Integrated sensing and communication (ISAC) has recently emerged as a viable technique for establishing sensing and communication using the same resources. Nonetheless, the operation of ISAC networks is often challenged by the absence of a direct link between the sensing node and the targets, and by the risk of disclosing confidential data to malicious targets when using the same signal for both tasks. In this paper, a robust reconfigurable intelligent surface (RIS)-aided scheme for securing a full-duplex (FD) ISAC network is proposed. The considered network consists of uplink and downlink users served in FD through a multi-antenna dual-functional radar communication base station (BS), which employs co-located multi-antenna communication-radar arrays to detect multiple malicious targets while preserving communication secrecy in their presence. Additionally, the BS utilizes an optimized artificial noise (AN) that serves to disrupt the malicious targets’ reception and increase the sensing illumination power. By optimally designing the RIS phase shifts, transmit beamforming matrix, AN covariance matrix, and uplink users’ transmit power and combining vectors using an alternating optimization-based algorithm, the network’s sensing performance is maximized under secrecy and total power constraints. Numerical results present the proposed scheme’s efficacy, particularly when a direct link between the BS and the various nodes/targets is absent.

Understanding human gaze communication from a video is critical for decoding complex social interactions in dynamic, real-world environments. Existing gaze communication models focus on a single interaction, such as mutual gaze or shared attention, leaving the full spectrum of dyadic gaze states unaddressed. Unlike low-level gaze tracking that focuses on eye movement anatomy, this work addresses high-level gaze behaviors such as mutual gaze, referential gaze, and shared attention, which reflect the social-cognitive functions of gaze in multi-agent contexts. To this end, a spatiotemporal transformerbased framework is proposed, which involves human-object detection and tracking, gaze-following prediction, and a robust spatiotemporal transformer architecture for fine-grained classification and localization of these gaze behaviors. Moreover, the proposed model incorporates human gaze information, which provides explicit, fine-grained cues about each individual’s focus of attention, allowing more precise alignment of visual features with underlying social intent. Evaluated on a benchmark dataset, the proposed model substantially improves over strong graph-based and transformer-based baselines, particularly in accurately identifying rare yet socially meaningful gaze behaviors. This study contributes a scalable architecture for multi-class gaze analysis, supporting socially aware AI systems in healthcare through applications like autism screening and social engagement assessment, as well as in robotics and behavioral science.

Autistic children often face challenges in reciprocal communication leading to difficulties with social turn-taking (STT), affecting their social interactions. Prior technical interventions show limitations in personalization and sensory adaptability, while also exhibiting scalability constraints. However, recent advances in generative artificial intelligence (GenAI) offer the opportunity to develop adapted tools. Therefore, this Ph.D. work aims to design and evaluate a GenAI-driven, gamified tool to support STT in reciprocal communication for verbal autistic children. The Gamified Adaptive Interaction Platform (GAIP) integrates GenAI personalization with gamification. This research will deliver this key contribution: a novel methodology for adaptive STT interventions using multimodal behavioural sensing to support reciprocal communication. GAIP plans to advance autism interventions through scalable, adaptive AI, advancing HCI and autism inclusion.

Satellite communication is expected to play a key role in future networks due to its ability to deliver wide-area coverage and high-capacity links. Inter-satellite communication (ISC), which facilitates real-time data exchange between satellites, is therefore critical for important satellite applications such as navigation, earth observation, and defense. However, the broadcast nature of the wireless medium renders ISC vulnerable to various security threats. In this paper, we investigate impersonation attack scenarios in LEO ISC and propose a novel machine learning (ML)-based physical layer authentication (PLA) scheme. The proposed method leverages Doppler frequency shift (DFS) features, arising from relative satellite motion, to enable secure authentication of the transmitting satellite. To address the challenge of acquiring ground-truth labels, we employ a long short-term memory (LSTM) network to learn temporal patterns from the satellite dynamics. A synthetic dataset simulating a 30-day mission involving three satellites (two legitimate and one malicious) is generated using a MATLAB-based orbital propagation method, incorporating 3D position and velocity vectors. The LSTM model is trained on 25 days of data from legitimate satellites and evaluated over the remaining 5 days using both legitimate and malicious transmissions. Authentication is performed via binary hypothesis testing, and we derive tractable analytical expressions for the false alarm and missed detection probabilities and validate the results through simulations.

In this paper, a robust pinching antenna-based scheme for ensuring secure wireless communication systems is proposed. In the presence of several malicious eavesdroppers targeting the legitimate signal of various genuine users, the designed approach exploits the spatial flexibility of a pinchingantennas system (PAS) composed of several waveguides and pinching antennas to provide secure communication to legitimate nodes. In particular, multiple pinching antennas can be positioned in each waveguide spanning a long distance, providing additional degrees of freedom and flexibility to adjust the channel response with respect to the various users and eavesdroppers. By virtue of semidefinite programming, an optimization problem aiming at optimizing the transmit beamforming to minimize the total transmit power, subject to secrecy constraints, is formulated and solved. The obtained results demonstrate the total transmit power reduction by increasing the number of antennas and waveguides subject to the same secrecy constraints. Furthermore, the proposed scheme outperforms the benchmark one, consisting of an array of co-located transmit antennas at the base station, when either a direct link from the latter to the users is blocked or when the eavesdroppers are located in the line of sight of the legitimate users.

In this paper, a robust and secure cooperative integrated sensing and communication (ISAC) scheme is proposed and analyzed. The considered scheme exploits multiple dual-functional radar communication (DFRC) base stations (BSs) in order to (i) better illuminate the sensed environment and increase the target detection performance, and (ii) ensure secure communication with respect to several malicious targets. The cluster of cooperating BSs beamform the confidential signals beams to the receiving legitimate users as well as an artificial noise (AN) signal to the set of malicious targets, whereby the AN signal is designed for sensing malicious targets and safeguarding confidential signals from being leaked to the latter nodes, acting as eavesdroppers. By optimizing the transmit beamforming and AN covariance matrices at each of the DFRC BSs, the network’s sensing performance is maximized subject to a minimal secrecy capacity and power constraints. The obtained results demonstrate the proposed cooperative ISAC scheme’s potential in enhancing the sensing performance compared to the baseline (i) single-BS DFRC-ISAC scheme and (ii) cooperative DFRC-ISAC employing a zero-forcing beamforming.

In this paper, a robust reconfigurable intelligent surface (RIS)-aided carrier frequency offset (CFO)-based physical layer authentication (PLA) scheme for wireless networks is proposed. The considered network consists of a legitimate transmitter, a spoofer, and a receiver, acting as an authenticator, who aims to identify the sender's legitimacy relying on the estimated CFO from received signals. Thus, the proposed scheme exploits an RIS to increase the received signal-to-noise ratio (SNR) and enhance the authentication performance. A deep reinforcement learning framework is developed to jointly optimize the RIS phase shifts and the preamble length to maximize the authentication performance under a minimal channel capacity constraint. Then, a supervised machine learning classifier is employed for node authentication, exploiting the optimized RIS reflection and preamble length. The results show that the authentication performance is enhanced with the increase in the RIS size and the difference between the transmitters' CFOs. Also, the proposed scheme outperforms the baseline RIS-aided CSI-based one in mobility scenarios.

In this paper, a robust enhanced Sybil attack detection scheme is proposed using both the Doppler shift and received signal strength (RSS) as physical layer parameters to identify Sybil nodes in a mobile network. The proposed scheme employs the absolute value of the difference between Doppler shift and RSS values for all pairs of nodes as test statistics, where threshold-based statistical hypothesis testing is performed to detect Sybil nodes. A performance evaluation of the scheme is provided in terms of its true positive rate (TPR) and false positive rate (FPR), and where an approximate expression for both metrics is provided for the particular two-user case. The proposed scheme yields a significant security enhancement compared to its single-attribute Doppler shift- and RSS-based schemes, where the proposed scheme's TPR manifests an increase surpassing 32% and 255%, with respect to the two aforementioned schemes, respectively. The performance evaluation shows the potential of incorporating multiple channel-based features for a robust Sybil attack detection scheme in mobile networks.

In this article, a robust reconfigurable intelligent surface (RIS)-aided physical layer authentication (PLA) scheme is proposed. The designed scheme leverages carrier frequency offset (CFO) as a hardware-based attribute for authentication and RIS’s reflective elements tunability to ensure an enhanced received signal-to-noise ratio at the authenticator in a wireless mesh network, resulting in improved authentication performance. Under the presence of a malicious eavesdropper in the network, and by leveraging semidefinite programming, the RIS phase-shifting optimization problem is solved, where a near-optimal RIS configuration maximizing the authentication performance (mitigating impersonation attacks) while fulfilling a minimal secrecy capacity (SC) value with respect to the eavesdropping attack is obtained. The obtained results show an enhanced authentication performance by the increase in the RIS size or the CFO difference between the pair of legitimate and illegitimate transmitters. Furthermore, it is shown that the proposed scheme achieves an authentication-confidentiality performance balance where the proposed scheme outperforms the benchmark one, maximizing the SC, in terms of authentication performance at the cost of a certain SC loss.

In this paper, a robust machine learning (ML)-based scheme for Sybil attack detection in mobile networks is proposed. The proposed scheme exploits three physical-layer features, namely the Doppler shift, received signal strength (RSS), and channel state information (CSI) for identifying Sybil nodes. By employing a Bayesian optimization method, an optimized Random Forest ML classifier is utilized for the classification phase by exploiting the estimated and processed physical-layer attributes, yielding an efficient node classification and Sybil attack detection in a mobile network. A thorough performance evaluation of the proposed scheme is performed in terms of its receiver operating characteristic (ROC) curve, demonstrating higher node classification accuracy gains. Furthermore, the proposed scheme outperforms its benchmark schemes, namely the single- and dual-attribute schemes and the three-features hypothesis-based one. Specifically, the proposed scheme improves the true positive rate (TPR) by 12.5% compared to its dual-feature RSS-Doppler shift-based counterpart, and enhances the Doppler shift-, RSS-, and CSI-based single-attribute ones by 216%, 137%, and 36%, respectively, in terms of the TPR.

Abstract In intelligent systems for real-time security and safety monitoring, the proliferation of surveillance cameras has fueled a growing interest in using deep learning-based artificial intelligence (AI) models for violence detection. Most current approaches consider violence detection as a video classification task, overlooking the fact that violent activities occur within relatively small spatiotemporal regions. Moreover, these activities depend on relationships among multiple such regions, making a single region analysis inadequate, especially for larger-scale violence. This paper proposes a novel temporal–spatial attention framework inspired by human visual perception, which dynamically focuses on multiple informative regions across space and time. By learning where, when, and for how long to attend within a video, using dynamic three-dimensional attention prediction networks, the model captures complex patterns of violent behavior more effectively. Experiments on four public benchmark datasets and a real-world dataset created for this study demonstrate that the proposed approach outperforms existing methods in accuracy and interpretability.

Abstract Food computing has emerged as a promising research field, employing artificial intelligence, deep learning, and data science methodologies to enhance various stages of food production pipelines. To this end, the food computing community has compiled a variety of data sets and developed various deep-learning architectures to perform automatic classification. However, automated food classification presents a significant challenge, particularly when it comes to local and regional cuisines, which are often underrepresented in available public-domain data sets. Nevertheless, obtaining high-quality, well-labeled, and well-balanced real-world labeled images is challenging since manual data curation requires significant human effort and is time-consuming. In contrast, the web has a potentially unlimited source of food data but tapping into this resource has a good chance of corrupted and wrongly labeled images. In addition, the uneven distribution among food categories may lead to data imbalance problems. All these issues make it challenging to create clean data sets for food from web data. To address this issue, we present AutoCleanDeepFood, a novel end-to-end food computing framework for regional gastronomy that contains the following components: (i) a fully automated pre-processing pipeline for custom data sets creation related to specific regional gastronomy, (ii) a transfer learning-based training paradigm to filter out noisy labels through loss ranking, incorporating a Russian Roulette probabilistic approach to mitigate data imbalance problems, and (iii) a method for deploying the resulting model on smartphones for real-time inferences. We assess the performance of our framework on a real-world noisy public domain data set, ETH Food-101, and two novel web-collected datasets, MENA-150 and Pizza-Styles. We demonstrate the filtering capabilities of our proposed method through embedding visualization of the feature space using the t-SNE dimension reduction scheme. Our filtering scheme is efficient and effectively improves accuracy in all cases, boosting performance by 0.96, 0.71, and 1.29% on MENA-150, ETH Food-101, and Pizza-Styles, respectively.

This paper explores downlink Cooperative Rate-Splitting Multiple Access (C-RSMA) in a multi-cell wireless network with the assistance of Joint-Transmission Coordinated Multipoint (JT-CoMP). In this network, each cell consists of a base station (BS) equipped with multiple antennas, a cell-center user (CCU), and a cell-edge user (CEU) located at the edge of adjacent cells. Through JT-CoMP, all BSs collaborate to simultaneously transmit the data to all users including the CCUs and CEU. To enhance the signal quality for the CEU, CCUs relay the common stream to the CEU by operating in half-duplex (HD) relaying mode. We aim to jointly optimize the beamforming vectors at the BS, the allocation of common stream rates, the transmit power at relaying users, i.e., CCU s, and the time slot fraction aiming to maximize the minimum achievable data rate. The formulated problem is non-convex and challenging to solve directly. To address this, we employ change-of-variables, first-order Taylor approximations and a low-complexity algorithm based on Successive Convex Approximation (SCA). We demonstrate the efficacy of the proposed scheme, in terms of average achievable data rate, and we compare its performance to that of four baseline schemes, including HD cooperative non-orthogonal multiple access (C-NOMA), NOMA, and RSMA without user cooperation. The results show improvements of 12% and 41 % over RSMA and HD C-NOMA, respectively in high channel disparity between the BS and UEs.

The Internet of Things (IoT) is a popular technology that refers to a network of internet-connected physical devices that interact to perform tasks with minimal human intervention. However, as these networks expand, ensuring their security becomes challenging due to the communication broadcasting nature and extensive data exchanges. Traditional cryptographic security methods may not be optimal due to the constrained resources of loT devices. In this study, we propose a novel secure key distribution scheme from a physical layer perspective suitable for an loT environment. The proposed scheme takes advantage of the availability of Channel State Information (CSI) at both ends of the communication to enhance security. Specifically, CSI is utilized to precode the key symbols during the key distribution process. Additionally, the scheme employs the xor operation to add an extra layer of difficulty for potential eavesdroppers that attempt to retrieve the transmitted key symbols. The performance of the proposed scheme is evaluated in terms of Key Error Rate (KER) at legitimate nodes and eavesdroppers by using Monte Carlo simulations.

Unmanned aerial vehicles (UAV), also known as drones, is an aircraft without a human pilot onboard and controlled simultaneously by computers remotely. UAVs have been employed in different applications which include fire fighting, security, data coverage, and information transformation. UAVs represent a key technology for next-generation wireless networks that support internet of things (IoT) systems and smart cities. However, one of the bottlenecks of UAV communications systems is power consumption. Most of the UAV energy is consumed on the propulsion part which affects the ability of the UAV to transfer information. Energy harvesting can be incorporated into UAV systems to reduce network operating costs and carbon footprints. Hence, we formulate a trajectory optimization problem for UAV-based communications systems powered by energy harvesting. Then, we provide a solution based on convex optimization to tackle the UAV energy efficiency constraint. Indeed, this paper presents an energy-efficient scheme based on simultaneously powering a UAV with solar energy and optimizing the trajectory to increase the energy efficiency of the drone. This approach has not only been shown to increase the energy efficiency of the drone but also decrease the carbon footprints. Numerical simulations are done to show the efficiency of the proposed scheme.

Reconfigurable Intelligent Surfaces (RISs) have shown great prospects in securing mmWave communication from potential eavesdropping by configuring reflecting elements to strengthen the signal strength at the desired location and creating nulls at potential eavesdropping locations. Acquiring perfect channel information is crucial for optimizing RIS configuration; however, obtaining such information is costly and, as a result, should be performed sparingly. This work studies the impact of the age of channel information on the secrecy performance of a RIS-assisted mmWave network. In particular, we investigate how outdated channel information affects the joint optimization of transmit beamforming and RIS configuration. In our Monte-Carlo simulations, we first identify the factors influencing the aging process of a RIS-assisted mmWave channel in both the near and far fields of the RIS. Subsequently, we examine the impact of channel aging on secrecy capacity and demonstrate that adequate secrecy capacity can still be achieved even when channel information is slightly outdated, thus reducing the need for frequent RIS configuration.

In this paper, we tackle the issue of moral hazard within the realm of the vehicular Metaverse. A pivotal facilitator of the vehicular Metaverse is the effective orchestration of its market elements, primarily comprised of sensing internet of things (SIoT) devices. These SIoT devices play a critical role by furnishing the virtual service provider (VSP) with real-time sensing data, allowing for the faithful replication of the physical environment within the virtual realm. However, SIoT devices with intentional misbehavior can identify a loophole in the system post-payment and proceeds to deliver falsified content, which cause the whole vehicular Metaverse to collapse. To combat this significant problem, we propose an incentive mechanism centered around a reputation-based strategy. Specifically, the concept involves maintaining reputation scores for participants based on their interactions with the VSP. These scores are derived from feedback received by the VSP from Metaverse users regarding the content delivered by the VSP and are managed using a subjective logic model. Nevertheless, to prevent “good” SIoT devices with false positive ratings to leave the Metaverse market, we build a vanishing-like system of previous ratings so that the VSP can make informed decisions based on the most recent and accurate data available. Finally, we validate our proposed model through extensive simulations. Our primary results show that our mechanism can efficiently prevent malicious devices from starting their poisoning attacks. At the same time, trustworthy SIoT devices that had a previous miss-classification are not banned from the market.

This paper explores a novel Neural Network (NN) architecture suitable for Beamformed Fingerprint (BFF) localization in a millimeter-wave (mmWave) multiple-input multiple-output (MIMO) outdoor system. The mmWave frequency bands have attracted significant attention due to their precise timing measurements, making them appealing for applications demanding accurate device localization and trajectory estimation. The proposed NN architecture captures BFF sequences originating from various user paths, and through the application of learning mechanisms, subsequently estimates these trajectories. Specifically, we propose a method for trajectory estimation, employing a transformer network (TN) that relies on attention mechanisms. This TN-based approach estimates wireless device trajectories using BFF sequences recorded within a mmWave MIMO outdoor system. To validate the efficacy of our proposed approach, numerical experiments are conducted using a comprehensive dataset of radio measurements in an outdoor setting, complemented with ray tracing to simulate wireless signal propagation at 28 GHz. The results illustrate that the TN-based trajectory estimator outperforms other methods from the existing literature and possesses the ability to generalize effectively to new trajectories outside the training dataset.

Abstract In recent years, crowd behavior detection has posed significant challenges in the realm of public safety and security, even with the advancements in surveillance technologies. The ability to perform real-time surveillance and accurately identify crowd behavior by considering factors such as crowd size and violence levels can avert potential crowd-related disasters and hazards to a considerable extent. However, most existing approaches are not viable to deal with the complexities of crowd dynamics and fail to distinguish different violence levels within crowds. Moreover, the prevailing approach to crowd behavior recognition, which solely relies on the analysis of closed-circuit television (CCTV) footage and overlooks the integration of online social media video content, leads to a primarily reactive methodology. This paper proposes a crowd behavior detection framework based on the swin transformer architecture, which leverages crowd counting maps and optical flow maps to detect crowd behavior across various sizes and violence levels. To support this framework, we created a dataset comprising videos capable of recognizing crowd behaviors based on size and violence levels sourced from CCTV camera footage and online videos. Experimental analysis conducted on benchmark datasets and our proposed dataset substantiates the superiority of our proposed approach over existing state-of-the-art methods, showcasing its ability to effectively distinguish crowd behaviors concerning size and violence level. Our method’s validation through Nvidia’s DeepStream Software Development Kit (SDK) highlights its competitive performance and potential for real-time intelligent surveillance applications. Graphical abstract

Cardiac arrhythmia is one of the prime reasons for death globally. Early diagnosis of heart arrhythmia is crucial to provide timely medical treatment. Heart arrhythmias are diagnosed by analyzing the electrocardiogram (ECG) of patients. Manual analysis of ECG is time-consuming and challenging. Hence, effective automated detection of heart arrhythmias is important to produce reliable results. Different deep-learning techniques to detect heart arrhythmias such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, and Hybrid CNN-LSTM were proposed. However, these techniques, when used individually, are not sufficient to effectively learn multiple features from the ECG signal. The fusion of CNN and LSTM overcomes the limitations of CNN in the existing studies as CNN-LSTM hybrids can extract spatiotemporal features. However, LSTMs suffer from long-range dependency issues due to which certain features may be ignored. Hence, to compensate for the drawbacks of the existing models, this paper proposes a more comprehensive feature fusion technique by merging CNN, LSTM, and Transformer models. The fusion of these models facilitates learning spatial, temporal, and long-range dependency features, hence, helping to capture different attributes of the ECG signal. These features are subsequently passed to a majority voting classifier equipped with three traditional base learners. The traditional learners are enriched with deep features instead of handcrafted features. Experiments are performed on the MIT-BIH arrhythmias database and the model performance is compared with that of the state-of-art models. Results reveal that the proposed model performs better than the existing models yielding an accuracy of 99.56%.

A co-design process involving autistic children can provide a substantial benefit and optimal utilization of technologies to an off-the-shelf design-based one. Having a voice and making a contribution plays a major role in the co-design process. Yet autistic children exhibit varying communication and social skill and some of them may be minimally verbal or non-verbal. For these reasons, harmonizing the techniques of the co-design process with autistic children with varying characteristics requires detailed and careful consideration. To understand the techniques of the co-design process that accommodates all categories of autistic children, a systematic review of a co-design process involving autistic children was conducted, using six large databases (Scopus, ACM Digital Library, ScienceDirect, IEEE Xplore, SpringerLink, and Google Scholar). The search result includes 2482 papers of which only 82 met the inclusion criteria. The result of the data extraction analysis collection is classified according to techniques for accommodating autistic children of varying characteristics, the challenges encountered, and methods of minimizing those challenges. The review identifies four prominent themes within co-design research for autism: advances in co-design objectives and outcomes, participant recruitment determinants, core co-design methods, and the management of co-design challenges. Highlighting the need for inclusivity and equitable support, the study proposes recommendations for better integration of diverse communication abilities and multiple diagnoses in the co-design process, underlining the importance of adaptive technologies and methods to accommodate the needs of all children.

The pervasiveness of the Internet of Things (IoT) in our daily lives has been remarkably increasing over the past years. Due to their massive connectivity and limited resources, ensuring decent security levels for these networks has been challenging. In this article, a novel and efficient physical layer key exchange scheme for IoT devices is proposed. The proposed scheme leverages on the well-known index modulation (IM) technique for the key exchange process by exploiting IM-based selected carrier frequency indices at the legitimate transceiver pairs (i.e., Alice and Bob) to exchange key symbols. Additionally, a random power level selection along with channel precoding is performed for each symbol transmission to enhance the secrecy level against potential eavesdroppers. The performance of the proposed scheme is analyzed based on the upper-bound expression for the key error probability (KEP) metric. As compared to the benchmark scheme, results reveal a promising performance in the KEP, where a minimum of 10 dBW can be gained at the legitimate node, while the KEP at the eavesdropper is kept close to one regardless of its channel conditions. Moreover, extensive numerical results corroborate the accuracy of the derived mathematical framework and endorse the proposed scheme’s robustness under the existence of a smart and powerful adversarial node.

The rapid growth of Internet of Things (IoT) networks brings new security challenges for service providers. Due to the resource constrained nature of IoT networks, conventional security methods are not always suitable. Therefore, physical layer security (PLS) has come to the forefront, providing a high level of security while respecting the limited resources of IoTs. A Sybil attack is an insider attack in which a malicious node illegitimately fakes multiple identities, to impersonate legitimate nodes in the IoT network. This study introduces a novel Sybil attack detection scheme for mobile IoT networks that corresponds to time-varying channel. doppler-shift caused by mobile IoT nodes is considered as a novel detection metric to identify available Sybil attacks. The proposed scheme is analyzed by both the true positive rate and the false positive rate, which are mathematically formulated to verify the simulation results. Results demonstrate that as the randomness in the mobility pattern of IoT nodes increases, the proposed detection mechanism based on doppler-shift offers improved identification of the Sybil nodes. Moreover, this work provides receiver operating characteristics (RoCs) for mobile IoT networks to evaluate the effect of different system parameters, including carrier frequency, velocity, subcarrier spacing (SCS), and the size of cyclic prefix (CP). The performance of the proposed scheme improves with an increase in both the carrier frequency and velocity, as the doppler-shift becomes more pronounced.

This paper investigates the channel aging problem of mobile light-fidelity (LiFi) systems. In the LiFi physical layer, the majority of the optimization problems for mobile users are non-convex and require the use of dual decomposition or heuristics techniques. Such techniques are based on iterative algorithms, and often cause a high processing delay at the physical layer. Hence, the obtained solutions are rendered sub-optimal since the LiFi channels are evolving. In this paper, a proactive-optimization (PO) approach that can alleviate the LiFi channel aging problem is proposed. The core idea is to design a long-short-term-memory (LSTM) network that is capable of predicting posterior positions and orientations of mobile users, which can be then used to predict their channel coefficients. Consequently, the obtained channel coefficients can be exploited to derive near-optimal transmission-schemes prior to the intended service-time, which enables real-time service. Through various simulations, the performance of the designed LSTM model is evaluated in terms of prediction error and inference complexity, as well as its application in a practical LiFi optimization problem.

Honeypot technologies provide an effective defense strategy for the Industrial Internet of Things (IIoT), particularly in enhancing the Advanced Metering Infrastructure’s (AMI) security by bolstering the network intrusion detection system. For this security paradigm to be fully realized, it necessitates the active participation of small-scale power suppliers (SPSs) in implementing honeypots and engaging in collaborative data sharing with traditional power retailers (TPRs). To motivate this interaction, TPRs incentivize data sharing with tangible rewards. However, without access to an SPS’s confidential data, it is daunting for TPRs to validate shared data, thereby risking SPSs’ privacy and increasing sharing costs due to voluminous honeypot logs. These challenges can be resolved by utilizing Federated Learning (FL), a distributed machine learning (ML) technique that allows for model training without data relocation. However, the conventional FL algorithm lacks the requisite functionality for both the security defense model and the rewards system of the AMI network. This work presents two solutions: first, an enhanced and cost-efficient FedAvg algorithm incorporating a novel data quality measure, and second, FedPot, the development of an effective security model with a fair incentives mechanism under an FL architecture. Accordingly, SPSs are limited to sharing the ML model they learn after efficiently measuring their local data quality, whereas TPRs can verify the participants’ uploaded models and fairly compensate each participant for their contributions through rewards. Moreover, the proposed scheme addresses the problem of harmful participants who share subpar models while claiming high-quality data through a two-step verification approach. Simulation results, drawn from realistic mircorgrid network log datasets, demonstrate that the proposed solutions outperform state-of-the-art techniques by enhancing the security model and guaranteeing fair reward distributions.

Abstract Detecting the attention of children with autism spectrum disorder (ASD) is of paramount importance for desired learning outcome. Teachers often use subjective methods to assess the attention of children with ASD, and this approach is tedious and inefficient due to disparate attentional behavior in ASD. This study explores the attentional behavior of children with ASD and the control group: typically developing (TD) children, by leveraging machine learning and unobtrusive technologies such as webcams and eye-tracking devices to detect attention objectively. Person-specific and generalized machine models for face-based, gaze-based, and hybrid-based (face and gaze) are proposed in this paper. The performances of these three models were compared, and the gaze-based model outperformed the others. Also, the person-specific model achieves higher predictive power than the generalized model for the ASD group. These findings stress the direction of model design from traditional one-size-fits-all models to personalized models.

In this paper, we propose a Deep Reinforcement Learning (DRL) framework to optimize the secrecy performance of a Multi-User (MU)-Multiple-Input Single-Output (MISO) Underwater Optical Wireless Communication (UOWC) system. The network consists of several light-emitting diodes connected with various underwater users through optical beams. The legitimate transmission is threatened by several eavesdroppers attempting to overhear the confidential message sent to each user. Thus, digital precoding is employed to cancel the inter-user interference and maximize the per-user secrecy rate and, consequently, the secrecy sum rate (SSR). Leveraging the developed DRL algorithm, the MU-MISO precoding matrix is optimized for enhancing the system's SSR. Numerical results show the superiority of the proposed DRL framework compared to the baseline zero-forcing and random pre coding schemes, even with corrupted CSI at the transmitter due to seawater dynamics and estimation errors.

In children with autism spectrum disorders (ASD), attention assessment plays a crucial role in understanding their behavioral and cognitive functioning. Difficulties with attention are a common feature of children with autism and have a significant impact on their ability to learn and socialize. In this paper, we propose a non-invasive and objective method to assess attention in children with autism from real videos by utilizing the head poses and motion parameters. The proposed approach is an ensemble of a deep learning model that extracts head pose parameters, an optical flow approach that extracts motion parameters from consecutive frames, temporal head pose parameters extraction and an autoencoder for attention assessment. The experimental study was conducted on 39 children (ASD = 19, neurotypical children = 20) by giving different attention tasks and capturing their video using an attached webcam. Results are analyzed for participant and task differences, which demonstrate that our approach is successful in measuring a child's attention control and inattention. In particular, the assessment of the head poses and motion parameters will enable the development of real-time attention recognition systems that can be used for both learning and targeted intervention.

Advanced Information Communication Technology (ICT) is used in smart grid systems to introduce intelligence and efficiency, potentially outperforming conventional power systems. A fundamental component of a smart grid system is the Smart Meters (SMs), which are integrated with billing utilities, such as national control centers (NCC), and advanced metering infrastructure (AMI). However, like most emerging technologies, some security vulnerabilities and attacks were found. In this paper, we address such vulnerabilities, specifically associated with SMs, that occur when energy consumption is reported to the billing system, specifically through the IEC-60870-5-104(IEC-104) protocol. Since existing datasets do not include sufficient data related to such vulnerabilities, especially in SM with IEC-104 protocol communication, we developed a testbed with a virtual environment and generated a dataset with and without attack vectors. We then proposed a novel anomaly detection algorithm based on LSTM autoencoder, which combines the functional benefits of LSTM and the deep learning of autoencoders. The model's performance is evaluated against two popular attacks, MITM and Replay, and our result shows that the replay attack is harder to find since the attack is executed without data alteration.

Research in underwater communication is rapidly becoming attractive due to its various modern applications. An efficient mechanism to secure such communication is via physical layer security. In this paper, we propose a novel physical layer authentication (PLA) mechanism in underwater acoustic communication networks where we exploit the position/location of the transmitter nodes to achieve authentication. We perform transmitter position estimation from the received signals at reference nodes deployed at fixed positions in a predefined underwater region. We use time of arrival (ToA) estimation and derive the distribution of inherent uncertainty in the estimation. Next, we perform binary hypothesis testing on the estimated position to decide whether the transmitter node is legitimate or malicious. We then provide closed-form expressions of false alarm rate and missed detection rate resulted from binary hypothesis testing. We validate our proposal via simulation results, which demonstrate errors’ behavior against the link quality, malicious node location, and receiver operating characteristic (ROC) curves. We also compare our results with the performance of previously proposed fingerprint mechanisms for PLA in underwater acoustic communication networks, for which we show a clear advantage of using the position as a fingerprint in PLA.

In this study, the instantaneous channel capacity of orthogonal frequency division multiplexing (OFDM) transmission with low carrier frequency offset (CFO) over additive white Gaussian noise (AWGN) channels is obtained by taking advantage of the relationship between average bit error rate (ABER) and average channel capacity (ACC) performance metrics. In other words, the channel capacity of OFDM is investigated using bit error rate performance with a novel measurement method. Moreover, the results are extended to the exact ACC analysis over generalized flat fading channels and the cases of Rayleigh and Nakagami-m flat fading environments are investigated. The proposed closed-form expressions are compared with the well-known Gaussian approximation (GA) method to show their advantage and then verified with numerical results.

In this paper, the secrecy of a dual-hop unmanned aerial vehicle-based wireless communication system, in the presence of mobility and imperfect channel state information (CSI), is investigated. The system consists of a decode-and-forward relay connecting a source and destination node. The transmission is performed under the presence of two eavesdroppers aiming to intercept independently the source-relay and source-destination communication channels. It is assumed that the transmitters are equipped with one transmit antenna, while the receivers have multiple receive antennas. Based on the statistical properties of the per-hop signal-to-noise ratio (SNR), a closed-form formula for the network’s secrecy intercept probability (IP) is derived, in terms of the main system and channel parameters. The results correlate the impact of such parameters on the secrecy level of the system, where the latter can be enhanced by increasing the number of antennas at the legitimate receivers and the average SNRs of the legitimate links. Furthermore, it is shown that as the CSI imperfection level, nodes’ speed, delay, and carrier frequency increase, the system’s secrecy degrades. All the derived results are verified through Monte Carlo simulations.

In this work, we investigate the secrecy performance of reconfigurable intelligent surfaces (RIS)-aided network consisting of two legitimate nodes (i.e., transmitter and receiver) and several passive eavesdroppers. A RIS is installed between the legitimate transmitter and receiver to enhance the received signal quality and, consequently, increase the achievable secrecy rates. Furthermore, we consider a multi-antenna legitimate receiver combining the received signal copies, reaching via the RIS, using the maximal-ratio combining technique. In addition, we assume the presence of a friendly jammer that aims at degrading the eavesdroppers’ links quality. We propose two RIS phase shift configuration strategies, where the RIS is either aligned to the channel of the antenna with the best cascaded channel quality or to a randomly-selected one’s channel. An approximate expression for the system’s secrecy outage probability (SOP) is provided for the second strategy, while extensive numerical simulation results are provided for both proposed schemes, showing the superiority of the former strategy in terms of SOP performance for different values of the number of reflective elements, legitimate receiver antennas, and eavesdroppers.

Twelve lead electrocardiogram signals capture unique fingerprints about the body's biological processes and electrical activity of heart muscles. Machine learning and deep learning-based models can learn the embedded patterns in the electrocardiogram to estimate complex metrics such as age and gender that depend on multiple aspects of human physiology. ECG estimated age with respect to the chronological age reflects the overall well-being of the cardiovascular system, with significant positive deviations indicating an aged cardiovascular system and a higher likelihood of cardiovascular mortality. Several conventional, machine learning, and deep learning-based methods have been proposed to estimate age from electronic health records, health surveys, and ECG data. This manuscript comprehensively reviews the methodologies proposed for ECG-based age and gender estimation over the last decade. Specifically, the review highlights that elevated ECG age is associated with atherosclerotic cardiovascular disease, abnormal peripheral endothelial dysfunction, and high mortality, among many other cardiovascular disorders. Furthermore, the survey presents overarching observations and insights across methods for age and gender estimation. This paper also presents several essential methodological improvements and clinical applications of ECG-estimated age and gender to encourage further improvements of the state-of-the-art methodologies.

Guaranteeing decent secrecy levels in future wireless network generations has gained crucial importance due to the unprecedented increase in wireless connectivity worldwide. In this paper, an enhanced hybrid channel/device-based physical layer authentication (PLA) scheme is proposed. The channel state information (CSI) and device-dependent carrier frequency offset (CFO) are employed to discriminate various malign and benign devices in a wireless network. In particular, CSI-based hypothesis testing (HT) is applied initially on the received authentication requests of several unknown transmitters, relying on legitimate CSI values from previous transmissions to classify such nodes. Then, a second stage takes place using the CFO HT on either the interval containing misclassified legitimate or illegitimate nodes to improve the initial stage’s classification results. Approximate expressions for the authentication and detection probabilities are retrieved, whose tightness is endorsed by extensive Monte Carlo simulations. Results show that the proposed scheme enhances the single-attribute PLA performance (CSI-and CFO-based). Also, the authentication probability improves by the increase in the average legitimate signal-to-noise ratio (SNR) and lower nodes’ speed. In addition, the detection probability rises at high legitimate and intruder links SNRs, while it degrades for low SNR (i.e., noisy attributes observations). Lastly, the more significant the difference between the actual malign and benign nodes’ CFOs, the better the detection probability.

In this article, the physical-layer security of a dual-hop unmanned aerial vehicle-based wireless network, subject to imperfect channel state information (CSI) and mobility effects, is analyzed. Specifically, a source node$(S)$communicates with a destination node$(D)$through a decode-and-forward relay$(R)$, in the presence of two wiretappers$(E_{1}$and$E_{2}$) independently trying to compromise the two hops. Furthermore, the transmit nodes$(S,R) $have a single transmit antenna, while the receivers$(R,D,E_{1},E_{2}) $are equipped with multiple receive antennas. Based on the per-hop signal-to-noise ratios (SNRs) and correlated secrecy capacities’ statistics, a closed-form expression for the secrecy intercept probability (IP) metric is derived, in terms of key system parameters. Additionally, asymptotic expressions are revealed for two scenarios, namely: 1) mobile nodes with imperfect CSI and 2) static nodes with perfect CSI. The results show that a zero secrecy diversity order is manifested for the first scenario, due to the presence of a ceiling value of the average SNR, while the IP drops linearly at high average SNR in the second one, where the achievable diversity order depends on the fading parameters and number of antennas of the legitimate links/nodes. Furthermore, for static nodes, the system can be castigated by a 15-dB secrecy loss at IP$=3\times 10^{-3}$, when the CSI imperfection power raises from 0 to 10−3. Finally, the higher the legitimate nodes’ speed, carrier frequency, delay, and/or relay’s decoding threshold SNR, the worse is the system’s secrecy. Monte Carlo simulations endorse the derived analytical results.

The performance of wireless networks is constrained by the dynamic and random nature of the wireless channels. Intelligent reflecting surface (IRS) is a promising approach that can smartly reconfigure wireless propagation environment to increase the spectral efficiency in 6G networks. However, IRS deployment optimization in a complex and random 6G environment remains a limiting factor in improving the performance. To address the issue, we propose a deep reinforcement learning (DRL) network empowered by a generative adversarial network (GAN) to jointly optimize the IRS placement and reflecting beamforming matrix of IRS as well as the transmit beamforming at the base station (BS) in an IRS-assisted wireless network. Simulation results show that the proposed technique outperforms the benchmark scheme in terms of achievable rate and signal-to-noise ratio (SNR) by learning the optimal IRS locations in an IRS-aided wireless network.

IoT (Internet of Things) networks are becoming an integral part of everyday life. The exponential growth in these networks poses various privacy and security threats for the users and the vendors. Among these threats are Sybil attacks, which occurs due to poor authentication capabilities and thus a malicious node gets access to any information on the host. The malicious node uses its' fake identities to impersonate legitimate nodes and transmit misleading data to the central entity. However, conventional cryptographical approaches are not always suitable for IoT nodes due to the their limited resources. Therefore, physical layer security (PLS) solutions become more and more important for IoT networks. In this regard, this study introduces a novel technique for detecting Sybil attacks in mobile networks, which stands in contrast to the current methods developed for stationary environment, i.e., time-invariant channel. Specifically, this work exploits the Doppler shift caused by the mobility in the environment to identify Sybil nodes in the network. If the nodes belong to the same terminal, they experience the same amount of Doppler shift. The detection performance of the proposed scheme has been evaluated under different system configurations. The obtained results show that the performance of the proposed scheme improves as the amount of Doppler shift increases.

In this paper, we investigate an energy-efficient Long Range (LoRa) wireless network powered by hybrid energy which consists of an energy harvesting source and the grid. The grid allows to compensate for the randomness and intermittency of the harvested energy. The aim is to propose a dynamic energy-efficient resource management scheme for LoRa wireless networks that enables green Internet of Things (IoT). Hence, we formulate a grid energy cost minimization problem subject to minimum received signal-to-noise ratio (SNR), and channel, spreading factor (SF) and energy availability constraints. The formulated problem is simplified and decoupled into two sub-problems which allows to derive the optimal resource management solution but with high computational complexity. Then, we propose a low complexity heuristic channel and SF assignment, and energy management algorithm for dynamic LoRa wireless networks. Numerical results shows the efficient use of renewable energy in green dynamic LoRa wireless networks.

LoRa wireless networks are considered as a key enabling technology for next-generation Internet of Things (IoT) systems. New IoT deployments (e.g., smart city scenarios) can have thousands of devices per square kilometer leading to huge amount of power consumption to provide connectivity. In this article, we investigate green LoRa wireless networks powered by a hybrid of the grid and renewable energy sources, which can benefit from harvested energy while dealing with the intermittent supply. This article proposes resource management schemes of the limited number of channels and spreading factors (SFs) with the objective of improving the LoRa gateway energy efficiency. First, the problem of grid power consumption minimization while satisfying the system’s quality of service demands is formulated. Specifically, both scenarios the uncorrelated and time-correlated channels are investigated. The optimal resource management problem is solved by decoupling the formulated problem into two subproblems: 1) channel and SF assignment problem and 2) energy management problem. Since the optimal solution is obtained with high complexity, online resource management heuristic algorithms that minimize the grid energy consumption are proposed. Finally, taking into account the channel and energy correlation, adaptable resource management schemes based on reinforcement learning (RL) are developed. Simulation results show that the proposed resource management schemes offer efficient use of renewable energy in LoRa wireless networks.

In this article, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base stations (BSs) employs massive multiple-input–multiple-output (MIMO) to serve a set of users powered by independent energy harvesting sources. Since a certain number of users may not be able to participate in FL due to interference and energy constraints, a joint energy management and user scheduling problem in FL over wireless systems is formulated. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To find how the transmit power, the number of scheduled users and user association, affect the training loss, the FL convergence rate is first analyzed. Given this analytical result, the original optimization problem can be decomposed, simplified, and solved. Simulation results show that the proposed user scheduling and user association algorithm can reduce training loss compared to a standard FL algorithm.

Security is a critical issue in Internet of Things (IoT) networks and it has been under investigation by researchers worldwide. Different from other wireless networks, IoT networks suffer from conventional security mechanisms due to complexity and resource consumption which cannot be tolerated in IoT networks. Among the recently proposed security schemes for IoT networks is the tag-embedding message authentication scheme in which a tag is embedded to the modulated message and concurrently sent over the same channel. Although it has avoided significant resource expenditure, its performance still requires improvement especially in terms of immunity against nearby eavesdroppers. In this article, a novel scheme is proposed that is able to enhance the authentication rate and the tag confidentiality without inducing any extra requirements. The proposed scheme implies performing tag puncturing at the transmitter side where only a part of the tag is embedded to the message based on the instantaneous channel phase. The performance of the proposed scheme is mathematically analyzed where the authentication failure probability is derived in closed-form expression, and compared to the conventional tag-embedding scheme.

In this paper, we investigate the dynamic power allocation for a visible light communication (VLC) cellular system consisting of two coordinating attocells, each equipped with one access-point (AP). The coordinated multipoint (CoMP) between the two cells is introduced to assist users experiencing high inter-cell-interference (ICI). Specifically, the coordinated zero-forcing (ZF) precoding is used to cancel the ICI at the users located near the centers of the cells, whereas the joint transmission (JT) is employed to eliminate the ICI at the users located at the edge of both cells and to improve their receptions as well. Furthermore, two multiple access techniques are invoked within each cell, namely, non-orthogonal-multiple-access (NOMA) and cooperative non-orthogonal-multiple-access (C-NOMA). Hence, two multiple access techniques are proposed for the considered multi-user multi-cell system, namely, the CoMP-assisted NOMA scheme and the CoMP-assisted C-NOMA scheme. For each scheme, two power allocation frameworks are formulated each as an optimization problem, where the objective of the former is maximizing the network sum data rate while guaranteeing a certain quality-of-service (QoS) for each user, whereas the goal of the latter is to maximize the minimum data rate among all coexisting users. The formulated optimization problems are not convex, and hence, difficult to be solved directly unless using heuristic methods, which comes at the expense of high computational complexity. To overcome this issue, optimal and low complexity power allocation schemes are derived. In the simulation results, the performance of the proposed CoMP-assisted NOMA and CoMP-assisted C-NOMA schemes are compared with those of the CoMP-assisted orthogonal-multiple-access (OMA) scheme, the C-NOMA scheme and the NOMA scheme, where the superiority of the proposed schemes are demonstrated. Finally, the performance of the proposed schemes and the considered baselines is evaluated while varying various system parameters.

The prevalence of Diabetes mellitus (DM) in the Middle East is exceptionally high as compared to the rest of the world. In fact, the prevalence of diabetes in the Middle East is 17-20%, which is well above the global average of 8-9%. Research has shown that food intake has strong connections with the blood glucose levels of a patient. In this regard, there is a need to build automatic tools to monitor the blood glucose levels of diabetics and their daily food intake. This paper presents an automatic way of tracking continuous glucose and food intake of diabetics using off-the-shelf sensors and machine learning, respectively. Our system not only helps diabetics to track their daily food intake but also assists doctors to analyze the impact of the food in-take on blood glucose in real-time. For food recognition, we collected a large-scale Middle-Eastern food dataset and proposed a fusion-based framework incorporating several existing pre-trained deep models for Middle-Eastern food recognition.

LoRa supports the exponential growth of connected devices. In this paper, we investigate green LoRa wireless networks powered by both the grid power and a renewable energy source. The grid power compensates for the randomness and intermittency of the harvested energy. We propose an efficient and smart resource management scheme of the limited number of channels and spreading factors (SFs) with the objective of improving the LoRa gateway (LG) energy efficiency. We formulate the problem of grid power consumption minimization while satisfying the quality of service demands. The optimal resource management problem is solved by decoupling the formulated problem into two sub-problems: channel and SF assignment problem and energy management problem. Next, we develop an adaptable resource management schemes based on Reinforcement Learning (RL) taking into account the channel and energy correlation. Simulations results show that the proposed resource management schemes offer efficient use of renewable energy in LoRa wireless networks.

In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

Tag-embedded has been proposed in the literature as an efficient message authentication scheme due to low spectrum, power and time resources required as compared to the conventional tag-appending schemes. This work addresses the mathematical analysis of the performance of the tag-embedded message authentication scheme, which has never been presented in the literature. The authentication fail probability, as a performance evaluation metric, has been derived in closed form expressions based on two different detection methods, namely, joint detection and successive detection. The derived formulas are validated through simulation results where exact matching is noted.

Long Range (LoRa) wireless networks, which is made up of low-powered connected devices, is a key technology for next generation wireless networks that support internet of things applications. Specifically, LoRa devices (LDs) may be powered by energy harvesting sources for greening wireless communications systems. Furthermore, LoRa modulation is based on the chirp spreading modulation (CSM) which consists of assigning various orthogonal spreading factors (SFs) among the LDs in the network. Hence, this paper investigates energy-efficient resource allocation in LoRa wireless networks, where the LDs are powered by independent energy harvesting sources. First, the problem of maximizing the number of scheduled LDs under quality of service constraints and making use of the available harvested energy, is formulated. Next, the relationship between the assigned SF, the instantaneous channel coefficients and the available energy at the batteries is analytically established. Hence, the optimal energy management, device scheduling, and SF assignment algorithm is proposed. Simulations results shows that the proposed resource allocation approaches offer efficient use of renewable energy which allows to enhance the rate of successful transmissions.

The massive deployment of IoT devices being utilized by home automation, industrial and military scenarios demands for high security and privacy standards to be achieved through innovative solutions. This paper proposes KaFHCa, a crypto-less protocol that generates shared secret keys by combining random frequency hopping collisions and source indistinguishability independently of the radio channel status. While other solutions tie the secret bit rate generation to the current radio channel conditions, thus becoming unpractical in static environments, KaFHCa guarantees almost the same secret bit rate independently of the channel conditions. KaFHCa generates shared secrets through random collisions of the transmitter and the receiver in the radio spectrum, and leverages on the fading phenomena to achieve source indistinguishability, thus preventing unauthorized eavesdroppers from inferring the key. The proposed solution is (almost) independent of the adversary position, works under the conservative assumption of channel fading (σ=8dB), and is capable of generating a secret key of 128 bits with less than 564 transmissions.

The chirp spreading modulation (CSM) is used as modulation technique for Long Range (LoRa) wireless networks that support internet of things (IoT) systems. However, this transmission scheme is limited in terms of spectral efficiency. Hence, a novel index modulation technique is proposed for CSM wireless communications systems to enhance the spectral efficiency. The proposed scheme is based on using a variety of spreading factors (SFs) in CSM systems in order to convey additional bits. The performance analysis of the proposed scheme is analytically investigated by deriving the symbol error rate. Moreover, the system performance of the proposed scheme may be investigated in terms of symbol error rate (SER) via numerical simulations and its superiority compared to the conventional CSM transmission scheme is shown.

The recent pandemic of COVID-19 has changed the way people socially interact with each other. A huge increase in the usage of social media applications has been observed due to quarantine strategies enforced by many governments across the globe. This has put a great burden on already overloaded cellular networks. It is believed that direct Device-to-Device (D2D) communication can offload a significant amount of traffic from cellular networks, especially during scenarios when residents in a locality aim to share information among them. WiFi Direct is one of the enabling technologies of D2D communications, having a great potential to facilitate various proximity-based applications. In this work, we propose power saving schemes that aim at minimizing energy consumption of user devices across D2D based multi-hop networks. Further, we provide an analytical model to formulate energy consumption of such a network. The simulation results demonstrate that a small modification in the network configuration, such as group size and transmit power can provide considerable energy gains. The observed energy consumption is reduced by 5 times for a throughput loss of 12%. Additionally, we measure the energy per transmitted bit for different configurations of the network. Furthermore, we analyze the behavior of the network, in terms of its energy consumption and throughput, for different file sizes.

It is vital and challenging to devise new efficient transmission techniques for next generation wireless networks that support internet of things (IoT) systems. Long range (LoRa) wireless networks are based on the deployment of connected devices with limited energy and where end-devices need higher data rates. This system is a key technology that enables smart city applications. The chirp spread spectrum is used as the modulation technique for LoRa networks which consists of assigning various orthogonal spreading factors (SF) among the connected devices in the network. In particular, each device uses a fixed SF for data transmission, which is assigned based on its distance from the gateway. This paper proposes a new SF assignment scheme aiming at enhancing the overall performance. In particular, the proposed scheme no longer assigns SFs based on the distance; but instead, it assigns them depending on the instantaneous channel realizations. Such a dynamic assignment of the SFs among LoRa users significantly enhances the overall performance compared to conventional SF assignment schemes. The proposed system is evaluated in terms of symbol error rate (SER) via numerical simulations.

In this paper, we investigate a cell-free massive MIMO system that is compromised of a large number of distributed access points (APs) powered by independent micro-grids, each with different prices. We enable this system with energy exchange capabilities in order to offset the power consumption cost. Moreover, we exploit the cooperation between the APs through energy exchange via a smart grid infrastructure in order to enhance the energy efficiency of massive MIMO systems. Hence, the problem of total grid power consumption minimization has to be solved by efficiently managing the power delivered from different sources while satisfying the system requirements in terms of user quality of service demands. This paper solves the optimal power cooperation and allocation problem using linear programming. In addition, the optimal power allocation problem is solved when neglecting cooperation between APs. Next, a joint AP selection and user scheduling algorithm is devised ensuring the feasibility of the problem. Finally, simulation results show that the proposed power cooperation technique allows to significantly enhance the energy efficiency of cell-free massive MIMO systems.

The concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose‐level. As a consequence, there is an ever‐increasing need for automatic tools able to help diabetics to manage their diet and also help physicians to better analyse the effects of various types of food on the glucose‐level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose‐level using glucose measuring sensors. For food recognition, we rely on several feature extraction and classification techniques individually and jointly using an early and three different late fusion techniques, namely (i) Particle Swarm Optimisation (PSO), (ii) Genetic Algorithms (GA) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several handcrafted and deep features and compare the results against state‐of‐the‐art. In addition, we collect a large‐scale dataset containing images from several types of local Middle‐Eastern food, which is intended to become a powerful support tool for future research in the domain.

We investigate in this paper the energy efficiency of cell-free massive MIMO systems made up of a set of distributed access points, each of which is powered by both an independent energy harvesting source and the grid. The grid energy source allows to compensate for the randomness and intermittency of the harvested energy. Moreover, we enable this system with energy exchange capabilities through a smart-grid infrastructure in order to enhance the energy efficiency of massive MIMO systems. Indeed, the problem of minimizing the grid power consumption has to be solved by efficiently managing the energy delivered from different sources while satisfying the system requirements in terms of users' quality of service demands. First, the optimal offline energy cooperation and management problem is solved using linear programming. Next, we investigate the online energy cooperation and management problem by proposing an efficient online algorithm based on energy prediction. Simulations results shows that the proposed energy cooperation and management approaches offer efficient use of non-renewable energy to compensate the variability of renewable energy in cell-free MIMO systems.

Medical implants are an important part of Wireless Body Area Networks (WBANs) and play an important role to monitor, diagnose, and control various medical conditions. These tiny sensors are injected inside human body to measure and communicate various vital signs of a human body. Since the information transmitted by implants is very sensitive and critical in nature, both availability and confidentiality of such information are of prime importance. A possible security threat in medical implants that can breach the availability of the medical implants is a Denial of Service (DoS) attack. In this work, we propose a solution to mitigate DoS attack in the Medical Implant Communication Service (MICS) network. We propose a three-level trust model for a MICS network based on its environment and couple a threshold of maximum allowed data rate to each environment. The simulation results show that DoS attacks can be seamlessly mitigated in many MICS settings.

People experience mental stress on a daily basis from a variety of different reasons, including environmental reasons (traffic, noise, or bad weather), social reasons (family issues, friends, and financial problems), or from events such as wedding planning or giving a presentation in front of large audience. A manageable amount of stress is healthy and can motivate a person; however, a large amount of continuous stress or a strong response to stress can be harmful. For this reason, the detection of mental stress, as well as its prediction, has become a significant area of research. In this paper, we review and summarize various approaches found in the literature for stress detection using machine learning and suggest directions for future research and interventions.

WiFi direct is a variant of Infrastructure mode WiFi, which is designed to enable direct Device-to-Device (D2D) communications between proximity devices. This new technology enables various proximity-based services such as social networking, multimedia content distribution, cellular traffic offloading, Internet of Things (IoT), and mission critical communications. However, energy consumption of battery-constrained devices remains a major concern in all the aforementioned applications. In this paper, we model energy consumption of the WiFi direct protocol, starting from device discovery to actual data transmissions for intra group D2D communications. We simulate a content distribution scenario in Matlab and analyze our model for the energy consumption of the devices. We argue that the energy spent in device discovery becomes significant in the case of small data sizes. In particular, we find that smaller data sizes, such as 100KB, cause the equal amount of energy to spend in both device discovery and data transmission phases, even when the device discovery time is very small.

The smartphones have evolved a lot during recent years. However, they are still limited in their battery time, computational power and storage space. Mobile Cloud Computing (MCC) has emerged as a promising solution that aims to augment smartphone's capabilities by providing a vast pool of computational power and storage space at cloud data center. In parallel to this, cooperation based computing is a recent concept in MCC that augments smartphone's capabilities by accumulating the computational resources of nearby devices to run a task. In this paper, we discuss different scenarios of computational offloading for a User Equipment (UE) and find an optimal option in terms of its energy consumption and task completion time. In particular, we compare the energy consumption and task completion time of a mobile application for local processing, offloading to a remote cloud and exploiting the cooperation based computing in the local Mobile Cloud (MC).We mark an offloading threshold for different offloading scenarios, so a UE can decide among offloading to a local MC or to a remote cloud, depending upon the size of the task it is offloading.

In this paper, we propose a new methodology for soft forwarding which is based on a novel technique known as soft angular modulation (SAM). This is effective even under poor source-relay link conditions. The new treatment presented here allows a more flexible system design. This makes soft forwarding, which is not practical with current infrastructure, a feasible approach. In this work, we convert soft information from the soft domain into the angular domain. We then forward unity amplitude symbols using wireless fading channels. Due to the analogue nature of the probabilistic content (or soft information), the soft information relaying (SIR) scheme is not treated as a practically feasible relay protocol. We offer a remedy to this by forwarding unity amplitude symbols from the relay. Using the expression of soft noise variance, we deduct an approximate log likelihood ratio (LLR) expression for a parallel relay network employing SAM scheme. It is shown that the derived BER of SAM and numerical BER are closely aligned. The proposed scheme yields improved BER performance as compared to other conventional schemes.

In this paper, we present the network coverage issues for both Femto Users (FUs) and Macro Users (MUs) located at cell edges. The cognitive-femtocell networks functioning under the vicinity of a macrocell frontier where the parameters such as pathloss, shadowing, Rayleigh fading have considered into the system model. The users, located at network border are positioned far apart from the Macro Base Station (MBS)-treated as the underprivileged users. They are to be facilitated by the femto cell base stations to provide uninterrupted QoS. We present an overall outage probability of Single Input single Output (SISO) users and Single Input Multiple Output (SIMO) users, respectively, by taking several circumstantial components such as such as probability density function (PDF), location gap between base stations (BSs) and users, intra-tier interference and inter-tier interference into account. Further, evaluation has been extended by considering network throughput as the efficiency measures based on the sub-carrier and the power allotment in the dual tier network.

In vivo wireless medical devices have a critical role in healthcare technologies due to their continuous health monitoring and noninvasive surgery capabilities. In order to fully exploit the potential of such devices, it is necessary to characterize the in vivo wireless communication channel which will help to build reliable and high-performance communication systems. This paper presents preliminary results of experimental characterization for this fascinating communications medium on a human cadaver and compares the results with numerical studies.

This paper investigates energy efficient in vivo communication with multi-source nodes. In such a network, the in vivo sensor nodes transmit their sensing information to an on-body destination node. Due to the associated high path loss with implant devices, on-body relay nodes can be used to convey the information bits from the in vivo source nodes to the on-body destination node in an energy efficient manner. In this context, the paper objective is to select the optimal on-body relay locations that result in the minimum per bit average energy consumption for the in vivo networks using the minimum number of on-body relay nodes. The problem is formulated as an integer program that can be efficiently solved using commercial optimization solvers. Numerical results demonstrate the significant improvement in energy consumption and quality-of-service (QoS) support, when on-body relays are optimally located.

Abstract This paper focuses on the development of multiuser access schemes for spectrum sharing systems whereby secondary users are allowed to share the spectrum with primary users under the condition that the interference observed at the primary receiver is below a predetermined threshold. In particular, two scheduling schemes are proposed for selecting a user among those that satisfy the interference constraint and achieve an acceptable signal‐to‐noise ratio level. The first scheme focuses on optimizing the average spectral efficiency by selecting the user that reports the best channel quality. In order to alleviate the relatively high feedback required by the first scheme, a second scheme based on the concept of switched diversity is proposed, where the base station (BS) scans the secondary users in a sequential manner until a user whose channel quality is above an acceptable predetermined threshold is found. We develop expressions for the statistics of the signal‐to‐interference and noise ratio as well as the average spectral efficiency, average feedback load, and the delay at the secondary BS. We then present numerical results for the effect of the number of users and the interference constraint on the optimal switching threshold and the system performance and show that our analysis results are in perfect agreement with the numerical results. Copyright © 2014 John Wiley & Sons, Ltd.

The paper presents the improvement offered by spatial diversity to reduce fading in ultra wideband (UWB) body-centric wireless communication channel in context of second order statistics for five different measured links, i.e., waist-to-chest, waist-to-head, waist-to-wrist, waist-to-ankle and waist-to-back. Average fade duration (AFD) and level crossing rate (LCR) values are presented and compared for diversity combined signal with respect to branch signals. In addition AFD and LCR of diversity combined signals are also compared for five different on-body channels and for three different locations in an indoor environment. Result and analysis of second order channel parameters shows the importance of considering these parameters when designing an enhanced body-area network system.

This paper proposes a novel variational approach for proving the extremal entropy inequality (EEI) [1]. Unlike previous proofs [1], [2], the proposed variational approach is simpler and it does not require neither the classical entropy power inequality (EPI) [1], [2] nor the channel enhancement technique [1]. The proposed approach is versatile and can be easily adapted to numerous other applications such as proving or extending other fundamental information theoretic inequalities such as the EPI, worst additive noise lemma, and Cramér-Rao inequality.

In this paper, we develop multiuser access schemes for spectrum sharing systems whereby secondary users are allowed to share the spectrum with primary users under the condition that the interference observed at the primary receiver is below a predetermined threshold. In particular, we devise two schemes for selecting a user among those that satisfy the interference constraint and achieve an acceptable signal-to-noise ratio level. The first scheme selects the user that reports the best channel quality. In order to alleviate the high feedback load associated with the first scheme, we develop a second scheme based on the concept of switched diversity where the base station scans the users in a sequential manner until an acceptable user is found. In addition to these two selection schemes, we consider two power adaptive settings at the secondary users based on the amount of interference available at the secondary transmitter. In the On/Off power setting, users are allowed to transmit based on whether the interference constraint is met or not, while in the full power adaptive setting, the users are allowed to vary their transmission power to satisfy the interference constraint. Finally, we present numerical results for our proposed algorithms where we show the trade-off between the average spectral efficiency and average feedback load for both schemes.