Search

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

The process of team composition in multiplayer sports such as football has been a main area of interest within the field of the science of teamwork, which is important for improving competition results and game experience. Recent algorithms for the football team composition problem take into account the skill proficiency of players but not the interactions between players that contribute to winning the championship. To automate the composition of a cohesive team, we consider the internal collaborations among football players. Specifically, we propose a Team Composition based on the Football Players’ Attributed Collaboration Network (TC-FPACN) model, aiming to identify a cohesive football team by maximizing football players’ capabilities and their collaborations via three network metrics, namely, network ability, network density and network heterogeneity&homogeneity. Solving the optimization problem is NP-hard; we develop an approximation method based on greedy algorithms and then improve the method through pruning strategies given a budget limit. We conduct experiments on two popular football simulation platforms. The experimental results show that our proposed approach can form effective teams that dominate others in the majority of simulated competitions.

Localisation is an important part of many applications. Our motivating scenarios are short-term construction work and emergency rescue. These scenarios also require rapid setup and robustness to environmental conditions additional to localisation accuracy. These requirements preclude the use of many traditional high-performance methods, e.g. vision-based, laser-based, Ultra-wide band (UWB) and Global Positioning System (GPS)-based localisation systems. To overcome these challenges, we introduce iMag+, an accurate and rapidly deployable inertial magneto-inductive (MI) mapping and localisation system, which only requires monitored workers to carry a single MI transmitter and an inertial measurement unit in order to localise themselves with minimal setup effort. However, one major challenge is to use distorted and ambiguous MI location estimates for localisation. To solve this challenge, we propose a novel method to use MI devices for sensing environmental distortions for accurate closing inertial loops. We also suggest a robust and efficient first quadrant estimator to sanitise the ambiguous MI estimates. By applying robust simultaneous localisation and mapping (SLAM), our proposed localisation method achieves excellent tracking accuracy and can improve performance significantly compared with only using a Magneto-inductive device or inertial measurement unit (IMU) for localisation.

We present a fast and precise deep-learning architecture, which we term O-Net, for obtaining super-resolved images from conventional phase-modulated optical microscopical techniques, such as phase-contrast microscopy and differential interference contrast microscopy. O-Net represents a novel deep convolutional neural network that can be trained on both simulated and experimental data, the latter of which is being demonstrated in the present context. The present study demonstrates the ability of the proposed method to achieve super-resolved images even under poor signal-to-noise ratios and does not require prior information on the point spread function or optical character of the system. Moreover, unlike previous state-of-the-art deep neural networks (such as U-Nets), the O-Net architecture seemingly demonstrates an immunity to network hallucination, a commonly cited issue caused by network overfitting when U-Nets are employed. Models derived from the proposed O-Net architecture are validated through empirical comparison with a similar sample imaged via scanning electron microscopy (SEM) and are found to generate ultra-resolved images which came close to that of the actual SEM micrograph.

To further preserve the data privacy of federated learning (FL), we propose a differentially private FL (DPFL) scheme with misaligned power allocation (MPA-DPFL). Unlike most existing over-the-air FL studies, in MPA-DPFL, the gradients are aggregated through over-the-air computation (Aircomp) but do not need to be aligned in the transmission. Therefore, MPA-DPFL can avoid the problem that the signal-to-noise ratio (SNR) of the system is limited by the device with the worst channel condition. We formulate an optimization problem to minimize the optimality gap of MPA-DPFL while guaranteeing a certain degree of privacy protection. Additionally, we demonstrate that the MPA-DPFL is more suitable than the DPFL with aligned power allocation (APA-DPFL) when the channel condition of a device in the system is lower than a threshold. The analytical results are validated through simulation.

The ability of robots to write Chinese strokes, which is recognized as a sophisticated task, involves complicated kinematic control algorithms. The conventional approaches for robotic writing of Chinese strokes often suffer from limited font generation methods, which limits the ability of robots to perform high-quality writing. This paper instead proposes a developmental evolutionary learning framework that enables a robot to learn to write fundamental Chinese strokes. The framework first considers the learning process of robotic writing as an evolutionary easy-to-difficult procedure. Then, a developmental learning mechanism called “Lift-constraint, act and saturate” that stems from developmental robotics is used to determine how the robot learns tasks ranging from simple to difficult by building on the learning results from the easy tasks. The developmental constraints, which include altitude adjustments, number of mutation points, and stroke trajectory points, determine the learning complexity of robot writing. The developmental algorithm divides the evolutionary procedure into three developmental learning stages. In each stage, the stroke trajectory points gradually increase, while the number of mutation points and adjustment altitudes gradually decrease, allowing the learning difficulties involved in these three stages to be categorized as easy, medium, and difficult. Our robot starts with an easy learning task and then gradually progresses to the medium and difficult tasks. Under various developmental constraint setups in each stage, the robot applies an evolutionary algorithm to handle the basic shapes of the Chinese strokes and eventually acquires the ability to write with good quality. The experimental results demonstrate that the proposed framework allows a calligraphic robot to gradually learn to write five fundamental Chinese strokes and also reveal a developmental pattern similar to that of humans. Compared to an evolutionary algorithm without the developmental mechanism, the proposed framework achieves good writing quality more rapidly.

This letter investigates a virtual reality (VR) delivery system, where the original VR contents requested by all users are stored at the macro base station (MBS). To reduce latency, MBS can either transmit the original VR data or the computed VR data to multiple users aided by an intelligent reflecting surface (IRS) to prevent attacks from an eavesdropper with imperfect channel state information (CSI). We jointly optimize the transmission policies, MBS transmit power, IRS phase shift and computing frequency to minimize the latency over all users subject to security constraint. Numerical results validate the robustness of our proposed algorithm.

Human activity recognition based on generated sensor data plays a major role in a large number of applications such as healthcare monitoring and surveillance system. Yet, accurately recognizing human activities is still challenging and active research due to people’s tendency to perform daily activities in a different and multitasking way. Existing approaches based on the recurrent setting for human activity recognition have some issues, such as the inability to process data parallelly, the requirement for more memory and high computational cost albeit they achieved reasonable results. Convolutional Neural Network processes data parallelly, but, it breaks the ordering of input data, which is significant to build an effective model for human activity recognition. To overcome these challenges, this study proposes causal convolution based on performers-attention and supervised contrastive learning to entirely forego recurrent architectures, efficiently maintain the ordering of human daily activities and focus more on important timesteps of the sensors’ data. Supervised contrastive learning is integrated to learn a discriminative representation of human activities and enhance predictive performance. The proposed network is extensively evaluated for human activities using multiple datasets including wearable sensor data and smart home environments data. The experiments on three wearable sensor datasets and five smart home public datasets of human activities reveal that our proposed network achieves better results and reduces the training time compared with the existing state-of-the-art methods and basic temporal models.

In this paper, we present the computation-efficient resource allocation (RA) schemes for millimeter-wave mobile edge computing (mmWave-MEC) system with the aid of reconfigurable intelligent surface (RIS), which is used to assist the uplink communication from the users to the base station (BS). By means of the theoretical analysis, the achievable rate and computation efficiency (CE) are derived. Then, the optimization problem for the CE maximization under the constraints of the minimum rate, maximum power consumption and local CPU frequency is formulated, where the joint design of the hybrid beamforming at the BS and the passive beamforming at the RIS as well as the local resource allocation of each user is carried out. An effective iterative algorithm based on the penalized inexact block coordinate descent (BCD) method is proposed to obtain the computation-efficient RA scheme. Next, a low-complexity suboptimal RA scheme based on the BCD method is proposed, and corresponding algorithm is presented. Simulation results show that the proposed schemes are effective, and high CE can be attained. Moreover, the second scheme can achieve the CE performance close to the first scheme but with lower complexity. Besides, it is effective to deploy the RIS scheme in mmWave-MEC system, which can strike a balance between the CE and energy consumption when compared to the conventional relay schemes. 10.13039/501100001809-Natural Science Foundation of China (Grant Number: 62031017, 61971220 and 61971221); Open Research Fund of State Key Laboratory of MillimeterWaves of Southeast University (Grant Number: K202215).

The outbreak of COVID-19 has attracted people’s attention to our healthcare system, stimulating the advancement of next-generation health monitoring technologies. IoT attracts extensive attention in this advancement for its advantage in ubiquitous communication and sensing. RFID plays a key role in IoT to tackle the challenges in passive communication and identification and is now emerging as a sensing technology which has the ability to reduce the cost and complexity of data collection. It is advantageous to introduce RFID sensor technologies in health-related sensing and monitoring, as there are many sensors used in health monitoring systems with the potential to be integrated with RFID for smart sensing and monitoring. But due to the unique characteristics of the human body, there are challenges in developing effective RFID sensors for human health monitoring in terms of communication and sensing. For example, in a typical IoT health monitoring application, the main challenges are as follows: (1) energy issues, the efficiency of RF front-end energy harvesting and power conversion is measured; (2) communication issues, the basic technology of RFID sensors shows great heterogeneity in terms of antennas, integrated circuit functions, sensing elements, and data protocols; and (3) performance stability and sensitivity issues, the RFID sensors are mainly attached to the object to be measured to carry out identification and parameter sensing. However, in practical applications, these can also be affected by certain environmental factors. This paper presents the recent advancement in RFID sensor technologies and the challenges for the IoT healthcare system. The current sensors used in health monitoring are also reviewed with regard to integrating possibility with RFID and IoT. The future research direction is pointed out for the emergence of the next-generation healthcare and monitoring system.

Steganography is the art of secret communication and steganalysis is the art of detecting the hidden messages embedded in digital media covers. One of the covers that is gaining interest in the field is video. Presently, the global IP video traffic forms the major part of all consumer Internet traffic. It is also gaining attention in the field of digital forensics and homeland security in which threats of covert communications hold serious consequences. Thus, steganography technicians will prefer video to other types of covers like audio files, still images or texts. Moreover, video steganography will be of more interest because it provides more concealing capacity. Contrariwise, investigation in video steganalysis methods does not seem to follow the momentum even if law enforcement agencies and governments around the world support and encourage investigation in this field. In this paper, we review the most important methods used so far in video steganalysis and sketch the future trends. To the best of our knowledge this is the most comprehensive review of video steganalysis produced so far.

Existing models based on sensor data for human activity recognition are reporting state-of-the-art performances. Most of these models are conducted based on single-domain learning in which for each domain a model is required to be trained. However, the generation of adequate labelled data and a learning model for each domain separately is often time-consuming and computationally expensive. Moreover, the deployment of multiple domain-wise models is not scalable as it obscures domain distinctions, introduces extra computational costs, and limits the usefulness of training data. To mitigate this, we propose a multi-domain learning network to transfer knowledge across different but related domains and alleviate isolated learning paradigms using a shared representation. The proposed network consists of two identical causal convolutional sub-networks that are projected to a shared representation followed by a linear attention mechanism. The proposed network can be trained using the full training dataset of the source domain and a dataset of restricted size of the target training domain to reduce the need of large labelled training datasets. The network processes the source and target domains jointly to learn powerful and mutually complementary features to boost the performance in both domains. The proposed multi-domain learning network on six real-world sensor activity datasets outperforms the existing methods by applying only 50% of the labelled data. This confirms the efficacy of the proposed approach as a generic model to learn human activities from different but related domains in a joint effort, to reduce the number of required models and thus improve system efficiency.

In this paper, we aim to minimize the total power of all the Internet of Things devices (IoTDs) by jointly optimizing user association, computation capacity, transmit power, and the location of unmanned aerial vehicles (UAVs) in an UAV-assisted cloud radio access network (C-RAN). In order to solve this non-convex problem, we propose an effective algorithm by solving four subproblems iteratively. For the user association and the computation capacity subproblems, the non-convex constraints are relaxed and the optimal solutions are obtained. For the transmit power control and the location planning subproblems, successive convex approximation (SCA) technique is used to transform the non-convex constraints into convex ones. Moreover, to obtain the suboptimal solutions, slack variables are also introduced to deal with the feasibility-check problems. The simulation results demonstrate that the proposed algorithm can greatly reduce the total power consumption of IoTDs.

Designers and developers of pervasive technologies have started to address privacy concerns. However, little work has been done to address the numerous safety concerns for specific social and population groups that fall outside conventional threat modeling based on network-based adversaries. If researchers, engineers, and designers are conscious about concerns for privacy, they must also be considerate of the safety of users of their systems. By using feminist and justice-orientated lenses to technology creation and testing, we present the concept of safety as a challenge and a hopeful aspiration for pervasive computing. We present a feminist vision for the future of pervasive technologies that engages with issues of technology-mediated harms to mitigate or aim to eradicate them entirely. By examining two concrete concepts of trust and abusability that will assist on this aspirational journey, we highlight ways to build safer technologies that are grounded in justice and safety for all.

In this paper, we investigate multiple unmanned aerial vehicles (UAVs) enabled data collection system in Internet of Things (IoT) networks with time windows, where multiple rotary-wing UAVs are dispatched to collect data from time constrained terrestrial IoT devices. We aim to jointly minimize the number and the total operation time of UAVs by optimizing the UAV trajectory and hovering location. To this end, an optimization problem is formulated considering the energy budget and cache capacity of UAVs as well as the data transmission constraint of IoT devices. To tackle this mix-integer non-convex problem, we decompose the problem into two subproblems: UAV trajectory and hovering location optimization problems. To solve the first subproblem, an modified ant colony optimization (MACO) algorithm is proposed. For the second subproblem, the successive convex approximation (SCA) technique is applied. Then, an overall algorithm, termed MACO-based algorithm, is given by leveraging MACO algorithm and SCA technique. Simulation results demonstrate the superiority of the proposed algorithm.

Facial phenotyping for medical prediagnosis has recently been successfully exploited as a novel way for the preclinical assessment of a range of rare genetic diseases, where facial biometrics is revealed to have rich links to underlying genetic or medical causes. In this paper, we aim to extend this facial prediagnosis technology for a more general disease, Parkinson's Diseases (PD), and proposed an Artificial-Intelligence-of-Things (AIoT) edge-oriented privacy-preserving facial prediagnosis framework to analyze the treatment of Deep Brain Stimulation (DBS) on PD patients. In the proposed framework, a novel edge-based privacy-preserving framework is proposed to implement private deep facial diagnosis as a service over an AIoT-oriented information theoretically secure multi-party communication scheme, while data privacy has been a primary concern toward a wider exploitation of Electronic Health and Medical Records (EHR/EMR) over cloud-based medical services. In our experiments with a collected facial dataset from PD patients, for the first time, we proved that facial patterns could be used to evaluate the facial difference of PD patients undergoing DBS treatment. We further implemented a privacy-preserving information theoretical secure deep facial prediagnosis framework that can achieve the same accuracy as the non-encrypted one, showing the potential of our facial prediagnosis as a trustworthy edge service for grading the severity of PD in patients.

Medical image segmentation is a crucial step in diagnosis and analysis of diseases for clinical applications. Deep convolutional neural network methods such as DeepLabv3+ have successfully been applied for medical image segmentation, but multi-level features are seldom integrated seamlessly into different attention mechanisms, and few studies have fully explored the interactions between medical image segmentation and classification tasks. Herein, we propose a feature-compression-pyramid network (FCP-Net) guided by game-theoretic interactions with a hybrid loss function (HLF) for the medical image segmentation. The proposed approach consists of segmentation branch, classification branch and interaction branch. In the encoding stage, a new strategy is developed for the segmentation branch by applying three modules, e.g., embedded feature ensemble, dilated spatial mapping and channel attention (DSMCA), and branch layer fusion. These modules allow effective extraction of spatial information, efficient identification of spatial correlation among various features, and fully integration of multi-receptive field features from different branches. In the decoding stage, a DSMCA module and a multi-scale feature fusion module are used to establish multiple skip connections for enhancing fusion features. Classification and interaction branches are introduced to explore the potential benefits of the classification information task to the segmentation task. We further explore the interactions of segmentation and classification branches from a game theoretic view, and design an HLF. Based on this HLF, the segmentation, classification and interaction branches can collaboratively learn and teach each other throughout the training process, thus applying the conjoint information between the segmentation and classification tasks and improving the generalization performance. The proposed model has been evaluated using several datasets, including ISIC2017, ISIC2018, REFUGE, Kvasir-SEG, BUSI, and PH2, and the results prove its competitiveness compared with other state-of-the-art techniques.

The DC power system, due to its convenience of conversion, integration, and use, is getting immense attention in the field of power transmission and distribution. It is superior to traditional AC systems in terms of efficiency, reliability, and control simplicity as well. A DC circuit breaker is one of the important elements of any DC power system. It is a sophisticated technology designed to break DC current only. The breaking of a DC current is always challenging compared to the breaking of an AC current, as DC current does not have natural zero crossing points like AC current has. Moreover, DC current breaking becomes more critical when the current is inductive as energy stored in the network inductance opposes instantaneous current breaking. Hence, this energy needs to be absorbed and dissipated as heat during the current breaking operation, which is exactly what is done in the traditional DC circuit breaker topologies. This paper introduces a new topology for DC circuit breakers with a mechanism to reuse this stored energy instead of dissipating it. The mechanism is analogous to regenerative braking in electric drive systems and can enhance the overall system efficiency. The proposed scheme was analyzed through rigorous computer simulation and was experimentally validated.

Spiking Neural Networks (SNNs) use spatio-temporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation. Motivated by the success of deep learning, the study of Deep Spiking Neural Networks (DeepSNNs) provides promising directions for artificial intelligence applications. However, training of DeepSNNs is not straightforward because the well-studied error back-propagation (BP) algorithm is not directly applicable. In this paper, we first establish an understanding as to why error back-propagation does not work well in DeepSNNs. To address this problem, we propose a simple yet efficient Rectified Linear Postsynaptic Potential function (ReL-PSP) for spiking neurons and propose a Spike-Timing-Dependent Back-Propagation (STDBP) learning algorithm for DeepSNNs. In STDBP algorithm, the timing of individual spikes is used to convey information (temporal coding), and learning (back-propagation) is performed based on spike timing in an event-driven manner. Our experimental results show that the proposed learning algorithm achieves state-of-the-art classification accuracy in single spike time based learning algorithms of DeepSNNs. Furthermore, by utilizing the trained model parameters obtained from the proposed STDBP learning algorithm, we demonstrate the ultra-low-power inference operations on a recently proposed neuromorphic inference accelerator. Experimental results show that the neuromorphic hardware consumes 0.751~mW of the total power consumption and achieves a low latency of 47.71~ms to classify an image from the MNIST dataset. Overall, this work investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems., This work has been submitted to the IEEE for possible publication. Copyrightmay be transferred without notice, after which this version may no longer beaccessible

Congestion control is a fundamental technology to balance the traffic load and the network. The Internet Engineering Task Force (IETF) Quick UDP Internet Connection (QUIC) protocol has flexible congestion control and at the same time possesses the advantages of high efficiency, low latency, and easy deployment at the application layer. Bottleneck bandwidth and round-trip propagation time (BBR) is an optional congestion control algorithm adopted by QUIC. BBR can significantly increase throughput and reduce latency, in particular over long-haul paths. However, BBR results in high packet loss in low bandwidth and low fairness in multi-stream scenarios. In this article, we propose the enhanced BBR congestion control (eBCC) algorithm, which improves the BBR algorithm in two aspects: (1) 10.87% higher throughput and 74.58% lower packet loss rate in the low-bandwidth scenario and (2) 8.39% higher fairness in the multi-stream scenario. This improvement makes eBCC very suitable for IoT communications to provide better QoS services.

Vehicle platoon systems are widely recognized as a key enabler to address mass-transport. Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) are two technologies that drive platooning. The inter-vehicle spacing and the collaboration velocity in the platoon are main important parameters that must be controlled. Recently, a new mass-transport system has been proposed, called the Tracked Electric Vehicles (TEV). In TEV, the inter-vehicular spacing is reduced to only a quarter of the regular car length and cars drive at 200km/h which enable mass transport at uniform speed. However, conventional radar based Adaptive Cruise Control (ACC) system fail to control each vehicle in these scenarios. Lately, Sliding Mode Control (SMC) has been applied to control platoons with communication technology but with low speed and without delay. This paper proposes a novel SMC design for TEV using global dynamic information with the communication delay. Also, graph theory has been employed to investigate different V2V communication topology structures. To address the issues of node vehicle stability and string stability, Lyapunov candidate function is chosen and developed for in-depth analysis. In addition, this paper, uses first-order vehicle models with different acceleration and deceleration parameters for simulation validations under communication delay. The results show that this novel SMC has a significant tolerance ability therefore meet the design requirements of TEV.

For technology (like serious games) that aims to deliver interactive learning, it is important to address relevant mental experiences such as reflective thinking during problem solving. To facilitate research in this direction, we present the weDraw-1 Movement Dataset of body movement sensor data and reflective thinking labels for 26 children solving mathematical problems in unconstrained settings where the body (full or parts) was required to explore these problems. Further, we provide qualitative analysis of behaviours that observers used in identifying reflective thinking moments in these sessions. The body movement cues from our compilation informed features that lead to average F1 score of 0.73 for binary classification of problem-solving episodes by reflective thinking based on Long Short-Term Memory neural networks. We further obtained 0.79 average F1 score for end-to-end classification, i.e. based on raw sensor data. Finally, the algorithms resulted in 0.64 average F1 score for subsegments of these episodes as short as 4 seconds. Overall, our results show the possibility of detecting reflective thinking moments from body movement behaviours of a child exploring mathematical concepts bodily, such as within serious game play.

In this paper, intelligent reflecting surface (IRS) is introduced to enhance the network performance of cognitive radio (CR) systems. Specifically, we investigate robust beamforming design based on both bounded channel state information (CSI) error model and statistical CSI error model for primary user (PU)-related channels in IRS-aided CR systems. We jointly optimize the transmit precoding (TPC) at the secondary user (SU) transmitter (ST) and phase shifts at the IRS to minimize the ST' s total transmit power subject to the quality of service of SUs, the limited interference imposed on the PU and unit-modulus of the reflective beamforming. The successive convex approximation (SCA) method, Schur's complement, General sign-definiteness principle, inverse Chi-square distribution and penalty convex-concave procedure are invoked for dealing with these intricate constraints. The non-convex optimization problems are transformed into several convex subproblems and efficient algorithms are proposed. Simulation results verify the efficiency of the proposed algorithms and reveal the impacts of CSI uncertainties on ST's minimum transmit power and feasibility rate of the optimization problems. Simulation results also show that the number of transmit antennas at the ST and the number of phase shifts at the IRS should be carefully chosen to balance the channel realization feasibility rate and the total transmit power., Accepted by IEEE Transactions on Cognitive Communications and Networking. Keywords: Reconfigurable Intelligent Surface, Intelligent Reflecting Surface, Cognitive Radio Networks, Robust Design, Imperfect CSI

In this paper, we study the transmission design for reconfigurable intelligent surface (RIS)-aided multiuser communication networks. Different from most of the existing contributions, we consider long-term CSI-based transmission design, where both the beamforming vectors at the base station (BS) and the phase shifts at the RIS are designed based on long-term CSI, which can significantly reduce the channel estimation overhead. Due to the lack of explicit ergodic data rate expression, we propose a novel deep deterministic policy gradient (DDPG) based algorithm to solve the optimization problem, which was trained by using the channel vectors generated in an offline manner. Simulation results demonstrate that the achievable net throughput is higher than that achieved by the conventional instantaneous-CSI based scheme when taking the channel estimation overhead into account.

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

This brief investigates the resilient consensus control for multiagent systems over a time-varying directed random network. We propose a median-based consensus strategy, which is purely distributed and, as opposed to the Weighted-Mean-Subsequence-Reduced approaches in the existing literature, shared estimate regarding the number of malicious agents in the neighborhood of each cooperative agent is not required. This offers more applicability and flexibility as seeking a shared estimate of surrounding threats is often difficult in practice. In addition to malicious agents, random availability of communication edges is accommodated in the random network framework. Sufficient conditions are derived for reaching almost sure consensus by using a martingale convergence theorem. Finally, the theoretical findings are illustrated by numerical simulations.

Gait abnormalities are typically derived from neurological conditions or orthopaedic problems and can cause severe consequences such as limited mobility and falls. Gait analysis plays a crucial role in monitoring gait abnormalities and discovering underlying deficits can help develop rehabilitation programs. Contemporary gait analysis requires a multi-modal gait analysis approach where spatio-temporal, kinematic and muscle activation gait characteristics are investigated. Additionally, protocols for gait analysis are going beyond labs/clinics to provide more habitual insights, uncovering underlying reasons for limited mobility and falls during daily activities. Wearables are the most prominent technology that are reliable and allow multi-modal gait analysis beyond the labs/clinics for extended periods. There are established wearable-based algorithms for extracting informative gait characteristics and interpretation. This paper proposes a multi-layer fusion framework with sensor, data and gait characteristics. The wearable sensors consist of four units (inertial and electromyography, EMG) attached to both legs (shanks and thighs) and surface electrodes placed on four muscle groups. Inertial and EMG data are interpreted by numerous validated algorithms to extract gait characteristics in different environments. This paper also includes a pilot study to test the proposed fusion approach in a small cohort of stroke survivors. Experimental results in various terrains show healthy participants experienced the highest pace and variability along with slightly increased knee flexion angles (≈1°) and decreased overall muscle activation level during outdoor walking compared to indoor, incline walking activities. Stroke survivors experienced slightly increased pace, asymmetry, and knee flexion angles (≈4°) during outdoor walking compared to indoor. A multi-modal approach through a sensor, data and gait characteristic fusion presents a more holistic gait assessment process to identify changes in different testing environments. The utilisation of the fusion approach presented here warrants further investigation in those with neurological conditions, which could significantly contribute to the current understanding of impaired gait.

Creating realistic characters that can react to the users’ or another character’s movement can benefit computer graphics, games and virtual reality hugely. However, synthesizing such reactive motions in human–human interactions is a challenging task due to the many different ways two humans can interact. While there are a number of successful researches in adapting the generative adversarial network (GAN) in synthesizing single human actions, there are very few on modeling human–human interactions. In this paper, we propose a semi-supervised GAN system that synthesizes the reactive motion of a character given the active motion from another character. Our key insights are two-fold. First, to effectively encode the complicated spatial–temporal information of a human motion, we empower the generator with a part-based long short-term memory (LSTM) module, such that the temporal movement of different limbs can be effectively modeled. We further include an attention module such that the temporal significance of the interaction can be learned, which enhances the temporal alignment of the active–reactive motion pair. Second, as the reactive motion of different types of interactions can be significantly different, we introduce a discriminator that not only tells if the generated movement is realistic or not, but also tells the class label of the interaction. This allows the use of such labels in supervising the training of the generator. We experiment with the SBU, the HHOI and the 2C datasets. The high quality of the synthetic motion demonstrates the effective design of our generator, and the discriminability of the synthesis also demonstrates the strength of our discriminator.

This paper concentrates upon the event-driven controller design problem for a class of nonlinear single input single output (SISO) parametric systems with full state constraints. A varying threshold for the triggering mechanism is exploited, which makes the communication more flexible. Moreover, from the viewpoint of energy conservation and consumption reduction, the system capability becomes better owing to the contribution of the proposed event triggered mechanism. In the meantime, the developed control strategy can avoid the Zeno behavior since the lower bound of the sample time is provided. The considered plant is in a lower-triangular form, in which the match condition is not satisfied. To ensure that all the states to retain in a predefined region, a barrier Lyapunov function (BLF) based adaptive control law is developed. Due to the existence of the parametric uncertainties, an adaptive algorithm is presented as an estimated tool. All the signals appearing in the closed-loop systems are then proven to be uniformly ultimately bounded (UUB). Meanwhile, the output of the system can track a given signal as far as possible. In the end, the effectiveness of the proposed approach is validated by an aircraft wing rock motion system.

In this work, a face recognition method is proposed for face under pose variations using a multi-task convolutional neural network (CNN). Furthermore, a pose estimation method followed by a face identification module are combined in a cascaded structure and used separately. In the presence of various facial poses as well as low illuminations, datasets that include separated face poses can enhance the robustness of face recognition. The proposed method relies on a pose estimation module using a convolutional neural network model and trained on three categories of face image capture such as the Left side, Frontal, and right side. Second, three CNN models are used for face identification according to the estimated pose. The Left-CNN model, Front-CNN model, and Right-CNN model are used to identify the face for the left, frontal, and right pose of the face, respectively. Because face images may contain some useless information (e.g. background content), we propose a skin-based face segmentation method using structure-decomposition and the Color Invariant Descriptor. Experimental evaluation has been conducted using the proposed cascade-based face recognition system that consists of the aforementioned steps (i.e., pose estimation, face segmentation, and face identification) is assessed on four different datasets and its superiority has been shown over related state-of-the-art techniques. Results reveal the contribution of the separate representation, skin segmentation, and pose estimation in the recognition robustness.

Traditional personalized tag recommendation methods cannot guarantee that the collaborative signal hidden in the interactions among entities is effectively encoded in the process of learning the representations of entities, resulting in insufficient expressive capacity for characterizing the preferences or attributes of entities. In this paper, we firstly propose a graph neural networks boosted personalized tag recommendation model, namely NGTR, which integrates the graph neural networks into the pairwise interaction tensor factorization model. Specifically, we exploit the graph neural networks to capture the collaborative signal, and integrate the collaborative signal into the learning of representations of entities by transmitting and assembling the representations of neighbors along the interaction graphs. In addition, we also propose a light graph neural networks boosted personalized tag recommendation model, namely LNGTR. Different from NGTR, our proposed LNGTR model removes feature transformation and nonlinear activation components as well as adopts the weighted sum of the embeddings learned at all layers as the final embedding. Experimental results on real world datasets show that our proposed personalized tag recommendation models outperform the traditional tag recommendation methods.

A myriad of recent literary works has leveraged generative adversarial networks (GANs) to generate unseen evasion samples. The purpose is to annex the generated data with the original train set for adversarial training to improve the detection performance of machine learning (ML) classifiers. The quality of generated adversarial samples relies on the adequacy of training data samples. However, in low data regimes like medical diagnostic imaging and cybersecurity, the anomaly samples are scarce in number. This paper proposes a novel GAN design called Evasion Generative Adversarial Network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. EVAGAN not only can generate evasion samples, but its discriminator can act as an evasion-aware classifier. We have considered Auxiliary Classifier GAN (ACGAN) as a benchmark to evaluate the performance of EVAGAN on cybersecurity (ISCX-2014, CIC-2017 and CIC2018) botnet and computer vision (MNIST) datasets. We demonstrate that EVAGAN outperforms ACGAN for unbalanced datasets with respect to detection performance, training stability and time complexity. EVAGAN’s generator quickly learns to generate the low sample class and hardens its discriminator simultaneously. In contrast to ML classifiers that require security hardening after being adversarially trained by GAN-generated data, EVAGAN renders it needless. The experimental analysis proves that EVAGAN is an efficient evasion hardened model for low data regimes for the selected cybersecurity and computer vision datasets. Code will be available at HTTPS://www.github.com/rhr407/EVAGAN.

Crowd simulations are used extensively to study the dynamics of human collectives. Such studies are underpinned by specific movement models, which encode rules and assumptions about how people navigate a space and handle interactions with others. These models often give rise to macroscopic simulated crowd behaviours that are statistically valid, but which lack the noisy microscopic behaviours that are the signature of believable real crowds. In this article, we use an existing Turing test for crowds to identify realistic features of real crowds that are generally omitted from simulation models. Our previous study using this test established that untrained individuals have difficulty in classifying movies of crowds as real or simulated, and that such people often have an idealised view of how crowds move. In this follow-up study (with new participants) we perform a second trial, which now includes a training phase (showing participants movies of real crowds). We find that classification performance significantly improves after training, confirming the existence of features that allow participants to identify real crowds. High-performing individuals are able to identify the features of real crowds that should be incorporated into future simulations if they are to be considered realistic.

Different from conventional wired line connections, industrial control through wireless transmission is widely regarded as a promising solution due to its reduced cost, increased long-term reliability, and enhanced reliability. However, mission-critical applications impose stringent quality of service (QoS) requirements that entail ultra-reliability low-latency communications (URLLC). The primary feature of URLLC is that the blocklength of channel codes is short, and the conventional Shannon's Capacity is not applicable. In this paper, we consider the URLLC in a factory automation (FA) scenario. Due to densely deployed equipment in FA, wireless signal are easily blocked by the obstacles. To address this issue, we propose to deploy intelligent reflecting surface (IRS) to create an alternative transmission link, which can enhance the transmission reliability. In this paper, we focus on the performance analysis for IRS-aided URLLC-enabled communications in a FA scenario. Both the average data rate (ADR) and the average decoding error probability (ADEP) are derived under finite channel blocklength for seven cases: 1) Rayleigh fading channel; 2) With direct channel link; 3) Nakagami-m fading channel; 4) Imperfect phase alignment; 5) Multiple-IRS case; 6) Rician fading channel; 7) Correlated channels. Extensive numerical results are provided to verify the accuracy of our derived results., Comment: Accepted by IEEE TCOM

This paper develops a multisensor data fusion-based deep learning algorithm to locate and classify faults in a leader-following multiagent system. First, sequences of one-dimensional data collected from multiple sensors of followers are fused into a two-dimensional image. Then, the image is employed to train a convolution neural network with a batch normalisation layer. The trained network can locate and classify three typical fault types: the actuator limitation fault, the sensor failure and the communication failure. Moreover, faults can exist in both leaders and followers, and the faults in leaders can be identified through data from followers, indicating that the developed deep learning fault diagnosis is distributed. The effectiveness of the deep learning-based fault diagnosis algorithm is demonstrated via Quanser Servo 2 rotating inverted pendulums with a leader-follower protocol. From the experimental results, the fault classification accuracy can reach 98.9%.

Background Colorectal and prostate cancers are the most common types of cancer in men worldwide. To diagnose colorectal and prostate cancer, a pathologist performs a histological analysis on needle biopsy samples. This manual process is time-consuming and error-prone, resulting in high intra- and interobserver variability, which affects diagnosis reliability. Objective This study aims to develop an automatic computerized system for diagnosing colorectal and prostate tumors by using images of biopsy samples to reduce time and diagnosis error rates associated with human analysis. Methods In this study, we proposed a convolutional neural network (CNN) model for classifying colorectal and prostate tumors from multispectral images of biopsy samples. The key idea was to remove the last block of the convolutional layers and halve the number of filters per layer. Results Our results showed excellent performance, with an average test accuracy of 99.8% and 99.5% for the prostate and colorectal data sets, respectively. The system showed excellent performance when compared with pretrained CNNs and other classification methods, as it avoids the preprocessing phase while using a single CNN model for the whole classification task. Overall, the proposed CNN architecture was globally the best-performing system for classifying colorectal and prostate tumor images. Conclusions The proposed CNN architecture was detailed and compared with previously trained network models used as feature extractors. These CNNs were also compared with other classification techniques. As opposed to pretrained CNNs and other classification approaches, the proposed CNN yielded excellent results. The computational complexity of the CNNs was also investigated, and it was shown that the proposed CNN is better at classifying images than pretrained networks because it does not require preprocessing. Thus, the overall analysis was that the proposed CNN architecture was globally the best-performing system for classifying colorectal and prostate tumor images.

Identifying sleep stages and patterns is an essential part of diagnosing and treating sleep disorders. With the advancement of smart technologies, sensor data related to sleeping patterns can be captured easily. In this paper, we propose a Convolution Neural Network (CNN) architecture that improves the classification performance. In particular, we benchmark the classification performance from different methods, including traditional machine learning methods such as Logistic Regression (LR), Decision Trees (DT), k-Nearest Neighbour (k-NN), Naive Bayes (NB) and Support Vector Machine (SVM), on 3 publicly available sleep datasets. The accuracy, sensitivity, specificity, precision, recall, and F-score are reported and will serve as a baseline to simulate the research in this direction in the future.

This article proposes a fuzzy logic-based energy-management system (FEMS) for a grid-connected microgrid with renewable energy sources (RESs) and energy storage system (ESS). The objectives of the FEMS are reducing the average peak load (APL) and operating cost through arbitrage operation of the ESS. These objectives are achieved by controlling the charge and discharge rate of the ESS based on the state of charge of ESS, the power difference between load and RES, and electricity market price. The effectiveness of the fuzzy logic greatly depends on the membership functions (MFs). The fuzzy MFs of the FEMS are optimized offline using a Pareto-based multiobjective evolutionary algorithm, nondominated sorting genetic algorithm (NSGA-II). The best compromise solution is selected as the final solution and implemented in the fuzzy-logic controller. A comparison with other control strategies with similar objectives is carried out at a simulation level. The proposed FEMS is experimentally validated on a real microgrid in the energy storage test bed at Newcastle University, U.K.

Contrary to a popular belief of lawyers having the most strict perception of law, law professionals actually strongly skew toward more favorable views of digital sharing. According to our qualitative study, relying on in-depth interviews with 50 Harvard lawyers, digital piracy is quite acceptable. It is considered fair, especially among friends and for noncommercial purposes. We argue that this not only can indicate that the existing law is becoming outdated because of its inability to be enforced, but also that ethically it is not corresponding to what is considered fair, good service, or being societally beneficial. The common perception of relying on a fixed price for digital content is eroding. We show that on the verges of business, society, and law, there is a potential for the new paradigm of digital commons to emerge.

This article embarks a study on multiagent transfer learning (TL) for addressing the specific challenges that arise in complex multiagent systems where agents have different or even competing objectives. Specifically, beyond the essential backbone of a state-of-the-art evolutionary TL framework (eTL), this article presents the novel TL framework with prediction (eTL-P) as an upgrade over existing eTL to endow agents with abilities to interact with their opponents effectively by building candidate models and accordingly predicting their behavioral strategies. To reduce the complexity of candidate models, eTL-P constructs a monotone submodular function, which facilitates to select Top- ${K}$ models from all available candidate models based on their representativeness in terms of behavioral coverage as well as reward diversity. eTL-P also integrates social selection mechanisms for agents to identify their better-performing partners, thus improving their learning performance and reducing the complexity of behavior prediction by reusing useful knowledge with respect to their partners’ mind universes. Experiments based on a partner-opponent minefield navigation task (PO-MNT) have shown that eTL-P exhibits the superiority in achieving higher learning capability and efficiency of multiple agents when compared to the state-of-the-art multiagent TL approaches.

The field of digital forensics has grown exponentially to include a variety of digital devices on which digitally stored information can be processed and used for different types of crimes. As a result, as this growth continues, new challenges for those conducting digital forensic examinations emerge. Digital forensics has become mainstream and grown in importance in situations where digital devices used in the commission of a crime need examining. This article reviews existing literature and highlights the challenges while exploring the lifecycle of a mobile phone examination and how the disclosure and admissibility of digital evidence develops.

To (i) examine the use of social media before and after the COVID-19 outbreak; (ii) examine the self-perceived impact of social media before and after the outbreak; and (iii) examine whether the self-perceived impacts of social media after the outbreak varied by levels of mental health. A cross-national online survey was conducted in Norway, UK, USA and Australia. Participants (n = 3810) reported which social media they used, how frequently they used them before and after the COVID-19 outbreak, and the degree to which they felt social media contributed to a range of outcomes. The participants also completed the 12-item General Health Questionnaire. The data were analyzed by chi-square tests and multiple linear regression analysis. Social media were used more frequently after the pandemic outbreak than compared to before the outbreak. Self-perceived effects from using social media increased after the COVID-19 outbreak, and in particular stress and concern for own and others’ health. Emotional distress was associated with being more affected from using social media, in particular in terms of stress and concern for own or others’ health. The use of social media has increased during the coronavirus outbreak, as well as its impacts on people. In particular, the participants reported more stress and health concerns attributed to social media use after the COVID-19 outbreak. People with poor mental health appear to be particularly vulnerable to experiencing more stress and concern related to their use of social media.

The detection and quantification of the rolling contact fatigue (RCF) in rail tracks are essential for rail safety and condition-based maintenance. The tomographic reconstruction of the rolling contact fatigue is challenging work. The x-ray is unable to do in-situ inspection effectively. This paper proposes a new approach for RCF construction using 3D eddy current pulsed thermography. A differential time-square-root (sqrt) of temperature drop (DTSTD) is proposed as a mean to construct the sectional images and to reconstruct the thermal tomography image. The proposed method is validated through artificial angular crack slots as well as natural RCF crack. The thermal tomographic reconstruction is compared with the x-ray computed tomography on a rail track head cut-off with RCF cracks.

Recurrent neural network (RNN) has become popular for human motion prediction thanks to its ability to capture temporal dependencies. However, it has limited capacity in modeling the complex spatial relationship in the human skeletal structure. In this work, we present a novel diffusion convolutional recurrent predictor for spatial and temporal movement forecasting, with multi-step random walks traversing bidirectionally along an adaptive graph to model interdependency among body joints. In the temporal domain, existing methods rely on a single forward predictor with the produced motion deflecting to the drift route, which leads to error accumulations over time. We propose to supplement the forward predictor with a forward discriminator to alleviate such motion drift in the long term under adversarial training. The solution is further enhanced by a backward predictor and a backward discriminator to effectively reduce the error, such that the system can also look into the past to improve the prediction at early frames. The two-way spatial diffusion convolutions and two-way temporal predictors together form a quadruple network.\ud \ud Furthermore, we train our framework by modeling the velocity from observed motion dynamics instead of static poses to predict future movements that effectively reduces the discontinuity problem at early prediction. Our method outperforms the state of the arts on both 3D and 2D datasets, including the Human3.6M, CMU Motion Capture and Penn Action datasets. The results also show that our method correctly predicts both high-dynamic and low-dynamic moving trends with less motion drift.

International audience; Visible light communications (VLC) (VLC) has been introduced as a complementary wireless technology that can be widely used in industrial indoor environments where automated guided vehicles aim to ease and accelerate logistics. Despite its advantages, there is one significant drawback of using an indoor vehicular VLC (V-VLC) network that is there is a high handover outage duration. In line-of-sight VLC links, such handovers are frequently due to mobility, shadowing, and obstacles. In this paper, we propose a frequency diversity and link aggregation solution, which is a novel technique in Data link layer to tackle handover challenge in indoor V-VLC networks. We have developed a smallscale prototype and experimentally evaluated its performance for a variety of scenarios and compared the results with other handover techniques. We also assessed the configuration options in more detail, in particular focusing on different network traffic types and various address resolution protocol intervals. The measurement results demonstrate the advantages of our approach for lowoutage duration handovers in V-VLC. The proposed idea is able to decrease the handover outage duration in a two-dimensional network to about 0.2 s, which is considerably lower compared to previous solutions.

Existing studies on formation control for unmanned aerial vehicles (UAV) have not considered encircling targets where an optimum coverage of the target is required at all times. Such coverage plays a critical role in many real-world applications such as tracking hostile UAVs. This paper proposes a new path planning approach called the Flux Guided (FG) method, which generates collision-free trajectories for multiple UAVs while maximising the coverage of target(s). Our method enables UAVs to track directly toward a target whilst maintaining maximum coverage. Furthermore, multiple scattered targets can be tracked by scaling the formation during flight. FG is highly scalable since it only requires communication between sub-set of UAVs on the open boundary of the formation's surface. Experimental results further validate that FG generates UAV trajectories $1.5 \times$ shorter than previous work and that trajectory planning for 9 leader/follower UAVs to surround a target in two different scenarios only requires 0.52 seconds and 0.88 seconds, respectively. The resulting trajectories are suitable for robotic controls after time-optimal parameterisation; we demonstrate this using a 3d dynamic particle system that tracks the desired trajectories using a PID controller., Comment: 37 pages, 9 figures, 3 table

The use of automation, Internet-of-Things (IoT), and smart technologies is being rapidly introduced into the development of agriculture. Technologies such as sensing, remote monitoring, and predictive tools have been used with the purpose of enhancing agriculture processes, aquaponics among them, and improving the quality of the products. Digital twinning enables the testing and implementing of improvements in the physical component through the implementation of computational tools in a ‘twin’ virtual environment. This paper presents a framework for the development of a digital twin for an aquaponic system. This framework is validated by developing a digital twin for the grow beds of an aquaponics system for real-time monitoring parameters, namely pH, electroconductivity, water temperature, relative humidity, air temperature, and light intensity, and supports the use of artificial intelligent techniques to, for example, predict the growth rate and fresh weight of the growing crops. The digital twin presented is based on IoT technology, databases, a centralized control of the system, and a virtual interface that allows users to have feedback control of the system while visualizing the state of the aquaponic system in real time.

Contemporary approaches to gait assessment use wearable devices within free-living environments to capture habitual information, which is more informative compared to data capture in the lab. Wearables range from inertial to camera-based technologies but pragmatic challenges such as analysis of big data from heterogenous environments exist. For example, wearable camera data often requires manual time-consuming subjective contextualization, such as labelling of terrain type. There is a need for the application of automated approaches such as those suggested by artificial intelligence (AI) based methods. This pilot study investigates multiple segmentation models and proposes use of the PSPNet deep learning network to automate a binary indoor floor segmentation mask for use with wearable camera-based data (i.e., video frames). To inform the development of the AI method, a unique approach of mining heterogenous data from a video sharing platform (YouTube) was adopted to provide independent training data. The dataset contains 1973 image frames and accompanying segmentation masks. When trained on the dataset the proposed model achieved an Instance over Union score of 0.73 over 25 epochs in complex environments. The proposed method will inform future work within the field of habitual free-living gait assessment to provide automated contextual information when used in conjunction with wearable inertial derived gait characteristics.

In this paper, we investigate a reconfigurable intelligent surface (RIS)-assisted wireless communication system with energy harvesting. In the single information user (IU) scenario, we consider the power control of base station (BS) and the random deployment of energy users (EUs). To this end, we first characterize the statistical features of the channel gains over BS-RIS-IU and BS-RIS-EU cascaded links. Then, we derive a closed-form expression of the information outage probability (IOP) of the IU and show an upper bound of the energy outage probability (EOP) of EUs by invoking the Jensen's inequality. Furthermore, we consider two more general extensions, namely, the existence of imperfect phase alignment and multiple IUs. Finally, the correctness of the analysis results is verified by Monte-Carlo simulation.