Industries have been racing to integrate Internet of Things (IoT) devices into their systems and make full use of their readings, as these devices give a glimpse into the current state of particular entities. This is enormously insightful for real-time querying in the industries’ domains and areas of interest. However, the heterogeneous nature of the generated IoT data poses a bottleneck, slowing down the collaboration between IoT systems. This work aims to provide an effective solution for cooperation between IoT systems by introducing a simplified yet efficient data unification framework that is capable of integrating different heterogeneous data in a simpler manner than previously proposed approaches. In addition, we provide a qualitative comparison between our data unification framework and other popular approaches in collaborative IoT systems, such as IoTivity, SensorML (Sensor Model Language), and SenSquare. We conducted an interoperability test on our data unification framework across various scenarios. The results indicate that our framework enhances the optimization of different sensor profiles by an average of 88% compared to state-of-the-art solutions. Furthermore, through interoperability testing, our solution has demonstrated its ability to function efficiently across diverse domains and use cases, thereby establishing its reliability.

Task offloading in Vehicular Edge Computing (VEC) can significantly enhance Cooperative Perception (CP) for Autonomous Vehicles (AVs), improving situational awareness and traffic safety. However, the widespread adoption of VEC is often constrained by the high deployment costs of Roadside Units (RSUs). In this paper, we propose the Truthful and Quality-Aware Task Offloading (TQTO) scheme. TQTO leverages the prolific yet underutilized computational resources of parked vehicles for CP tasks in VEC to alleviate RSU scarcity. Using vehicle-to-vehicle (V2V) communication, parked vehicles can be strategically involved in CP processing and are incentivized to contribute their resources. TQTO introduces a distributed, truthful, double-auction-based multi-agent deep reinforcement learning framework that enables user vehicles to offload CP tasks to parked vehicles in a utility-maximizing manner, while respecting their individual budget constraints. Concurrently, TQTO considers the provider-side (i.e., parked vehicles) costs and ensures a truthful, incentive-compatible, and budget-balanced marketplace for VEC. A critical value-based payment mechanism is used to ensure fair compensation for parked vehicles and to align task requesters’ payments with their utility. TQTO formulates the task offloading problem as a Double Auction Quadratic Multiple Knapsack Problem (DA-QMKP) and solves it using a QMIX-based heuristic for scalable decision-making under partial observability. Extensive evaluations show that TQTO outperforms a prominent non-auction-based scheme by up to 39% in terms of social welfare.

Traffic collisions pose a significant global challenge, resulting in considerable human and economic losses. Accurate prediction of the severity of highway collisions is critical for effective emergency response and resource allocation. Highways, due to their high traffic volumes, are especially prone to diverse collision types, from minor incidents to severe multi-vehicle collisions. However, recent studies often overlook the detailed characterization of spatiotemporal factors influencing collision severity. In this paper, we analyze and model the severity of traffic collisions on highways, with a focus on the Queen Elizabeth Way (QEW), a major transportation corridor in Canada. We collect and examine collision data from 2017 to 2019 across multiple segments of the QEW, encompassing a range of types of incident. We then propose a deep learning model capable of predicting collision severity using spatiotemporal features. Our approach demonstrates superior performance, achieving an overall accuracy of 99%, and outperforms existing machine learning models. The results emphasize the importance of integrating spatiotemporal characteristics to improve predictive accuracy and inform proactive road safety interventions.

The disparity in surgical care between urban and rural areas remains a significant challenge due to geographical and connectivity constraints. Telesurgery, enabled by digital twins, has emerged as a potential solution to bridge this gap. However, the reliability of telesurgical procedures is heavily influenced by network variability, including latency fluctuation, jitter, packet loss, and varying throughput. This paper investigates the impact of network instability on telesurgery key performance indicators (KPIs) and evaluates the correlation between network parameters and surgical precision, system responsiveness, and operational safety. To achieve this, we developed a Robotic Telesurgery Digital Twin (RTDT) framework that models network conditions and performs real-time risk analysis. Using Pearson, Spearman, and ANOVA correlation methods, we quantify the influence of network variability on telesurgical performance. Additionally, decision trees is used to predict high-risk scenarios before modeling stochastic network disruption with Monte Carlo. Simulation results indicate that a latency exceeding 150 ms results in a 98% failure rate in telesurgery. Additionally, packet loss greater than 30% can reduce surgical precision by 55%. Furthermore, a throughput below 150 Mbps drastically impacts the operation, leading to a 98% probability of failure. These findings highlight the importance of controlling latency, packet loss, and throughput variations to maintain reliable surgical performance.

Task offloading in Vehicular Edge Computing (VEC) enhances cooperative perception (CP) for Autonomous Vehicles (AVs), improving traffic awareness. However, the high cost of Roadside Unit (RSU) and the underutilization of parked vehicles pose challenges. Leveraging Vehicle-to-Vehicle (V2V) communication, parked vehicles can form collaborative worker groups for efficient perception aggregation. We propose CoGroup, a two-tier framework integrating task offloading and dynamic worker grouping. Modeled as a double quadratic multiple knapsack problem, it employs Hierarchical Reinforcement Learning (HRL): QMIX for decentralized task allocation and DQN for optimized worker grouping. Experiments show that CoGroup improves traffic awareness by 21% over non-cooperative methods, reducing RSU dependence and offering a scalable, cost-effective solution for next-generation VEC systems.

Task offloading in Vehicular Edge Computing (VEC) is crucial for enhancing cooperative perception (CP) in Autonomous Vehicles (AVs), thereby improving traffic situational awareness. However, existing approaches often neglect the balance between high-quality execution of interdependent tasks and conserving AVs limited budget, including communication and financial resources. To address this, we propose the Quality and Budget-Aware Task Offloading (QBATO) framework. QBATO is the first framework to balance the quality of cooperative perception with budget conservation. QBATO models the budget as a queue to ensure stability, balancing resource use while prioritizing situational awareness in CP. Additionally, QBATO enhances CP quality by predicting vehicles movements and estimating their regions of interest, thereby improving the Value of Information (VOI). The task offloading problem is modeled as a Quadratic Multiple Knapsack Problem (QMKP), an NPhard problem that optimizes vehicle allocation by evaluating the quality of assigning multiple vehicles to the same worker through a quadratic objective function.To manage resources effectively, we apply the queue stability Lyapunov drift-minus-bonus approach. We also introduce the QBATO-Heuristic (QBATO-H), which solves the problem in a decentralized, time-efficient manner using a multi-agent deep reinforcement learning technique that leverages the Q-Mixing Network (QMIX) method, which employs monotonic value decomposition to coordinate the actions of multiple agents. Extensive evaluations show that QBATO outperforms prominent quality and budget-oblivious schemes by up to 49%, 15%, and 35% in terms of budget conservation, situational awareness, and efficiency, respectively. QBATO-H also yields a small gap of up to 7% and 11% with QBATO in terms of budget conservation and efficiency, respectively.

The enhancement of the vehicle perception model represents a crucial undertaking in the successful integration of assisted and automated vehicle driving. By enhancing the perceptual capabilities of the model to accurately anticipate the actions of vulnerable road users, the overall driving experience can be significantly improved, ensuring higher levels of safety. Existing research efforts focusing on the prediction of pedestrians’ crossing intentions have predominantly relied on vision-based deep learning models. However, these models continue to exhibit shortcomings in terms of robustness when faced with adverse weather conditions and domain adaptation challenges. Furthermore, little attention has been given to evaluating the real-time performance of these models. To address these aforementioned limitations, this study introduces an innovative framework for pedestrian crossing intention prediction. The framework incorporates an image enhancement pipeline, which enables the detection and rectification of various defects that may arise during unfavorable weather conditions. Subsequently, a transformer-based network, featuring a self-attention mechanism, is employed to predict the crossing intentions of target pedestrians. This augmentation enhances the model’s resilience and accuracy in classification tasks. Through evaluation on the Joint Attention in Autonomous Driving (JAAD) dataset, our framework attains state-of-the-art performance while maintaining a notably low inference time. Moreover, a deployment environment is established to assess the real-time performance of the model. The results of this evaluation demonstrate that our approach exhibits the shortest model inference time and the lowest end-to-end prediction time, accounting for the processing duration of the selected inputs.

During the COVID-19 pandemic, the traditional emergency healthcare systems faced unprecedented strain due to the sharp rise in demands for urgent care, scarcity of resources, and increased risks of people getting infected while waiting at the emergency care facility. We present Triage-Bot, an online medical triage provisioning service, that can revolutionize emergency care by decreasing the load on emergency departments (ED), reducing healthcare expenses, and improving the quality of care. Empowered by artificial intelligence and natural language processing, the Triage-Bot service assesses and prioritizes patients' needs based on symptoms, medical history, and perceived conditions from multimodal video, audio, and text data captured during patients' interactions. The captured summarized information with a severity ranking is sent to a human expert to suggest the next action on the user's part. The diverse data types used by the Triage-Bot in communication, authentication, data collection, storage, and analytics requires a robust and scalable system architecture for online service provisioning. In this paper, we specifically focus on the system design and architecture of the Triage-Bot for emergency healthcare settings. With integrated electronic medical records (EMR) and online platforms, the bot fosters collaboration among healthcare professionals and enables swift and informed decision-making even in the face of crises. By partially automating and offering a hybrid triage process, the Triage-Bot improves resource allocation, reduces healthcare management costs for emergency care, minimizes patient waiting times, and improves wellbeing. To address the complexities and demands of healthcare data management, our proposed system incorporates MongoDB database for flexibility, scalability, and versatility in supporting different types of data. Additionally, we implement a data linking and analytics pipeline utilizing a data Lakehouse system to effectively ingest, manage, process, and generate knowledge from heterogeneous data sources.

This paper proposes an edge computing-enhanced testbed for Vehicle-to-Everything (V2X) communication, using a scaled autonomous vehicle model. Addressing the limitations of traditional vehicle testing and simulations, our approach utilizes an F1Tenth scale vehicle to replicate real-world traffic scenarios, with a focus on non-line-of-sight and pedestrian-occluded challenges. The testbed incorporates a Road Side Unit (RSU) for edge-based data processing, allowing rapid data acquisition and transmission. Our controlled experiments assess the vehicle's response to V2X communication in complex environments specifically in NLOS scenarios such as occluded pedestrians, highlighting the potential of edge computing to augment autonomous vehicle perception and decision-making. Performance evaluation shows that the vehicle can effectively handle emergencies, achieving an end-to-end response time of less than 146 ms on an edge device. Compared to other popular autonomy frameworks, which rely on higher computational units unsuitable for deployment on edge devices. This study advances V2X technology in edge computing contexts for autonomous vehicles and paves the way for future research in robust, safe, and reliable autonomous systems.

Long Short-term Memory (LSTM) is a Recurrent Neural Network (RNN) that is widely used in time series traffic forecasting. LSTM captures both short-term and long-term trends and dependency in sequential data like time series data, as it contains specialized memory cells to store information in memory for longer periods. Existing traffic forecasting approaches lack features to forecast the traffic speed of interconnected road links and provide multivariate (i.e., multi-input and multi-output) and multi-step traffic forecasting both in the short- and long-term. We propose an Encoder-Decoder LSTM-based sequence-to-sequence architecture to capture the traffic speed of interconnected road links and provide multivariate multistep traffic forecasting both in the short-term (15 minutes) and long-term (two days). We apply a sliding-window approach to feed the short-term traffic forecasting as input to the model to project long-term traffic forecasting. Our model can incorporate multiple interconnected road links and providing traffic speed forecasting for multiple future steps. We conducted our experiment at an intersection in Oshawa, ON, Canada, and evaluated performance using the error distribution and Mean Absolute Error. The evaluation shows that the model can forecast traffic speed across interconnected road links with negligible error, both in the short-term and the long-term.

Autonomous vehicles should be capable of operating in all types of weather conditions. Drivable road region detection is a core component of the perception stack of self-driving vehicles. Current approaches for detecting road regions perform well in good weather but lack in inclement weather conditions. In this paper, we examine the effect of inclement weather on the camera-based state-of-the-art deep learning approaches and introduce a new camera and automotive radar-based multimodal deep learning model to efficiently detect drivable road regions in all weather conditions. We also propose a novel approach to overcome the sparse resolution problem of automotive radars and a way to effectively use it in higher precision tasks such as image segmentation. To validate our work, we have augmented the nuScenes data with rain and fog to add challenging weather conditions. Experimental results show that the performance of the state-of-the-art techniques drops 18% in bad weather conditions while our proposed method improves the performance by 12% compared to the state-of-the-art.

In today’s technological landscape, data has become a cornerstone for numerous applications, witnessing exponential growth driven by the advent of sophisticated devices capable of generating and analyzing user data daily. This surge in data volume has spurred a competitive push among industries and firms to develop scalable applications designed to efficiently take advantage of this wealth of information to offer services that capitalize on the vast data repositories. Simultaneously, the Internet of Things (IoT) has seen a remarkable rise in popularity, resulting in the expanding range and significance of sensor applications. Sensors now play a pivotal role across various domains, providing real-time insights into the monitored subjects’ status. This paper introduces a comparative analysis between different data modeling techniques using a unified schema for heterogeneous IoT sensor data. This analysis aims to identify the most suitable approach for handling both structured and unstructured data within a sensor integration framework. Performance evaluation shows that the document data model, implemented by MongoDB, demonstrates superior efficiency in the READ, UPDATE, and DELETE operations under high data loads compared to traditional relational models. Despite a slower performance in CREATE operations due to overheads associated with index creation and document structuring, the document data model still maintained superiority over other approaches. Additionally, when compared with various CRUD operations, the document data model showed increased throughput with higher workloads, outperforming both the column and the EAV data models.

Agile network security is paramount in our modern world which is currently dominated by Internet systems and expanding digital spaces. This rapid digital transformation has created more opportunities for cyberattackers to exploit different vulnerabilities and launch sophisticated and continuously evolving cyberattacks. Increasingly, intrusion detection systems are relying on new methods based on Machine Learning (ML) and Deep Learning (DL) techniques to detect and mitigate such cyberattacks. While such techniques normally can identify known network attack patterns with a reasonable degree of success, their ability to identify complicated atypical, polymorphic, and unknown attacks is shown to be limited. In this paper, we present a comprehensive survey of recent research for detecting unknown, atypical, and polymorphic network attacks using DL techniques. We further highlight and discuss the main challenges in this area and identify the future research directions.

Today's networked systems face significant security challenges due to sophisticated attacks. Several Machine Learning (ML) and Deep Learning (DL) models are employed to combat these diverse attacks. Adversarial attacks, which can evade detection by AI-based intrusion detection systems (IDS) through small alterations to network attack traffic, pose a significant concern. These AI-synthesized adversarial attacks must adhere to network constraints to seem plausible. In this work, we explore the validation criteria for such adversarial attacks and propose a methodology for analyzing their quality. We evaluate adversarial attack samples synthesized by state-of-the-art generative DL models such as Variational autoencoder (VAE), Conditional Variational autoencoder (CVAE), Generative Adversarial Network (GAN) and compare the performance with our CVAE-Adversarial Network (CVAE-AN) model. Results indicate the effectiveness of CVAE-AN in synthesizing realistic adversarial attacks.

Autonomous vehicles heavily rely on sensor data to make pivotal driving and traffic management decisions. However, the reliability of such data can be profoundly impacted by many impairments, such as the adverse environmental and weather conditions, the presence of obstacles, and the vehicle's limited view of road and traffic conditions of larger areas. Collaboration between vehicles can help improve the perception of vehicles beyond their line-of-sight, and increase accurate detection of objects. Vehicular Edge Computing (VEC) has emerged as a propitious computing paradigm that can foster the realization of autonomous vehicles. However, maximizing the cooperative perception of vehicles has been mostly overlooked. In this paper, we propose the Cooperative Perception-based Task Offloading (CPTO) scheme. CPTO enables task offloading in VEC with the goal of maximizing the cooperative perception of vehicles and minimizing the latency of perception aggregation, while abiding by a certain deadline. Towards that end, we formulate the task offloading problem as a multi-objective 0–1 integer linear program (0–1 ILP). We also propose a greedy heuristic, called the CPTO-Heuristic (CPTO-H) scheme, to solve the optimization problem. Extensive simulations show that CPTO significantly outperforms the baseline task offloading scheme in terms of perception intensity, service capacity, and satisfaction ratio. Furthermore, CPTO-H closely approaches the optimal solution, with a small gap of up to 3.7% and 2.4% in terms of perception intensity and satisfaction ratio, respectively.

Leveraging task offloading in Vehicular Edge Computing (VEC) via V2X can present unique and robust solutions to the challenges associated with cooperative perception in Autonomous Vehicles (AVs). However, making task offloading decisions that account for the risk of communication failure due to path loss, while adhering to the stringent QoS requirements of cooperative perception has been mostly overlooked. In this paper, we propose PLTO, a Path Loss-Aware Task Offloading scheme that accounts for path loss for Line-of-Sight (LOS), Obstructed LoS (OLoS), and Non-LoS (NLoS) propagation in vehicular communications. We formulate the task offloading problem as a 0–1 Integer Linear Program (0–1 ILP) that aims to minimize the path loss and response delay, while sustaining a certain satisfactory level of improved perception and situational awareness demanded by users. We also propose PLTO-Heuristic (PLTO-H), a scheme to solve the task offloading problem using the MTHG heuristic. Extensive simulations show that PLTO yields significant improvements of up to 17%, 10%, and 23% in terms of packet delivery ratio, Received Signal Strength Indicator (RSSI), and average response delay, respectively, compared to a baseline task offloading scheme that does not consider communication efficiency. In addition, PLTO-H achieves a near optimal solution, with a small gap of up to 6%, 5% and 1.2% in terms of packet delivery ratio, RSSI, and satisfaction ratio, respectively.

Colorectal cancer (CRC) is considered the third most common cancer worldwide and is recently increasing in Africa. It is mostly diagnosed at an advanced state causing high fatality rates, which highlights the importance of CRC early diagnosis. There are various methods used to enable early diagnosis of CRC, which are vital to increase survival rates such as colonoscopy. Recently, there are calls to start an early detection program in Egypt using colonoscopy. It can be used for diagnosis and prevention purposes to detect and remove polyps, which are benign growths that have the risk of turning into cancer. However, there tends to be a high miss rate of polyps from physicians, which motivates machine learning guided polyp segmentation methods in colonoscopy videos to aid physicians. To date, there are no large-scale video polyp segmentation dataset that is focused on African countries. It was shown in AI-assisted systems that under-served populations such as patients with African origin can be misdiagnosed. There is also a potential need in other African countries beyond Egypt to provide a cost efficient tool to record colonoscopy videos using smart phones without relying on video recording equipment. Since most of the equipment used in Africa are old and refurbished, and video recording equipment can get defective. Hence, why we propose to curate a colonoscopy video dataset focused on African patients, provide expert annotations for video polyp segmentation and provide an AI-assisted tool to record colonoscopy videos using smart phones. Our project is based on our core belief in developing research by Africans and increasing the computer vision research capacity in Africa.

Phone of Things (PoT) is a new paradigm in IoT that has been recently coined in the literature. PoT provides a framework for leveraging the ubiquitous phone network assets and infrastructure by making them part of the IoT architecture to manage and control IoT gadgets. PoT proposes a lightweight SIP-based messaging protocol, which we call tSIP, that we can map to its corresponding original SIP protocol messages with the help of a proxy (i.e., the PoT gateway). tSIP facilitates communication between resource-constrained smart objects and the communication server using mature phone technologies with abstractions that people are already familiar with. In this context, the paper proposes a lightweight decentralized registration and authentication mechanism based on blockchain technology for smart gadgets in the PoT system to facilitate their association with the communication server. The proposed mechanism provides a secure, trustless, and scalable environment for PoT without requiring high-end communication servers, affecting the existing SIP-based VoIP architecture, or mandating trust in third-party entities. The proposed mechanism uses the Ethereum blockchain and smart contracts to implement a programmatic, immutable access control mechanism to administer the association of IoT devices with the communication server. As a proof of concept, we provide a prototype implementation of the proposed mechanism using a private blockchain due to its privacy characteristics, fast transaction processing, and cost-effectiveness. We conduct a feasibility study of the proposed mechanism and a security analysis. The analysis demonstrates that the proposed mechanism complies with the security standards of the SIP protocol and fits the constraints of embedded smart objects.

Jaywalking refers to pedestrians walking or crossing in a roadway that is not dedicated to pedestrians. Due to illegal jaywalking, every year a lot of accidents happen worldwide that cause a significant amount of death and other physical injuries. Real-time jaywalking detection and notification systems can contribute to protecting vulnerable road users and increasing road safety. Many computer vision-based image processing techniques have been proposed to detect jaywalking including deep learning, motion path analysis, motion object segmentation, trajectory forecasting and position localization. However, these techniques are designed and evaluated for a single road area and have limited notification capability. In this paper, we propose a real-time multi-object tracking approach for jaywalking detection and notification that can be applied in multiple road areas simultaneously. We use the state-of-the-art deep learning model YOLOv4 and the multi-object tracking algorithm DeepSORT for real-time object detection and tracking, respectively. The notification component incorporates a novel vehicle-region pair matching algorithm based on the proximity of vehicles to the monitored region. Performance evaluation shows that our proposed approach can effectively detect jaywalking with 100% accuracy and provide push notifications to nearby vehicles in real-time.

Continuous real-time electrocardiogram (ECG) monitoring can detect arrhythmia and provide early warning for heart attacks. Effective power management signals and controlling the mode of operation to reduce the need for full fidelity ECG signal. This work studies the impact of the base-delta compression technique for different cardiac conditions on power consummation. It also aims to evaluate operational strategies and their effect on the battery life when the ECG patch can switch between different operating modes (e.g., varying the number of leads according to the cardiac conditions). We use a binary classifier to inform the decision of switching between different operational strategies. Both scenarios are evaluated in terms of execution time, Bluetooth Low Energy (BLE) communication airtime, power consumption, and energy-saving ratios on a Texas Instruments CC2650 Micro-controller Unit (MCU). We compare the performance of the base-delta compression and changing the mode of operation scenarios on various cardiac abnormalities. Performance evaluation shows that operational strategies outperforms data compression in power saving for normal ECG readings by a double fold. In contrast, operational strategies incurs an additional overhead of 1011 ms during an abnormal status. However, base-delta satisfies the embedded platform constraints on execution time and airtime with 25 ms and 20 ms, respectively in the MCU environment.

Edge Computing (EC) has paved the way toward the realization of the Internet of Things (IoT). This can be attributed to the ability of EC to bring the computational resources within close proximity to end-users, which significantly improves the response time. However, performance gain in EC can be compromised by service interruptions triggered by various dynamic changes. Consequently, reliable service migration is crucial in EC. However, most service migration schemes either fail to consider the profound impact of the dynamic computation load on service continuity or provide impractical and time-inefficient solutions based on optimization techniques. This paper proposes the Heuristic-based Load-induced Proactive Migration (HLPM) scheme. HLPM incorporates a Finite State Machine (FSM) to model the dynamic computation load. It then makes proactive migration decisions based on the underlying transition probabilities. The proactive migration problem is solved using the MTHG heuristic algorithm. Performance evaluation shows that HLPM produces a significant decrease of up to 97% in migration decision latency compared to conventional optimization techniques. Furthermore, the performance gap of HLPM with respect to the optimal migration solution is just 1.44% latency and 3.89% number of migrations.

ECG monitoring systems have a significant role in detecting cardiovascular diseases and reducing the rate of sudden cardiac deaths. One of the critical factors to support real-time ECG tracking is to guarantee monitoring system availability. Hence, this work targets battery life expansion for a 12 Lead ECG patch. ECG patch operational hours are extended by reducing Bluetooth Low Energy (BLE) communication airtime, hence reducing the overall transmission power and extending the battery life. Huffman, delta, and base-delta compression techniques are implemented on a Texas Instruments CC2650 Microcontroller Unit using different sampling rates and cardiac conditions such as normal, ventricular tachycardia, and ventricular fibrillation state. The performance of each encoding algorithm is evaluated in terms of compression ratio, the execution time, and power consumption of the ECG patch. Our findings show that the base-delta encoding technique outperforms other techniques and achieves 70% data compression on normal ECG data, 41% on ventricular fibrillation, and 44% on ventricular tachycardia. The execution time of base-delta encoding takes less than 25 ms execution time and saves up to 36 % of the power consumption on the MCU environment.

Traffic simulation is a great tool to demonstrate complex traffic structures which can be extremely useful for the planning, development, and management of road traffic networks. Current traffic simulators offer very limited features when it comes to interactive and adaptive traffic modeling. This paper presents RegTraffic, a novel interactive traffic simulator that integrates dynamic regression-based spatiotemporal traffic analysis to predict congestion of intercorrelated road segments. The simulator models traffic congestion of road segments depending on neighboring road links and temporal features of the dynamic traffic flow. The simulator provides a user-friendly web interface to select road segments of interest, receive user-defined traffic parameters (e.g., level of congestion in terms of traffic speed and other road events), and visualize the traffic for the flow of correlated road links based on the user inputs and the underlying correlation of these road links. We experimented RegTraffic in an intersection of Oshawa, ON, Canada. Performance evaluation shows that RegTraffic can effectively predict traffic congestion with a Mean Squared Error of 1.3 Km/h and Root Mean Squared Error of 1.71 Km/h. RegTraffic can effectively simulate the results and provide visualization on interactive geographical maps.

In response to the rapid digital revolution and the COVID-19 pandemic, the healthcare landscape has significantly shifted from physical to virtual care and telemedicine. As a result, healthcare providers and patients have shown increased interest and adoption for up-to-date technologies to monitor ongoing health conditions, including cardiovascular diseases. Driven by the importance of an efficient remote cardiovascular monitor for virtual care, we present a platform that enables remote ECG testing and provides ubiquitous data access to patients and their healthcare providers. A patent-pending 12-lead data acquisition ECG patch is attached to the patient's body to simultaneously collect heart signals, perform binary classification, and transmit the data to healthcare providers for further analysis at a high rate of up to 480 samples per second. As a preliminary classification phase, the presented platform introduces a machine learning technique to classify ECG signals near the ECG patch. The classification function is optimized for power-constrained devices using machine learning techniques. Moreover, the preliminary results of the energy consumption profile show that the ECG patch provides up to 37 hours of continuous 12-lead ECG streaming.

The Internet of Things (IoT) is one of the fastest-growing technologies in recent years. However, many IoT service providers design their IoT solutions with non-interoperable hard-ware, scenario-specific features, and unique architectures that make these deployments fragmented rather than collaborative. Collaborative IoT (C-IoT) systems are considered the natural evolution of the traditional IoT. Sharing the infrastructure is one of the main concepts that C-IoT depends on to create a collaborative environment between different applications. With the current fragmented IoT, these applications cannot share their infrastructure and data due to the lack of standards to organize the C-IoT space. In this paper, we introduced Unified Interoperable Driver for IoT (UIDI) nodes. UIDI uses a novel programming methodology that enables node interpreters to provide general-purpose firmware for IoT nodes. UIDI allows the users to configure IoT nodes according to their usage, preferences, and needs through the cloud. We developed a proof-of-concept prototype to demonstrate the feasibility and usability of the proposed UIDI using NodeMCU and Arduino-Uno. The performance of UIDI outperforms Firmata by 27%. In addition to that, the UIDI platform is a standalone node that connects directly to the cloud, whereas the Firmata node requires a host to be accessible from the cloud.

Phone of things (PoT) is a novel idea for loT systems connectivity that allows legacy and non-loT-enabled devices to be interfaced through the mature and ubiquitous telephone network infrastructure. This paper evaluates the performance of the Raspberry Pi board families, embedded Linux platforms based on ARM processors, on processing VolP calls for PoT applications. The paper assesses and contrasts the ability of the boards in handling passthrough and trans coded VolP calls. Based on the obtained results, the paper proposes best practices for employing the boards as Asterisk servers and advocates the maximum number of simultaneous calls at different scenarios to preserve the hardware safety and maintain better performance regarding system stability and VolP call quality measurements. The results show that Raspberry Pi 4 B can gracefully han-dle up to 364 active passthrough channels (equivalent to 182 simultaneous calls). Nevertheless, Pi Zero W, the least powerful version of the Raspberry Pi, can gracefully handle up to 24 active passthrough channels. The results promote the utilization of embedded Linux platforms as appropriate, tiny form factor, and cost-effective candidates to act as PoT gateways in homes and small-to-medium sized business domains.

This paper explores ways for energy consumption reduction in wearable and Remote Patient Monitoring (RPM) devices. We use the XBeats ECG patch as a case study application for remote Electrocardiogram (ECG) wearable device power consumption benchmarking. Systematic energy consumption profiling criteria is proposed for evaluating participating components in an RPM device. We isolate each hardware component to find power-intensive processes in the XBeats system, discover energy consumption patterns, and measure voltage, current, power, and energy consumption for a given time period. The proposed optimization techniques demonstrate significant improvements to the hardware components on the ECG patch. The results show that optimizing the data acquisition process saves 8.2% compared to the original power consumption and 1.62% in data transmission over BLE, thus extending the device lifetime. Lastly, we optimize the data logging operation to save 54% of data initially written to an external drive.

Today, the world has become crowded with sensing devices that are connected to the Internet, making the Internet of Things (IoT) a mainstream paradigm. A decade earlier, the Public Sensing term appeared to utilize a limited network of sensing devices that collect information from the surrounding for a specific purpose. The limited connectivity, heterogeneity of the sensing devices, and the immaturity of technologies hindered the widespread implementation of Public Sensing as a Service (PSaaS) in real-world scenarios. To date, there is no clear definition for Public Sensing, and it is frequently confused with other terms such as mobile crowdsensing and crowdsourcing. In this paper, we redefine Public Sensing in the context of the widespread IoT and propose a new architecture for Public Sensing as a Service. The conclusion of the discussion demonstrates that the proposed PSaaS holds a considerable promise for public adoption and will offer real-time smart services to inform decision-making and improve quality of life.

This paper presents 3D-RadViz, a visualization method for high dimensional data using a three dimensional radial visualization technique. The proposed technique extends the capabilities of the classical two dimensional radial visualization (RadViz) in order to reduce overlapping data points. For evaluation purposes, the paper applies the proposed 3D-RadViz alongside with t-SNE and a recently published 3-dimensional radial visualization technique to the same real-world datasets from the UCI machine learning repository. The contribution of the work is an interactive, deterministic, and high-performance library, implemented in Python, that can be utilized to realize better high dimensional data visualization using the proposed 3D-RadViz technique. The paper also suggests some directions for future enhancements to the proposed visualization approach.

Network Intrusion Detection Systems (NIDS) are powerful tools for identifying and deterring cybersecurity attacks nowadays. However, while these modern IDS can detect typical attacks, recent studies show their poor performances in identifying unknown or dynamically changing atypical attacks. Another issue with the training aspect of such systems is the problem of class imbalance which impedes their performance, especially for minority attack classes. This renders IDS systems vulnerable to both adversarial as well as non-AI synthesized atypical attacks when deployed in a real network. To reduce misclassification (especially for minority classes) and detect atypical attack flows, we propose a novel adversarial incremental learning approach based on a hybrid model consisting of a Conditional Variational Autoencoder (CVAE) and a Generative Adversarial Network (GAN) namely, CVAE-Adversarial Network (CVAE-AN). The binary IDS has been trained using the CICIDS2017 dataset and evaluated using multiple atypical attacks. Simulation results demonstrate that the proposed technique significantly improves the performance of the IDS against different atypical attacks and outperforms the state-of-the-art detection models as well as class balancing methods.

Road traffic modelling, analysis, and prediction require accurate and preprocessed spatiotemporal traffic data including measurements like traffic speed and count. Many existing and emerging surveillance systems are currently used to facilitate traffic data collection. Google Maps is a web mapping service that leverages GPS crowdsourcing to retrieve accurate traffic data verified by both the research community and industry. Google Maps facilitates APIs to provide access to this data with a paid subscription. Google Maps also make this traffic data publicly available through their web interface, but with limited features and requires further pre-processing. All existing tools to facilitate these publicly available traffic data through the Google Maps web interface is either lack essential functionalities or are proprietary. We have developed an open-source web-based data scraper tool to extract and export available traffic data from the Google Maps web interface in multiple usable formats. The tool provides a user-friendly interface that enables users to visually mark the locations of interests and to flexibly determine the required periods for data collections. Performance evaluation shows that the tool can retrieve traffic data from Google Maps in a linear time complexity with no significant computational overhead. Limitations and challenges to develop such tools are also investigated.

In the era of the Internet of Things (IoT), it has become possible for a set of smart devices to collaborate autonomously and communicate seamlessly to achieve complex tasks that require a high degree of intelligence. Unlike traditional internet devices, a compromised IoT device can cause real-world damages. The severity of these damages increases dangerously in sensitive contexts especially when these devices are controlled by system insiders. Detecting abnormal access behaviors in such environments is quite challenging, due to frequent changes in the access contexts under which the IoT device can be accessed. In this paper, we propose an adaptive access control policy framework that dynamically refines the system access policies in response to changes in the device-to-device access behavior. We apply supervised machine learning to model and classify the device access behavior based on a real-life data set. We provide a use case scenario of a door locking system to validate our work. Results show that our framework provides improved security, dynamic adaptability and sufficient scalability to the target application domain.

This article presents a dynamic access control framework for the Internet of Things (DACIoT). The main objective of DACIoT is to prevent unauthorized access to IoT devices and tightens the authorized access while an IoT device is in use. The rigidness of existing access control (AC) techniques in terms of manual policy specification, discontinuity of access decision making, and immutability to changing access behaviors makes these solutions fall short in highly dynamic IoT environments. DACIoT supports three functionalities that are lacking in existing AC solutions: 1) automatic policy generation; 2) continuous policy enforcement; and 3) adaptive policy adjustment. The DACIoT extends the standard reference model of the extensible AC markup language (XACML) with the added three functionalities to improve the adaptability of attribute-based AC policies to highly dynamic IoT environments. Results show that DACIoT provides improved security, dynamic adaptability, and can scale efficiently to IoT environments.

In this study, we propose an anomaly detection algorithm on sensor traffic data. The algorithm is composed of three distinct steps: temporal detection, spatial detection, and GPS calibration. The temporal detection is based on time series analysis and detects anomalies in real-time when measured sensor values are far offset from expected readings. The spatial detector is used to prune the output of the temporal detector, identifying those anomalies which are not consistent with measurements from neighboring sensors. Both temporal and spatial prediction use the widely adopted ARIMA model. The final step is to compare the predicted speed with the average speed gathered from vehicles equipped with GPS devices and subscribed to provide their data. Experimental results on real data demonstrate that the proposed algorithm effectively differentiates between abnormal traffic events and malicious manipulation of traffic data with an average accuracy of 94%.

Traffic congestion is a widely recognized challenging problem that is increasingly growing around the world. This paper leverages ARIMA-based modeling to study some factors that significantly affect the rate of traffic congestion. We present a short-term time series model for non-Gaussian traffic data. The model helps decision-makers to better manage traffic congestion by capturing and predicting any abnormal status. We begin by highlighting the characteristics and structure of the dataset that negatively impact the performance of time series analysis. We use R to preprocess and prepare the dataset for the modeling phase. We use the widely adopted ARIMA model to analyze and predict the traffic flow observations, measured at an hourly-basis, in a designated area of study in California, USA. Several ARIMA models are built using ACF and PACF analysis of the traffic time series to compare with the model suggested by the auto.arima function provided by the R language that uses random walk with drift. The residual obtained from our model demonstrates high performance in predicting future traffic status.

Advancements and convergence in IoT enabling technologies along with ubiquitous connectivity have led to the generation of new wave of smart services and applications based on real-time data access. The popularity of ubiquitous data access and accelerated adoption of these services pose significant challenges on user and data privacy. Thus, controlling access to such services in highly dynamic environments with continuously changing context becomes even more challenging. The wide adoption of IoT in our everyday life in many vital domains such as healthcare and military operations requires continuous and tight access control to prevent unauthorized and unintended access. A delay in making access decisions when context changes may result in consequences that cause harm and property damage. Therefore, continuity in access policy enforcement becomes a necessity in highly dynamic IoT environments for the entire access session not only at the time of request. This paper presents CAPE, a continuous access policy enforcement framework for IoT deployments. CAPE describes access control elements using predicates, and stores them as primitive facts in a K Dimensional tree data structure. Our algorithms automatically match access requests with primitive facts, generate access policies, make context-aware access decisions at run time and continuously monitor access control parameters based on which access decisions were made. Performance evaluation of CAPE demonstrates that this framework efficiently controls access in highly dynamic IoT environments.

Resources discovery is a fundamental requirement to the full realization of the vision of Internet of Things. Discovery includes resource properties, capabilities, and metadata. It enables consumers to build IoT applications and services that utilize “smart things” with no prior knowledge about these things. This paper studies three of the most commonly used discovery protocols, CoAP, MQTT and UPnP. We compare between their performance and behavior in IoT deployments. Each protocol is implemented and deployed on a mobile phone as a client and a Raspberry Pi as a broker/server. The implementation includes a WeMo switch and a TI SensorTag as resources. The paper provides insights on the different features, behavioural attributes, and a comparative analysis between these protocols. We also present performance indexes of each protocol in terms of memory and CPU usage, latency, and traffic exchange between a publisher and a subscriber. Our analysis shows that despite the three protocols are fundamentally different and each one has pros and cons, they are all highly useful in IoT environments. However, CoAP is generally more flexible and scalable, but requires a higher memory footprint.

Data privacy becomes a primary impediment to the realization of the IoT vision. One approach to the IoT security and privacy problem is to restrict access to sensitive data via access control and authorization models. Yet access context in IoT changes frequently raising the need for flexible and dynamic access control policies. Towards developing dynamic access control policies, context-based access control techniques are being investigated due to their robustness in assigning dynamic access permissions according to changes in context. In this paper, we propose to automate the generation of access control policies to overcome the inflexibility in traditional access policy specification techniques, and improve its adaptability to dynamic IoT environments. In our framework, we use context, attributes, and predication to describe the core access control elements. In response to access requests, our algorithm automatically produces conflict-free access control policies and makes the final access decisions at runtime. Our framework prevents non-authorized data accesses, and satisfies privacy constraints for authorized access requests in highly dynamic IoT environments. Our preliminary evaluation shows that the proposed approach offers greater flexibility and improved scalability than the current state-of-the-art methods.

Video traffic accounts for more than 70% of Internet traffic and is likely to reach 90% in 2020. Real-time video streaming is used in many applications such as sports, video conferencing, video surveillance, and public safety. Video streaming protocols such as MPEG-DASH, HDS and RTMP provide adaptive streaming capability, and application-level fault tolerance to handle failures while providing uninterrupted live video streaming service. Network outages and congestion is common in many situations during emergencies, or large public events. These failures impact live video streaming performance in terms of packet loss, latency, jitter, and video quality. Both transport layer and video streaming protocols have in-built fault tolerance mechanisms. Integrating streaming protocol's fault handling mechanism with the automatic network fault recovery would provide optimized video streaming performance. The goal of this paper is to investigate how different video streaming protocols perform when fault tolerance is provided by the SDN network. We created a self-healing SDN based MESH network testbed that transports video from a live source to the server. Our experimental results show that RTMP outperforms both MPEG- DASH, and HDS in terms of live video stream recovery and resiliency to link, port, switch, and or controller failures. These results were obtained under controlled network conditions with acceptable latency and jitter. However, switching time for recovery is significantly higher than traditional network setup, but with SDN better programable and automated recovery is possible than traditional network.

The Internet of Things (IoT) is a network of Internet‐enabled devices that can sense, communicate, and react to changes in their environment. Billions of these computing devices are connected to the Internet to exchange data between themselves and/or their infrastructure. IoT promises to enable a plethora of smart services in almost every aspect of our daily interactions and improve the overall quality of life. However, with the increasing wide adoption of IoT, come significant privacy concerns to lose control of how our data is collected and shared with others. As such, privacy is a core requirement in any IoT ecosystem and is a major concern that inhibits its widespread user adoption. The ultimate source of user discomfort is the lack of control over personal raw data that is directly streamed from sensors to the outside world. In this survey, we review existing research and proposed solutions to rising privacy concerns from a multipoint of view to identify the risks and mitigations. First, we provide an evaluation of privacy issues and concerns in IoT systems due to resource constraints. Second, we describe the proposed IoT solutions that embrace a variety of privacy concerns such as identification, tracking, monitoring, and profiling. Lastly, we discuss the mechanisms and architectures for protecting IoT data in case of mobility at the device layer, infrastructure/platform layer, and application layer.

Smartphones have become the most convenient and ubiquitous interface for Internet services. They are equipped with a multitude of sensors that can significantly improve the user's cognitive ability. Face recognition is one of the fastest growing applications in mobile domains due to the wide range of potential uses. However, face recognition is a computation-intensive process and requires resources beyond the capacity of even modern mobile devices. In this paper, we present an efficient facial recognition approach based on cloud computation offloading. The architecture performs initial image processing on the mobile devices to reduce the network traffic and save battery power before offloading the recognition to the cloud. Preliminary results show more than 230% reduction in the overall response time and over 200% energy savings on the mobile device.

The widespread use and increasing capabilities of mobiles devices are making them a viable platform for offering mobile services. However, the increasing resource demands of mobile services and the inherent constraints of mobile devices limit the quality and type of functionality that can be offered, preventing mobile devices from exploiting their full potential as reliable service providers. Computation offloading offers mobile devices the opportunity to transfer resource-intensive computations to more resourcefulcomputing infrastructures. We present a framework for cloud-assisted mobile service provisioning to assist mobile devices in delivering reliable services. The framework supports dynamic offloading based on the resource status of mobile systems and current network conditions, while satisfying the user-defined energy constraints. It also enables the mobile provider to delegate the cloud infrastructure to forward the service response directly to the user when no further processing is required by the provider. Performance evaluation shows up to 6x latency improvement for computation-intensive services that do not require large data transfer. Experiments show that the operation of the cloud-assisted service provisioning framework does not pose significant overhead on mobile resources, yet it offers robust and efficient computation offloading.

The growing popularity of cloud computing has magnified the rise of software reuse by facilitating service provisioning over the Internet. At the same time, a new generation of mobile apps has emerged relying on backend services that expand the app functionally, while reducing the overhead on limited mobile resources. The Web service approach promises great flexibility in offering software functionality over the network, while maintaining interoperability between heterogeneous platforms. In addition, recent years have witnessed the rise of user-facing service developments that can be consumed on-the-go with a standard interface, such as Restful Web services. However, the discovery of such services does not match their growing popularity and remain challenging. Users cannot tolerate long latency in finding relevant services to their requests. In this paper, we propose a robust and efficient Web service discovery approach that uses statistical methods and indexing techniques to improve the precision and response time of the discovery process. Experimental results demonstrate that the proposed approach outperforms the state-of-the-art discovery mechanisms and significantly reduces the query response time by at least 77%, while maintaining comparable accuracy.

Peer-to-peer (P2P) systems present a unique medium for resource sharing among cliques of participants (peers) in a distributed and self-organized manner. With the advent of mobile users and the increasing power of mobile devices, the spectrum of P2P capabilities should scale. Peers establish transient or persistent relationships with other peers based on mutual interest. Communicating peers may use intermediary peers to forward communication messages, if a direct link is beyond their communication range. A critical design parameter is establishing a resilient communication topology, yet reduce the overhead of control messages required to instill and maintain it. This rises as a significant hindrance in mobile environments, which pose additional challenges on P2P networks due to the heterogeneity of nodes, limited resources, dynamic contexts in addition to the inherited wireless network stringencies. Thus far, efforts in establishing P2P networks via super peers (SPs) have been capped by considering a subset of peer properties to evaluate their candidacy. This paper presents RobP2P, a robust architecture to construct mobile P2P networks and efficiently maintain network state. RobP2P introduces a SP selection protocol based on a dynamic score function that takes into account peers’ capabilities and context, such as location and quality of connectivity. The paper also presents an agile utility function through which SPs can delegate monitoring responsibilities to comparably powerful and stable peers to ensure self-healing topology maintenance. We present an elaborate performance evaluation of RobP2P implemented on Network Simulator NS-3. Our results illustrate the efficiency of RobP2P, its resilience to failures, and the improvements in lowering overhead traffic while reliably maintaining the consistency of network state.

The rate of data growth in many domains is straining our ability to manage and analyze it. Cloud computing appears as a promising platform for data-intensive computing because it offers “infinite” resources on demand, and on a pay-as-you-go basis. Surprisingly, we observe that public clouds are not being used for “serious” data-processing on a continuous basis except by the cloud vendors. We primarily attribute this observation to the long data transfer times over wide-area networks between the clients and the centralized public clouds. We introduce the idea of a near-cloud that brings a public cloud in the close proximity of a user to overcome the data transfer bottlenecks. The near-clouds also provide a unique opportunity to localize the privacy and security policies to boost confidence of a user in using shared resources for data processing. To the cloud providers, near-cloud ensures a minimum constant stream of revenue from dedicated clients.

Mobile devices are now the most convenient and ubiquitous interface for accessing information services. The advanced sensing capabilities of these devices enable them to effectively observe, analyze and understand the context of the current environment and thus are used as service providers. However, the resource constraints of mobile devices limit the type and scale of functionality that can be offered by mobile applications/services. Mobile cloud promises to bridge the gap between limited resources and increasing demands of future mobile applications through an elastic resource provisioning model. Mobile ubiquitous cloud enables resource-constrained mobile devices to offload some or all of their processing and storage requirements to the cloud infrastructure, on the go. This convergence between cloud computing technologies and the convenience of mobile devices offers improved performance of mobile systems and superior user experience. The topic of ubiquitous mobile cloud draws on inspirational ideas from many diverse domains including cloud computing, wireless technologies, context-aware computing, mobile commerce, location-based services, and vehicular networks.

The global mobile application market is booming and business giants, viz. Google and Apple, have acknowledged the huge expansion in their respective application market. There is a demand though for a system that can elevate the momentum of context-aware mobile applications, where application behavior can be customized according to various context information. This paper proposes AppaaS, a context-aware system that provides mobile applications as a service. AppaaS handles various context information to provision the best relevant mobile application to such a context. AppaaS also supports state preservation, where application-specific data is stored for future references. Our prototype demonstrates an agile system performance with respect to finding relevant applications to a specific context and controlling the applications functions according the users requirements and access privileges.

Mobile devices with their various form factors have become the most convenient and pervasive computing platform, whether to carry out everyday business or to get online. Mobile users tend to adopt the fast food trend even in consuming online mobile services and functionalities. The Web service approach promises great flexibility in offering software functionality over the network, while maintaining interoperability between heterogeneous platforms. However, the diversity that exists in mobile devices and their platforms with variations in capabilities present unique challenges in developing services that can accommodate such diversity. Recent years have witnessed the rise of user-facing service developments that can be consumed on the go with standard interface, such as RESTful Web services. However, the discovery of such services does not match their growing popularity. In addition, existing discovery approaches lack supporting mechanisms that ensure the proper functioning of discovered services within the user context and failing to match personal preferences. This paper introduces personalized Web service discovery for mobile environments. Preliminary results show that incorporating user preferences and context significantly improves the overall precision of service discovery.

This paper introduces personal mobile Web services, a new user-centric architecture that enables service-oriented interactions among mobile devices that are controlled via user-specified authorization policies. Personal mobile Web services exploit the user's contact list (ranging from phonebook to social lists) in order to publish and discover Web services while placing users in full control of their own personal data and privacy. We present a proof-of-concept implementation of an example personal mobile Web service to demonstrate the usefulness and feasibility of the concept.

Recent advancements in the design of mobile devices and wireless technologies have produced a successful coupling of mobile devices and Web services, where mobile devices can be a service provider or a consumer. However, finding relevant Web services that match requests remain a major hindrance to its booming. The challenges facing Web service discovery are further magnified by the stringent constraints of mobile devices, and the inherit complexity of wireless heterogeneous networks. While significant research has focused on service discovery protocols in isolation, they mostly lack a holistic capacity to address the different limitations collectively. We introduce a novel discovery framework that addresses all aspects of mobile Web service discovery, yet does not jeopardize the efficiency requirement for this discovery; especially as an application run in resource- constrained environments.

The increasing use of the Web for everyday tasks is making Web services an essential part of the Internet customer's daily life. Users query the Internet for a required Web service and get back a set of Web services that may or may not satisfy their request. To get the most relevant Web services that fulfill the user's request, the user has to construct the request using the keywords that best describe the user's objective and match correctly with the Web Service name or location. Clustering Web services based on function similarities would greatly boost the ability of Web services search engines to retrieve the most relevant Web services. This paper proposes a novel technique to mine Web Service Description Language (WSDL) documents and cluster them into functionally similar Web service groups. The application of our approach to real Web services description files has shown good performance for clustering Web services based on function similarity, as a predecessor step to retrieving the relevant Web services for a user request by search engines.

The choice of SC-FDMA for uplink access in Long Term Evolution (LTE) facilitates great flexibility in allocating medium resources to users while adapting to medium condition. A multicarrier multiple access technique, SC-FDMA gains an advantage over OFDMA in that it reduces the energy requirements in user equipment. 3GPP Releases 8 and 9, however, do not detail a specific scheduler and, accordingly, proposals have been made in the literature in designing an efficient and capable uplink scheduler for LTE. This paper presents a preliminary performance evaluation for representative proposals, and offers medium of comparison in order to highlight the individual characteristics of each proposals.