Estimating the equilibrium parameters of environmental systems is a fundamental task, yet it is often hampered by sparse and noisy sensor data. While the standard Maximum Likelihood Estimator (MLE) is intuitive, Stein's paradox famously shows that it is statistically inefficient in high dimensions. To address this, we introduce STEADY, an estimator that generalises Stein's paradox by integrating physical knowledge. We derive our estimator from a principled empirical Bayes model where the prior distribution over the equilibria is a direct consequence of the stationary properties of the system's governing differential equations. This leads to a novel adaptive shrinkage mechanism, where the amount of shrinkage applied to each observation is naturally modulated by the physical stability of the measured system. We provide a rigorous frequentist analysis of our estimator, proving that STEADY not only dominates the MLE but is also minimax under certain conditions, offering the strongest possible guarantee of robustness. We validate our claims on synthetic data and demonstrate STEADY's utility on the global Argo ocean float dataset, showing that it effectively filters noise to reveal the ''North Atlantic Warming Hole''. The source code is available at https://github.com/shanfenghu/steady

High-definition (HD) maps generated from autonomous vehicle (AV) sensor data are essential for enabling high levels of driving automation. However, offloading large volumes of raw sensory data to edge servers in dense vehicular ad hoc networks (VANETs) introduces significant latency due to network congestion and packet collisions. Existing solutions primarily focus on dynamically adjusting the minimum contention window (CWmin), while additional MAC-layer parameters — including the maximum contention window (CWmax) and interframe space number (IFSn) — remain largely underexplored. To address this, we propose a cross-layer multi-agent reinforcement learning (MARL) framework that jointly optimises CWmin–CWmax, IFSn, and transmission waiting time within IEEE 802.11p-compliant bounds. The proposed multi-task mixed-dependence (MTMD) framework decomposes the optimisation problem into specialised subtasks handled by selectively coupled agents, balancing coordination and scalability while avoiding the overhead of fully symmetric MARL or centralised hierarchical controllers. A lightweight orchestration layer coordinates agent interaction with the simulation environment via secure message exchange. Evaluated against standard EDCA and representative RL baselines, MTMD achieves latency reductions of 31%, 49%, 87.3%, and 64% for Voice, Video, HD Map, and Best-Effort traffic, respectively, confirming the effectiveness of structured multi-parameter optimisation for latency-critical vehicular applications.

Efficient service function chain (SFC) placement is critical for optimizing network service delivery in dynamic cross-domain networks (CDNs), especially under resource-constrained and heterogeneous environments. However, existing approaches face fundamental limitations in achieving effective multi-objective optimization, particularly in balancing latency minimization with efficient resource utilization. These challenges are further compounded by the inability to capture future resource dynamics and limited visibility across multiple domains. To address these challenges, we propose a novel multi-objective framework for SFC placement that jointly considers latency and resource utilization. The framework integrates Transformer-based prediction with linear programming (LP) to explicitly model future deployability, enabling proactive and globally informed placement decisions. In addition, a dynamic modeling mechanism is developed using domain-aware detection and graph autoencoders (GAEs) to capture evolving network topologies and cross-domain structural dependencies. A Pareto-based optimization strategy is further employed to systematically balance latency and resource efficiency across heterogeneous domains and varying workload conditions. Extensive experiments across multiple network scales and diverse SFC configurations demonstrate that the proposed framework achieves a superior trade-off between latency and deployment capability, while improving scalability, robustness, and long-term resource efficiency in dynamic and large-scale CDN environments.

Current mobile payment schemes gather detailed information about purchases customers make. This data can then be used to infer a customer’s spending behaviour, potentially violating their privacy. To tackle this problem, we propose an untraceable mobile payment scheme that strikes a better balance, preserving user privacy while allowing the Third-Party Service Provider (TPSP) to collect necessary information such as card details and transaction amount for regulatory compliance. Our scheme offers untraceability for legitimate users from malicious adversaries and curious TPSPs using cryptographic primitives such as partially blind signatures, zero-knowledge proofs, and identity-based signatures. It also guarantees that only authorised TPSPs can issue valid payment tokens, and even with limited data, the TPSP can still prevent dishonest customers/merchants from double-spending a payment token. We also propose a comprehensive evaluation framework to assess the untraceable payment schemes against seven key criteria such as untraceability, exculpability—merchant double-spending, exculpability—customer double-spending, unforgeability, confidentiality, message authenticity, efficiency, and regulatory compliance. We rigorously benchmark the security and privacy of our proposed payment scheme against this framework and other established schemes. Furthermore, we formally verify these properties using complexity-based analysis and Proverif modelling.

The adoption of High-Definition (HD) mapping applications represents a critical step towards achieving Level-5 autonomous driving, revolutionizing road safety and paving the way for unprecedented advancements in transportation technology. However, HD mapping imposes significant computational demands in processing the raw data generated by autonomous vehicle sensors. To mitigate this issue, researchers have opted to offload the data reducing the processing time. Unfortunately, the current de-facto standard IEEE802.11p in Vehicular Ad-hoc Network (VANET) does not provide the best latency or throughput for applications with low latency and heavy data transfer requirements. This is because of the fixed Contention Window (CW). To address this problem, solutions have been developed to dynamically allocate the CW nowadays with the help of Machine Learning (ML) paradigms. Nonetheless, these solutions do not include a strategy to dynamically allocate an optimal CW per service type. Instead, they focus on sharing the wireless channel fairly. In this paper, we have developed a cross-layer Reinforcement Learning (RL) algorithm between the application and Medium Access Control (MAC) layer that allocates CW per service type. Results showed improvement with a different gap in the latency Cumulative Distribution Function (CDF) of 181%, 120%, 107%, and 119% for Voice, Video, HD Map, and Best-effort respectively compared to other different approaches.

One effective way to optimize the offloading process is by minimizing the transmission time. This is particularly true in a Vehicular Adhoc Network (VANET) where vehicles frequently download and upload High-definition (HD) map data which requires constant updates. This implies that latency and throughput requirements must be guaranteed by the wireless system. To achieve this, adjustable contention windows (CW) allocation strategies in the standard IEEE802.11p have been explored by numerous researchers. Nevertheless, their implementations demand alterations to the existing standard which is not always desirable. To address this issue, we proposed a Q- Learning algorithm that operates at the application layer. Moreover, it could be deployed in any wireless network thereby mitigating the compatibility issues. The solution has demonstrated a better network performance with relatively fewer optimization requirements as compared to the Deep Q Network (DQN) and Actor-Critic algorithms. The same is observed while evaluating the model in a multi-agent setup showing higher performance compared to the single-agent setup.

Botnet detectors based on machine learning are potential targets for adversarial evasion attacks. Several research works employ adversarial training with samples generated from generative adversarial nets (GANs) to make the botnet detectors adept at recognising adversarial evasions. However, the synthetic evasions may not follow the original semantics of the input samples. This paper proposes a novel GAN model leveraged with deep reinforcement learning (DRL) to explore semantic aware samples and simultaneously harden its detection. A DRL agent is used to attack the discriminator of the GAN that acts as a botnet detector. The agent trains the discriminator on the crafted perturbations during the GAN training, which helps the GAN generator converge earlier than the case without DRL. We name this model RELEVAGAN, i.e. [“relieve a GAN” or deep REinforcement Learning-based Evasion Generative Adversarial Network] because, with the help of DRL, it minimises the GAN’s job by letting its generator explore the evasion samples within the semantic limits. During the GAN training, the attacks are conducted to adjust the discriminator weights for learning crafted perturbations by the agent. RELEVAGAN does not require adversarial training for the ML classifiers since it can act as an adversarial semantic-aware botnet detection model. The code will be available at https://github.com/rhr407/RELEVAGAN.

High-definition (HD) map is a key enabler to achieving fully autonomous driving. Unlike traditional multimedia data, HD map consists of hybrid data types including 3D point clouds, images, GPS, etc. However, transporting HD map data to and from autonomous vehicles is challenging. IEEE 802.11p Vehicular ad-hoc networks (VANETs) are the de facto standard to establish short-range communications for vehicle-to-everything (V2X). One of the key limitations of 802.11p is ensuring quality of service for HD map traffic, since it might be categorised as best-effort (low priority) between all four access categories (AC) best-effort, background, voice, and video. We proposed a new AC for HD map traffic in this paper to address the aforementioned limitation. We also demonstrate the benefits of using the new AC, as well as the importance of selecting the appropriate channel control parameters within the AC, such as contention window (CW) and Arbitrary Inter-Frame Space (AIFS). Various values of CW and AIFS were examined under dynamic vehicular density and mobility to investigate end-to-end latency and throughput. Experimental results reveal that both, the average delay and throughput of HD map traffic improved by 80%, with the new AC. Furthermore, the delay manifested a steady behavior of 2.3 seconds for thirty, forty, and fifty vehicles. For the selection of AFS and CW parameters, a correlation is observed between vehicular mobility and density.

With advanced 5G/6G networks, data-driven interconnected devices will increase exponentially. As a result, the Industrial Internet of Things (IIoT) requires data secure information extraction to apply digital services, medical diagnoses, and financial forecasting. This introduction of high-speed network mobile applications will also adapt. As a consequence, the scale and complexity of Android malware are rising. Detection of malware classification is vulnerable to attacks. A fabricated feature can force misclassification to produce the desired output. This article proposes a subset feature selection method to evade fabricated attacks in the IIoT environment. The method extracts application-aware features from a single android application to train an independent classification model. Ensemble-based learning is then used to train the distinct classification models. Finally, the collaborative ML classifier makes independent decisions to fight against adversarial evasion attacks. We compare and evaluate the benchmark Android malware dataset. The proposed method achieved 91% accuracy with 14 fabricated input features.

Recommendation systems rely heavily on behavioural and preferential data (e.g., ratings and likes) of a user to produce accurate recommendations. However, such unethical data aggregation and analytical practices of Service Providers (SP) causes privacy concerns among users. Local differential privacy (LDP) based perturbation mechanisms address this concern by adding noise to users’ data at the user-side before sending it to the SP. The SP then uses the perturbed data to perform recommendations. Although LDP protects the privacy of users from SP, it causes a substantial decline in recommendation accuracy. We propose an LDP-based Matrix Factorization (MF) with a Gaussian Mixture Model (MoG) to address this problem. The LDP perturbation mechanism, i.e., Bounded Laplace (BLP), regulates the effect of noise by confining the perturbed ratings to a predetermined domain. We derive a sufficient condition of the scale parameter for BLP to satisfy$\varepsilon$-LDP. We use the MoG model at the SP to estimate the noise added locally to the ratings and the MF algorithm to predict missing ratings. Our LDP based recommendation system improves the predictive accuracy without violating LDP principles. We demonstrate that our method offers a substantial increase in recommendation accuracy under a strong privacy guarantee through empirical evaluations on three real-world datasets, i.e., Movielens, Libimseti and Jester.

In this paper, the intelligent reflecting surface (IRS)-aided unmanned aerial vehicle (UAV) communication system is studied, where the UAV is deployed to serve the user equipment (UE) with the assistance of multiple IRSs mounted on several buildings to enhance the communication quality between UAV and UE. We aim to maximize the energy efficiency of the system, including the data rate of UE and the energy consumption of UAV via jointly optimizing the UAV's trajectory and the phase shifts of reflecting elements of IRS, when the UE moves and the selection of IRSs is considered for the energy saving purpose. Since the system is complex and the environment is dynamic, it is challenging to derive low-complexity algorithms by using conventional optimization methods. To address this issue, we first propose a deep Q-network (DQN)-based algorithm by discretizing the trajectory, which has the advantage of training time. Furthermore, we propose a deep deterministic policy gradient (DDPG)-based algorithm to tackle the case with continuous trajectory for achieving better performance. The experimental results show that the proposed algorithms achieve considerable performance compared to other traditional solutions.

Many works have proposed integrating sentiment analysis with collaborative filtering algorithms to improve the accuracy of recommendation systems. As a result, service providers collect both reviews and ratings, which is increasingly causing privacy concerns among users. Several works have used the Local Differential Privacy (LDP) based input perturbation mechanism to address privacy concerns related to the aggregation of ratings. However, researchers have failed to address whether perturbing just ratings can protect the privacy of users when both reviews and ratings are collected. We answer this question in this paper by applying an LDP based perturbation mechanism in a recommendation system that integrates collaborative filtering with a sentiment analysis model. On the user-side, we use the Bounded Laplace mechanism (BLP) as the input rating perturbation method and Bidirectional Encoder Representations from Transformers (BERT) to tokenize the reviews. At the service provider’s side, we use Matrix Factorization (MF) with Mixture of Gaussian (MoG) as our collaborative filtering algorithm and Convolutional Neural Network (CNN) as the sentiment classification model. We demonstrate that our proposed recommendation system model produces adequate recommendation accuracy under strong privacy protection using Amazon’s review and rating datasets.

Due to recent developments in electric mobility, public charging infrastructure will be essential for modern transportation systems. As the number of electric vehicles (EVs) increases, the public charging infrastructure needs to adopt efficient charging practices. A key challenge is the assignment of EVs to charging stations (CSs) in an energy efficient manner. In this paper, a Reinforcement Learning (RL)-based EV Assignment Scheme (RL-EVAS) is proposed to solve the problem of assigning EV to the optimal CS in urban environments, aiming at minimizing the total cost of charging EVs and reducing the overload on Electrical Grids (EGs). Travelling cost that is resulted from the movement of EV to CS, and the charging cost at CS are considered. Moreover, the EV’s Battery State of Charge (SoC) is taken into account in the proposed scheme. The proposed RL-EVAS approach will approximate the solution by finding an optimal policy function in the sense of maximizing the expected value of the total reward over all successive steps using Q-learning algorithm, based on the Temporal Difference (TD) learning and Bellman expectation equation. Finally, the numerous simulation results illustrate that the proposed scheme can significantly reduce the total energy cost of EVs compared to various case studies and greedy algorithm, and also demonstrate its behavioural adaptation to any environmental conditions.

Long-range wide-area network (LoRaWAN) is one of the most promising IoT technologies that are widely adopted in low-power wide-area networks (LPWANs). LoRaWAN faces scalability issues due to a large number of nodes connected to the same gateway and sharing the same channel. Therefore, LoRa networks seek to achieve two main objectives: 1) successful delivery rate and 2) efficient energy consumption. This article proposes a novel game-theoretic framework for LoRaWAN named best equal LoRa (BE-LoRa), to jointly optimize the packet delivery ratio and the energy efficiency (bit/Joule). The utility function of the LoRa node is defined as the ratio of the throughput to the transmit power. LoRa nodes act as rational users (players) which seek to maximize their utility. The aim of the BE-LoRa algorithm is to maximize the utility of LoRa nodes while maintaining the same signal-to-interference-and-noise-ratio (SINR) for each spreading factor (SF). The power allocation algorithm is implemented at the network server, which leads to an optimum SINR, SFs, and transmission power settings of all nodes. Numerical and simulation results show that the proposed BE-LoRa power allocation algorithm has a significant improvement in the packet delivery ratio and energy efficiency as compared to the adaptive data rate (ADR) algorithm of legacy LoRaWAN. For instance, in very dense networks (624 nodes), BE-LoRa can improve the delivery ratio by 17.44% and reduce power consumed by 46% compared to LoRaWAN ADR.

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE). We aim to minimize energy consumption of all UEs via optimizing user association, resource allocation and the trajectory of UAVs. To this end, we first propose a Convex optimizAtion based Trajectory control algorithm (CAT), which solves the problem in an iterative way by using block coordinate descent (BCD) method. Then, to make the real-time decision while taking into account the dynamics of the environment (i.e., UAV may take off from different locations), we propose a deep Reinforcement leArning based trajectory control algorithm (RAT). In RAT, we apply the Prioritized Experience Replay (PER) to improve the convergence of the training procedure. Different from the convex optimization based algorithm which may be susceptible to the initial points and requires iterations, RAT can be adapted to any taking off points of the UAVs and can obtain the solution more rapidly than CAT once training process has been completed. Simulation results show that the proposed CAT and RAT achieve the considerable performance and both outperform traditional algorithms.

Despite all the acknowledged advantages and recent developments in terms of reducing the environmental impact, noise reduction and energy efficiency, the electric mobility market is still below the expectations. Among the most important challenges that limit the market penetration of Electric Vehicles (EVs) as well as achieving a sustainable mobility system in cities is the efficient distribution of adequate EV charging stations (CSs). In this paper, we propose a novel approach to find the best locations for EVCSs that considers a combination of factors including displacement between the EV and CS, elevation difference between their locations and finite capacities of CSs. The problem is formulated as a Mixed Integer Linear problem (MILP) to minimize the total energy consumption of EVs to reach CSs. A combination of the Genetic Algorithm (GA) technique and the Branch and Bound (B&B) algorithm are used to solve the problem. The proposed EVCSs placement technique is experimentally tested considering different case studies. With real world datasets, the results demonstrate the energy centric benefits of the proposed EVCSs placement technique.

In recent years the number and sophistication of Android malware have increased dramatically. A prototype framework which uses static analysis methods for classification is proposed which employs two feature sets to classify Android malware, permissions declared in the Androidmanifest.xml and Android classes used from the Classes.dex file. The extracted features were then used to train a variety of machine learning algorithms including Random Forest, SGD, SVM and Neural networks. Each machine learning algorithm was subsequently optimised using optimisation algorithms, including the use of bio-inspired optimisation algorithms such as Particle Swarm Optimisation, Artificial Bee Colony optimisation (ABC), Firefly optimisation and Genetic algorithm. The prototype framework was tested and evaluated using three datasets. It achieved a good accuracy of 95.7 percent by using SVM and ABC optimisation for the CICAndMal2019 dataset, 94.9 percent accuracy (with fl-score of 96.7 percent) using Neural network for the KuafuDet dataset and 99.6 percent accuracy using an SGD classifier for the Andro-Dump dataset. The accuracy could be further improved through better feature selection.

This study proposes a chaos‐based security model applied to the physical (PHY) layer of visible light communication (VLC) systems in accordance with the IEEE 802.15.7 standard. The proposed model employs a chaotic signal generated by a Colpitts oscillator to encrypt the header of IEEE 802.15.7 VLC frames in the PHY layer to prevent eavesdropping, traffic analysis and error function attacks. The encryption method employed here is chaotic inclusion or embedding, which is known as one of the most secure chaos‐based approaches. Thus, the essential information pertaining to the employed chaotic oscillator, i.e. its structure, parameter set, the utilised modulation and synchronisation methods is not visible or traceable to the eavesdropper. Moreover, the unencrypted payload is extended by an additional number of random padding bits which can only be determined by decrypting the header of the VLC frame hence the payload is unrecognisable to eavesdroppers though it has not been encrypted. At the legitimate receiver side, the received IEEE 802.15.7 frames are successfully recovered by removing the chaotic wave using chaotic synchronisation techniques. The simulation results show that the encrypted header and the unencrypted payload of the IEEE 802.15.7 frames are well protected and successfully recovered by legitimate receivers.

The use of bot malware and botnets as a tool to facilitate other malicious cyber activities (e.g. distributed denial of service attacks , dissemination of malware and spam , and click fraud). However, detection of botnets , particularly peer-to-peer (P2P) botnets, is challenging. Hence, in this paper we propose a sophisticated traffic reduction mechanism, integrated with a reinforcement learning technique . We then evaluate the proposed approach using real-world network traffic, and achieve a detection rate of 98.3%. The approach also achieves a relatively low false positive rate (i.e. 0.012%).

In this paper, we propose a deep metric for unifying the representation of mesh saliency detection and non-rigid shape matching. While saliency detection and shape matching are two closely related and fundamental tasks in shape analysis, previous methods approach them separately and independently, failing to exploit their mutually beneficial underlying relationship. In view of the existing gap between saliency and matching, we propose to solve them together using a unified metric representation of surface meshes. We show that saliency and matching can be rigorously derived from our representation as the principal eigenvector and the smoothed Laplacian eigenvectors respectively. Learning the representation jointly allows matching to improve the deformation-invariance of saliency while allowing saliency to improve the feature localization of matching. To parameterize the representation from a mesh, we also propose a deep recurrent neural network (RNN) for effectively integrating multi-scale shape features and a soft-thresholding operator for adaptively enhancing the sparsity of saliency. Results show that by jointly learning from a pair of saliency and matching datasets, matching improves the accuracy of detected salient regions on meshes, which is especially obvious for small-scale saliency datasets, such as those having one to two meshes. At the same time, saliency improves the accuracy of shape matchings among meshes with reduced matching errors on surfaces.

In this paper, multi-unmanned aerial vehicle (UAV) enabled mobile edge computing (MEC), i.e., UAVE is studied, where several UAVs are deployed as flying MEC platform to provide computing resource to ground user equipments (UEs). Compared to the traditional fixed location MEC, UAV enabled MEC (i.e., UAVE) is particular useful in case of temporary events, emergency situations and on-demand services, due to its high flexibility, low cost and easy deployment features. However, operation of UAVE faces several challenges, two of which are how to achieve both 1) the association between multiple UEs and UAVs and 2) the resource allocation from UAVs to UEs, while minimizing the energy consumption for all the UEs. To address this, we formulate the above problem into a mixed integer nonlinear programming (MINLP), which is difficult to be solved in general, especially in the large-scale scenario. We then propose a Reinforcement Learning (RL)-based user Association and resource Allocation (RLAA) algorithm to tackle this problem efficiently and effectively. Numerical results show that the proposed RLAA can achieve the optimal performance with comparison to the exhaustive search in small scale, and have considerable performance gain over other typical algorithms in large-scale cases.

Active Constellation Extension (ACE) is widely used to reduce Peak-to-Average Power Ratio (PAPR) in Offset Quadrature Amplitude Modulation based Orthogonal Frequency Division Multiplexing (OFDM/OQAM). To improve overall performance and energy efficiency in OFDM/OQAM systems, this paper proposes Adaptive Scaling (AS) for effective ACE (AS-ACE). The proposed scheme exploits the overlapping structure of the OFDM/OQAM signals and jointly considers adjacent data blocks to obtain the clipping noise. The proposed scheme adaptively extends the constellation points to effectively eliminate peaks in OFDM/OQAM signals. This is achieved by using peak samples of clipping noise, used to generate the peak correcting signal. Least square approximation algorithm is used to fit the waveform of peak correcting signal to the waveform of clipping noise without any decrease in the constellation distance. Simulation results show that the AS-ACE reduces PAPR and Bit Error Rate (BER) and improves convergence speed compared to OSGP technique without requiring increased processing or additional information at the receiver end.

Continuous and effective developments in Autonomous Vehicles (AVs) are happening on daily basis. Industries nowadays, are interested in introducing less costly and highly controllable AVs to public. Current so-called AVP solutions are still limited to a very short range (e.g., even only work at the entrance of car parks). This paper proposes a parking scheduling scheme for long-range AVP (LAVP) case, by considering mobility of Autonomous Vehicles (AVs), fuel consumption and journey time. In LAVP, Car Parks (CPs) are used to accommodate increasing numbers of AVs, and placed outside city center, in order to avoid traffic congestions and ensure road safety in public places. Furthermore, with positioning of reference points to guide user-centric long-term driving and drop-off/pick-up passengers, simulation results under the Helsinki city scenario shows the benefits of LAVP. The advantage of LAVP system is also reflected through both analysis and simulation.

Location-oriented services in vehicular cyber-physical system (VCPS) have witnessed significant attention due to their potentiality to address traffic safety and efficiency related issues. The multichannel communication aids these services by tuning their overall performance in vehicular environments. Related literature on multichannel communication focuses on interference as channel quality measure. However, uncertain mobility and density of vehicles significantly affect channel quality apart from interference. The static quantification of channel quality is not suitable due to the dynamic characteristics of the channel quality parameters. In this context, this paper proposes fuzzy-based channel selection framework for location-oriented services in multichannel VCPS environments. A system model is presented for deriving channel access delay (CAD) using Markov chain model. The channel quality is estimated using CAD and signal-to-interference ratio (SIR). The fuzzy logic-based channel selection framework is developed considering fuzzification and defuzzification of CAD and SIR. The comparative performance evaluation attests the benefit of the framework as compared to the state-of-the-art techniques in VCPS.

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

Charging management for Electric Vehicles (EVs) on-the-move (moving on the road with certain trip destinations) is becoming important, concerning the increasing popularity of EVs in urban city. However, the limited battery volume of EV certainly influences its driver's experience. This is mainly because the EV needed for intermediate charging during trip, may experience a long service waiting time at Charging Station (CS). In this paper, we focus on CS-selection decision making to manage EVs' charging plans, aiming to minimize drivers' trip duration through intermediate charging at CSs. The anticipated EVs' charging reservations including their arrival time and expected charging time at CSs, are brought for charging management, in addition to taking the local status of CSs into account. Compared to applying traditionally applying cellular network communication to report EVs' charging reservations, we alternatively study the feasibility of applying Vehicle-to-Vehicle (V2V) communication with Delay/Disruption Tolerant Networking (DTN) nature, due primarily to its flexibility and cost-efficiency in Vehicular Ad hoc NETworks (VANETs). Evaluation results under the realistic Helsinki city scenario show that applying the V2V for reservation reporting is promisingly cost-efficient in terms of communication overhead for reservation making, while achieving a comparable performance in terms of charging waiting time and total trip duration.

Human activity recognition through posture identification is increasingly used for medical, surveillance and entertainment applications. This paper proposes a ubiquitous solution to activity recognition through the use of tri-axial accelerometers of smartphones. Use of smartphones for activity recognition poses new challenges such as variation in hardware configuration and usage behavior like where the smartphone is kept. Only a few works address one or more of these challenges. Consequently, in this paper we present an activity recognition framework for identifying both static and dynamic activities addressing above mentioned challenges in order to make the framework ubiquitous. Since accelerometer is widely available in many smartphone configurations, activities are detected based on accelerometer readings only. The framework forms a two-phase classifier to address the variance due to different hardware configuration and usage behavior in terms of where the smartphone is kept (pant pocket, shirt pocket or bag). The framework is implemented and tested on real data set collected from 10 users with 6 different device configurations. It is observed that, with our proposed two phase approach, recognition accuracy increases by 9% on an average than single phase approach in energy efficient manner.

The increasing mobility of Internet users is becoming an emerging issue for low-latency anonymity networks such as Tor. The increase in network churn, generated by a growing mobile client base recycling connections, could impact maintaining the critical balance between anonymity and performance. New combinatorial approaches for measuring both anonymity and performance need to be developed in order to identify critical changes to the network dynamics, and trigger intervention if and when required. We present q-factor, a novel longitudinal approach to measuring anonymity and performance within highly dynamic environments. By modelling q-factor, we show that the impact of mobility, over time, on anonymity is significant. However, by using q-factor, we are able to anticipate and significantly reduce the number of these critical events occurring. In order to make more effective strategic design and/or real-time network decisions in the future, low-latency anonymity networks will be required to adopt an even more proactive approach to network management. The potential impact from increasing mobile usage needs to be considered, as what may initially be perceived as a good solution, may in fact degrade, or in the worst case could destroy the anonymity of users over time.

The number of wireless mobile devices connecting to the Internet, is predicted to surpass static connections by 2014. A desire for privacy will provide additional challenges in the future, for anonymity networks such as Tor, in supporting this increasing mobile user base. In this paper, we assess the potential performance impact to a mobile user accessing Tor while roaming from different Internet connections. An experiment was undertaken to simulate a mobile user at various mobility speeds (e.g. walking) alongside a range of Tor circuit build times. The results show that the impact to the mobile user (and potentially the overall Tor network) was significant when roaming between networks, and as expected, increased with higher mobility speeds and longer circuit build times. We also reviewed previous related research and, as one potential solution, considered whether Bridge Relays could additionally be used to provide a persistent connection to the Tor network, for roaming mobile users. Performance is critical for low latency anonymity networks, such as Tor, and understanding the potential impact of this increasing mobile user base, to both the mobile user and overall Tor network, is becoming critical.

This paper introduces a Bayesian model to predict and classify the mobility of a node in Mobile Ad-hoc Networks (MANETs). The proposed model does not use the additional information from Global Positioning System (GPS) for its prediction as some existing models did. Instead, it relies on the “average encounter rate” and “node degree” calculated at each node. However, the outcome is still recorded at high accuracy, i.e. prediction error is fewer than 10% at high speed level (above 15m/s). The aim of this model is to help a routing protocol in MANETs avoid broadcasting request messages from a high mobility node/region relied on the outcome of the prediction. Through simulation experiments, route error rate observed reduced significantly compared to normal broadcast scheme of the Ad-hoc On-demand Distance Vector (AODV) protocol. The packet delivery ratio improved up to 46.32% at the maximum velocity of 30m/s (equal to 108km/h) in the density of 200nodes/km2.

In this paper, we introduce Compact-Security (C-Sec), an energy efficient link layer encryption protocol for Wireless Sensor Networks (WSNs). The protocol minimizes energy consumption by eliminating the need for transmitting all header and trailer fields related to security, while keeping security functions and services intact. Such fields include message authentication code, freshness counter, and source address. Our work relies on merging security related data with the essential headers of the next packet. This will dramatically reduce security related communication overhead. In addition, it includes a unique security feature that does not exist in any of the current protocols: hiding the packet header information. C-Sec is implemented using Very high speed integrated circuit Hardware Description Language (VHDL). Experimental results using synthesis for Spartan-6 low-power FPGA demonstrates that the proposed protocol outperforms related work in terms of computational time and energy consumption, in addition to the large savings in communication energy and bandwidth.

In this paper we present a new data collection scheme using mobile actors in a large scale wireless sensor network (WSN). A mobile actor, or for convenience, M-actor is a mobile node that has powerful energy source, computation, and communication features. The mobile node is able to move freely through the sensor deployment, traversing through the radio transmission range of wireless sensor nodes to collect the sensed data. Once data from all sensors is collected, the M-actor returns to the base station to off-load the collected data. This paper makes two contributions. First, we present a heuristic to compute collection points, referred to as the rendezvous points (RPs). These points are computed such that full coverage is guaranteed. Second, the optimal path for the M-actor is modeled using a genetic algorithm (GA)based traveling salesman problem (TSP). The proposed scheme is evaluated through simulations. We demonstrate that the proposed scheme achieves significant improvement in reducing the tour length for the M-actor when compared with other schemes.

In the design of Wireless Sensor Networks (WSNs), energy conservation is a goal at all system levels, from the application down to the hardware. This paper focuses on network-level opportunities for energy conservation, with emphasis on the multi-hop transmissions, topology control and routing-level issues. Specifically, the paper considers energy efficient information broadcasting in WSNs deploying co-operating nodes which by adjusting their transmission ranges minimize the total transmitted power in the network. To this end, the design of routing protocols with a single relay is proposed for multiple multicast sessions in a network with randomly distributed nodes. The protocols take advantage of topological diversity created by adapting the transmission power and exploit the benefits of network coding in a system where nodes are periodically generating data packets. Energy efficiency of the conventional, store-and-forward, and network coding based relaying schemes is analyzed in different propagation conditions and for various node densities.

In recent years a flurry of research activity has produced many suggested schemes for clustering wireless sensor networks, but no hard numbers for real-world implementations. This lack of guidance for developers makes it very difficult to effectively and confidently build working networks. This paper partially addresses these concerns by deriving minimal timing bounds on the clustering process in a typical and recently suggested clustering schemes. This is achieved through low-level network simulation in NS -2. We present detailed results that provide insight to timings involved in different phases of cluster set up. Results show ideal clusters can be constructed within 0.5 s for expected node densities (≤ 0.04 nodes/m2).

This paper investigates coverage and connectivity issues for Wireless Sensor Networks (WSNs) under three dimensional deployment scenarios. WSNs are deployed over a region to sense the events of interest in a geographical area and transmit collected data to a Base Station (BS). We exploit the inherent redundancy in WSN deployment by finding an optimal set of sensor nodes that can cover the 3D deployment region efficiently while maintaining the network connectivity. In this regard we propose a distributed coverage algorithm (DCA) that allows sensor nodes to form a 1-covered topology by exchanging messages based on the local information. We also present an analytical relation that is used to estimate the sensing range used by the DCA. Experimental results demonstrate the feasibility of the proposed scheme.

In large scale wireless sensor networks clustering is often used for improving energy efficiency and achieving scalable performance. In this paper we present a novel energy efficient cluster formation algorithm based on a multi-criterion optimization technique. Our technique is capable of using mul- tiple individual metrics in the cluster formation process as input while optimizing on the energy efficiency of the individual sensor nodes as well as the overall system. The proposed technique is implemented as distributed protocol in which each node makes its decision based on local information only. The feasibility of proposed technique is demonstrated with simulation results. The performance of the proposed method compares favorably with other well known clustering protocols with respect to energy consumed and network life time.

Most of the proposed MAC and routing protocols for \nwireless sensor networks (WSNs) consider energy efficiency as the main objective and assume data traffic with unconstrained delivery requirements. However, applications such as rescue and disaster recovery, and tracking moving objects demand end-toend performance guarantees as the timely delivery of data is as important as energy efficiency. This paper presents a reservation based medium access control (MAC) for applications with different QoS priorities in a clustered WSN environment. The protocol is based on a combination of CDMA, TDMA and contention based access mechanisms. The protocol employs a slot assignment algorithm to handle adaptive resource allocation in a clustered environment. Simulations that demonstrate the feasibility of the proposed MAC protocol and the resource allocation is discussed.