence (AI) and Blockchain are playing and will continue to play an imperative role in providing secure and decentralized resource sharing to solve complex and time-sensitive problems at the edge. The integration of both those techniques will enhance the performance of smart vehicular services, especially in beyond 5G (B5G) networks. Ensuring secure transactions in complex autonomous network architectures is an immense challenge. This article addresses computational, storage, connectivity and intelligence concerns using a collaborative approach to engage multiple Internet of Things (IoT) nodes such as connected- vehicles, drones and mobile devices for the provisioning of QoS-optimal complex service compositions in autonomous mobile networks. Continuous and fast compositions emerge using decentralized decisions and interactions with diversified neighboring nodes with the aid of reinforcement learning. Blockchain is used to ensure that nodes interact with each other verifiably and record transactions without the need for trusted intermediaries. We assess whether having an AI-enabled blockchain collaborative composition solution improves service availability and delivery of smart city vehicular services.

Cloudlet-based mobile cloud offloading is an emerging technology designed to augment mobile elements by migrating resource-hungry components to adjacent local resource pooling. However, the Cloudlet resources are usually limited in terms of the computing utility, storage and network bandwidth. In this scenario, the remote Cloud infrastructure can provide additional computing and storage utility during run-time; the heterogeneous offloading methods for different mobile applications and diverse offloading resources complicate the Cloudlet-based offloading and resource allocation process. As a result, a considerable amount of delay is caused by setting up the execution environment, communication overhead and waiting in the queue, which significantly downgrade the QoS and the usability of such systems. In this paper, we propose a novel hybrid offloading model to solve the heterogeneous resource-constraint offloading issues in the Cloudlet, concerning the offloading energy and execution efficiency. A queue-based offloading framework is developed to formulate and analyze the mixed migration-based and partition-based offloading behaviors in the Cloudlet. The execution and energy-aware heterogeneous offloading resource allocation problem is formalized, and a Particle Swarm Optimization heuristic solution is presented. A SARIMA-based load prediction model is designed in the Cloudlet to achieve fine-grain proactive resource allocation. Experimental results reveal that the proposed framework can effectively reduce the offloading energy cost and execution time, compared to currently existing solutions.

Underwater wireless sensor networks (UWSNs) have emerged as an enabling technology for aquatic monitoring. However, data delivery in UWSNs is challenging, due to the harsh aquatic environment and characteristics of the underwater acoustic channel. In recent years, underwater nodes with multi-modal communication capabilities have been proposed to create communication diversity and improve data delivery in UWSNs. Nevertheless, less attention has been devoted to the design of networking protocols leveraging multi-modal communication capabilities of underwater nodes. In this paper, we propose a novel stochastic model for the study of opportunistic routing (OR) in multi-modal UWSNs. We also design two candidate set selection heuristics, named OMUS-E and OMUS-D, for the joint selection of the most suitable acoustic modem for data transmission and next-hop forwarder candidate nodes at each hop, aimed to reduce the energy consumption and improve the network data delivery ratio in multi-modal UWSNs, respectively. Numerical results showed that both proposed heuristics reduced the energy consumption by 65%, 70%, and 75% as compared to the DBR, HydroCast, and GEDAR classical related work protocols, while maintaining a similar data delivery ratio. Furthermore, the proposed solutions outperformed the CAPTAIN routing protocol in terms of data delivery ratio, while maintaining comparable energy consumption.

In the recent years, the Internet of Things has been becoming a vulnerable target of intrusion attacks. As the academia and industry move towards bringing the Internet of Things (IoT) to every sector of our lives, much attention needs to be given to develop advanced Intrusion Detection Systems (IDS) to detect such attacks. In this work, we propose Codebook-based Encoded Flow Features (CEFFs) as an innovative method to transform the raw flow-based statistical features into more discriminative representations taking into account the different flow features and patterns of various devices. Based on the proposed CEFFs, we build and leverage Support Vector Machine (SVM)-based classifiers to discriminate the malicious flows from the benign ones. The effectiveness of the proposed CEFFs for intrusion detection is evaluated on two state-of-the-art realistic datasets, achieving high accuracies and low false positive rates across a variety of intrusion attacks.

Cloud Computing has emerged as a foundation of smart environments by encapsulating and virtualizing the underlying design and implementation details. Concerning the inherent latency and deployment issues, Mobile Edge Computing seeks to migrate services in the vicinity of mobile users. However, the current migration-based studies lack the consideration of migration cost, transaction cost, and energy consumption on the system-level with discussion on the impact of personalized user mobility. In this paper, we implement an enhanced service migration model to address user proximity issues. We formalize the migration cost, transaction cost, energy consumption related to the migration process. We model the service migration issue as a complex optimization problem and adapt Deep Reinforcement Learning to approximate the optimal policy. We compare the performance of the proposed model with the recent Q-learning method and other baselines. The results demonstrate that the proposed model can estimate the optimal policy with complicated computation requirements.

For releasing the public concern on road safety, as an essential driving assistant technique for supporting autonomous deriving, considerable research efforts have been paid on developing practical traffic-related target/object detection methods. In recent years, by exploiting the powerful parallel processing capability of GPU and the feature extraction ability of deep convolutional neural network (CNN), the visible light image-based pedestrian detection method has gradually been considered as a potential solution. However, although it has been proven in the existing literature that CNN-based pedestrian detection methods can greatly improve the detection efficiency for lightly occluded pedestrians, the detection of low-visible pedestrians is still an open challenge. Accordingly, in this paper, we propose a novel collaborative pedestrian detection frame based on the Internet-of-Vehicles (IoV) to detect low-visible/hidden pedestrians or even hidden pedestrians. We further evaluate the proposed pedestrian detection framework relying on simulation experiments.

Internet of Underwater Things (IoUT) has gained increased attention as an envisioned technology for supporting smart ocean applications. However, the harsh aquatic environment and challenges of underwater acoustic communication still severely limit data collection in underwater networks and IoUT applications. In recent years, programmable physical layer and multi-modal communication for IoUT have been proposed to improve the performance of underwater networks. However, several fundamental challenges need yet to be investigated and tackled, in order to achieve efficient data collection in IoUT. One of the daunting fundamental challenge to be solved is the design of innovative routing protocols for multi-modal IoUT. In this paper, we propose a mathematical model for the study of opportunistic routing (OR) in multi-modal IoUT. The devised mathematical framework models the unique characteristics of OR in multi-modal IoUT scenarios, while considering the peculiar characteristics of the underwater environment and acoustic communication. Moreover, we propose a candidate set selection procedure of OR, which jointly selects the acoustic modem and next-hop forwarder candidate nodes at each hop, to increase data delivery. Numerical results showed the potential of multimodal communication for improving data delivery in the harsh environment of underwater acoustic communication.

Evaluating Blockchain performance is not an easy task. It is difficult to compare different systems, since the evaluation is often incomprehensible and conducted in different environments with distinct workloads. Only a handful of prior tools were proposed, e.g., BLOCKBENCH and HFBench. Unfortunately, these tools have several limitations. We first identify these limitations. Second, motivated by our observations, we then present a benchmarking tool, Boston Blockchain Benchmarking (BBB). BBB is configurable, extensible, and easy-touse. In particular, BBB can be used to test Blockchain from a networking perspective, a feature that we have not observed in prior tools. Similar to BLOCKBENCH, we focus on the private Blockchain. Concretely, we integrate our tool with Mininet, and provide a simple mechanism to test how network properties (e.g., latency, bandwidth, package loss rate) affect the performance of the chosen Blockchain. We present our preliminary result of evaluating Ethereum. We stress that the architecture of BBB is general, and could be extended to other Blockchain systems. BBB is extremely lightweight and can be used on your laptop to test a small network. Such a feature allows quick evaluation of the Blockchain and speeds up innovation and development.

Mobile Crowdsensing (MCS) builds on the Sensing as a Service model, and is considered to be an integral component of the Internet of Things systems. Since MCS does not build on a thoroughly assessed and established trust mechanism between all parties various threats including data poisoning, fake sensing tasks and clogging task attacks remain challenges. Fake task submissions are the least investigated although they have the potential to drain significant amount of resources (e.g. battery, sensors, processing, storage) and clog the MCS servers. This paper proposes a knowledge-based technique alongside sequential feature selection methodology to detect fake sensing tasks submitted to the MCS servers so that the tasks do not get assigned to the participants but filtered at the MCS servers. The proposed methodology is compared to fake task detection under Knowledge Based Deep Neural Network which is also enhanced by feature selection, and the simulation results show that the proposed methodology, by utilizing Deep Prior Knowledge Input with Self-Organizing Feature Map can outperform the deep neural network-based detection by 9.7% in terms of accuracy.

Stop signs are located at road intersections, school buses and besides pedestrians crosswalks. Drivers should obey a full halt that their vehicles have no momentum for a certain period of time infront of these signs. However, this requires early notification for drivers to start the safe and smooth stop at adequate time and distance. In some scenarios drivers miss to see these stop signs early enough to respond properly. This is due to some obstacles, road design and/or bad weather conditions. Moreover, the optimal time and distance of each vehicle to start reducing its speed aiming to stop depends on that vehicle's type and its traveling speed, the road design and weather conditions. Thus, drivers may face some difficulties in many scenarios to stop their vehicles smoothly. In this paper, we propose a driving assistance protocol that early detects the existed stop signs in the surrounding road network. It also notifies each vehicle regarding the time, location and deceleration rate where it should start reducing its speed to park smoothly in front of the next stop sign. The proposed protocol uses the technology of the vehicular network to gather the real-time conditions of each scenario. It proves a good performance in terms of enhancing the safety of vehicles around stop signs.

With the increasing demands for various wireless communication technologies and standards, new challenges arise in seamless connectivity among different techniques. Mobility management protocols face a new difficulty in vehicular network heterogeneity, from deployment issues to optimal handover management process. However, due to the dynamic environment in vehicular networks, providing the best quality of service is a critical issue. Additionally, conventional mobility management solutions do not consider user's preferences when selecting the next points of access. In this paper, we present a load balancing and QoS-aware handover scheme in Heterogeneous Vehicular Networks (Het-VeNET) in order to choose the least loaded network, while maintaining the high level of required quality of service. We define the vehicle's mobility and QoS measurements and demonstrate the stated handover process in a vehicular environment. The proposed scheme performance showed a higher rate of successful handoff and load balance on different cells and scenarios when compared to benchmark schemes.

For improving the road safety and efficiency of the transportation system, tremendous approaches for autonomous driving and Intelligent Transportation System (ITS) have been proposed. Among them, the Lane Departure Warning System (LDWS) is a key issue. The main function of LDWS is that when the vehicle being driven is offset from the center of the lane too much, it will notify the driver as fast as possible in a variety of ways, such as vibration or sound. Accordingly, effectively detect the road lane and accurately calculate the deviation between the vehicle's trajectory and the lane centerline is a key issue to achieve this design goal. For improving the performance of LDWS, many computer vision-based methods have been proposed in recent years. In this paper, we propose a novel LDWS model by improving the methods of image processing, lane detection, and lane departure recognition. By comparing our experimental results with RTCF-LDWS and CRAL, our model is more efficient in accuracy and processing time.

Diversified Internet of Things services are becoming more complex and strictly user-defined. Traditional cloud solutions proved to be both costly in terms of resources and time efficiency. To overcome such a burden, researchers developed fog solutions for faster service responsiveness. Fog-to-Fog communication and cooperation was then introduced to compose services on-the-go for user-specific requests with the aid of mobile edge devices. This paper introduces a blockchain-based decentralized service composition solution for complex multimedia service delivery to cloud subscribers. The proposed work dynamically creates user-defined services without requiring any intermediary service or network provider entities to authenticate and deliver composite services. The composition process uses a reinforcement learning technique to construct secure and reliable composition paths. Participants are rewarded by cloud and fog entities for solving complex composition processes. Simulation results conducted on the system show that by adapting the proposed technique, fog and cloud entities require less resources and reduced power usage with increased service delivery success rates to cloud subscribers.

This paper proposes a new framework to reconstruct vehicle trajectories from GPS datasets. GPS-embedded vehicles generate massive vehicular trajectory data that are crucial for many applications, such as route recommendation, traffic analysis, urban planning, and Intelligent Transportation Systems (ITS). In order to achieve that, it is necessary to employ processing techniques such as noise filtering, segmentation, and map matching to prepare the data to be properly used by real applications. The proposed framework aims to reconstruct the trajectories completely, even from low sampled data, which naturally present gaps. Experimental results show the effectiveness and efficiency of the framework to reconstruct trajectories with different sampling rates and different characteristics.

Reliable traffic flow prediction can greatly support the Intelligent Transportation System (ITS) to generate more effective traffic management decisions. Previous volume predictions mainly focused on the single road with simple flow patterns, such as suburban highways. However, with the development of the urban transportation system, the reliable flow information support becomes more significant for forming a solid ITS. Besides, travel delay is another widely neglected problem but can affect the prediction result significantly. Specifically, vehicles need some time to move from one place to another, and this time is called the travel delay. For further enhancing the prediction performance under the urban scenario, we propose a delay-based deep learning framework (MDGRU) to improve the accuracy of the short-term traffic flow prediction, in which travel delay is handled in the form of a weighted matrix enrolled into a multivariate input stacked Recurrent Neural Network (RNN). Multivariate input makes this approach has a stronger mining ability for spatial relationships capture, and the stacked structure leads to a more accurate pattern learning process. The results show that our approach is accurate and reliable.

Nowadays, traffic flow prediction, as a vital part of the Intelligent Transportation System (ITS), has attracted considerable attention from both academia and industry. Many prediction methods have been proposed and can be categorized into parametric methods and non-parametric methods. Nonparametric methods, especially Machine Learning (ML)-based methods, compared to parametric methods, need less prior knowledge about the relationship among different traffic patterns and can better fit the non-linear features of traffic data. However, we notice that, due to the complex structure, ML-models require a higher cost of implementation regarding time consumption of training and predicting. Therefore, in this paper, we evaluate not only the accuracy but also the efficiency and scalability of some state-of-the-art ML-models, which is the key to apply a prediction model into the real world. Furthermore, we design an off-line optimization method, Desensitization, to improve the scalability of a given model.

Energy efficiency is a crucial issue for a practical wireless sensor network (WSN) due to the battery-powered sensors. For improving energy efficiency, many methods have been designed in WSNs thanks to the emerging techniques, i.e., data gathering and wireless charging. The data gathering algorithms are advantageous to decrease the energy consumption of nodes, and the wireless charging schemes can replenish energy to sensors for achieving the semi-permanent WSN. Though lots of approaches of each technique have been designed, the joint methods of both are still lacking. In this paper, a joint data gathering and wireless charging scheme is designed by adopting the mobile chargers (MCs) which can execute the energy charging and the data collection simultaneously. To decrease the data latency, an improved clustering algorithm is implemented first to construct the topology of the WSN. Then, a heuristic-based MC scheduling scheme is proposed for maximizing the charging utility while minimizing the energy consumption of MCs. Compared with the existing joint method, the proposed scheduling scheme achieves the outperformance on delay and charging utility.

Top-k considers as a technique to retrieve, from a hypothetically big data set, only the k (k ≥ 1) best (most relevant/important) candidates. Top-k query processing is a decisive necessity in various collaborative environments that comprise big data such as the Internet of Things (IoT) networks. Particularly, efficient top-k processing in large-scale distributed systems has shown a positively noticeable effect on their performance. This paper considers the distributed approximate top-k processing algorithms dedicated to the IoT-based networks and improve the accuracy of algorithms introduced previously. We then propose a safety-based fault-tolerance notation and contribute to improving a known algorithm in terms of accuracy. Our algorithms have been evaluated using simulation and real-world data and show superiority over conventional methods.

In this paper, we address a fundamental problem in vehicular networks, which consists of sending messages from a source vehicle to a destination vehicle. This problem becomes even more complex in the absence of fixed infrastructure or any other controlling entity. Although there are some solutions in the literature to work around this problem, they can cause significant network overhead and generate an amount of redundant data. In this regard, we develop a routing protocol that considers individual vehicular mobility as a determining factor for routing decisions. Through simulations using realistic vehicular mobility trace, we have observed that our strategy considerably decreases network overhead and the number of hops between source and destination while maintaining similar values for delivery ratio and latency.

With the increasing highlighted security concerns in Intelligent Transportation System (ITS), Vehicle Make and Model Recognition (VMMR) has attracted a lot of attention in recent years. The VMMR method can be widely used in suspicious vehicle recognition, urban traffic monitoring, and the automated driving system. With the development of the Vehicle-to-Everything (V2X) technology, the vehicle information recognized by the AI-based VMMR method can be shared among vehicles and other participants within the transportation system, and can help the police fast locate the suspicious vehicles. VMMR is complicated due to the subtle visual differences among vehicle models. In this paper, we propose a novel Recurrent Attention Unit (RAU) to expand the standard Convolutional Neural Network (CNN) architecture for VMMR. The proposed RAU learns to recognize the discriminative part of a vehicle on multiple scales and builds up a connection with the prominent information in a recurrent way. RAU is a modular unit. It can be easily applied to different layers of the vanilla CNN architectures to boost their performance on VMMR. The efficiency of our models is tested on three challenging VMMR benchmark datasets, i.e., Stanford Cars, CompCars, and CompCars Surveillance. The proposed ResNet101-RAU achieves the best recognition accuracy of 93.81% on the Stanford Cars dataset and 97.84% on the CompCars dataset.

To increase traffic safety and transportation efficiency, adopting intelligent transportation systems (ITS) has become a trend. As an important component of ITS, one essential task of autonomous vehicles is to detect pedestrians accurately, which is of great significance for improving traffic safety and building a smart city. In this paper, we propose an anchor-free pedestrian detection model named Bi-Center Network (BCNet) by fusing the full body center and visible part center for each pedestrian. Experimental results show that the performance of pedestrian detection can be improved with a strengthened heatmap, which combines the full body with the visible part semantic. We compare our BCNet with state-of-the-art models on the CityPersons dataset and the ETH dataset, which shows that our approach is effective. Compared to the backbone model, our BCNet improves the detection accuracy by 1.2% on the Reasonable setup and Partial Setup of the CityPersons dataset.

Mobile Crowdsensing (MCS) leverages Sensing as a Service paradigm to contribute to the Internet of Things ecosystems through non-dedicated sensing capabilities of smart mobile devices. Distributed and non-trusted nature of MCS systems are vulnerable against various threats for the devices, MCS platforms, as well as the participating devices that provide sensory data services. Out of the many threats, submission of fake tasks may lead to drained resources at the participating devices, and clogged sensing server resources at MCS platforms. In this paper, classical machine learning (ML) performance is boosted by knowledge-based methods and sequential feature selection which is proposed for the first time against fake tasks submission to MCS platforms. Prior Knowledge Input and Prior Knowledge Input with Difference exploit AdaBoost and Decision Tree methods as initial accuracy to improve the accuracy of learning the legitimacy of submitted tasks to MCS platforms. Moreover, Sequential Feature Selection is implemented to investigate further improvements for the detection of task legitimacy in MCS campaigns. Intelligently selected 5 features amongst 10 possible features and implementation of knowledge-based methods boost the accuracy of machine learning performance from 93.67% to 97.37% for AdaBoost, and from 92.28% to 97.58% for Decision Trees.

Software-Defined Vehicular Networks has been a vital component for heterogeneous radio access technologies to support massive data load through various safety and infotainment applications. Elevating the constraint of static hardware network devices into a programmable unit and providing a global view of the network status and standard interface between heterogeneous radio access technologies. However, having a logically centralized control unit brings several challenges, including bottleneck problem and densification issues. A distributed control plane comes as a possible solution to the centralized control plane yet with several questions of where to deploy the control units and how many SDN controllers are needed in a given network structure. In this paper, we present an adaptive Flow-based controller deployment and assignment strategy for distributed Software-Defined Vehicular Networks through the utilization of the communication latencies between switch-enabled access points and their corresponding vehicles' flow over a time window. We evaluate the proposed method's performance in terms of end-to-end delay and load on the resulted controller's points and their cluster's set. The clustering method is compared to several types of static placement strategies, in which the proposed method showed a reduction in controllers' average delays while distributing the load among them over time.

In addition to being one of the primary means of transport, with the advent of sensing and communication technologies, buses belonging to the public transport system have gained a new role in urban centers. They have been applied as a powerful vehicular network that covers an entire city, called BUS-VANET. For the design and validation of solutions for this type of network, the nodes' mobility information is essential. For instance, data from the buses' GPS trajectories can be used to understand the dynamics of encounters between them. This knowledge can be applied to design applications and services for different users, besides providing the necessary information to properly manage this important public transport solution. However, real-world trajectories have several imperfections. In particular, GPS trajectories are heterogeneous, asynchronous, and typically contain a low sample rate. These characteristics impose certain limitations on the use of this dataset in the design of solutions for a BUS-VANET. In this work, we propose a hybrid method of calibrating trajectories based on historical information of trajectories and a road network to overcome these problems. We showed that our method surpasses the state-of-the-art techniques in several perspectives through evaluation with realistic data.

Eco-driving techniques are methods that drivers can take in order to improve their vehicles’ fuel efficiency. One way of implementing such methods is to recommend changes in driving habits focusing on saving fuel. Recommendation systems in the context of efficient driving may take numerous data sources as input and serve multiple purposes. In this work, we develop a recommendation system that suggests changes in engine revolutions per minute (RPM) that reduce fuel consumption. We simulate the effects of this system using a vehicular sensor dataset that contains location, speed, RPM, and consumption. We also investigate the effects of including location data in the recommendations as a way to leverage local habits and behaviors. Both methods reduced fuel consumption in all recorded trips. Moreover, using only local data yielded a mean fuel reduction of 43%, whereas using the entire dataset reduced the fuel consumption in 56% on average. Upon analyzing the resulting changes, we noted that such a difference in fuel consumption is due to the local recommendations not having access to global optimal data points and accounting for local behavior that is affected by aspects such as terrain.

Modern cars can collect several hundreds of sensor data through the controller area network (CAN) bus technology that provides almost real-time information about the car, the surrounding environment, and the driver. These data can be later processed and analyzed to offer efficient solutions and insights for human behavior analysis and further applied in a variety of fields such as accident prevention, driver identification, driving models design, and vehicle energy consumption. By analyzing and identifying unique driving behavior, we can distinguish drivers, which can be helpful in driver profiling and security of the cars (anti-theft systems). In this paper, we evaluate the performance of data-driven end-to-end models designed for driving behavior identification. We present a critical analysis of the principles considered in designing the models. Moreover, various data-driven deep learning and machine learning models are implemented and the cross-validation results are presented employing the naturalistic driving dataset.

The next revolution of industrial applications, known as smart industry or Industry 4.0, will rely on Internet of Things (IoT) to automate the monitoring, inspection, and control of industrial equipment and processes. In Industry 4.0, efficient content delivery is one of the fundamental challenges to be addressed. Nowadays, the promising solution for content delivery in smart industrial applications is the use of hierarchical caching systems at the network edge (5G small cells). This approach reduces the delay for content delivery and helps improve the performance of smart industrial applications. However, the caching management is a challenging and complex task, especially in those scenarios of shared storage resources on edge devices to support multiple concurrent applications (e.g., industrial, mobile users, and connected cars applications). In this article, we study the performance of a shared edge caching system for content delivery in smart industry and connected cars applications. To do so, we propose a mathematical framework to model the performance of a hierarchical shared edge caching system. The proposed mathematical framework considers the distinct content catalogs of the different applications (e.g., industrial and connected cars applications) and content request characteristics from industrial IoT devices and vehicles. Numerical results show that the performance of the shared edge caching system is sensitive to vehicular mobility (i.e., vehicular speed).

Computation offloading for vehicular edge computing (VEC) architecture has gained increasing attention, with the emergence of mobile and vehicular applications with high-computing and low-latency demands, such as Intelligent Transportation Systems and IoT-based applications. However, existing challenges need to be addressed for VEC's resources to be used in an efficient manner. The fundamental challenges arise from high vehicular mobility and intermittent or lack of connectivity. In this paper, we model the computation offloading task in VEC, with the goal of assessing the ability to simulate the elements that contribute to enhancing its performance in VEC. In addition, we propose the Mobility Prediction Retrieval (MPR) data retrieval protocol, which allows VEC to efficiently retrieve the output processed data of the offloaded application by using both vehicles and road side units as communication nodes. The developed protocol uses geo-location information of the network infrastructure and the users to accomplish an efficient data retrieval in a Vehicular Edge Computing environment. Finally, the experiments performed show that the proposed protocol to achieves a more reliable data retrieval with lower communication delay when compared to related techniques.

Vehicles are integral elements of urban computing and urban analytics, providing sensed data and thus being closely related to the exchange and gathering of a massive quantity of data in real-time. Vehicular Clouds consist of joining Vehicular Networks with Mobile Cloud Systems, allowing vehicles to share their resources and facilitate the transfer of information. Due to its mobility, the pool of resources in a Vehicular Cloud changes constantly. Thus, these Clouds need to adapt according to the input and output of their resources to meet the requirements of quality of service. Resource management and discovery are crucial elements for enabling and maintaining such Clouds. In this paper, we describe and discuss important issues about identifying and organizing resources in a Vehicular Cloud, as well as the specific techniques involved. Finally, we discuss challenges and issues for potential future works.

Nowadays, wireless sensor networks (WSNs) are widely adopted by many civil/military applications. However, due to the limited capacity of the built-in battery, the lifetime of the sensor is limited, which in turn affects the working time of the whole system. Therefore, the limited energy supply is the most direct and critical constraint to maintain the long-term and efficient operation of the system. Accordingly, reducing energy consumption/improving energy efficiency is an essential prerequisite for designing a sustainable WSN. To address this problem, many approaches have been proposed. To help readers fully understand the techniques/methods in this area of research, we present a taxonomy of the existing energy-efficient strategies for achieving sustainable WSNs. We first introduce some basic concepts and assumptions commonly adopted in energy-efficient WSNs designs. Then, we discuss existing approaches designed for conventional WSNs (consisting of static nodes or nodes with limited mobility) from five aspects: clustering-based schemes, node deployment strategies, node scheduling algorithms, energy-efficient routing schemes, and energy-efficient joint designs. We compare these schemes and highlight their strengths and drawbacks. Additionally, we discuss state-of-the-art approaches relying on some emerging techniques, e.g., high-mobility data collectors, energy-harvesting techniques, etc. Finally, we conclude the paper and present some open challenges.

Efficient MAC protocols are fundamental to conserve energy and enable sustainable delay-tolerant sensor networks (DTSNs). They can be explored to reduce energy consumption, deal with relaxed latency requirements, support mobility and address diverse traffic loads. In this paper, we theoretically analyze the performance of reservation-based and contention-based MAC protocols in DTSNs regarding throughput and energy consumption, respectively. According to the derived theoretical results, we propose a TRaffic-adaptive energy-efficient MAC protocol (TREEM) to achieve better data transmissions as well as energy efficiency, in order to satisfy DTSN requirements. More precisely, our protocol can dynamically switch its working mode between contention and reservation to adapt to the varying data traffic. In addition, to further improve the energy efficiency of DTSN, our algorithm can also calculate the more suitable duty/active period length. The simulation results of TREEM demonstrate better performance in terms of energy efficiency and traffic adaptability than the schedule-based MAC protocol TDMA, the contention-based protocol CSMA, and the traffic-adaptive protocol TRAMA under mobile DTSN environments.

Virtual Machines (VMs) are used to increase flexibility and to reuse available resources in a vehicular cloud. These VMs allow the use of an environment capable of executing processes without the need for physical resources. Due to the mobility characteristics of vehicles in a vehicular cloud, these VMs can be migrated to different physical hosts. Furthermore, this migration of VMs can occur due to the need for load balancing, the scarcity of cloud resources, and the need to optimize the energy consumption of the vehicular cloud infrastructure. Establishing a mobile cloud migration policy becomes a major challenge due to the characteristics of the vehicular networks. In this paper, we propose an architecture for VMs migration in vehicular clouds based on the Energy-Aware paradigm. We also propose a new migration policy of VMs based on the energy expenditure of this migration, considering the energy expenditure of the VMs in the cloud and in the cloudlet, as well as the energy consumption of the communication between cloudlets, clouds, and vehicles. Simulation results show that the proposed policy achieved a reduction in the system's power consumption of about 10 percent. Furthermore, the proposed approach also reduced the number of drop migration of VMs by 5 percent.

Recently, the Vehicular Network (VN) has received a lot of attention from researchers around the world. By allowing wireless communication, VNs enable information exchange among vehicles, which in turn has allowed drivers to become more aware of their surrounding road conditions. Accordingly, road safety is improved. However, due to the fast speed and frequent changes of direction of vehicles, the network topology of VNs is transient in nature. Hence, achieving efficient data dissemination/content delivery is a critical issue in the VNs-environment. In this article, we will introduce a novel passive roadside unit (RSU) detection-based proactive (PRDP) handover scenario. Consequently, the overhead of the handover process can be reduced, and the probability of successfully established connections can be improved. More precisely, by taking advantage of the Doppler effects of the received beacon signal, the passive RSU detection (PRD) scheme is derived by the maximum likelihood estimation function. Then, in combination with the extended Kalman filter (EKF), the PRDP handover protocol is designed to improve the energy efficiency of the handover procedure in the VNs-environment. We conduct intensive simulations to verify the proposed RSU detection scheme, and the experimental results further evaluate the performance of the proposed energy-efficient proactive handover protocol.

Nowadays, to deal with driving safety-related issues and improve travel comfort, the VehiculAr NETwork (VANET) has gained tremendous attention from researchers in both academia and industry around the world. By taking advantage of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications, the VANET can significantly enhance road safety and travel comfort by improving drivers' awareness of their surrounding road environment and providing entertainment-related data service for passengers, respectively. However, due to the highly dynamic nature of the network topology in VANET, how to achieve reliable data transmission and content delivery is a critical task for implementing VANETs. Accordingly, in this article, we provide a novel data-highway-assisted content delivery protocol for addressing the content delivery problem in VANETs, in which, we explore the advantages of the predicted vehicular traffic volume driven by a newly designed fast traffic flow prediction scheme. We evaluate the performance of the proposed traffic flow prediction scheme by using three different data sets with different vehicles traffic flow patterns are chosen from the England Highways data set. Moreover, extensive simulations have been implemented to evaluate the proposed content delivery protocol.

Wireless networks development to support the highly dynamic vehicular environment pose several significant challenges for vehicular network services and applications, in efforts to guarantee seamless communication. Intelligent Vehicular Networks goal is to provide high-quality services that can learn and forecast clients' needs and intentions. Machine Learning (ML) is one type of artificial intelligence that can be effective in utilizing the vehicular network's data to predict users movements and allocate resources ahead of time. In this paper, we propose a novel online ML-based Roadside Unit (RSU) prediction scheme for mobility management in Vehicular Networks, to provide seamless mobile connectivity to vehicles and enhance the performance of the prediction model. An Online Probabilistic Neural Network (O-PNN) prediction model is designed and adjusted for VANETs mobile IP protocol. Extensive simulation experiments were performed on the Network Simulator NS-2, and the performance of the prediction model is studied with different traffic and mobility scenarios. Our results showed a high accuracy rate in comparison to several other machine learning models.

Every year, natural and human-induced disasters result in infrastructural damages, monetary costs, distresses, injuries and deaths. Unfortunately, climate change is strengthening the destructive power of natural disasters. In this context, distributed simulation-based disaster management and response systems have been proposed to cope with disasters and emergencies by training first responder with the latest ICT technology, and improving the disaster detection and search/rescue missions during disaster response. With the recent advances in wireless communication, and the proliferation of portable computer and micro-sensor devices, we are witnessing a growing interest in using wireless multimedia sensor networks and collaborative virtual environment technologies for safety and security class of applications. In this talk, we will give an overview of some research projects related to smart emergency preparedness and response that are currently being investigated at the PARADISE Research Laboratory at the Ottawa. We will show how collaborative virtual environment, context aware computing, wireless multimedia, and wireless sensor networks can be used to ensure public safety and security. We will focus upon the design of large-scale distributed simulation system for applications that require critical condition monitoring using both location/context aware computing and wireless sensor technologies. The second part of the talk will conclude by presenting two testbeds that are currently under development at PARADISE: the LIVE testbed, and the SWiMNet testbed. LIVE is a testbed for applications that require emergency preparedness and response. LIVE’s architecture integrates wireless sensor networks with wireless multimedia and virtual environment technologies. SWiMNet is a testbed of a high-performance simulation system that supports very detailed and realistic model specifications to enable the design and evaluation of new protocols and applications for future generations of mobile networks, vehicular networks as well as sensor networks.

The advancements in mobile hardware and network technologies facilitate the processing power, storage capability, and connection quality. Such developments enable sophistic functions, ubiquitous power- and bandwidth-hungry applications that fundamentally changes the individual's lifestyle. Although Cloud Computing technologies have already been leveraged to coordinate with the capability and battery-constraint mobile User Equipment (UE), the long-distance propagation delay downgrades the network QoS and user QoE. In this paper, we propose a queueing-based Mobile Edge Computing (MEC) model that concerns the offloading procedure, especially in the time-constraint scenarios. A queueing model is proposed for the offloading process, considering the dynamic network queueing delay. A heuristic scheduling model is designed to maximize the offloading energy and execution efficiency. A regression prediction model is implemented to achieve dynamic resource allocation. In the experiment, the proposed model is compared to the recent studies, and the results indicate that the proposed model can outperform the current studies in terms of execution time and energy reservation.

Recently, to improve the efficiency and safety of the transportation system that is severely affected by the increasing traffic demand, the Internet-of-Vehicles (IoVs)/Vehicular Networks (VNets) have received more and more attention because it can effectively improve the ability of the participants in the transportation system to perceive the traffic environment around them through Vehicle-to-everything (V2X) technique. Moreover, V2X also makes it possible to share computing and storage power between vehicles, which further promotes the development of vehicular edge computing (VEC). However, due to the highly dynamic nature of the VNet's topology, based on the instant traffic flow condition, how to determine whether the vehicles on a given road can form a relatively stable cloudlet with certain computing or data storage capabilities to support certain VEC applications becomes a crucial task that needs to be solved. Therefore, in this paper, we proposed a Cloudlet-Dwell-time (CDT) estimation method to theoretically derive some essential parameters for implementing VEC applications, i.e., the vehicular cloudlet existence probability and its corresponding dwell-time. We further demonstrate the results of the proposed work based on traffic flow data chosen from the England Highways data set.

Understanding the mobility of vehicles plays a fundamental role in the design of solutions for intelligent vehicular networks. Considering that different types of vehicles have different characteristics of mobility, we are interested in investigating how bus mobility impacts the formation of these networks. In this sense, we present clear understanding the bus mobility for vehicular networks. Our analysis is based on a real mobility trace of buses from several days of Dublin, Ireland. Particularly, our study reveals key features of a vehicular network obtained from a real bus mobility trace such as the network structure over the days and how the components of the networks are arranged in the space and time. Additionally, we investigate the potential of bus mobility for urban sensing. In summary, due to network fragmentation identified in our analysis, data dissemination mechanisms that use store-carry-and-forward and street-centric routing are more indicated for intelligent vehicular networks based on bus mobility. Moreover, we show how the use of buses as sensors can compose a powerful urban sensing infrastructure.

Broadcast is one of the fundamental primitives to enable large-scale networks such as sensor networks and IoT. There is a rich study on achieving reliable broadcast under various kind of failures. In this paper, we use the notion of trust to improve the performance of reliable broadcast. We focus on Certified Propagation Algorithm (CPA), one of the simple algorithms that does not rely on a cryptographic infrastructure and has a proven guarantee on resilience (number of node failures tolerated). Specifically, the paper has two main contributions: (i) A new algorithm Trust-CPA which integrates CPA with trusted nodes has been proposed and shown to increase the resilience from the original CPA, and (ii) A natural optimization problem related to Trust-CPA (i.e., finding the location to place trusted nodes to reduce the broadcast latency) has been proposed as well. We first show that it is NP-hard to find an exact answer and even NP-hard to find a good approximation. A greedy heuristic algorithm has been used and its efficacy has been examined using simulation. We show that our algorithm performs relatively well in geometric random graphs, an appropriate model for large- scale wireless sensor networks.

Due to the limited battery capacity, the lifetime and performance of the battery-powered WSNs are constrained. In order to prolong the lifetime, applying mobile data collectors to gather data in WSNs is a promising approach. In this paper, we design a two-phase data gathering strategy with the mobile data collector in the cluster-based WSN to improve energy efficiency and satisfy the delay constraints. More precisely, the sensors are divided into a set of clusters in the first phase, which ensures that the sensors can communicate with the mobile data collector within predetermined hops. We then develop the path for the mobile data collector using a genetic algorithm that is an applicable strategy for the optimization problem with respect to the shortest path finding in the large-scale WSNs. We evaluate the performance of the proposed path planning protocol by conducting intensive simulations. The simulation results indicate that the proposed scheme outperforms some state-of-the-art techniques on energy efficiency while enhancing the data update rate.

Freeways have been known over decades as high-speed multi-lane roads, where the opposite traffic directions are completely separated. No intersections, pedestrians, or bicycles are expected on these road scenarios, besides specific ramps are designed to facilitate the entrance and exit of vehicles. Although freeway driving is considered safer and faster for experienced drivers, it can be more demanding and difficult for fresh or exhausted ones. Entering and existing the freeway road are considered the most critical situations where the driver needs to achieve high synchronizations with the surrounding traffic there. In this work, we introduce a freeway driving assistance protocol for drivers aiming to reduce the difficulties for fresh drivers and enhance the safety and efficiency conditions over the freeway road scenarios. This proposed protocol can also be used by the autonomous vehicles where no drivers control the vehicle. We evaluate the performance of the proposed protocol using several simulated driving scenarios. It shows a good performance in terms of increasing the safety of traffic and smoothing the traffic speed of vehicles.

Vehicular Networks will play a leading role in the next generation of Autonomous Driving (AD), as recent advances in vehicular networks are a promising solution for traffic management and congestion issues, as well as lane optimization. Wireless mobile communication in VANETs is essential for the content delivery of local and global information for intelligent operation decisions in autonomous driving control applications. However, the vehicles' high mobility and topology changes affect the performance of traditional mobility management protocols over VANETs. Therefore, an efficient mobility management solution that mitigates the challenges of vehicles' mobility is needed to support autonomous driving. In this paper, we present an efficient probabilistic neural network-based Road Side Unit (RSU) prediction scheme for autonomous driving control using vehicular networks. We evaluate the performance of the predictor against different machine learning models. Our results showed a high accuracy rate in comparison to several neural network models in various mobility environments.

Understanding mobility is a fundamental task in the design of mobile networking solutions. The adoption of mobility traces is extremely relevant both to obtain a meaningful understanding of mobility and to create realistic simulation scenarios. However, those traces may have different features that lead to conclusions inconsistent with reality and, consequently, impact the performance of the proposed solutions. In this work, we propose a methodology to evaluate mobility traces considering their spatial and temporal aspects. Furthermore, we review real, publicly available, and widely adopted mobility traces and discuss the application them to vehicular networks. The results show that the use of mobility data for vehicular networks is extremely timely, but that they must undergo a process of quality improvement.

In recent years, the opportunistic routing (OR) paradigm has been shown as one of the most viable solutions at the network layer for efficient data delivery under the nosily underwater acoustic channel. Since then, several OR protocols for underwater sensor networks, with major and minor variations, were proposed in the literature. While the performance of these protocols, in terms of data delivery rate, delay, and energy consumption, has been extensively studied in the literature, there is a lack of studies devoted for the evaluation of the topological properties OR will incur. In this paper, we evaluate the performance of the candidate set selection procedures of opportunistic routing protocols designed for underwater sensor networks. We discuss the principles that have been extensively considered for the design of OR protocols for underwater sensor networks. Moreover, we conduct a simulation-based performance evaluation to study topological properties (e.g., number of hops, number of paths and number of candidates), which will impact the performance of underwater wireless sensor network applications.

We are witnessing the development of the new era of the vehicles' evolution history: the era of connected and autonomous vehicles. In this new era, vehicles will be empowered with processing, sensing, actuators and wireless communication capabilities, which will support a wide range of vehicular applications to improving safety, efficiency and enjoyableness of transportation. In this revolution, processing and exchange of multimedia and big data will be fundamental. Therefore, content distribution is one of the critical challenges in connected cars and intelligent vehicular networks. In this tutorial, we will discuss the recent advancements and research directions towards the development of solutions for content distribution in connected cars and vehicular networks. We will highlight the current state-of-the-art and identify research opportunities that could interest researchers willing to contribute in different areas, such as vehicles' mobility characterization and modeling, modeling and performance evaluation of information-centric networking in vehicular networks, broadcast storm avoidance of Interest and Data packets, content placement and cache policies, as well as networking protocols and architectures for service-oriented information-centric multimedia content distribution for vehicular networking and connected vehicles' applications [1]-[12].

The great revitalization of information and communication technologies has facilitated broad connectivity to the Internet. However, this convenience in terms of connectivity comes with costly caveats, including internet fraud, information damage or theft, and cybersecurity issues. Most individuals rely on anti-virus software for protection. This anti-virus software has long been a foe to malware authors, but there are brief moments when new techniques slip through the cracks, and even the most sophisticated engines sometimes fail. A new tool, namely Metasploits new evasion modules, claims to exploit that. In this study, we compare and evaluate legacy evasion techniques with the novel tactics presented by Metasploits lead researcher Wei Chen. We consider the benefits and pitfalls of each technique and evaluate the new modules successes (or failures!).

Internet of Underwater Things (IoUTs) has emerged as an evolution of traditional underwater wireless sensor networks, with programmable nodes interconnected to the Internet. Despite the advancements, IoUTs will still face critical challenges imposed by the use of the lossy and energy-hungry underwater acoustic channel. Two major critical challenges faced by IoUT applications are the low reliable data delivery due to the poor quality of underwater acoustic links, and the high energy cost for underwater wireless communication. In this paper, we tackle both challenges by proposing the PCon protocol. The PCon is a power-controlled opportunistic routing protocol for data routing in duty-cycled IoUTs. At each hop, the PCon protocol selects the most suitable transmission power, from a set of discrete transmission power levels, to maintain a reasonable data delivery ratio while reducing the energy consumption of duty-cycled IoUTs. To do so, the PCon takes into consideration the energy cost for delivering the data packet, calculated as a function if the probability of having the next-hop node awake during the transmission. Simulation results showed that the PCon protocol, even in a harsh scenario of duty-cycling of 50%, ensures a packet delivery rate of 40% while decreases the energy cost in 78%.

The increase in traffic congestion in big cities causes negative impacts on several areas, such as health and the economy. One of the main alternatives to reduce traffic jams are Intelligent Transportation Systems (ITS) that use technologies such as inductive loops, Global Positioning System (GPS), and wireless communication. The vehicular networks enable the wireless communication in the vehicular environment. This communication may occur from Vehicle to Vehicle (V2V) or from Vehicle to Infrastructure (V2I). However, the installation and maintenance of the infrastructures necessary to cover urban areas may have high costs. Therefore, this work presents a new Distributed and low-overhead protocol for Traffic Congestion control (DisTraC) based on V2V communication. The protocol aims to reduce the average travel time of vehicles ensuring a low communication overhead. Simulations results shown that DisTraC outperforms other studies found in the literature in terms of communication overhead and is more efficient in reducing traffic congestion.

How to provide accurate and timely traffic flow information has become a hot topic in recent years since they can help schedule trips better and reduce traffic congestion. In previous studies, some machine learning (ML)-based models were proposed to predict the traffic volume at a single road segment/position, and these models performed not bad. However, when applied in a more complicated road network, they show low efficiency or need to pay higher computing costs. To solve this problem, an innovative ML-based model named selected stacked gated recurrent units model (SSGRU), is proposed for predicting the traffic flow through a sparse road network in this paper. There are mainly two parts in this model, one is used to do spatial pattern mining based on linear regression coefficients, and the other one includes a stacked gated recurrent unit (SGRU) which is essential for multi-road traffic flow prediction. A binarytree is adopted to approximate the sparse road network in the suburban area. To evaluate the proposed model, seven different traffic volume data sets recorded at 15-min interval are chosen from the England Highways data set to test our proposed work. The result shows that our model has greater adaptability and higher accuracy than others when applied to a multi-road input infrastructure.

In recent years, aiming to improve deriving safety and supporting autonomous driving, pedestrian detection has attracted considerable attention from both industry and academic. Moreover, by taking advantage of the powerful computational capacity of GPU and high-level feature learning ability of the deep convolutional neural network, tremendous image/video-based pedestrian detection methods have been proposed. However, most of the existing approaches are designed relying on the computer vision-based target detection techniques. Accordingly, the evaluation criteria they consider in the design are often from the computer vision research field. Therefore, these existing methods tend to focus on the improvement of accuracy and ignore some of the special requirements that need to be considered in the field of autonomous driving. In this paper, we will analyze and summarize the features of the state-of-the-art pedestrian detection methods in detail. Then, by considering the practical application scenarios of autonomous driving techniques, we further discuss the open challenges of designing a practical pedestrian detection method for supporting autonomous deriving.

In this work, we apply information theory metrics to car trips logged by volunteers around the world and use quantifiers such as location entropy to reveal aspects of users' mobility, like the context in which trips happened. The dataset used in this work was collected from the enviroCar project and contains not only location logs but also sensor readings associated with each location. Information theory measurements can also reveal relationships between sensor measurements in order to reveal rare occurrences and reduce uncertainty. This work shows that it is possible to differentiate driving contexts and capture relationships among sensors using location entropy and mutual information, respectively. These contributions pave the way for developing new features that may ultimately improve traffic context classification results.

Integrating Cognitive Radio (CR) technology in Internet-of-Things (IoT) devices allows efficient large-scale deployment of IoT systems. Recently, research efforts are shifted toward adopting CR in IoT as a response for the spectrum scarcity problem. Unfortunately, CR Networks (CRNs) share the same security weaknesses with traditional wireless networks. CR communication is also vulnerable to jamming attacks which can significantly affect network performance, consume network resources and results in delays, that make it less suitable for IoT time-critical systems. Routing in CR-based IoT networks, in general, considered as a challenging issue. Under the jamming attack, routing becomes even more challenging. In this paper, we introduce a new jamming-aware routing and channel assignment protocol that deals with proactive jamming attacks in CR-based IoT networks without requiring extra resources. The proposed protocol attempts at improving the overall packet delivery ratio in the network while considering the primary user's activities, multi-channel fading and jamming behavior. The proposed protocol consists of three phases: route discovery, channel assignment, and path selection. The channel assignment problem along each path is formulated as an optimization problem with the objective of maximizing the end-to-end probability of success. This problem is shown to be an uni-modular problem, which can be solved in polynomial-time using linear programming techniques. Compared to reference protocols, simulation results reveal that the proposed protocol significantly improves network performance in terms of packet delivery ratio.

In recent years, with the development of the Internet of Things (IoT) and the Vehicular Networks (VNets), a large number of computers and sensors equipped on different vehicles (e.g., onboard CPU, camera, GPS, etc.) can not only help the vehicle to collect its own surrounding environment information, but also share those information with other participants in the transportation system through Vehicle-to-everything (V2X) technique. This ability to share information further makes VNets a precious resource for information and resources, which can support the vehicular edge computing (VEC) environment. However, due to the high moving speed of vehicles and the relative motion between vehicles, the topology of vehicle networking is highly dynamic. How to estimate the number of vehicles and the time period that they can form a vehicular cloudlet in a road segment is a challenging task for enabling VEC. Hence, in the paper, we present a queueing model-assisted traffic density estimation scheme to derive and analyze some essential parameters for implementing VEC, i.e., the vehicular cloudlet existence probability and the corresponding lifetime. We further demonstrate the results derived by the proposed scheme.

Recently, the evolution of both wireless communication technologies and vehicular technology have greatly promoted the development of Vehicular Networks (VNs). The VN allows for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications using wireless local area network technologies. The distinctive features of their candidate applications (e.g., collision warning and local traffic information for drivers), resources (e.g., computational sources), and their ability to collect various data from their environment (e.g., vehicular traffic flow patterns) make VNs a rich resource for information and resources. However, due to the transient nature of the network topology, data dissemination/content delivery is a challenging task in the VNs. Accordingly, in this article, we investigate the data dissemination/content delivery problem in VNs, and provide a novel traffic volume-aware data routing (TVDR) protocol for VNs. More precisely, by exploring the advantages of the various densities of coexistence vehicular traffic flows, the presented TVDR protocol can derive the data forwarding path with maximum link connection probability for the on-road vehicle. We evaluate the performance of the proposed TVDR protocol by conducting intensive simulations.

Public transit is a cornerstone of urban mobility, yet very little research is focused on its integration and potential roles as part of Intelligent Transportation Systems. Vehicular networks, for example, can greatly benefit from services provided by bus-based mass transit systems. The capillarity of bus-based transport systems and close proximity to other road vehicles further signal for integrative solutions. In this work, we perform an in-depth discussion of bus-based transit systems into VANETs not only as participating members but as service providers and official agents. We discuss the roles buses can take as part of vehicular networks and associated challenges. Then, we analyze and discuss public-transit-based network coverage in the urban environment using real-world data. The results obtained demonstrate that buses can achieve over 20% city-wide network coverage during significant portions of the week and complete coverage of central regions during specific time-frames, evidencing the potential that public transit has to provide services in vehicular networks.

How to achieve a fast and safe data dissemination in the Vehicular ad-hoc network (VANET) is a hot research topic these days. However, the high mobility of the vehicles makes the topology of VANET unstable, and real-time road information is generally limited. Considering these shortcomings, it is helpful to use the accurate traffic prediction to assist the topology control in the VANET. For offering a better traffic flow prediction, this paper proposes an innovative hybrid prediction method, Delay-based Spatial-Temporal Autoregressive Moving Average model (DSTARMA) to enhance prediction effect. This model mainly focuses on dealing with the travel delay problem in short-term traffic flow prediction. In other words, vehicles always need some time to move from one place to another in a real traffic situation, and this period is called travel delay. In previous spatial-temporal models, no one takes this factor into account. In our model, the travel delay is handled in the form of spatial-temporal weighted matrices and treated as a key role. We evaluated our approach based on data in England highway traffic system. The result proves our approach is reliable and has the ability to offer more accurate road information in advance to support VANET.

In order to improve simulation performance and to integrate simulation resources among geographically distributed locations, the concept of distributed simulation is proposed. Several types of distributed simulation standards, such as DIS and HLA, are established to formalize simulations and achieve reusability and interoperability of simulation components. To implement these distributed simulation standards and to manage the underlying system of distributed simulation applications, we employ grid computing and cloud computing technologies. These tackle the details of operation, configuration, and maintenance of simulation platforms in which simulation applications are deployed. However, for modelers who may not be familiar with the management of distributed systems, it is challenging to make a simulation-run-ready environment among different types of computing resources and network environments. In this article, a new multi-layered cloud-based scheme is proposed for enabling modeling and simulation based on different distributed simulation standards. This scheme is designed to ease the management of underlying resources and to achieve rapid elasticity that can provide unlimited computing capability to end users; it considers energy consumption, security, multi-user availability, scalability, and deployment issues. A mechanism for handling diverse network environments is described; by adopting it, idle public resources can be easily configured as additional computing capabilities for the local resource pool. A fast deployment model is built to relieve the migration and installation process of this platform. An energy-saving strategy is utilized to reduce the consumption of computing resources. Security components are implemented to protect sensitive information and block malicious attacks in the cloud. In the experiments, the proposed scheme is compared with its corresponding grid computing platform; the cloud computing platform achieves similar performance, but incorporates many advantages that the Cloud can provide.

Intelligent transportation systems (ITSs) are comprised of multiple technologies that are applied to improve the quality of transport, offering services and applications that will monitor, manage the transportation systems, and increase the level of comfort and safety for passengers and drivers. ITSs services are available for vehicular users through the infrastructure, based on the vehicular network. Furthermore, they can use a vehicular cloud to take advantage of all the resources that a cloud can provide. To achieve this, the ITSs require a mechanism that will aggregate and manage all the available resources provided by the vehicles. Moreover, the aggregation and allocation resource schemes must address the characteristics of the vehicular network to attempt all the quality of service requirements. Therefore, one of the greatest challenges lies in managing the allocation and aggregation of vehicle resources when there is no external infrastructure that will support the system. Hence, we propose an aggregate and allocate resource approach to maximize the availability of service. For this, we formulate the problem through the semi-Markov decision process (SMDP) that will provide an optimal solution for the aggregation and allocation problem. Moreover, we use an average reward function and iterative algorithm to solve the SMDP. The results show that the proposed approach showed stable behavior regardless of the frequency of receiving requests for service. Furthermore, the proposed solution has high average reward when compared to other work in the paper.

Recent advancements in underwater wireless sensor networks (UWSNs) are enabling day-one underwater monitoring applications. However, energy efficient and reliable UWSNs must be developed for achieving large scale and sustainable underwater monitoring and exploration applications. In this regard, the use of the underwater acoustic channel poses several daunting challenges. The acoustic channel is energy hungry and has low reliability, which shortens the UWSN lifetime and diminishes the performance of underwater monitoring applications. In the literature, both challenges have been addressed separately by means of duty-cycling and opportunistic routing, respectively. In this paper, we shed light on the symbiotic design of anypath routing and duty-cycling for sustainable UWSNs. We propose novel strobed preamble low power listening (LPL) and low power probing (LPP) methodologies for the design of asynchronous duty-cycling protocols, which symbiotically consider anypath routing for data delivery. Moreover, we develop an analytical framework for the performance evaluation of such a symbiotic design. Numerical results highlight potentials and drawbacks of this proposed approach in different classes of UWSN applications, and provide useful insights for the future symbiotic design of opportunistic routing and duty-cycling protocols for UWSNs.

This paper proposes a new framework for GPS-less identification of location of public transportation vehicles by using machine intelligence algorithms by exploiting the vehicular crowd-sensing concept. Since data trustworthiness is vital when data is crowd- solicited via various non-dedicated sensors, assessment and quantification of the trustworthiness of participating sensors plays a key role in the accuracy of the acquired information. To this end, we propose two trustworthiness-aware recruitment schemes for the non-dedicated sensors in a vehicular crowd-sensing environment: Reliability-driven naive recruitment (RDNR) and Reliability-driven exclusive recruitment (RDER). The former determines to use the data of a mobile device with a probability equal to the reliability of the device whereas the latter excludes the participating devices whose reliability scores are below a certain threshold. The data acquired from the recruited participant pool then undergoes an unsupervised machine learning module that is hosted in the cloud. We evaluate the performance of RDNR and RDER in comparison to each other and a non-restrictive recruitment mechanism which does not consider reliability of participants at all. Through simulations, we show that over 85% and 98% accuracy can be achieved in the worst and best cases, respectively while consuming less energy than GPS-based localization approaches.

Currently, traffic congestion has become a part of daily life of people in the cities around the world, and impacts people's lives adversely, e.g., the extra time spent on commuting, the extra exhaust emissions, etc. In order to reduce the effects of congestion on our lives, intensive research efforts have been proposed on this issue. Intelligent Transportation System (ITS) is one of potential solutions to enable various applications to improve road safety and travel comfort, and has gained a lot of attention from researchers around the world. In order to efficiently manage the transportation system and reduce traffic congestion, one of the paramount problems needed to be solved in ITS is the accurate traffic prediction. In this article, we firstly combine Fourier analysis with wavelet denoising technique to cope with the traffic flow forecasting problem. A two-layer fast Fourier transform (FFT)-based traffic prediction scenario is proposed, in which the discrete wavelet transform (DWT) with two different threshold values are adopted to decompose the high-frequent-noise and identify low-frequent traffic flow changing trend from the original data. Three different data sets with different traffic flow patterns are chosen from the England Highways data set to test our proposed work. Intensive simulations are implemented to verify the proposed work.

Roundabouts or traffic cycles reduce the possibilities of accidents and smooth the traffic at road intersections. In order to master the rules of driving around these traffic cycles intensive practicing is required. The more congested the area of the roundabout, the more confused for drivers to drive there. Especially, fresh or exhausted drivers which panic or/and do mistakes while entering, cycling or existing the roundabout. In this work, we aim to introduce a driving assistance protocol to help drivers choosing the best lane to enter the roundabout and the best time to enter or exist the roundabout. The proposed protocol recommends the best reaction of any vehicle regarding the roundabout based on its location, its targeted destination, and the distribution of traffic in the vicinity of the roundabout. Using some experimental scenarios, we evaluate the performance of this protocol in terms of decreasing the percentage of accidents, increasing throughput of the roundabout and decreasing the waiting delay time of vehicles.

Vehicular ad hoc network (VANET) is a fundamental building block in the design of an Intelligent Transportation System (ITS). Considering the various applications in ITS, a VANET must provide communication solutions in different situations. In particular, we are interested in dealing with situations where the unicast communication problem occurs in sparse network scenarios. In this paper, we shed light on the need for mechanisms that take into account the vehicles' trajectories. We present a characterization that shows the spatiotemporal regularity of the vehicle movement. We propose a new methodology for identifying the spatiotemporal relationship between vehicle trajectories. We create a novel method named ROSTER for unicast routing in sparse VANETs. Simulations results show that the proposed solution considerably reduces message overhead in the network by maintaining compatible levels of delivery rate in comparison with other protocols.

This paper proposes a new framework for emulating the functionality of a sensor by using multiple available soft sensors and machine intelligence algorithms. As a case study, the localization of city buses in a smart city setting is investigated by using the accelerometer and microphones of the passengers and a Support Vector Machine (SVM) running in the cloud; in this application, the GPS functionality is emulated by using these two soft sensors. What makes such an emulation feasible is the statistical dependence of the location data (which would normally be obtained from a GPS) on the accelerometer and microphone data; while accelerometers capture data that relate to the typical stop/start patterns of the buses, microphone capture enter/exit patterns of the passengers through the sound levels inside the bus. We evaluate our proposed scheme through simulations and show that the proposed framework can operate with more than 90% accuracy in estimating the location of public buses while preserving the actual location privacy of the smartphone users. This approach results in smartphone battery energy savings of 38-46% (as compared to GPS-based approaches) due to the elimination of the power-hungry GPS devices.

Machine learning method have increased in popularity in Advanced Driving Assistant System (ADAS) field recently. Although most of the best performances are achieved by machine learning and deep learning methods in benchmarks, a matured database of road markings with labels has not yet been built. This paper analyzes the road markings detection using Histogram of Oriented Gradient (HOG) with Support Vector Machine (SVM) on our local database. Compared with the results of the rulebased detection method, our exploration provides a possible solution to improve the machine learning method in order to get a balance on speed and accuracy.

Long driving trips that traverse several states or counties are common these days, for tourism or products shipping aims. These trips are usually classified as dangerous trips due to the challenges and difficulties they introduce. The diversity of geometry and quality of road networks over the extended traveling areas, the diversity of weather conditions, and the long time of the day that drivers witness during these driving hours make even expert drivers in need for professional advices. In this work, we propose a driver assistance protocol that uses the real-time critical conditions of each driving area to recommend the safety speed. Moreover, this protocol measures the speed of each traveling vehicle and compares it to the recommended speed aiming to determine the severity of the dangerous situation introduced by drivers that are not following the safety recommendations. Severe scenarios should be reported to surrounding vehicles to be more careful regarding this irresponsible driver and/or reported to the driving authorities to enforce the driver to follow the driving safety rules.

Every year, natural and human-induced disasters result in infrastructural damages, monetary costs, distresses, injuries and deaths. Unfortunately, climate change is strengthening the destructive power of natural disasters. In this context, Internet-of-Things (IoT)-based disaster detection and response systems have been proposed to cope with disasters and emergencies by improving the disaster detection and search and rescue missions during disaster response. Accordingly, IoT devices are used to collect data and help to identify hazards after disasters and to localize injured people. However, a solely IoT-based detection and response system will not be totally suitable for emergency response in smart cities, as the lack of connectivity with IoT devices might occur, due to breakages in communication infrastructures or network congestions. Therefore, we propose a novel architecture for smart disaster detection and response system for smart cities. We discuss the main building blocks of our envisioned smart system, as well as the critical challenges that will be faced ahead to implement our smart system.

Vehicular networks are seen as the key communication solution for intelligent transportation systems. An essential task for the development of solutions for vehicular networks is to understand aspects related to their communication topology along the time, mainly because it is directly impacted by vehicular mobility. In this sense, a natural question that arises is how can we model the communication topology in order to have a real representation of network connectivity? Particularly, this question becomes even more complex when we consider the dynamic behavior of mobility over time. In the literature, there are some efforts that aim to model the topology of a vehicular network to better understand its dynamics. However, we note that current approaches have limitations in the temporal perspective leading to the loss of important information. In this work, we show the strengths and weaknesses of current approaches in the characterization and analysis of vehicular network topology. In addition, we present how a model derived from the temporal network theory can be applied to capture the dynamics of a large-scale realistic vehicular mobility trace.

The peculiar characteristics of vehicular networks (e.g., high vehicular mobility, poor wireless link quality and short-lived and intermittent connectivity among vehicles) challenge host-centric content search and distribution in vehicular networking applications. In this regard, recent studies have proposed information-centric protocols to improve content distribution in vehicular networks. However, they are still severely impaired by the highly dynamic nature of vehicular network topologies and the broadcast storm problem due to uncontrolled Interest packet flooding for content discovery. In this paper, we tackle the broadcast storm problem of Interest packet transmissions for content discovery in vehicular named-data networks. We propose the location-based content distribution protocol (LOCOS) for oriented Interest packet transmissions towards the proximity area of a recently discovered content source vehicle. The LOCOS protocol leverages the recently discovered location of a vehicle content source to controlled transmit Interest packets to the area where the content source is located. Simulation results show that the LOCOS protocol improves content delivery rate in 10% and 28% when compared with related work, while it reduces the content delivery delay in 80%.

Due to the limitation of the mobile device battery lifespan, the concept of Mobile Cloud Computing(MCC) offloading is popularly introduced to handle the conflicts between the resource-hungry mobile tasks and the limited internal energy capacity. To further reduce the communication delay and energy cost between the offloader and offloadee, the Cloudlet model is proposed that performs as the agent of remote Cloud Datacenter. In this case, many offloading tasks used to be executed by the distant Cloud can be processed locally on the Cloudlet. However, unlike the remote Cloud that is assumed to provide ”unlimited” computing utility, the Cloudlet is still bounded regarding computing power, storage, network bandwidth and coverage. In this paper, a Cloudlet-based offloading model is proposed to enable energy and execution efficient offloading. A task-centric resource allocation model is presented to handle the resource limitation issue of the local Cloudlet. In the experiments, the proposed model is compared to the traditional device-based solutions, and the offloading execution results present an overall improvement of the offloading energy reservation as well as execution throughput.

In Vehicular networks, applications commonly have location-dependent requirements. Services such as those transit-related may require that vehicles obtain content from specific regions. In these cases, unless previously cached by another node, requests must necessarily be provided by nodes near the physical location for which information is requested. This asymmetry in content availability poses a significant challenge to content provisioning. In this work, we propose a caching policy based on collaborative observation of locality in request frequency, designed to allow vehicles to preemptively distribute and store in a reserved portion of the cache based on the cooperative observation of requests with provider-based location correlation. The proposed solution can significantly improve content delivery, with over 30% improvement in overall content delivery when compared to scenarios where Provider-based Location Correlation (PLC) is observed but no targeted policy is employed.

To enhance the programmability and flexibility of network and service management, the Software-Defined Networking (SDN) paradigm is gaining growing attention by academia and industry. Motivated by its success in wired networks, researchers have recently started to embrace SDN towards developing next generation wireless networks such as Software-Defined Internet of Vehicles (SD-IoV). As the SD-IoV evolves, new security threats would emerge and demand attention. And since the core of the SD-IoV would be the control plane, it is highly vulnerable to Distributed Denial of Service (DDoS) Attacks. In this work, we investigate the impact of DDoS attacks on the controllers in a SD-IoV environment. Through experimental evaluations, we highlight the drastic effects DDoS attacks could have on a SD-IoV in terms of throughput and controller load. Our results could be a starting point to motivate further research in the area of SD-IoV security and would give deeper insights into the problems of DDoS attacks on SD-IoV.

Wireless sensor networks (WSN) are widely used in environmental applications where the aim is to sense a physical parameter such as temperature, humidity, air pollution, etc. Most existing WSN-based environmental monitoring systems use data interpolation based on sensor measurements in order to construct the spatiotemporal field of physical parameters. However, these fields can be also approximated using physical models which simulate the dynamics of physical phenomena. In this paper, we focus on the use of wireless sensor networks for the aim of correcting the physical model errors rather than interpolating sensor measurements. We tackle the activity scheduling problem and design an optimization model and a heuristic algorithm in order to select the sensor nodes that should be turned off to extend the lifetime of the network. Our approach is based on data assimilation which allows us to use both measurements and the physical model outputs in the estimation of the spatiotemporal field. We evaluate our approach in the context of air pollution monitoring while using a dataset from the Lyon city, France and considering the characteristics of a monitoring system developed in our lab. We analyze the impact of the nodes' characteristics on the network lifetime and derive guidelines on the optimal scheduling of air pollution sensors.

We consider a VoD (Video on-Demand) platform designed for vehicles traveling on a highway or other major roadway. Typically, cars or buses would subscribe to this delivery service so that their passengers get access to a catalog of movies and series stored on a back-end server. Videos are delivered through IEEE 802.11p Road Side Units deployed along the highway. In this paper, we propose a simple analytical and yet accurate solution to estimate (at the speed of a click) two key performance parameters for a VoD platform: (i) the total amount of data downloaded by a vehicle over its journey and (ii) the total "interruption time'', which corresponds to the time a vehicle spends with the playback of its video interrupted because of an empty buffer. After validating its accuracy against a set of simulations run with ns-3, we show an example of application of our analytical solution for the sizing of an IEEE 802.11p-based VoD platform.

Multimedia data traffic will explosively increase in vehicular networking scenarios as the current advances in vehicular communication technologies and connected cars penetrate on the market. However, current data dissemination protocols and even the host-centric content delivery paradigm will not support the anticipated traffic load without degrading vehicular applications QoS/QoE. Recent research efforts are proposing the information-centric networking paradigm as a viable solution for handling multimedia content distribution in vehicular networks and connected and autonomous vehicles [1-10].

Oceans are a great unknown. To change this worryingly reality, underwater wireless sensor networks (UWSNs) have been proposed for the automated and real-time data collection from ocean, including the life and events beneath them. Currently, the underwater acoustic channel is the most viable technology for long-range underwater wireless communication, but its use impairs the data collection in UWSNs. It presents strong signal absorption and is severely affected by human-made and natural noise in the aquatic environment. Therefore, data collection in UWSNs is unreliable. In the recent years, opportunistic routing has been proposed to improve UWSN communication's reliability and, consequently, data delivery. However, not always the proposed opportunistic routing protocols will perform well, as the neighborhood configuration of a node might not be dense enough or at a maximum distance that would favor data communication. In this paper, we proposed the power control-based opportunistic routing protocol, named PCR, for reliable and energy-efficient data delivery in UWSNs. The proposed PCR protocol selects the most suitable transmission power level at each underwater sensor node, aimed at improving the packet delivery probability at each hop. To avoid the selection of high power transmission and the uncontrolled inclusion of neighboring nodes in the next-hop candidate set, which would drastically increase the energy consumption, the PCR protocol considers the energy waste that will occur in each neighboring underwater sensor node. Numerical results showed that PCR improves the packet delivery probability and reduces the energy waste for data delivery by adjusting the proper transmission power and selecting the suitable candidate set, leading to energy conservation when compared with related proposals presented in the literature.

Underwater wireless sensor networks (UWSNs) have been proposed for autonomous monitoring of underwater environments. Despite the recent advances on underwater acoustic modems, unreliable data delivery and high energy cost are two critical research problems that remain in UWSNs. In this context, energy-efficient and reliable data collection protocols must be proposed for UWSNs. In this paper, we propose to combine power control and anypath routing in order to simultaneously address both problems in UWSNs. We propose an analytical that considers the characteristics of power control, multiple next-hop forward nodes of anypath routing, underwater acoustic channel and aquatic environment. The model devised in this work is a mathematical tool to enable researchers and practitioners to study important performance metrics of UWSN applications, when power control and anypath routing are jointly explored. Moreover, it is helpful to provide insights for the future design of joint power control and anypath routing protocols for UWSNs. Numerical results show that for a reduced number of next-hop candidate nodes, data delivery can still be improved by increasing the transmission power of the sender. Conversely, for a high number of next-hop candidates nodes, a high transmission power leads to energy waste.

In this paper, we introduce Drizzle, a new algorithm for maintaining routing information in the low-power and lossy networks. The aim is to address the limitations of the currently standardized routing maintenance (i.e., Trickle algorithm) in such networks. Unlike Trickle, Drizzle has an adaptive suppression mechanism that assigns the nodes different transmission probabilities based on their transmission history so to boost the fairness in the network. In addition, Drizzle removes the listen-only period presented in Trickle intervals leading to faster convergence time. Furthermore, a new scheme for setting the redundancy counter has been introduced with the goal to mitigate the negative side effect of the short-listen problem presented when removing the listen-only period and boost further the fairness in the network. The performance of the proposed algorithm is validated through extensive simulation experiments under different scenarios and operation conditions. In particular, Drizzle is compared to four routing maintenance algorithms in terms of control-plane overhead, power consumption, convergence time, and packet delivery ratio (PDR) under uniform and random distributions and with lossless and lossy links. The results indicated that Drizzle reduces the control-plane overhead, power consumption and the convergence time by up to 76%, 20%, and 34%, respectively, while maintaining approximately the same PDR rates.

Vehicular ad hoc networks (VANETs), essential components of intelligent transportation systems, are attracting an increasing amount of interest in research and industrial sectors. As multifunctional mobile nodes that integrate transporting, sensing, information processing, and wireless communication capabilities, vehicular nodes are facing remarkable security issues and are more vulnerable to malware attacks than conventional communication nodes. In this paper, we examine the behaviors and security concerns relating to worm spreading in VANETs. We discuss various approaches for worm spreading in VANETs, and propose an infrastructure-based worm containment (IBWC) strategy. The IBWC problem is modeled as a minimum contamination problem by introducing the expected contamination degree. The simplified Greedy method is then proposed to solve the minimum expected contamination degree problem on road networks. Simulation results show that the proposed method outperforms the existing greedy method and the max-flow based method from both complexity and solution quality aspects.

Wireless sensor networks (WSNs) have been widely adopted to fulfil the imperative requirement of real-time monitoring and/or long-term surveillance of the field-of-interest. However, due to the limited battery capacity, energy is the most critical constraint for improving the sustainability of a WSN. Hence, conserving energy and extending battery life are important in designing a sustainable WSN. Fortunately, the emerging energy harvest techniques provide us with a semi-permanent energy resource to power WSNs. In this article, we introduce a novel energy-aware hierarchical two-tier (HTT) energy harvesting-aided WSNs deployment scenario. More precisely, we consider two types of nodes in the system: one is the regular battery-powered sensor node (RSN), and the other is the energy harvesting-aided data relaying node (EHN). The objective is to use only RSNs to monitor FoI, while EHNs focus on collecting the sensed data from RSNs and forwarding the gathered data to the data sink. The minimum number of EHNs is deployed based on a newly designed probability density function to minimize the energy consumption of RSNs. This, in turn, extends the lifetime of the deployed WSN. The simulation results indicate that the proposed scheme outperforms some well-known techniques in the network lifetime, while enhancing the total throughput.

To support increasingly sophisticated sensors and resource-hungry applications with the current-used Lithium-based batteries and to augment mobile computing power further, the concept of the Cloudlet-based offloading is proposed which enables to migrate part of application computing tasks from battery-limited low-capacity mobile elements to local Cloudlets. However, due to the limited processing capability and the lack of fine-grain resource management schemes on the Cloudlet, the Cloudlet resources can be quickly overloaded especially in the large-scale multi-user offloading scenarios. As a result, a considerable number of offloading requests are forwarded to the remote Cloud, which may significantly increase the communication overhead for the energy-sensitive mobile offloading tasks. In this paper, we develop and formulate a novel task-centric energy-aware Cloudlet-based Mobile Cloud model to address this issue. We concern the offloading performance, scalability, security, and availability problems, aiming at increasing the Cloudlet processing throughput, reducing the energy cost on the remote Cloud, and improving offloading execution efficiency and energy-efficiency on the mobile devices. A Cloudlet task-based offloading mechanism is proposed to achieve fine-grain energy-aware offloading resource preparation and scheduling on the Cloudlet. A Cloud task-centric scheduling algorithm is presented for the green collaborative offloading processing between Cloudlet and remote Cloud. The experiment results demonstrate that the energy-aware offloading model can efficiently enhance offloading performance for mobile devices, and the offloading scheduling schemes for the Cloudlet and remote Cloud outperform the traditional protocol class.

Opportunistic routing (OR) has been showed efficient for the harsh and challenging scenarios of underwater wireless sensor networks (UWSNs). This routing paradigm leverages the broadcast nature of wireless communication, for improving data delivery. In contrast to traditional multi-hop routing, OR selects a subset of the neighboring nodes to be the next-hop candidate nodes, in which will participate forwarding data packets towards the destination. Hence, at each hop, a transmitted data packet is lost only if none of the next-hop candidate nodes receives it. Therefore, OR not only improves packet delivery rate, but also reduces network energy consumption since fewer retransmissions will be needed. However, the design of OR protocols for UWSNs is challenging, due to the characteristics of the underwater acoustic channel. For instance, the high and variable delay, multipath propagation, low bandwidth, and high energy consumption render impractical the use of the up to date protocols developed for wireless sensor and mesh networks. In this context, this tutorial gives a comprehensive review of the potentials and challenges of opportunistic routing in underwater sensor networks. In addition, based on an in-deep literature review, this tutorial will provide important guidelines for the design of novel protocols for different scenarios of UWSNs.

A wireless sensor network (WSN) is usually deployed in a field of interest (FoI) for detecting or monitoring some special events and then forwarding the aggregated data to the designated data center through sink nodes or gateways. Traditionally, the WSN requires the intensive deployment in which the extra sensor nodes are deployed to achieve the required coverage level. Fortunately, depending on the developments of the unmanned aerial vehicle (UAV) techniques, the UAV has been widely adopted in both military and civilian applications. Comparing with the traditional mobile sensor nodes, the UAV has much faster moving speed, longer deployment range and relatively longer serving time. Consequently, the UAV can be considered as a perfect carrier for the existing sensing equipment and used to form a UAV-based WSN (UWSN). In this paper, we theoretically analyse the coverage problem in the UWSN. Based on the integral geometry, we solve the aforementioned question. The experimental results further verifies our theoretical results.

Reservation-based and contention-based MAC protocols have their own advantages in data transmissions under mobile sensor networks. This paper presents a quantitative analysis of two types of MAC protocols in throughput, delay, and energy efficiency under various traffic loads environments using queueing theory. The analytical and simulation results show the design strategies of hybrid MAC protocols for mobile dynamic traffic scenarios.

Modeling and simulation have shown essential for forecasting load and resource availability in large-scale complex scenarios. The growth of urban environments, as well as the use of ICT in enabling applications and services, has encouraged several works on the modeling of transportation. High mobility of vehicles in such a context consists of a significant challenge in modeling traffic. Several microscopic and macroscopic models have been designed aiming to represent the movement of vehicles accurately in road segments, involving different levels of complexity, precision, and realism. Out of these models, Free-flow models have shown useful due to being light and reasonably accurate for estimating load in short-time predictions. A recent free-flow traffic flow modeled using queues assumed constant vehicle speed along the road segment; this assumption may lead to a lack of realism and accuracy. Therefore, we propose a free-flow model based on this previous work where the road segment is split into several intervals, representing the oscillations of the speed of vehicles. The proposed model has shown correctness comparable to the previous free-flow model, considering that it has included speed varying behavior of vehicles.

There has been a recent effort from both the academia and the industry to improve the communication management structure of vehicular networks to support multiple services and applications. To this end, software-defined networking has been used together with vehicular ad hoc networks to provide greater flexibility and programming capabilities for more dynamic scenarios. With this in mind, we build upon an existing hierarchical solution for software-defined vehicular networks to deal with the case when there are issues in the communication with the central SDN controller, allowing the vehicles to self- configure to maintain an active infrastructure. Simulation results showed out solution outperforms existing solutions regarding delivery ratio, and throughput, while keeping the communication overhead extremely low, making it suitable for large-scale networks.

The data dissemination and content delivery is a challenging research subject in the Internet of Things (IoT). Especially, in the Vehicular Networks environment, the network topology has the transient nature, due to the fast-moving velocity of the vehicles. One potential solution to this task is to improve the probability of the successful communication and content delivery. Hence, in this paper, we propose a novel and simple passive road side unit (RSU) localization scheme to estimate the location of the RSU, by which the vehicle can pre-determine the desired RSU to communicate based on its own position and routing information. By exploring the Doppler effects of the received signal, the RSU location estimator is derived by the maximum likelihood estimation method. Experimental results verify the correctness of the proposed estimation scheme.

Device-to-device (D2D) communication in both adhoc and cellular networks can provide efficient data transmission without additional infrastructure, and increase data throughput, spectrum usage, and energy efficiency. MAC protocols in D2D communication can efficiently schedule mobile users and allocate physical resources to multiple devices. Centralized MAC and peer-to-peer MAC in D2D can be designed for various traffic loads and density of devices. This paper analyzes the typical MAC approaches to improve data throughput, delay, and energy efficiency in D2D scenarios. The analytical evaluation and simulation results demonstrate the suitable MAC strategies for various traffic loads and mobile devices in D2D communication.

Intelligent Transportation Systems have recently received great deal of attention and Vehicular networks and its applications represent a major part of ITS. Many vehicular network applications require accurate location information to improve their performance. Over the past years, many researchers worked on state prediction/estimation techniques in tracking, navigation applications for mobile ad hoc networks and wireless sensor networks. Yet, few were into the field of Vehicular networks. In this paper, We study five different movement prediction models and their efficiency and effectiveness for VANETs. We compare them using both real vehicle mobility traces of taxi cabs and generated mobility traces from SUMO.

Opportunistic routing (OR) has emerged as a promising paradigm to the design of routing protocols for underwater sensor networks (UWSNs). However, despite of its advantages, it introduces a critical problem that has been neglected until now: the immutable transmission priority level of the next-hop forwarding nodes. This characteristic can lead to an overuse of a unique node (or a few of them), quickly depleting its battery, creating network partitions, shortening the network lifetime and, consequently, degrading the application's performance. In this paper, we shed light on the need for mechanisms for rotating the forwarding priority level between candidate nodes. We propose a baseline new lightweight energy-aware opportunistic routing (EnOR) protocol, leading to a balanced energy consumption and prolonged UWSN network lifetime. EnOR rotates the transmission priority level of the forwarding candidate nodes by considering the remaining energy, link reliability and packet advancement of them. Simulation results reveal that EnOR effectively extends the network lifetime as compared with other underwater sensor network opportunistic routing protocols.

Low-power and Lossy Networks (LLNs) have been a key component in the Internet of Things (IoT) paradigm. Recently, a standardized algorithm, namely Trickle algorithm, is adopted for routing information maintenance in such networks. This algorithm is originally designed for disseminating code updates through a wireless sensor network. Thus, when it comes to routing maintenance in LLNs, Trickle suffers from some issues related to power, convergence time, network overhead and load-distribution. In this paper, a new algorithm for maintaining the network topology in LLNs is developed motivated by Trickle weaknesses, namely, Drizzle algorithm. Unlike Trickle, Drizzle uses an adaptive suppression mechanism that permits the nodes to have different transmission probabilities consistent with their transmission history. Another distinctive feature of Drizzle in comparison with Trickle, is the absence of the listen-only period from Drizzle's intervals, thus, leading to faster convergence time. Furthermore, a new policy for setting the redundancy coefficient has been used to mitigate the negative effect of the short-listen problem presented when removing the listen-only period and to further boost the fairness in the network. Our extensive simulation experiments confirm the superiority of the proposed algorithm over Trickle under different operating conditions.

Currently, the number of resources within a vehicle is growing. The vehicle can provide its idle resources to other vehicles through a cloud. Thus, these vehicles can communicate with each other to dynamically create a vehicular cloud. Therefore, this vehicular cloud needs to adapt according to the number of available resources that the vehicle members in the cloud are sharing. In this kind of cloud, the control of allocated and shared resources becomes a challenge due to the high mobility of vehicles. With this challenge in mind, we propose an optimal resource allocation scheme in order to maximize the use of the available resources. The optimal problem to maximize the expected average reward system is formulated as a Semi-Markov Decision Process (SMDP). The SMDP problem is solved by an iterative algorithm. Numerical results have shown that the proposed scheme has a stable behavior independent of the frequency of requests or the amount of resources. Furthermore, the proposed solution keeps the block rate at 20%, priorizing the allocation that will maximize the utilization of the available resources.

Information-centric networking is poised as an alternative to the address based network model, being mobility friendly and allowing for improved caching. However, VANETs, one of the biggest trends in ad-hoc networking, are defined by their peculiarities and pose additional challenges to the implementation of caching systems. The volatile nature of VANETs requires the development of specialized solutions, tailored for highly mobile environments. Towards the definition of efficient caching policies for ICN-VANETS, in this work, we discuss the current state of ICN caching in VANET, the potential hurdles that need to be overcome. We perform a series of simulations and analyze the efficiency of popular caching in various network configurations to denote current shortcomings and pinpoint potential areas where caching can be improved.

Long Term Evolution (LTE) appears to be a practical alternative to IEEE 802.11p for vehicular applications. Vehicular safety applications are based on broadcasting messages, which contain information such as location and speed to the neighboring vehicles. However, as LTE is an infrastructure-based network, all communication should pass through it, which can cause congestion and substantial delays that are unsuitable for safety applications. By introducing direct D2D communication in 3GPP Release 12, known as LTE-Advanced, User Equipments (UEs) can communicate directly if they are in close enough proximity. In this paper, we propose an approach to use direct D2D, as well as cellular communication. This approach helps to reduce the amount of resources that are used for cellular communication, while keeping information of vehicles on a central server that can be utilized for other vehicular applications such as traffic efficiency.

A wireless sensor network (WSN) is usually deployed in a field of interesting (FoI) for detecting or monitoring some special events. Traditionally, the WSN requires intensive deployment in which the extra sensor nodes are deployed to achieve the required coverage level. While, depending on the developments of the unmanned aerial vehicle (UAV) techniques, the UAV has been widely adopted in both military and civilian applications. Comparing with the traditional mobile sensor nodes, the UAV has much faster moving speed, longer deployment range and relative long serving time. Consequently, the UAV can be considered as a perfect carrier for the existing sensing equipment and used to form a UAV-based WSN (UWSN). Naturally, in order to determine the efficiency of a UWSN, a question, “what is the probability of detecting a target in the Fol, if an UAV randomly scanned the FoI n times”, is raised. To solve this question, in this article, we theoretically analysed the target detection problem in the UWSN by considering static target and mobile target, respectively. The experimental results further verified our theoretical results.

Advanced Driving Assistant System (ADAS) was widely learned nowadays. As crucial parts of ADAS, video-based application like lane markings detection and other objects detection, have become more popular than before. However, most methods implemented in such areas cannot perfectly balance the performance of accuracy versus efficiency, and the mainstream methods (e.g. Machine Learning) suffer several limitations which can hardly break the wall between partial automation and fully automation. This paper proposed a real-time lane marking detection framework for ADAS, which included 4-extreme points set descriptor and a rule-based cascade classifier. Several experiments were conducted in highway and urban roads in Ottawa. The detection rate of the markings by the proposed algorithm reached an average accuracy rate of 96.77% while F1Score (harmonic mean of precision and recall) also attained a rate of 90.57%. In summary, the proposed method exhibited a state-of-the-art performance and represents a significant advancement of understanding.

Drivers change the lane over the road networks is a common seen practice when they face a slow, stopped or broken vehicle. Sometimes they have to change the lane to take the next exist or the next U-turn towards their targeted destination. Changing the lane requires that the driver should be aware of vehicles behind him on the new lane or vehicles intending to change to the same lane during that period of time. If any of these vehicles are located on the blind-spot or if the driver miss-expect that vehicle's location or speed, his attempt of changing the lane can be failed or on some scenarios this may lead to an accident. On highways this type of accident can be fatal due to the high speed vehicles which do not allow drivers to stop the severity situation. This paper presents an Intelligent LAne CHange assistant protocol (ILACH) for highway road scenario. This protocol assists drivers to change the lane safely and efficiently. Several scenarios are considered where a certain driver attempts to change the lane. From the experimental results we can see that the proposed protocol enhances the safety and the efficiency of the tested scenarios.

Mobile devices nowadays can connect to the network very conveniently using cellular data network or WiFi. However, latency is still a challenge caused by the stability and the availability of the network, mainly in the context of mobile environments. In this paper, we propose an architecture based on a Cloudlet model using CAching and pre-FEtching scheme (CAFE scheme) to improve data access efficiency. The prefetching scheme on the Cloud enables the retrieval of specific data in advance based on specific information of users. On the Cloudlet, a caching technique selectively stores data passing through the Cloudlet. The classification of data into specific and general takes both individual access behavior and common trends into consideration. Compared to an original model, the experiment results show that our architecture can really decrease latency and improve data access efficiency when users request data from a Cloudlet and the Cloud.

An increase of vehicles in a city without an efficient infrastructure of traffic management can cause damages not only financial but also environmental and social. In order to support urban traffic system to relieve the traffic congestion and the damage caused by congestion of vehicles, in this paper, we propose a mechanism for Intelligent Transport Systems named FOg RoutE VEhiculaR (FOREVER), in order to assist the traffic management in Vehicular Networks (VANET). For achieving this, FOREVER will detect and recommend an alternative route for the vehicles to avoid previous congestion. FOREVER is based on FOG computing paradigm that aims of to compute and modify the route of the vehicle to avoid the formation of congestion. Thus, the results show that FOREVER had a reduction about 7.9% of the CO2emissions, 8.3% the stop time and 7.6% of the trip time.

Mobile devices are now capable of handling many daily computing tasks that used to be accomplished by desktops or servers. However, these improvements also introduce resource-hungry mobile applications that require richer resource-hungry computing features and more complex functions. Mobile Cloud Computing (MCC) addresses these limitations considering the nature of mobility; this innovative strategy provides external computing and storage capability so that tasks can be offloaded. The concept Cloudlet model is proposed to perform as the local resource pool that receives outsourced tasks. However, Cloudlets are restricted by the computing power and storage capacity, limiting the scale of offloading devices. In this paper, a Cloudlet-based task offloading model is proposed. By utilizing caching technologies and N-to-N resource scheduling, Cloudlets can support a larger number of mobile devices compared to previous models. Based on the experimental results, the proposed scheduling model cloud achieve better overall efficiency on energy consumption and task execution.

A Vehicular Cloud is defined as a set of vehicles that share their computation resources in a cloud. These resources are scheduled on demand based on cooperation between vehicles and the roadside. The biggest challenge in this type of cloud is to create a structure that will manage the service and resource when the cloud does not depend on the roadside infrastructure. Thus, the vehicles need to collaborate with each other to provide services and resources through their embedded resources. To address this challenge, we propose a service scheduling that will manage the requested service and the allocation service to achieve the quality of service requirements, considering the vehicular network characteristics. Simulation results show that the proposed approach achieves a higher service ratio (approximately 95%) with a lack of service of about 5%. Furthermore, the proposed solution achieved an average of 93% when we consider the average service quality and an average of 0,6 second in the service consuming delay.

Vehicular Cloud is defined as a set of vehicles that share their computation resource in a cloud, these resources are scheduled on demand based on cooperation between vehicles and vehicles with the roadside. These clouds can adapt dynamically according to application quality of service requirements. Thus, resource management is very crucial for this kind of cloud. In this work, we address relevant issues about of the concepts related to the resource management in the vehicular cloud; and techniques that require consideration are discussed in the context of resource management for the vehicular cloud. Finally, we discuss challenges and issues for potential future work.

Increased Caching Capability is one of the main benefits of Information-Centric Networking and a necessity for highly mobile ad-hoc networks such as VANETs. Hence, it is crucial to efficiently store items to improve resource utilization, increasing cache efficiency, reducing network load. In this paper, we propose a cache content insertion policy, UG-Cache, for ICN-VANETs. In UG-Cache, cache insertion decisions are made based on recommendations from content sender dependent on request frequency and cache distance. Numerical results denote the benefits of increased control over cache variety via application of UG-Cache. Simulation results reveal increased delivery rates and reduced average hop count of content delivery of UG-Cache over other schemes. UG-Cache also achieves higher cache hit ratio than other on-demand caching strategies.

Efficient content distribution is a critical challenge in vehicular networks (VANETs). This is due to the characteristics of vehicular networks, such as high mobility, dynamic topologies, short-lived links and intermittent connectivity between vehicles. Recently, information-centric networking (ICN) has been proposed to VANET scenarios for improving content delivery of infotainmentapplications. However, ICN in VANETs suffers from the Interest transmission broadcast problem, which results in a waste of resources and diminishes the performance of VANETs' applications. In this paper, we propose the link stability-based Interest forwarding for content request (LISIC) protocol, in order to tackle the Interest broadcast storm problem during a content search in information-centric VANETs. The proposed protocol controls Interesttransmission by prioritizing neighboring vehicles with more stable links with the current sender. Simulation results show that the proposed protocol improves the content delivery rate by 40% while decreases the Interest packet transmissions by 26%, in scenario of a low number of content producers in the network.

In automotive applications, several components, offering different services, can be composed in order to handle one specific task (autonomous driving for example). Nevertheless, component composition is not straightforward and is subject to the occurrence of bugs resulting from components or services incompatibilities for instance. Hence, bugs detection in component-based systems at the design level is very important, particularly, when the developed system concerns automotive applications supporting critical services. In this paper, we propose a formal approach for modeling and verifying the reliability of an autonomous vehicle system, communicating continuously with off-road infrastructure. We focus on components offering critical services with hard time constraint defining the delay of their availability. We propose to verify whether a set of components, when composed according to the system architecture specified with SysML models, achieve their tasks by respecting their interaction protocols and their time constraints.

Underwater wireless sensor networks (UWSNs) emerge as an enabling technology for the monitoring of vast areas of aquatic environments. This technology will pave the way for future large-scale applications of ocean monitoring, which will help to change the worryingly current reality where oceans are completely unknown. However, due to the harsh nature of aquatic environments and the underwater wireless communication features, efficient data collection in UWSN is still a daunting task. This tutorial will provide a comprehensive review of the research challenges and potential approaches for efficient data collection in UWSNs. It will highlight the characteristics of UWSNs and of the underwater acoustic channel, which diminish the performance of networking protocols. It will analyze the benefits of geographic and opportunistic routing for reliable data delivery and the potentials of duty-cycling for energy conservation in UWSN. Finally, based on an in-deep literature review, this tutorial will provide useful insights for the further design of networking protocols for data routing in UWSNs.

In wireless sensor networks, a serial processing algorithm browses nodes one by one and can perform different tasks such as: creating a schedule among nodes, querying or gathering data from nodes, supplying nodes with data, etc. Apart from the fact that serial algorithms totally avoid collisions, numerous recent works have confirmed that these algorithms reduce communications and considerably save energy and time in large-dense networks. Yet, due to the path construction complexity, the proposed algorithms are not optimal and their performances can be further enhanced. To do so, in the present paper, we propose a new serial processing algorithm that, in most of the cases, approximates the optimal number of hops (i.e., it requires n - 1 communications to traverse a network of n nodes). The extensive OMNeT++ simulations confirm the outperformance and efficiency of the proposal in terms of scalability and energy/time consumption.

Smart cities emerge in computer science as a topic to cover how the technology of information and communication can be used in the urban centers to monitor its dynamics and allow the improvement of services for the citizens. In these urban centers, different methodologies are used in order to collect data and provide them to applications. These data come from several heterogeneous sources, thus there is an effort to integrate and standardize them before their use. Also, a significant amount of this data has spatio-temporal annotations, which may be used to analyze the city dynamics, such as the mobility flow. Due to these characteristics of the data generated in urban centers, and also the possibilities brought by their use and analyses, this work presents a novel approach to collect, integrate and perform some analysis tasks in mobility data from smart cities. Thus, the SMAFramework can analyze mobility patterns based on a Multi-Aspect Graph (MAG) data structure. To show the potential of the framework, it is proposed a method to analyze the saptio-temporal correlation between data from two different data sources in the same city. Real data collected from social media and a taxi system of the city of New York are used to evaluate this method. The obtained results allowed to understand some of the applicabilities of the framework and also provided some insights on how to use the framework to resolve specific problems when analyzing mobility in urban environments.

Vehicular traffic accidents are a crucial problem in big urban centers. Nearly one million people die in road crashes each year. In this paper, we propose a predictive vehicular collision detection protocol for VANETs. The proposed protocol takes advantage of the vehicle-to-vehicle communication in VANETs to predict potential collisions with vehicles in the proximity. Simulation results show that our proposed protocol achieves 92% accuracy in detecting collisions using real case Ottawa urban scenarios and several accidents scenarios. Also, applying a prediction model to estimate future trajectories of nearby vehicles, has significantly reduced the overhead of transmitted packets.

In this paper, we introduce possible approaches for transmission of safety messages using LTE/LTE-A network. The first solution is using only LTE cellular connections. Vehicles transmit messages to a central server and it forwards the messages to the vehicles in the awareness area of the transmitter vehicle. The second approach uses only D2D capability of LTE, allowing vehicles to communicate directly without the involvement of the infrastructure. The last approach uses both cellular and D2D connections of LTE. We compared the possible approaches using simulation results regarding the required amount of resources, central information accuracy, and successful discovery ratio of the vehicles in the awareness area of the transmitter vehicle. Each approach has advantages and disadvantages, thus the appropriate approach is chosen based on the specific vehicular applications requirements and also availability of resources.

Recently, information-centric networking has been proposed to VANETs scenarios for improving content delivery of infotainment applications. Using the ICN paradigm, content-oriented search and in-network caching have the potential to improve content delivery in spatial- and time-dependent applications for VANETs and smart transportation. However, uncontrolled Interest packet transmissions for content search will result in a waste of resources and diminish the performance of VANETs' applications. In this paper, we propose a lightweight protocol to tackle the Interest broadcast storm problem during a content search in information-centric VANETs. The proposed protocol considers the distance between a current forwarder and its neighboring vehicles to opportunistically control redundant Interest packet transmissions in vehicular named data networking. Simulation results show that the proposed protocol improves the content delivery rate by 60% while decreases the Interest packet transmissions by 40%, in the scenario of a low number of content producers in the network.

Intelligent transport systems (ITS) may take advantage of the mobile cloud, in other words, the vehicular cloud may provide a lot of services for assisting traffic, accident prevention, and content delivery, among others. However, search and allocation resources in the vehicular cloud has become challenging, due to vehicular network characteristics, and also to the necessity of attempting the QoS requirements of service independently of the external condition. Thus, one of the biggest obstacles in these environments is to allocate and share resources available in vehicles without the need for external infrastructure. With this challenge in mind, we propose a new protocol designed to facilitate resource sharing via mobile cloud in the vehicular network. Simulation results show that the proposed approach introduces a short search time of approximately 0.7 (ms) to query resources in one hop, and about 1.0 (ms) to seek resources in more than one hop. Furthermore, the proposed protocol enables a high availability of resources, about 95%.

Typically, the electric power companies employ a group of power meter readers to collect data on the customers energy consumption. This task is usually carried out manually, which can lead to high cost and errors, causing financial losses. Some approaches have tried to minimize these problems, using strategies such as discovering the minimal route or relying on vehicles to perform the readings. However, errors in the manual readings can occur and vehicles suffer from congestion and high fuel and maintenance costs. In this work, we go further and propose an architecture to the Automatic Meter Reading (AMR) system using Unmanned Aerial Vehicles (UAV). The main challenge of the solution is to design a robust and lightweight protocol that is capable of dealing with wireless communication collisions. Therefore, the main contribution of this work is the design of a new protocol to ensure wireless communication from UAV to the power meters. We validated and evaluated the architecture in an urban scenario, with results showing a decrease of time and distance when compared to other approaches. We also evaluated the system proposed with Linear Flight Plan, the Ant Colony Optimization and Guided Local Search metaheuristic. Our mechanism attains an improvement of 98% in reducing the message collisions and reducing the energy consumption of the power meters.

Simulation is the most frequently adopted approach for evaluating protocols and algorithms for Vehicular Ad hoc Networks (VANETs) and Delay-Tolerant Networks (DTNs). Usually, simulation tools use mobility traces to build the network topology based on the existing contacts between mobile nodes. However, quality of the traces, in terms of spatial and temporal granularity of each entry in the logfile, is a key factor that impacts the network topology directly. Therefore, the reliability of the results depends strongly on the accurate representation of the real network topology by the vehicular mobility model. We show that five widely adopted existing real vehicular mobility traces present gaps, leading to fallible outcomes. In this work, we propose a solution to fill those gaps, leading to more fine-grained traces, which lead to more trustworthy simulation results. We propose and evaluate a data-based solution using clustering algorithms to fill the gaps of real-world traces. In addition, we also present the evaluation results that compare the communication graph of the original and the calibrated traces using network metrics. The results reveal that the gaps do indeed induce network topologies differing from reality, decreasing the quality of the evaluation results. To contribute to the research community, we have made the calibrated traces publicly available, so that other researchers may adopt them to improve their evaluation results.

HLA-based simulation systems are prone to load imbalances due to lack management of shared resources in distributed environments. Such imbalances lead these simulations to exhibit performance loss in terms of execution time. As a result, many dynamic load balancing systems have been introduced to manage distributed load. These systems use specific methods, depending on load or application characteristics, to perform the required balancing. Load prediction is a technique that has been used extensively to enhance load redistribution heuristics towards preventing load imbalances. In this paper, several efficient Time Series model variants are presented and used to enhance prediction precision for large-scale distributed simulation-based systems. These variants are proposed to extend and correct the issues originating from the implementation of Holt's model for time series in the predictive module of a dynamic load balancing system for HLA-based distributed simulations. A set of migration decision-making techniques is also proposed to enable a prediction-based load balancing system to be independent of any prediction model, promoting a more modular construction.

Cloud computing environments mainly focus on the delivery of resources, platforms, and applications as services to users over the Internet. Cloud promises users access to as many resources as they need, making use of an elastic provisioning of resources. The cloud technology has gained popularity in recent years as the new paradigm in the IT industry. The number of users of Cloud services has been increasing steadily, so the need for efficient task scheduling is crucial for maintaining performance. In this particular case, a scheduler is responsible for assigning tasks to virtual machines efficiently, it is expected to adapt to changes along with defined demand. In this paper, we suggest an elastic scheduler that is able to alter its focus based on the current requirements demanded by the cloud service provider and the user of those services. The Elasticity Based Scheduling Heuristic (EBSH) suggested is measured against the bio-inspired optimization algorithms such as Ant Colony Optimization (ACO) and Honey Bee Optimization (HBO). Also, a networking algorithm is used in this study, namely Random Biased Sampling (RBS). The presented EBSH shows superior performance because of its ability to adapt to changes.

Mobile Cloud Computing is a concept infrastructure wherein Cloud Computing resources are utilized to offload tasks from mobile elements. The combination of Cloud Computing and Mobile Computing increases the complexity of modeling and performance evaluation in terms of task scheduling policies, energy consumption model, the mobility of mobile devices over a layered architecture of both local Clouds and remote Cloud data centers. In this paper, a distributed HLA-based Cloud toolkit is proposed, enabling the modeling and simulation of Mobile Cloud Computing environment. The proposed toolkit simulates the behaviors of the Mobile system and the Cloud infrastructure, within which different resource scheduling policies can be evaluated in a repeatable manner. In addition, an HLA-based simulation scheduling scheme is proposed, trying to improve simulation execution efficiency by automatically parallelizing and distributing simulation components. A Cloud-based simulation resource management paradigm is also implemented, handling the configuration and maintenance issues regarding underlying system resources and simulation data. Based on the experiments, the proposed toolkit can achieve better simulation execution efficiency, with consideration of both Cloud and Mobile behaviors, compared to current Cloud Computing environment simulators.

The popularity of personal devices has been creating a new location-based content era, where users produce, share and access content anytime and anywhere. Mobile devices in the same area can cooperate to each other by using a Device-to-Device (D2D) communication and maximize the usage of network resources and allow the creation of new applications and experiences. In this paper, we investigate the dynamics of physical proximity of peers in a long-term study. We used one year of collected data from social media for an analysis of spatiotemporal features of how users encounter each other and the opportunities for content offloading in cellular networks. The results provided insights about the regularity of encounters, the role of routine and other spatial characteristics.

A Vehicular Cloud generally focuses on several aspects, which include providing a set of computational services at low cost to vehicle drivers; minimizing traffic congestion, accidents, travel time, and environmental pollution; and ensuring the use of low energy and real-time services of software, platforms, and infrastructure with QoS to drivers. The largest challenge in vehicular mobile Clouds consists of creating a mechanism for management and search resources that does not depend on roadside infrastructure, which consequently requires the spontaneous and dynamic creation of a Cloud through the resources shared by vehicles. Therefore, the system must enable collaboration and co-operation between vehicles so that they may establish connections to provide resources. To address this challenge, we propose a peer-to-peer protocol to assist in the discovery and management of resources in a vehicular mobile Cloud without depending on the support of a roadside infrastructure so that vehicles are expected to organize themselves and establish collaborations to manage and share their resources. Simulation results show that the proposed approach introduces a short search time of approximately 0.5 (ms) to seek resources in one hop and approximately 0.9 (ms) to seek more of a hop in resources. Furthermore, the proposed protocol enables a high availability of resources, about 87%.

Vehicular Ad-hoc Networks (VANETs) technology has been utilized in recent applications to enhance the traffic fluency over the road network. Various types of emergency cases may negatively affect the efficiency of traffic flow in highway road scenarios, including accidents, damaged vehicles or the presence of emergency vehicles. These cases exaggerate the traffic problems in severe congestion scenarios. In this paper, we propose a traffic efficiency protocol which first aims to detect emergency cases over highway road scenarios. Then, it recommends the most appropriate response for each vehicle affected by the detected emergency case. The best response for each vehicle is determined based on the vehicle's location and speed. Our protocol also considers overall traffic conditions over the investigated road scenario. From the experimental results, we can prove that our proposed protocol has increased traffic fluency in the vicinity of emergency cases over highway road scenarios. Moreover, it has increased safety conditions for vehicles in such scenarios.

Delay-tolerant sensor networks (DTSNs) require efficient MAC transmission strategies that include energy constraint, relaxed latency, mobility support and diverse traffic load. Reservation-based and contention-based MAC schemes are used to improve throughput and energy consumption. In this paper, we propose a traffic adaptive, energy-efficient MAC protocol to achieve better data transmissions and as energy consumption, in order to satisfy the requirements in DTSN. In our protocol, reservation and contention modes are adjustable, in order to adapt to the traffic load with a suitable duty cycle length for achieving energy efficiency. The simulation results of our protocol demonstrate better performance in terms of energy efficiency and traffic adaptability than the schedule-based MAC protocol TDMA, the contention-based protocol CSMA, and the traffic adaptive protocol TRAMA under mobile DTSN environments.

Lately, there has been a growing interest in connecting opportunistic routing (OR) and low duty-cycling methodologies in underwater sensor network (UWSNs) applications. This connection improves the data collection reliability and prolongs the network lifetime. When sensor nodes operate in a duty-cycling manner, the properly sleep interval selection and its on-the-fly adjustment should be addressed. Both tasks are challenging when opportunistic routing protocols are used at the network layer, as they should consider the presence of the next-hop candidates set. In this paper, we propose a modeling framework to evaluate the effects of the sleep interval on the energy consumption of duty-cycled UWSNs, which employ opportunistic routing protocol at the network layer. We investigate the sleep interval control problem in the OR scenarios, formulating it as an optimization problem with the goal of extending the network lifetime. Our simulation results show that different fixed sleep interval duty-cycles do not impact on the average energy consumption whereas the sleep interval control can prolong the UWSN lifetime.

Vehicular network applications are emerging to bring many benefits to the users during their journey. However, the design and deployment of such applications require studies that provide insightful information about the network formed by vehicles. To this end, in the last years researchers have been characterizing real mobility traces collected from taxis equipped with GPS devices. However, these traces present temporal and spatial gaps, as it was demonstrated in other studies. In this work, we compare the real original traces with their calibrated version (i.e., with no gaps) to show that the existing gaps expressively affect key metrics such as contact duration, inter-contact time, and network capacity. As result, we contribute to the research community by presenting important analysis of real vehicular network topology and by showing the importance of calibrating the traces before evaluating vehicular network applications.

In recent years, there is a growing research interest in smart city applications based on opportunistic communications. The opportunistic networks in these scenarios are composed of disconnections, network partitions, high delay and strong influence of human mobility. To cope with these challenges, social-inspired approaches have been proposed considering the structure of networks and personal user features, however, limited studies have explored temporal variations of features and influence of exogenous variables, disregarding adaptive forwarding policies recommended for dynamic scenarios. In this paper, we address these challenges while investigating both, the temperature and the season calendar, as environmental features able to model the behavior of users' mobility and peer contacts. The results showed distinct social and spatiotemporal features characterized by thermal conditions able to affect the network performance. We also identified critical points of temperature able to provide early signals about the network changes. Finally, our results indicate that environmental data are crucial information towards the design of the next generation opportunistic mobile networks.

The choice of a suitable path for packet transmission represents a fundamental issue to any routing protocol. The principle of choosing the shortest path is also no longer a good option for route selection since many other aspects may influence communication performance. In that sense, the link quality of the path is more important than the length of the path in a wireless network because of the unstable conditions of the channel. Expected Transmission Count (ETX) is a widely-used routing metric, which servers into the selection of the path with fewer transmissions for a successful packet delivery. However, other factors should be also considered for route selection, such as the re-transmission delay. In this paper, a comprehensive analysis on the effect of the link layer delay to the transmission throughput is presented and discussed. Given the analysis outcome, this work proposes a routing metric based on the link layer delay for IEEE 802.11. This metric allows to determine the delay of each hop along the path to evaluate the quality of the path as whole. Experimental simulation results reveal that the proposed routing metric achieves better results when compared to two other known approaches.

Due to the nature of communication, mobility and portability in Mobile Computing, the handling of limited computing, storage and network capabilities become increasingly important especially when more features and richer functionality are required today. Cloud Computing, as an elastic computing utility provisioning framework, is shown to be a promising approach, addressing the concerns in Mobile Computing. Many achievements have been made by researchers regarding how to offload computational tasks from mobile systems to the Cloud. However, the proposed offloading methodologies are mainly from the perspectives of mobile application level, focusing on static estimation, dynamic partitioning, cloning, transmission overhead evaluation and migration. Issues related to multi-core Cloud systems are not fully considered, such as overall energy consumption of Cloud systems, information security, usability and availability. In this paper, a platform-based system model is designed from the view of the Cloud platform, trying to enable these Cloud benefits in addition to offloading, and to provide better execution efficiency and overall energy reduction by utilizing the proposed platform level scheduling. Based on the experiments, the proposed platform scheduling can achieve greater energy reduction with little computing overhead on the management node, compared to application-level scheduling methods.

Text detection and communication in the automotive context has attracted the attention of researchers only over the past few years. Detecting text in the automotive context, as opposed to the detection of text of printed pages, imposes additional challenges, such as the presence of obstacles, blurry frames, speedy vehicles, etc. In this paper, we present an in-vehicle real-time system able to localize texts and communicate them to the drivers. Our system begins by localizing regions of interest as a Maximally Stable Extremal Regions (MSERs). Afterwards, we apply a novel filtering stage which begins by dividing each ROI into 4 × 4 cells, counting the number of edges in each cell and comparing them to a well defined threshold. This is performed in order to filter out a considerable number of unwanted objects. The ROIs that contain text are fed into a recognition module based on the Optical Character Recognizer (OCR). Our proposed method achieves high f-scores when tested against several videos containing a numerous panels.

Vehicular network applications may be benefited by the use of simultaneous network interfaces to maximize through-put and reducing latency. In order to take advantage of all radio interfaces of the vehicle and to provide a good quality of service for vehicular applications, we have developed an architecture that performs the management of the flow mobility based on some classes of application for vehicle network. Our goal is to minimize the time of handover between the rings of flows in order to meet the minimum requirements of vehicular applications, as well as to maximize the throughput. Simulations have been conducted to analyze the performance of the proposed architecture by comparing it to other previously devised architectures. As a result, the proposed architecture presented a low delivery time of messages, packets with lower loss and lower delay.

Delay-Tolerant Sensor Networks (DTSN) experience long, unpredictable latency under fluctuating wireless networks with intermittent connectivity. Energy consumption and throughput improvement are essential in the design of MAC for DTSNs. However, when latency is relaxed in DTSN environments, traditional metrics such as throughput and energy consumption cannot express the transmission efficiency and energy consumption. Therefore, transmission strategies in DTSNs can use data packets over energy as energy efficiency to demonstrate efficiency under the requirements of high data volumes and energy conservation. In this paper, we examine and analyze the MAC parameters that impact energy efficiency with reservation-based and contention-based MAC approaches under DTSN environments. Simulation results from two typical MAC protocols also match the results of our analysis regarding energy efficiency in DTSN.

Opportunistic Routing (OR) protocols are known as a promising research area with the aim of delivering data packets to their destination more reliably. Security of such protocols, however, is still an open, and challenging research problem. In this paper, we propose an enhancement on OR protocols which benefits from an appropriate candidate coordination mechanism, and assists in salvaging data packets that are dropped by malicious nodes. More precisely, an analytical approach is proposed using Discrete-Time Markov Chain (DTMC) to model a packet salvaging mechanism in an OR-based wireless network, while malicious nodes attempt in degrading the network performance. The proposed model demonstrates how back-up candidates in the candidate set can help in salvaging dropped packets by supervising the behavior of other peers in the candidate set. Different network parameters including packet delivery, drop, salvage, and direct-delivery ratio are then extracted from the introduced model. Furthermore, the model is applied on a well-known OR protocol and is evaluated using both analytical approach, and network simulations. Evaluation results represent that the introduced model can dramatically boost the performance of a wireless network by delivering greater number of packets to their destination compared to a baseline protocol.

In underwater sensor networks, the design of energy efficient and reliable data collection protocols is a daunting challenge. In this context, topology control and opportunistic routing are promising techniques for improving reliability and conserve energy. However, due to the challenges of the underwater acoustic channel, the vast knowledge acquired and the solution proposed so far in the context of terrestrial wireless ad hoc sensor networks cannot be applied directly to underwater acoustic sensor networks. In this work, we shed light on network topology modeling from a routing viewpoint. We model the probabilistic multipath routing behavior driven by opportunistic routing protocols in underwater sensor networks. Afterward, we propose the PCen centrality metric to measure the importance of underwater sensor nodes to the data delivery task through opportunistic routing protocols. PCen is aimed to identify critical nodes that can be used to guide topology control solutions. Our simulation results consider different network densities and reveal the presence of a few number of nodes with high PCen centrality value that will have a high rate of carried traffic, being critical for the network performance.

With Vehicular mobile communication becoming an everyday requirement and an ever increasing number of services available, it is clear that vehicular networks require more efficient management. In this paper we discuss service orientation as an architectural model for Information Centric Networking (ICN) VANETs. We discuss the limitations faced by vehicles and propose structuring communication towards as a coordinated service-centric network. Intermittent connectivity and end-to-end network delay are amongst the issues tackled by this work as we envision our network model. Additionally, we perform a set of simulations to exemplify the benefits of service coordination.

As an important component of Smart Cities, transportation system plays a critical role to address the sustainability and mobility of the society. One key concern is that the number of vehicles continuously increases faster than the available infrastructure, as well as the traffic congestion is a difficult issue to deal with. Several solutions to Intelligent Transportation Systems (ITS) have been proposed to identify congestion and re-route the vehicles afterwards. In this direction, this work introduces SPARTAN, a fully distributed ITS solution, which notifies drivers about congested areas through Vehicle-to-Vehicle communication and employs a real-time decision making mechanism used to reroute vehicles to avoid the congested areas. Simulation results show the effectiveness of SPARTAN in calculating new routes and disseminating them to vehicles that approaching a congestion area. As a consequence, SPARTAN reduces the travel time and the congestion time in urban scenarios when compared to existing approaches.

The detection and recognition of Traffic Signs (TSs) by smart vehicles is of great interest. In this paper, we present a novel TSs localisation and recognition system using client-server architecture. To the best of our knowledge, this is the first architecture that uses non vision-based techniques to detect and recognise TSs. To discover TSs in lanes using our architecture, each travelling vehicle (known as client in our architecture) begins by sending a request, which contains its geographical position, to the data server. This server then sends all nearby TSs, found within a given radius in the lane, to the requester. Finally, we apply a filtering algorithm to select appropriate TSs from the previously found set of TSs. Our system can be used in a conjunction with a traditional vision-based system to further increase the accuracy of the whole system.

Traffic lights are located on the road intersections to control and manage the competing traffic flows. Several algorithms have been proposed considering the real-time traffic characteristics of each competing traffic flow at the road intersection. Emergency vehicles such as ambulance, fire truck and police vans should have higher priorities to cross any road intersection first. Whenever an emergency vehicle appears close to any road intersection, all vehicles on the competing flows should stop and allow that vehicle to proceed first. However, this may cause a hazards situation in the case that any driver miss-behaves or insists to follow the current traffic light phase. In this paper, we aim at designing a context-aware traffic light self-scheduling (CA-TLS) algorithm. This algorithm uses the traffic characteristics of the traffic flows and the emergency vehicles presence on the competing flows at any signalized road intersection. First, these parameters are gathered using periodic advertisement messages of traveling vehicles. Then, the CA-TLS algorithm sets the phases of each traffic light cycle according to the traffic gathered data. The green phase of any traffic flow can be interrupted to enable the fast proceeding of the appeared emergency vehicles. An extensive set of experiments have shown that this algorithm decreases the delay time of emergency vehicles at the signalized road intersections.

The accelerated growth of applications and services in intelligent transportation systems (ITS) are driven by interests from the public and private sectors. The intent to utilize the onboard resources, along with the advanced methods of managing the available computing capabilities in the conventional cloud, has led to the high popularity of Vehicular Clouds. Likewise in Vehicular Networks, vehicles provide the building blocks for forming these particular clouds, which can enable a large number of applications and services that can benefit the whole transportation system, as well as the drivers, passengers, and pedestrians. However, due to its high mobility, Vehicular Clouds show several inherent challenges, which increase complexity and restrict the design of solutions. Determining the number of vehicles and their time of availability in a given region through a model works as a critical stepping stone for enabling vehicular clouds, as well as any other system involving vehicles moving over the traffic network. Therefore, by implementing proper traffic models, we present a comprehensive stochastic analysis about the distribution of the number of vehicles inside a road segment in this paper. According to real parameters, we show that certain classes of applications are feasible even for highly mobile scenarios.

Summary Simulations have been used extensively for evaluating scenarios, which are very difficult, costly or impractical to implement in real systems. Testing in a synthetic, realistic environment provides a means to determine the viability of solutions. Simulations have proved to be very useful in the verification of algorithms and protocols, offering tools for testing them in different situations. The simulation of vehicular area networks pose additional challenges as realistic mobility models are crucial and must be incorporated in scenario elements while applications and communication protocols are tested. Several simulators and simulation frameworks have been designed that aim to synthetically reproduce communication and mobility of vehicles as realistically as possible. The majority of such simulators merge pre‐existing networking and mobility simulators, which add issues regarding compatibility and realism. Such simulators present limited run‐time 3D visualization tools, essential for providing immersive environments. Therefore, in this paper, we propose real‐time simulation and 3D visualization for vehicular networks of realistic scenarios. This proposed simulation system generates output in real time, making use of 3D‐modelled real‐world maps and effectively generating visualization as elements are updated in the simulation. Experiments have been conducted with simulation and visualization components to evaluate delays and performance of the proposed simulator. Copyright © 2016 John Wiley & Sons, Ltd.

Summary An examination of the multidimensional range query in existing peer‐to‐peer (P2P) overlay networks indicates that multidimensional range queries are sensitive to underlying topologies; this is because partitioning and mapping of multidimensional data space are two interconnected parts of a process that must be carried out cooperatively. The first section focuses on how to preserve data localities, whereas the second section concerns how to accommodate and maintain data localities at the P2P overlay layer. There are many studies that have been conducted on the first section since 1966, and those works that are well accepted are mostly based on recursive decomposition, which forms a tree structure in nature. However, less effort has been made to provide comparable support from the P2P overlay layer. In our previous work, we proposed the Hierarchically Distributed Tree (HD Tree) in order to better support multidimensional range queries in the P2P overlay network. This paper further explores error‐resilient routing and load balancing strategies that can be employed in the HD Tree. We also provide a complete set of experimental results for all routing operations: Join and Leave of nodes, range queries at different levels of selectivity, and the dynamic load balancing scheme. Comparisons are made by conducting simulations under both the ideal and the error‐prone routing environment and within various ary HD Trees. The experimental results show that load balancing in the HD Tree can be adjusted dynamically and globally, and it is actually a trade‐off between distributing the basic load and the involvement of nodes in range querying. The experimental results also indicate that a maximum of 10 percent of routing nodes’ failures do not have significant effects on the performance of range queries. However, a lower ary HD Tree appears to have better routing performance, whereas a higher ary HD Tree achieves a higher fault‐tolerant capacity. Nevertheless, the performance of range queries in a higher ary HD Tree can be further optimized if all possible routing options can be fully explored in the error‐prone routing environment. Copyright © 2013 John Wiley & Sons, Ltd.

Summary Cloud computing has evolved to provide computing resources on‐demand through a virtualized infrastructure, letting applications, computing power, data storage, and network resources to be provisioned and managed over private networks or over the Internet. Cloud services normally run on large data centers and demand a huge amount of electricity. Consequently, the electricity cost represents one of the major concerns of data centers, because it is sometimes nonlinear with the capacity of the data centers, and it is also associated with a high amount of carbon emission (CO2). However, energy‐saving schemes that result in too much degradation of the system performance or in violations of service‐level agreement (SLA) parameters would eventually cause the users to move to another cloud provider. Thus, there is a need to reach a balance between energy savings and the costs incurred by these savings in the execution of the applications. Therefore, in this paper, we propose and evaluate a power and SLA‐aware application consolidation solution for cloud federations. It comprises a multi‐agent system for server consolidation, taking into account SLA, power consumption, and carbon footprint. Different for similar solutions available in the literature, in our solution, when a cloud is overloaded, its data center needs to negotiate with other data centers before migrating the workload to another cloud. Simulation results show that our approach can reduce up to 46% of the power consumption while trying to meet performance requirements. Furthermore, we show that federated clouds can provide an adequate solution to deal with power consumption in the clouds. Copyright © 2016 John Wiley & Sons, Ltd.

Summary The recent advances in technology and mobile computing led to the rapid growth of networked 3D streaming applications. The emerging services can involve augmented reality, virtual environment walkthrough, multiplayer gaming just to mention a few. Because of the limited network bandwidth of the client‐server approach, research works are now turning toward mobile ad hoc networks‐based streaming, where the resources of each peer are used during the streaming service. Peer‐to‐peer technologies are considering the solution to adapt for scalable applications. Yet, supplying partner selection and 3D data delivery are still significant challenges to face because of the dynamic wireless environment that causes link breakages, high packet loss, an adverse impact on the quality of the 3D media, and a low user satisfaction. In this paper, we propose a supplying partner selection technique coupled with a content delivery technique for peer‐to‐peer 3D streaming over thin mobile devices. Our proposed protocol, which we refer to as MULTIPLY, considers multihop suppliers in order to alleviate the load on the server and uses the signal strength measurement to analyze the wireless link when sending back the 3D data. Given the high dynamicity of the network due to the mobility of the users, the streaming can be greatly affected. We therefore study the impact of the mobility on MULTIPLY. The performance evaluation of our protocol obtained using an extensive set of simulation experiments is then reported. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract In the recent years, we are witnessing a growing interest into the design of smart vehicles and smart roads for Intelligent transportation systems. Vehicles as part of the Internet of Things should provide to the driver and passenger with a variety of services using efficient gateway discovery mechanism while maintaining a certain level of security and authentication to avoid potential malicious attacks. In this paper, we propose a secure hybrid adaptive gateway discovery and communication protocol for smart vehicular networks, which we refer to as SEGAL. Our proposed SEGAL protocol is based upon building a secure clustered vehicular network, and permits the exchange of gateway discovery messages through authenticated clusterheads and cluster members. We shall present the design of our protocol, and describe how it can overcome the possible malicious attacks that might harm the network. Then, we report its efficiency and scalability using an extensive set of simulation experiments using Ns‐2 simulator. Our results indicate that the proposed SEGAL protocol is scalable while achieving high success rate, low response time and dropping rate. Copyright © 2016 John Wiley & Sons, Ltd.

Underwater wireless sensor networks (UWSNs) have been showed as a promising technology to monitor and explore the oceans in lieu of traditional undersea wireline instruments. Nevertheless, the data gathering of UWSNs is still severely limited because of the acoustic channel communication characteristics. One way to improve the data collection in UWSNs is through the design of routing protocols considering the unique characteristics of the underwater acoustic communication and the highly dynamic network topology. In this paper, we propose the GEDAR routing protocol for UWSNs. GEDAR is an anycast, geographic and opportunistic routing protocol that routes data packets from sensor nodes to multiple sonobuoys (sinks) at the sea's surface. When the node is in a communication void region, GEDAR switches to the recovery mode procedure which is based on topology control through the depth adjustment of the void nodes, instead of the traditional approaches using control messages to discover and maintain routing paths along void regions. Simulation results show that GEDAR significantly improves the network performance when compared with the baseline solutions, even in hard and difficult mobile scenarios of very sparse and very dense networks and for high network traffic loads.

In this paper, we propose and evaluate unexplored approaches for real-time automated vehicle make and model recognition (VMMR) based on a bag of speeded-up robust features (BoSURF) and demonstrate the suitability of these approaches for vehicle identification systems. The proposed approaches use SURF features of vehicles' front- or rear-facing images and retain the dominant characteristic features (codewords) in a dictionary. Two schemes of dictionary building are evaluated: “single dictionary” and “modular dictionary.” Based on the optimized dictionaries, the SURF features of vehicles' front- or rear-face images are embedded into BoSURF histograms, which are used to train multiclass support vector machines (SVMs) for classification. Two real-time VMMR classification schemes are proposed and evaluated: a single multiclass SVM and an ensemble of multiclass SVM based on attribute bagging. The processing speed and accuracy of the VMMR system are affected greatly by the size of the dictionary. The tradeoff between speed and accuracy is studied to determine optimal dictionary sizes for the VMMR problem. The effectiveness of our approaches is demonstrated through cross-validation tests on a recent publicly accessible VMMR data set. The experimental results prove the superiority of our work over the state of the art, in terms of both processing speed and accuracy, making it highly applicable to real-time VMMR systems.

Detecting large animals on roadways using automated systems such as robots or vehicles is a vital task. This can be achieved using conventional tools such as ultrasonic sensors, or with innovative technology based on smart cameras. In this paper, we investigate a vision-based solution. We begin the paper by performing a comparative study between three detectors: 1) Haar-AdaBoost; 2) histogram of oriented gradient (HOG)-AdaBoost; and 3) local binary pattern (LBP)-AdaBoost, which were initially developed to detect humans and their faces. These detectors are implemented, evaluated, and compared to each other in terms of accuracy and processing time. Based on our evaluation and comparison results, we design a two-stage architecture which outperforms the aforementioned detectors. The proposed architecture detects candidate regions of interest using LBP-AdaBoost in the first stage, which offers robustness to false positives in real-time conditions. The second stage is based on support vector machine classifiers that were trained using HOG features. The training data are generated from our novel dataset called large animal dataset, which contains common and thermographic images of large road-animals. We emphasize that no such public dataset currently exists.

One of the most interesting and promising challenges for Intelligent Transportation Systems (ITSs) relates to the traffic congestion problem. Congestion is a relevant issue for transportation because it reduces the efficiency of infrastructure and increases travel time, air pollution, and fuel consumption. Nowadays, the most promising technology in support of ITSs is found in the domain of Vehicular Ad Hoc Networks (VANETs). In this paper, we propose three protocols that are able to transmit traffic information for routes of interest on VANETs without any Road Side Unit (RSU) support. The proposed protocols adopt strategies to improve the performance of packet routing based on the density and location of vehicles; moreover, they enable an interesting comparison of the performance achievable with either reactive or proactive approaches. The extensive performance results reported show how it is possible to limit the congestion monitoring overhead along Routes of Interest (ROIs), while maintaining a sufficiently high performance in terms of traffic reporting. This may be done by employing context-aware data delivery techniques that autonomously adapt to runtime conditions. Copyright © 2016 John Wiley & Sons, Ltd.

In this paper, we propose both reactive and proactive balancing traffic path recommendation mechanisms, which we refer to as Bal-Traf and Abs-Bal, respectively. Bal-Traf is initiated when a certain output road segment located at any road intersection is detected in an overloaded situation. In the event that the existing traffic density of any output road exceeds its optimal capacity, Bal-Traf recommends that those vehicles that plan to pass over this road segment as next hop choose another, less congested output road segment. On the other hand, Abs-Bal is a proactive balancing traffic mechanism. Its main purpose is to distribute input traffic completely even among all output road segments at intersections. Moreover, Abs-Bal considers the best travel time of vehicles in addition to the goal of balancing traffic. From the experimental results, we can see that Bal-Traf eliminates the number of overwhelmed road segments over the road network in scenarios with only partial network congestion. It also decreases the number of congested road segments in scenarios with complete network congestion. However, it increases the density drastically over the remaining congested road segments in these scenarios. Abs-Bal performs well in decreasing the percentage of congested road segments and balancing traffic among road segments located throughout the road network, in the event of complete network congestion.

Load management is an essential and important factor for distributed simulations running on shared resources due to load imbalances that can caused considerable performance loss. This feature is essential for High Level Architecture (HLA)-based simulations since the HLA framework does not present the ability to manage resources or help detect load imbalances that could directly cause decrease of performance. A migration-aware dynamic balancing system has been designed for HLA simulations to offer an efficient load-balancing scheme that works in large-scale environments. This system presents some limitations on estimating costs and benefits, so we propose an enhancement to this existing load balancing system, which improves the accuracy of generating federate migrations. The proposed scheme aims to precisely estimate the migration delay and gain by analyzing the load on shared resources, preventing the issuing of migrations costly towards simulation execution time. Upon a performance analysis, the proposed decision-making analysis scheme has shown an improvement on decreasing the number of migrations and consequently decreasing execution time.

The HLA framework is widely used to formalize simulations and achieve reusability and interoperability of simulation components. In order to manage the underlying system of HLA-based simulations, Grid Computing and Cloud Computing are employed to tackle the details of operation, configuration, and maintenance of simulation platforms that simulation applications run on. However, to make a simulation-run-ready environment among different types of computing resources and network environments is challenging, especially for modelers who may not be familiar with the management of distributed systems. In this article, we propose a new cloud-based scheme for HLA based simulations, aiming to ease the management of underlying resources, particularly for those located on geographically distributed locations, and to achieve rapid elasticity that can provide adequate computing capability to end users. An approach for handling diverse network environments is given, by adopting it, idle public resources can be easily configured as additional computing resources for the local cloud infrastructure. In the experiments, compared with its corresponding Grid Computing platform, this Cloud Computing platform achieves a similar performance but with many advantages that Cloud can provide, such as energy consumption, security, and multi-user availability.

The fast and frequent movement of vehicles creates many challenges in vehicular networks, such as handling regular topological changes. Predicting a vehicle's future location by preemptively adjusting to changes caused by vehicle movements is a potential solution to many of these problems. However, reliably predicting vehicle movement remains an issue due to its stochastic nature. This paper proposes a prediction method that probabilistically analyzes the vehicle's current movement to determine the vehicle's future steps. This is accomplished by combining the Kalman filter and hidden Markov model to include both temporal and historical data, thus improving the prediction reliability by the consideration of more system variables. The proposed approach is tested and compared to other recent approaches through simulation using SUMO and NS-2. The results show a 50% prediction error reduction of the proposed approach in comparison to other methods.

Addressing the reliability and security of communications are of the most important challenges in wireless networks. Opportunistic Routing (OR) protocols assist in improving the reliability of routing whereas trust and reputation management protocols aim to improve the security. In this paper, a new comprehensive reputation system is proposed which benefits not only from the reliability of OR protocols but also from the security enhancements of reputation systems. The proposed model utilizes experience- based (direct) reputation resulting from direct interactions between nodes as well as recommendation-based (indirect) reputation. Conducted experimental results verify the performance of the introduced approach in delivering packets to their destination while malicious nodes try to attack the network.

Efficient protocols for data packet delivery in Vehicular Ad-hoc NETworks (VANETs) are crucial to guarantee the correct forwarding of data. However, communication in VANETs is a challenging task not only for the high mobility of the vehicles, but as recent studies have shown, there is a negative impact on protocol performances caused by an obstacle such as another vehicle in the line-of-sight (LOS). Many different routing protocols were presented in the last years, but only few of them were considering the effect of non line-of-sight (NLOS) propagation. In this work, we present a new solution to improve the data packet delivery ratio considering the problems caused by a high mobility and NLOS condition. Our proposal can be integrated in every position-based routing protocol. In fact, our method creates a support context awareness of neighbors before letting the protocol choose the next hop, without interfering with the specific logic. Simulation results of our context-aware version have been compared with the original protocols and with a modified version in accordance with the principle that every violation of LOS involves a discard of the packet: our solution always perform better in terms of packet delivery ratio and delay.

Internet of Thing (IoT) cloud system is a field attracting a great deal of recent attention. Vehicular networks is a key area in IoT, as they can offer novel experiences in infotainment, as well as driving assistance such as like real-time traffic forecasting, advertisements and on board entertainment. Most of these applications rely on high quality video sharing, which is still an open research topic in Vehicular networks. We proposed a Cloud-MERVS technique for video streaming in Vehicular networks, which integrates IoT cloud system techniques and the Multi-channel Error Recovery Video Streaming (MERVS), to provide a more satisfying driving and travel experience. There are two types of service providers in cloud computing: Control Service Providers (CSPs) and Video Service Providers (VSPs). CSPs are responsible for collecting advertisement messages from the VSPs. The VSPs are the real video and service providers. Some VSPs are connected to a selected CSP to form a Group Service Provider (GSP), which is organized in a hierarchical structure for to improve efficiency. The design is implemented in Network Simulator-2 (NS-2). In this paper, several verification simulations are conducted, and the simulation results are presented.

Vehicular delay-tolerant networks (VDTN) experience high-speed mobility and volatile topology on a large scale. Therefore, VDTN may not guarantee end-to-end connections. This gives the MAC layer the opportunity to adapt its transmission strategy to the current unstable wireless connections in order to improve transmission efficiency. We propose an adaptive frame length aggregation scheme in VDTN in order to improve transmission efficiency and increase data throughput. In our scheme, suitable aggregation frame lengths are calculated according to the current wireless status, and are applied in the MAC layer at the initiation of the data transmissions. We analyze and apply our adaptive frame length aggregation strategy to the current frame aggregation schemes in 802.11. Our simulations demonstrate improved results in data throughput, retransmissions, and transmission efficiency, compared to non-adaptive aggregation schemes.

TCP suffers degradation in wireless networks, which is caused by the improper, static definitions on the lower layers. In order to improve the TCP performance in wireless networks, the strategy of the lower layer should be reconsidered. In this paper, the TCP transmission is flattened in order to combine the TCP segment transmission and TCP Acknowledgement (ACK) transmission into one transmission. The performance of TCP is also analyzed, in order to find out the corresponding parameters affecting the TCP throughput. Based on the analysis, contention window size shows as one of the parameters that greatly affects the TCP performance. A discrete-time Markov decision process is adopted in order to solve the TCP throughput maximization. Based on the analysis, a TCP-distributed algorithm is proposed. Several simulations are conducted to verify the improvements of TCP-distributed by comparing both TCP Reno and TCP Vegas. Simulation results show that TCP-distributed can perform better than the two TCP variants, and it also limits the delay in an acceptable range.

Several research studies have introduced an efficient and intelligent path recommendation protocols for vehicular networks. Communications among traveling vehicles and located roadside units (RSUs) have been utilized to investigate the traffic distribution over the road network. This helps construct the optimal path towards each targeted destination located on the road network. However, none of the previous proposed protocols in this field have specifically considered potential faults among the nodes of the vehicular networks or potential link failures. In this paper, we present a fault tolerant distributed-based path recommendation (TD-PR) protocol. Our protocol detects and tolerates faults occur among nodes and/or communication links. We present TD-PR protocol in this paper and report on its performance evaluation. Our simulation experiments show that TD-PR improves the success rate significantly over our previously proposed path recommendation protocol (ICOD). The success ratio is improved in roadside failure and link failure scenarios. In general TD-PR has better performance in terms of decreasing the traveling time and traveling distance compared to ICOD in these scenarios.

Traffic jams frustrate drivers and cost billions per year in time and fuel consumption. In order to avoid such problems, this paper presents an intelligent transportation system that collects real-time traffic information and is able to detect and manage traffic congestion based on this information. Simulation results show that the proposed protocol can reduce the average travel time, CO2 emission and fuel consumption. In particular, the average travel time was reduced in approximately 23%, the average fuel consumption in 9% and average CO2 emission in 10%.

Cloud computing has been receiving a growing attention due to its features on the provisioning of computing resources for distributed processing. A lot of interest lays on the enabled benefits of flexible and elastic management of cheap and reliable computing sources though virtualization. The cheap characteristic brought from virtualization helps data centers to host more than one operating system on any machine. However, the time-sharing nature of virtualization and the existence of more software layers lead to larger delays in execution and network communications. The bundling of network messages directed to the same destination can be used as means to reduce the number of network transfers. In this paper, the effect of different message bundling aspects closely related to cloud applications is investigated. Analysis shows that message bundling effectively enhances communication efficiency; however, it is directly influenced by parameters such as number of messages, length of the bundling cycle, and number processing units.! Thus, the highest performance gain is achieved by flexibly adjusting according bundling parameters towards data communication in large-scale cloud environments.

Most Vehicular Ad-hoc Network (VANET) applications require the delivery of a variety of content to vehicles. Furthermore, content in such applications is usually geo-localized (i.e., designated to a specific region of interest). To help with the delivery of geo-localized content in VANET applications, content replication strategies can be exploited to keep content available where the interested vehicles are expected to be. To this end, we propose a Geo-Localized Origin-Destination-based Content Replication (GO-DCR) solution that relies on the vehicles' origin and destination points to select the vehicles most likely appropriate to replicate content. We compare GO-DCR to an existing solution through simulation. The results reveal that GO-DCR increases the content availability while reducing delivery cost.

Vehicular networks are a rapidly growing technology with vehicle manufacturers already taking steps for its implementation. However, adding IP services to vehicular networks remains an issue. This is in part due to the mobile IP handover causing overhead and latencies unsuitable for the faster movement of vehicles. Frequent topological changes caused by this movement require smooth IP handovers due to the regularity in which they occur. In this paper, we propose a predictive handover utilizing a movement prediction method to conduct the costly handover ahead of time, thus providing a consistent IP connection. The approach is tested and compared in a variety of simulated vehicle network environments. Results show an overall improvement in network performance with handover latency greatly reduced.

The problem of reliable data delivery at low energy cost arises as one of the most challenging research topics in underwater wireless sensor networks (UWSNs). Reliable data delivery is demanding because of the acoustic channel impairments and channel fading. Moreover, it is energy hungry given the high cost of acoustic communication. In wireless ad hoc & sensor networks, separately, opportunistic routing has been employed to improve data delivery whereas duty cycled operation mode has been adopted to achieve energy efficiency and prolonging network lifetime. In this paper, we investigate the benefits and drawbacks of collision between opportunistic routing paradigm and duty cycle techniques in UWSNs. We propose an analytical model to study and evaluate the performance of opportunistic routing protocols under duty cycled settings designed from three mainly paradigms: simple asynchronous, strobed preamble and receiver initiated; and different network densities and traffic loads. The results show that while duty cycle reduces the energy consumption, it affects negatively in the opportunistic routing performance, increasing the delay and the expected number of transmissions to deliver a packet. The simple duty cycled approach is shown to be suitable for applications that require long-lived network and can tolerate some degree of packet losses. Our results indicate that strobed preamble-based duty cycle is the most effective approach to be integrated with opportunistic routing, when high fidelity monitoring is required, even having not the best performance in terms of energy savings.

Simulation is the approach most adopted to evaluate Vehicular Ad hoc Network (VANET) and Delay-Tolerant Network (DTN) solutions. Furthermore, the results' reliability depends fundamentally on mobility models used to represent the real network topology with high fidelity. Usually, simulation tools use mobility traces to build the corresponding network topology based on existing contacts established between mobile nodes. However, the traces' quality, in terms of spatial and temporal granularity, is a key factor that affects directly the network topology and, consequently, the evaluation results. In this work, we show that highly adopted existing real vehicular mobility traces present gaps, and propose a solution to fill those gaps, leading to more fine-grained traces. We propose and evaluate a cluster-based solution using clustering algorithms to fill the gaps. We apply our solution to calibrate three existing, widely adopted taxi traces. The results reveal that indeed the gaps lead to network topologies that differ from reality, affecting directly the performance of the evaluation results. To contribute to the research community, the calibrated traces are publicly available to other researchers that can adopt them to improve their evaluation results.

In this paper, a semantic and self-decision geocast routing protocol for disseminating safety and non-safety information over VANET (SAS-GP) is presented. SAS-GP initially executes an algorithm for locally determining the semantic geocast area. Then, the protocol disseminates the information in three phases: Spread, Preserve, and Assurance, which utilize the traffic information system and the digital map. SAS-GP principally employs timer-based techniques in order to avoid overhead; nonetheless, novel factors are enhanced to calculate the values of each timer in the three phases. Simulation results demonstrate effective and reliable dissemination in terms of delivery ratio and number of false warning compared to existing protocols when evaluated in high scale and realistic scenarios. Also, SAS-GP performs faster in notifying vehicles resulting a higher geocast distance before approaching the location of the event.

Traffic efficiency applications are becoming increasingly popular over the road networks in the last few years. This type of applications aims mainly at increasing the traffic fluency over the road network, which minimizes the travel time of each vehicle towards its targeted destinations. The Vehicular Ad-Hoc Networks (VANETs) technology has been utilized to design these applications. Communications between vehicles, V2V, and between vehicles and installed Road Side Units (RSUs), V2I, helped designing these applications. Malicious, selfish and intruder drivers can take advantages of other cooperative drivers and use their trust. This paper introduces a Secure COngestion contrOL (SCOOL) protocol. This protocol aims to guarantee integrity and authenticity of transmitted data. It is designed to provide the security requirements of traffic efficiency protocols that have been proposed using the technology of VANETs. SCOOL also aims to preserve the privacy of the cooperative vehicles and drivers. From the experimental results we can infer that SCOOL detects the malicious nodes over the road network which enhances the correctness of the traffic efficiency applications.

Wireless Delay-Tolerant Sensor Networks often experience high unpredicted latency, dynamic wireless channel status and a lack of end-to-end connections. During the rare transmission opportunity in which connections can be found, the sensors seek the best strategies for improving transmission throughput and for reducing energy consumption. An effective way of improving transmission efficiency is to adjust the MAC frame size. This paper presents an efficient energy-aware MAC frame size adjustment scheme, which adapts the frame size to wireless channel conditions and possibility of collisions. Improved data throughput and energy consumption are the main matrices for evaluating transmission performance. Our simulation results show that this scheme can improve transmission time and significantly reduce energy consumption using adaptive frame size adjustment.

Vehicular ad hoc networks (VANETs) are no longer a futuristic promise but rather an attainable technology. The majority of services envisioned for VANETs either require the provisioning of multimedia support or have this support as an extremely beneficial feature. However, the highly dynamic topology of VANETs poses a demanding challenge for the fulfillment of the stringent requirements for video streaming. In this paper, we provide a deep understanding of the issue of unicast video streaming over VANETs and propose a novel protocol, VIRTUS. In video streaming, many packets are transmitted consecutively in a short period of time. VIRTUS takes this into consideration and extend the duration of the decision of nodes to forward packets from a single transmission to a time window. Furthermore, VIRTUS calculates the suitability of a node to relay packets based on a balance between geographic advancement and link stability. We also propose an extension, that separates the process of relay node selection from the transmission of video content and adopts a density-aware mechanism that adapts its behavior according to local density. Consequently, VIRTUS makes use of the reactive aspect of receiver-based solutions while remaining scalable to increases in transmission rates and density. We report through extensive realistic experiments the benefits of using VIRTUS towards delivering video at a higher quality, in a timely fashion, with lower overhead and fewer collisions.

Video dissemination over Vehicular Ad Hoc Networks is an attractive technology that supports many novel applications. The merit of this work lies in the design of an efficient video dissemination protocol that provides high video quality at different data rates for urban scenarios. Our objective is to improve received video quality while meeting delay and packet loss. In this work, we first employ a reliable scheme known as connected dominating set, which is an efficient receiver-based routing scheme for broadcasting video content. To avoid repeated computing of the connected dominating set, we add three statuses to each node. In nonscalable video coding, the distribution of lost frames can cause a major impact on video quality at the receiver's end. Therefore, for the second step, we employ Interleaving to spread out the burst losses and to reduce the influence of loss distributions. Although Interleaving can reduce the influence of cluster frame loss, single packet loss is also a concern due to collisions, and to intermittent disconnection in the topology. In order to fix these single packet losses, we propose a store-carry-forward scheme for the nodes in order to retransmit the local buffer stored packets. The results, when compared to the selected base protocols, show that our proposed protocol is an efficient solution for video dissemination over urban Vehicular Ad Hoc Networks.

The high quality video streaming in vehicular networks is an urgent topic to provide services on safety and infotainment on the road. To provide high quality video streaming, Forward Error Correction (FEC) is one of the most popular approaches to ensure the needed quality for video streaming by generating duplicated packets. However, several factors might cause problems to FEC in a VANET, like the limited resources of wireless networks, a highly dynamic topology and the large amount of data in video streaming. The duplicated packets might exceed the network capacity. Therefore, in this work, the retransmission mechanism is used to ensure the transmissions, rather than the FEC. The main problem of the retransmission mechanism is the delay. A multi-path solution based on a disjoint algorithm is proposed to reduce the interference and contention, leading to a higher transmission rate and an acceptable delay. In this solution, only I-frames are transmitted through the TCP protocol, and the inter-frames are transmitted through the UDP protocol. To improve the delay of TCP transmissions, a TCP-ETX algorithm is integrated to select the suitable path for TCP transmissions. Simulations are conducted and several results are presented by comparing them to other protocols. Based on the simulation results, the designed multi-path solution protocol provides a higher video quality with a reasonable delay than that of the other protocols.

Abstract A great interest in vehicular ad‐hoc networks has been noticed by the research community. General goals of vehicular networks are to enhance safety on the road and to ensure the convenience of passengers by continuously providing them, in real time, with information and entertainment options such as routes to destinations, traffic conditions, facilities' information, and multimedia/Internet access. Indeed, time efficient systems that have high connectivity and low bandwidth usage are most needed to cope with realistic traffic mobility conditions. One foundation of such a system is the design of an efficient gateway discovery protocol that guarantees robust connectivity between vehicles, while assuring Internet access. Little work has been performed on how to concurrently integrate load balancing, quality of service (QoS), and fault tolerant mechanisms into these protocols. In this paper, we propose a reliable QoS‐aware and location aided gateway discovery protocol for vehicular networks by the name of fault tolerant location‐based gateway advertisement and discovery. One of the features of this protocol is its ability to tolerate gateway routers and/or road vehicle failure. Moreover, this protocol takes into consideration the aspects of the QoS requirements specified by the gateway requesters; furthermore, the protocol insures load balancing on the gateways as well as on the routes between gateways and gateway clients. We discuss its implementation and report on its performance in contrast with similar protocols through extensive simulation experiments using the ns‐2 simulator. Copyright © 2013 John Wiley & Sons, Ltd.

HLA-based distributed simulations tend to suffer from load imbalances and degradation in performance as a result of running on distributed environment. High-Level Architecture (HLA) is a general purpose framework that eases the implementation of distributed simulations on top of dedicated resources without worrying about the computing infrastructure. Due to the high cost of hardware and other factors, some companies have ditched the concept of dedicated resources and shifted towards shared ones which revealed some HLA weaknesses, out of which, dynamic reaction to load imbalances and managing federates on the shared resources. Therefore, different efforts have proposed numerous dynamic load balancing systems to offer a balancing feature to running distributed simulations. In order to perform the load balancing task, these proposed systems gather and make use of a number of simulation and load metrics. Load prediction is a metric that is computed to provide load projections and prevent any prospective load imbalances by migrating federates from an overloaded shared resource to an underloaded shared resource. This work touches the federate migration decision-making process, which is the last step of the balancing task. The proposed federate migration decision-making methods are to overcome the dependency on predefined thresholds in previous work and offer dynamic decisions to migrate federates.

Evaluation and validation of algorithms and protocols in vehicular area networks is challenging and requires the support of simulators in most cases due to the restrictions on cost and scalability. Consequently, there is a need to identify or build a simulator that best fits into the characteristics of VANets. Such simulators need to reproduce the communication of networks together with the mobility of vehicles in a given simulated area. Many simulators and simulation frameworks have been developed, most of them combining pre-existing mobility and networking simulators in one solution. However, these simulators present limited features on 3D visualization. In this paper, we propose a real-time, realistic 3D visualization for VANet simulations, which makes use of 3D-modeled real-world maps; the proposed system effectively generates the intended visualization. Experiments have been conducted to evaluate the performance on the synchronization between simulation and visualization components through an analysis of overhead and delays.

The RSU deployment algorithms to cover interest regions have emerged as promising areas of research in vehicular ad hoc networks. However, there is few research on the discovery of the interest regions. Besides, the deployment algorithms are usually proposed for either continuous coverage or sparse coverage. The wisdom of the model selection are rarely addressed. In this paper, we proposed a new algorithm to discover interest regions. A budget-constrained coverage selection algorithm is also presented to help network designers choose suitable coverage models to meet the budget and quality requirements. The algorithms are implemented on top of Ns2 and the simulations are carried out using SUMO and OpenStreet Maps. The performance comparison between our algorithm and other two clustering algorithms prove that our algorithm has a better performance in terms of contact time for both sparse coverage and continue coverage.

Pedestrian Protection System (PPS) has become an active research area aimed to protect pedestrians by assisting inattentive drivers. Despite the enormous number of research works, most current systems are designed to recognize near-scale pedestrians. However, they perform poorly in mid-scale and fail in far-scale. In this paper, a new hardware-based architecture that detects pedestrians in near-, mid- and far-scales is introduced. Two regions are defined in this architecture: the near-to-mid area located in front of vehicles, called Region of High Risk (RHR); and the mid-to-far area, called Region of Low Risk (RLR). To implement this system, we use two identical cameras, each of which is equipped with a variable focal length lens. Moreover, we develop a mathematical model for our framework. Finally, we conduct a set of experiments in open park areas and in Ottawa roads. The results show that the system is able to accurately detect pedestrians that are located up to 130 meters away from the vehicle.

In this paper, we investigate the bottleneck traffic problems that are caused and/or amplified by path recommendation protocols in use. Distributed path recommendation protocols construct the path towards each destination in a hop-by-hop fashion. In some scenarios most of traveling vehicles, arriving the road intersection from several input road segments, are recommended to leave at the same output road segment. This is due to the fact that traveling vehicles are heading towards the same destination or close located destinations. Then, the paper introduces a traffic balancing mechanism (Bal-Traf) that eliminates the traffic congestion over road networks. At each road intersection, Bal-Traf distributes the input traffic among the output road segments towards the targeted destinations. From the experimental results we can see Bal-Traf completely eliminates the bottleneck problem over the road network.

In delay-tolerant sensor networks where connectivity is not guaranteed, sensors are seeking efficient ways to send the collected data during relatively rare transmission opportunities. Aggregation is one of the major ways to improve the data throughput while consuming less energy consumption. This paper proposes an adaptive aggregation scheme for MAC 802.11 to improve the transmission efficiency in unstable wireless delay-tolerant environments. The aggregation scheme not only considers the upper layer separation of quality of service (QoS) requirements into different queues, but also adapts the wireless channel status to the aggregation procedure. The simulation results show that the scheme improves the transmission efficiency and reduces the number of transmission times by aggregating data; thus saving sensor energy consumption.

Time-sensitive mobile service with vehicular networks depend on continuous coverage on the road system. It is a challenge to meet a tight budget while maintaining coverage quality. In order to resolve the problem, we model the road system as an undirected graph and reduce it to a Knapsack Constrained Steiner Tree model. Since the reduced model is an NP-hard problem, we resolve it by using Lagrangian decomposition approach. The terminal nodes in the graph are hotspots, where most vehicles accumulate; and, the paths connecting these hotspots are measured by a new metric: coverage value. We evaluated the our scheme by comparing it with the Maximum Continuous Coverage protocol in terms of the packet drop rate in the NS2 simulation. The final result shows that our coverage is reliable, and suitable for urban vehicular networks.

Efficient protocols for data packet delivery in mobile underwater sensor networks (UWSNs) are crucial to the effective use of this new powerful technology for monitoring lakes, rivers, seas, and oceans. However, communication in UWSNs is a challenging task because of the characteristics of the acoustic channel. In this work, we present a feasible solution for improving the data packet delivery ratio in mobile UWSN. The GEographic and opportunistic routing with Depth Adjustment-based topology control for communication Recovery (GEDAR) over void regions uses the greedy opportunistic forwarding to route packets and to move void nodes to new depths to adjust the topology. Simulation results shown that GEDAR outperforms the baseline solutions in terms of packet delivery ratio, latency and energy per message.

Animal-Vehicle Collisions (AVCs) have been a challenging problem since the creation of cars. Consequently, such collisions cause hundreds of human and animal deaths, thousands of injuries, and billions of dollars in property damage every year. To cope with this challenge, vehicles have to be equipped with smart systems able to detect animals (e.g., moose), which cross roadways, and warn drivers about the imminent danger. In this paper, we develop a new animal detection system following two criteria: detection accuracy and detection speed. To achieve these requirements, a two-stage strategy system is investigated. In the first stage, we use the LBP-Adaboost algorithm which supplies the second stage by a set of ROIs containing moose and other similar-objects. Whereas the second stage is based on an adapted version of HOG-SVM classifier. In this stage, the non-moose ROIs are rejected. To train and test our system, we create our own dataset, which is frequently updated by adding new images. Through an extensive set of simulations, we show that our system is able to detect more than 83% of moose.

Due to stringent requirements of video streaming and the highly dynamic topology of vehicular networks, the designing of an efficient protocol for disseminating high quality video over VANETs has become extremely challenging. A robust and efficient protocol should guarantee the quality of transmitted videos over a network in terms of Quality of Service (QoS) and Quality of user Experience (QoE). Most existing protocols for video streaming over VANETs focus on one aspect of QoS while overlooking others. Besides this, some of these protocols do not consider QoE; hence in some cases, even a very small percentage of packet loss in video networks could lead to provide unusable service. Thus, the goal of this work is to develop an efficient protocol that integrates various promising techniques in an optimal manner in order to support high quality video streaming by way of considering vehicular network peculiarities. This paper proposes a Hybrid Video Dissemination Protocol (HIVE) that deploys a receiver-based relay node selection technique in addition to a MAC congestion control mechanism; this is carried out to avoid high packet collision and latency in respect to vehicle traffic conditions. A combination of these two techniques in an integrated manner provides reasonably high packet delivery ratios. In addition to this, the applying of the Erasure Coding technique on the application layer enhances HIVE performance further by almost no packet loss. This protocol also outperforms the other existing video streaming protocols for VANETs in terms of reconstructed video quality while it complies with scalability and delay requirements for video streaming.

A reliable solution for the task of unicast video streaming over urban VANETs is of great demand. Single path solutions which address this topic are highly prone to collision at a high data rates which are necessary for high quality videos. Multipath solution solves this problem by distributing the heavy traffic load into a set of paths. Among numbers of multipath works, only 2-path LIAITHON+takes into consideration the high dynamic topology of VANETs, route coupling effect, and path length growth. In this paper, we make several improvements on top of the 2-path LIAITHON+. We evaluate the use of more than two paths in this multipath solution. Moreover, the impact of added redundancy on the both 2-path and 3-path LIAITHON+is investigated as a solution for packet loss.

In a wireless delay-tolerant sensor network, the sensors must carry the data and wait for the delivery opportunity to forward the data. The probability of delivery largely depends on the current wireless channel connections. The sensors can optimally use the delivery opportunities to transmit the data while considering the data and nodes attributes. In this paper, we propose a transmission strategy in MAC 802.11 to efficiently transmit different types of data with energy saving considerations in one contact interval. The transmission power consumption and data throughput are the main measurements in our strategy to evaluate the transmission performance. We also consider the node buffer and data types as elements that impact the transmission throughput and power consumption. The simulation results show that the strategy efficiently transmits different data in an energy-saving and data-throughput-balanced way in one contact interval.

Opportunistic Routing (OR) is a new class of routing protocols that selects the next-hop forwarder on-the-fly. It takes advantage of the broadcast nature of the wireless medium. By selecting a set of candidates for the purpose of forwarding the packet toward the destination, OR improves the reliability of wireless transmissions. In this paper, we propose a new heuristic and a quick candidate selection algorithm based on the link delivery probability from one node to a candidate node. We shall refer to it as Heuristic Candidate selection algorithm based on Optimum delivery Probability (HU-COP). HU-COP finds candidates through links that offer delivery probabilities that are close to optimum. We compare HU-COP with the two other well-known candidate selection algorithms proposed in the literature. The numerical results in terms of the expected number of transmissions show that HU-COP outperforms the well-known ExOR. In addition, the performance of HU-COP is very close to the results of the most efficient algorithm in various scenarios. Furthermore, HU-COP identifies the sets of candidates much faster than the other algorithms under study.

Opportunistic Routing (OR) [1] is a new promising paradigm, which has been proposed as a way to increase the performance of wireless networks by exploiting its broadcast nature. It benefits from the broadcast characteristic of wireless mediums to improve the network performance. In OR, instead of pre-selecting a single specific node to be the next-hop as a forwarder for a packet, multiple nodes, usually called a Candidate Set, can potentially be selected as the next-hop forwarder. Hence, each node in OR can use different potential paths to send packets toward the destination. This is different from the traditional unipath routing which selects one next-hop forwarder before starting the transmission [2], [3]. By using OR, for each packet a dynamic route toward the destination is built, this is done according to the condition of the wireless links at the moment when the packet is being transmitted. In OR when a candidate receives a packet, it coordinate with the other candidates to decide which of them must forward the packet and which one must discard it. This tutorial gives a comprehensive review of the important issues and different aspects of the state of the art of OR. It will enable the attendees to understand the OR concept and to make contributions on their own.

Local maximum problem, where the node fails in determine the next-hop neighbor to continue forwarding the packet towards the destination, severely degrades the performance of geographic routing protocols. This degradation is more substantial in underwater sensor networks, that intrinsically have harsh environments and high energy consumption due to the underwater acoustic communication characteristics. In this work, we focus on the performance of the most commonly three methodologies used in design of local maximum recovery procedures of geographic routing protocols for underwater sensor networks: power control, bypassing void regions, and mobility controlled. Taking into consideration the underwater acoustic communication characteristics, we further develop a network energy consumption model for representative solutions of local maximum recovery procedure designed from these methodologies and then we evaluate their performance in terms of the improvements on routing task and the energy consumption. Simulation results show that all three methodologies improve the routing even in hard scenarios of lower network density whereas particularities of each methodology impacts on the network energy consumption.

Opportunistic Routing (OR) takes advantage of the broadcast nature of the wireless medium to increase reliability in communications. Instead of selecting one node as the next-hop forwarder, OR selects a set of candidates to forward the packet. In this way, if one of them does not receive the packet from the source, another candidate will be able to do it, this avoids the need forare-transmission from the source. To increase the successful delivery ratio, we can increase the size of the candidate set or the number of re-transmissions, but, we must take into account the impact on the use of the network resources. In this paper, we propose a Markov chain as a general model for OR that can be applied to any kind of network topology and any candidate selection algorithm without any constraint. The only input parameters needed are: i) the candidate list of each node, ii) the link delivery probability between nodes, and, iii) the maximum number of re-transmissions in each node. Taking this dataintoaccount, our model all owsforth eevaluation of the performance of different candidate selection algorithms according to different metrics, such as the expected number of transmissions (ExNT), which is one of the most relevant metrics in OR. Our model also enables an evaluation of the influence of the number of candidates, its relation to the number of re-transmissions and how these two parameters together contribute to the successful delivery of data packets.

Energy efficient and reliable communication are two very important and conflicting requirements in the design of large-scale, self-organizing wireless sensor networks (WSNs). By reducing the transmission power level of the nodes, energy conservation is achieved whereas the communication reliability is degraded. We propose a novel opportunistic routing protocol to reduce the energy consumption while keep the communication reliability in acceptable levels. Transmission power Control-based Opportunistic Routing (TCOR) saves energy by reducing the transmission power of the nodes while maintains the communication reliability by employing the opportunistic forwarding paradigm, leveraging the broadcast nature of wireless transmission medium. We propose an expected energy cost function for next-hop forwarder set selection, which considers the multiple available transmission power levels and the impact of each one on the next-hop packet reception probability.

We present a novel lane detection and tracking system using a fusion of Maximally Stable Extremal Regions (MSER) and Progressive Probabilistic Hough Transform (PPHT). First, MSER is applied to obtain a set of blobs including noisy pixels (e.g., trees, cars and traffic signs) and the candidate lane markings. A scanning refinement algorithm is then introduced to enhance the results of MSER and filter out noisy data. After that, to achieve the requirements of real-time systems, the PPHT is applied. Compared to Hough transform which returns the parameters ρ and Θ, PPHT returns two end-points of the detected line markings. To track lane markings, two kalman trackers are used to track both end-points. Several experiments are conducted in Ottawa roads to test the performance of our framework. The detection rate of the proposed system averages 92.7% and exceeds 84.9% in poor conditions.

Text recognition in the automotive context is a crucial task for Intelligent Transportation Systems. Its objective is to supply the driver with important information found on traffic signs. This information could be speed limits, traffic orders (Stop, for example) or texts that describe the nature of the road ahead. In this paper, a four-stage text recognition strategy is investigated. The first stage uses Histogram of Oriented gradients (HOG) features in combination with a trained suppervector machine (SVM) to detect traffic signs, specifically text-based signs such as speed-limit signs or informative-signs describing traffic situations. The detection stage is followed by a filtering stage. This stage aims to 'clean' the detected traffic sign using some filters. The filters tested in this paper are the Grayscale filter, Bilateral filter, Median filtered, and the Gaussian filler. The filtered image is then fed into the third stage, the recognition stage. An open-source Optical Character Recognition tool (OCR) "Tesseract" is used to read the texts found on the detected traffic signs. The strategy concludes with a fourth stage, i.e., post- processing, in order to add a layer of immunity to false positive and false readings. Finally, we compare our work to the standard HOG-SVM scheme. The results show that our scheme exhibits a higher accuracy over the HOG-SVM scheme.

The broadcast nature of the wireless medium applied in Opportunistic Routing (OR) to improve the performance of wireless networks. OR protocols select a set of candidates as the next-hop forwarder. Each candidate can act as a potential forwarder if it receives the packet. Candidate selection is one of the main issues for OR protocols. In this paper, we implement and compare different ranges of OR protocols (simple, complex and optimum ones) in terms of different performance parameters using NS-2. The obtained results through extensive simulations show that OR improves the performance of network in different terms. Furthermore, our results provide insights to the use of each opportunistic routing protocols in different scenarios.

Video dissemination over vehicular networks is an attractive technology which supports many novel applications. However, it is a great challenge to analyse the performance of video dissemination protocols due to highly dynamic topology and stringent requirements of applications. In this paper, we evaluate five existing robust video dissemination protocols in urban scenarios. We evaluate three routing protocols and two error resilience protocols. We also modify the frame coding technique for better performance. The results, more specifically, show that only one of the three routing protocols fulfils the general quality requirements. As for the error resilient techniques, we find that our modified frame coding approach performs better than the original one in four aspects. The results also indicate that the video coding scheme guarantees reliable video qualities.