Editor’s Choice Articles

With growing evidence of deep learning-assisted smart process planning, there is an essential demand for comprehending whether cyber-physical production systems (CPPSs) are adequate in managing complexity and flexibility, configuring the smart factory. In this research, prior findings were cumulated indicating that the interoperability between Internet of Things-based real-time production logistics and cyber-physical process monitoring systems can decide upon the progression of operations advancing a system to the intended state in CPPSs. We carried out a quantitative literature review of ProQuest, Scopus, and the Web of Science throughout March and August 2021, with search terms including “cyber-physical production systems”, “cyber-physical manufacturing systems”, “smart process manufacturing”, “smart industrial manufacturing processes”, “networked manufacturing systems”, “industrial cyber-physical systems,” “smart industrial production processes”, and “sustainable Internet of Things-based manufacturing systems”. As we analyzed research published between 2017 and 2021, only 489 papers met the eligibility criteria. By removing controversial or unclear findings (scanty/unimportant data), results unsupported by replication, undetailed content, or papers having quite similar titles, we decided on 164, chiefly empirical, sources. Subsequent analyses should develop on real-time sensor networks, so as to configure the importance of artificial intelligence-driven big data analytics by use of cyber-physical production networks. Full article

In recent years the amount of malware spreading through the internet and infecting computers and other communication devices has tremendously increased. To date, countless techniques and methodologies have been proposed to detect and neutralize these malicious agents. However, as new and automated malware generation techniques emerge, a lot of malware continues to be produced, which can bypass some state-of-the-art malware detection methods. Therefore, there is a need for the classification and detection of these adversarial agents that can compromise the security of people, organizations, and countless other forms of digital assets. In this paper, we propose a spatial attention and convolutional neural network (SACNN) based on deep learning framework for image-based classification of 25 well-known malware families with and without class balancing. Performance was evaluated on the Malimg benchmark dataset using precision, recall, specificity, precision, and F1 score on which our proposed model with class balancing reached 97.42%, 97.95%, 97.33%, 97.11%, and 97.32%. We also conducted experiments on SACNN with class balancing on benign class, also produced above 97%. The results indicate that our proposed model can be used for image-based malware detection with high performance, despite being simpler as compared to other available solutions. Full article

Coronavirus has affected millions of people worldwide, with the rate of infected people still increasing. The virus is transmitted between people through direct, indirect, or close contact with infected people. To help prevent the social transmission of COVID-19, this paper presents a new smart social distance system that allows individuals to keep social distances between others in indoor and outdoor environments, avoiding exposure to COVID-19 and slowing its spread locally and across the country. The proposed smart monitoring system consists of a new smart wearable prototype of a compact and low-cost electronic device, based on human detection and proximity distance functions, to estimate the social distance between people and issue a notification when the social distance is less than a predefined threshold value. The developed social system has been validated through several experiments, and achieved a high acceptance rate (96.1%) and low localization error (<6 m). Full article

The data movement between the processing and storage units has been one of the most critical issues in modern computer systems. The emerging Resistive Random Access Memory (RRAM) technology has drawn tremendous attention due to its non-volatile ability and the potential in computation application. These properties make them a perfect choice for application in modern computing systems. In this paper, an 8-bit radix-4 non-volatile parallel multiplier is proposed, with improved computational capabilities. The corresponding booth encoding scheme, read-out circuit, simplified Wallace tree, and Manchester carry chain are presented, which help to short the delay of the proposed multiplier. While the presence of RRAM save computational time and overall power as multiplicand is stored beforehand. The area of the proposed non-volatile multiplier is reduced with improved computing speed. The proposed multiplier has an area of 785.2 $\mathsf{\mu }$m${}^2$ with Generic Processing Design Kit 45 nm process. The simulation results show that the proposed multiplier structure has a low computing power at 161.19 $\mathsf{\mu }$W and a short delay of 0.83 ns with 1.2 V supply voltage. Comparative analyses are performed to demonstrate the effectiveness of the proposed multiplier design. Compared with conventional booth multipliers, the proposed multiplier structure reduces the energy and delay by more than 70% and 19%, respectively. Full article

Cricket is one of the most liked, played, encouraged, and exciting sports in today’s time that requires a proper advancement with machine learning and artificial intelligence (AI) to attain more accuracy. With the increasing number of matches with time, the data related to cricket matches and the individual player are increasing rapidly. Moreover, the need of using big data analytics and the opportunities of utilizing this big data effectively in many beneficial ways are also increasing, such as the selection process of players in the team, predicting the winner of the match, and many more future predictions using some machine learning models or big data techniques. We applied the machine learning linear regression model to predict the team scores without big data and the big data framework Spark ML. The experimental results are measured through accuracy, the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE), respectively 95%, 30.2, 1350.34, and 28.2 after applying linear regression in Spark ML. Furthermore, our approach can be applied to other sports. Full article

This paper proposed an innovative mechanical design using the Rocker-bogie mechanism for resilient Trash-Collecting Robots. Mask-RCNN, YOLOV4, and YOLOv4-tiny were experimented on and analyzed for trash detection. The Trash-Collecting Robot was developed to be completely autonomous as it was able to detect trash, move towards it, and pick it up while avoiding any obstacles along the way. Sensors including a camera, ultrasonic sensor, and GPS module played an imperative role in automation. The brain of the Robot, namely, Raspberry Pi and Arduino, processed the data from the sensors and performed path-planning and consequent motion of the robot through actuation of motors. Three models for object detection were tested for potential use in the robot: Mask-RCNN, YOLOv4, and YOLOv4-tiny. Mask-RCNN achieved an average precision (mAP) of over 83% and detection time (DT) of 3973.29 ms, YOLOv4 achieved 97.1% (mAP) and 32.76 DT, and YOLOv4-tiny achieved 95.2% and 5.21 ms DT. The YOLOv4-tiny was selected as it offered a very similar mAP to YOLOv4, but with a much lower DT. The design was simulated on different terrains and behaved as expected. Full article

Vehicles are highly mobile nodes; therefore, they frequently change their topology. To maintain a stable connection with the server in high-speed vehicular networks, the handover process is restarted again to satisfy the content requests. To satisfy the requested content, a vehicular-content-centric network (VCCN) is proposed. The proposed scheme adopts in-network caching instead of destination-based routing to satisfy the requests. In this regard, various routing protocols have been proposed to increase the communication efficiency of VCCN. Despite disruptive communication links due to head vehicle mobility, the vehicles create a broadcasting storm that increases communication delay and packet drop fraction. To address the issues mentioned above in the VCCN, we proposed a multihead nomination clustering scheme. It extends the hello packet header to get the vehicle information from the cluster vehicles. The novel cluster information table (CIT) has been proposed to maintain several nominated head vehicles of a cluster on roadside units (RSUs). In disruptive communication links due to the head vehicle’s mobility, the RSU nominates the new head vehicle using CIT entries, resulting in the elimination of the broadcasting storm effect on disruptive communication links. Finally, the proposed scheme increases the successful communication rate, decreases the communication delay, and ensures a high cache success ratio on an increasing number of vehicles. Full article

The constant advancements in Information Technology have been the main driver of the Big Data concept’s success. With it, new concepts such as Industry 4.0 and Logistics 4.0 are arising. Due to the increase in data volume, velocity, and variety, organizations are now looking to their data analytics infrastructures and searching for approaches to improve their decision-making capabilities, in order to enhance their results using new approaches such as Big Data and Machine Learning. The implementation of a Big Data Warehouse can be the first step to improve the organizations’ data analysis infrastructure and start retrieving value from the usage of Big Data technologies. Moving to Big Data technologies can provide several opportunities for organizations, such as the capability of analyzing an enormous quantity of data from different data sources in an efficient way. However, at the same time, different challenges can arise, including data quality, data management, and lack of knowledge within the organization, among others. In this work, we propose an approach that can be adopted in the logistics department of any organization in order to promote the Logistics 4.0 movement, while highlighting the main challenges and opportunities associated with the development and implementation of a Big Data Warehouse in a real demonstration case at a multinational automotive organization. Full article

Machine learning-based systems are gaining interest in the field of medicine, mostly in medical imaging and diagnosis. In this paper, we address the problem of automatic cerebral microbleeds (CMB) detection in magnetic resonance images. It is challenging due to difficulty in distinguishing a true CMB from its mimics, however, if successfully solved, it would streamline the radiologists work. To deal with this complex three-dimensional problem, we propose a machine learning approach based on a 2D Faster RCNN network. We aimed to achieve a reliable system, i.e., with balanced sensitivity and precision. Therefore, we have researched and analysed, among others, impact of the way the training data are provided to the system, their pre-processing, the choice of model and its structure, and also the ways of regularisation. Furthermore, we also carefully analysed the network predictions and proposed an algorithm for its post-processing. The proposed approach enabled for obtaining high precision (89.74%), sensitivity (92.62%), and F1 score (90.84%). The paper presents the main challenges connected with automatic cerebral microbleeds detection, its deep analysis and developed system. The conducted research may significantly contribute to automatic medical diagnosis. Full article

The Tactile Internet (TI) is an emerging area of research involving 5G and beyond (B5G) communications to enable real-time interaction of haptic data over the Internet between tactile ends, with audio-visual data as feedback. This emerging TI technology is viewed as the next evolutionary step for the Internet of Things (IoT) and is expected to bring about a massive change in Healthcare 4.0, Industry 4.0 and autonomous vehicles to resolve complicated issues in modern society. This vision of TI makes a dream into a reality. This article aims to provide a comprehensive survey of TI, focussing on design architecture, key application areas, potential enabling technologies, current issues, and challenges to realise it. To illustrate the novelty of our work, we present a brainstorming mind-map of all the topics discussed in this article. We emphasise the design aspects of the TI and discuss the three main sections of the TI, i.e., master, network, and slave sections, with a focus on the proposed application-centric design architecture. With the help of the proposed illustrative diagrams of use cases, we discuss and tabulate the possible applications of the TI with a 5G framework and its requirements. Then, we extensively address the currently identified issues and challenges with promising potential enablers of the TI. Moreover, a comprehensive review focussing on related articles on enabling technologies is explored, including Fifth Generation (5G), Software-Defined Networking (SDN), Network Function Virtualisation (NFV), Cloud/Edge/Fog Computing, Multiple Access, and Network Coding. Finally, we conclude the survey with several research issues that are open for further investigation. Thus, the survey provides insights into the TI that can help network researchers and engineers to contribute further towards developing the next-generation Internet. Full article

The state of Michigan, U.S.A., was awarded USD 1 million in March 2018 for the Great Lakes Invasive Carp Challenge. The challenge sought new and novel technologies to function independently of or in conjunction with those fish deterrents already in place to prevent the movement of invasive carp species into the Great Lakes from the Illinois River through the Chicago Area Waterway System (CAWS). Our team proposed an environmentally friendly, low-cost, vision-based fish recognition and separation system. The proposed solution won fourth place in the challenge out of 353 participants from 27 countries. The proposed solution includes an underwater imaging system that captures the fish images for processing, fish species recognition algorithm that identify invasive carp species, and a mechanical system that guides the fish movement and restrains invasive fish species for removal. We used our evolutionary learning-based algorithm to recognize fish species, which is considered the most challenging task of this solution. The algorithm was tested with a fish dataset consisted of four invasive and four non-invasive fish species. It achieved a remarkable 1.58% error rate, which is more than adequate for the proposed system, and required only a small number of images for training. This paper details the design of this unique solution and the implementation and testing that were accomplished since the challenge. Full article

Future-oriented networking infrastructures are characterized by highly dynamic Streaming Data (SD) whose volume, speed and number of dimensions increased significantly over the past couple of years, energized by trends such as Software-Defined Networking or Artificial Intelligence. As an essential core component of network security, Intrusion Detection Systems (IDS) help to uncover malicious activity. In particular, consecutively applied alert correlation methods can aid in mining attack patterns based on the alerts generated by IDS. However, most of the existing methods lack the functionality to deal with SD data affected by the phenomenon called concept drift and are mainly designed to operate on the output from signature-based IDS. Although unsupervised Outlier Detection (OD) methods have the ability to detect yet unknown attacks, most of the alert correlation methods cannot handle the outcome of such anomaly-based IDS. In this paper, we introduce a novel framework called Streaming Outlier Analysis and Attack Pattern Recognition, denoted as SOAAPR, which is able to process the output of various online unsupervised OD methods in a streaming fashion to extract information about novel attack patterns. Three different privacy-preserving, fingerprint-like signatures are computed from the clustered set of correlated alerts by SOAAPR, which characterizes and represents the potential attack scenarios with respect to their communication relations, their manifestation in the data’s features and their temporal behavior. Beyond the recognition of known attacks, comparing derived signatures, they can be leveraged to find similarities between yet unknown and novel attack patterns. The evaluation, which is split into two parts, takes advantage of attack scenarios from the widely-used and popular CICIDS2017 and CSE-CIC-IDS2018 datasets. Firstly, the streaming alert correlation capability is evaluated on CICIDS2017 and compared to a state-of-the-art offline algorithm, called Graph-based Alert Correlation (GAC), which has the potential to deal with the outcome of anomaly-based IDS. Secondly, the three types of signatures are computed from attack scenarios in the datasets and compared to each other. The discussion of results, on the one hand, shows that SOAAPR can compete with GAC in terms of alert correlation capability leveraging four different metrics and outperforms it significantly in terms of processing time by an average factor of 70 in 11 attack scenarios. On the other hand, in most cases, all three types of signatures seem to reliably characterize attack scenarios such that similar ones are grouped together, with up to 99.05% similarity between the FTP and SSH Patator attack. Full article

The use of Ka and Q/V bands could be a promising solution in order to accommodate higher data rate, interactive services; however, at these frequency bands signal attenuation due to the various atmospheric phenomena and more particularly due to rain could constitute a serious limiting factor in system performance and availability. To alleviate this possible barrier, short- and large-scale diversity schemes have been proposed and examined in the past; in this paper a micro-scale site diversity system is evaluated in terms of capacity gain using rain attenuation time series generated using the Synthetic Storm Technique (SST). Input to the SST was 4 years of experimental rainfall data from two stations with a separation distance of 386 m at the National Technical University of Athens (NTUA) campus in Athens, Greece. Additionally, a novel multi-dimensional synthesizer based on Gaussian Copulas parameterized for the case of multiple-site micro-scale diversity systems is presented and evaluated. In all examined scenarios a significant capacity gain can be observed, thus proving that micro-scale site diversity systems could be a viable choice for enterprise users to increase the achievable data rates and improve the availability of their links. Full article

This paper develops a data-driven remaining useful life prediction model for solenoid pumps. The model extracts high-level features using stacked autoencoders from decomposed pressure signals (using complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm). These high-level features are then received by a recurrent neural network-gated recurrent units (GRUs) for the RUL estimation. The case study presented demonstrates the robustness of the proposed RUL estimation model with extensive empirical validations. Results support the validity of using the CEEMDAN for non-stationary signal decomposition and the accuracy, ease-of-use, and superiority of the proposed DL-based model for solenoid pump failure prognostics. Full article

This paper initially presents an overview of different miniaturization techniques used for size reduction of printed log-periodic dipole array (PLPDA) antennas, and then continues by presenting a design of a conventional PLPDA design that operates from 0.7–8 GHz and achieves a realized gain of around 5.5 dBi in most of its bandwidth. This antenna design is then used as a baseline model to implement a novel technique to extend the low-frequency response. This is completed by replacing the longest straight dipole with a triangular-shaped dipole and by optimizing the four longest dipoles of the antenna using the Trust Region Framework algorithm in CST. The improved antenna with extended low-frequency response operates from 0.4 GHz to 8 GHz with a slightly reduced gain at the lower frequencies. Full article

This paper reveals the relationship between the Miller plateau voltage and the displacement currents through the gate–drain capacitance ($C_{\mathit{GD}}$) and the drain–source capacitance ($C_{\mathit{DS}}$) in the switching process of a power transistor. The corrected turn-on Miller plateau voltage and turn-off Miller plateau voltage are different even with a constant current load. Using the proposed new Miller plateau, the turn-on and turn-off sequences can be more accurately analyzed, and the switching power loss can be more accurately predicted accordingly. Switching loss models based on the new Miller plateau have also been proposed. The experimental test result of the power MOSFET (NCE2030K) verified the relationship between the Miller plateau voltage and the displacement currents through $C_{\mathit{GD}}$ and $C_{\mathit{DS}}$. A carefully designed verification test bench featuring a power MOSFET written in Verilog-A proved the prediction accuracy of the switching waveform and switching loss with the new proposed Miller plateau. The average relative error of the loss model using the new plateau is reduced to 1/2∼1/4 of the average relative error of the loss model using the old plateau; the proposed loss model using the new plateau, which also takes the gate current’s variation into account, further reduces the error to around 5%. Full article

Modern wireless networks such as 5G require multiband MIMO-supported Base Station Antennas. As a result, antennas have multiple ports to support a range of frequency bands leading to multiple arrays within one compact antenna enclosure. The close proximity of the arrays results in significant scattering degrading pattern performance of each band while coupling between arrays leads to degradation in return loss and port-to-port isolations. Different design techniques are adopted in the literature to overcome such challenges. This paper provides a classification of challenges in BSA design and a cohesive list of design techniques adopted in the literature to overcome such challenges. Full article

Design closure in general VLSI physical design flows and FPGA physical design flows is an important and time-consuming problem. Routing itself can consume as much as 70% of the total design time. Accurate congestion estimation during the early stages of the design flow can help alleviate last-minute routing-related surprises. This paper has described a methodology for a post-placement, machine learning-based routing congestion prediction model for FPGAs. Routing congestion is modeled as a regression problem. We have described the methods for generating training data, feature extractions, training, regression models, validation, and deployment approaches. We have tested our prediction model by using ISPD 2016 FPGA benchmarks. Our prediction method reports a very accurate localized congestion value in each channel around a configurable logic block (CLB). The localized congestion is predicted in both vertical and horizontal directions. We demonstrate the effectiveness of our model on completely unseen designs that are not initially part of the training data set. The generated results show significant improvement in terms of accuracy measured as mean absolute error and prediction time when compared against the latest state-of-the-art works. Full article

The gyrotron travelling wave tube (gyro-TWT) is an ideal high-power, broadband vacuum electron amplifier in millimeter and sub-millimeter wave bands. It can be applied as the source of the imaging radar to improve the resolution and operating range. To satisfy the requirements of the W-band high-resolution imaging radar, the design and the experimentation of the W-band broadband TE₀₂ mode gyro-TWT were carried out. In this paper, the designs of the key components of the vacuum tube are introduced, including the interaction area, electron optical system, and transmission system. The experimental results show that when the duty ratio is 1%, the output power is above 60 kW with a bandwidth of 8 GHz, and the saturated gain is above 32 dB. In addition, parasitic mode oscillations were observed in the experiment, which limited the increase in duty ratio and caused the measured gains to be much lower than the simulation results. For this phenomenon, the reasons and the suppression methods are under study. Full article

This paper presents a state-of-the-art review of electric vehicle technology, charging methods, standards, and optimization techniques. The essential characteristics of Hybrid Electric Vehicle (HEV) and Electric Vehicle (EV) are first discussed. Recent research on EV charging methods such as Battery Swap Station (BSS), Wireless Power Transfer (WPT), and Conductive Charging (CC) are then presented. This is followed by a discussion of EV standards such as charging levels and their configurations. Next, some of the most used optimization techniques for the sizing and placement of EV charging stations are analyzed. Finally, based on the insights gained, several recommendations are put forward for future research. Full article

With the ever-increasing demand for bandwidth, appropriate mechanisms that would provide reliable and optimum service level to designated or specified traffic classes during heavy traffic loads in networks are becoming particularly sought after. One of these mechanisms is the resource reservation mechanism, in which parts of the resources are available only to selected (pre-defined) services. While considering modern elastic optical networks (EONs) where advanced data transmission techniques are used, an attempt was made to develop a simulation program that would make it possible to determine the traffic characteristics of the nodes in EONs. This article discusses a simulation program that has the advantage of providing the possibility to determine the loss probability for individual service classes in the nodes of an EON where the resource reservation mechanism has been introduced. The initial assumption in the article is that a Clos optical switching network is used to construct the EON nodes. The results obtained with the simulator developed by the authors will allow the influence of the introduced reservation mechanism on the loss probability of calls of individual traffic classes that are offered to the system under consideration to be determined. Full article

In recent years, dual-arm robots have been favored in various industries due to their excellent coordinated operability. One of the focused areas of study on dual-arm robots is obstacle avoidance, namely path planning. Among the existing path planning methods, the artificial potential field (APF) algorithm is widely applied in obstacle avoidance for its simplicity, practicability, and good real-time performance over other planning methods. However, APF is firstly proposed to solve the obstacle avoidance problem of mobile robot in plane, and thus has some limitations such as being prone to fall into local minimum, not being applicable when dynamic obstacles are encountered. Therefore, an obstacle avoidance strategy for a dual-arm robot based on speed field with improved artificial potential field algorithm is proposed. In our method, the APF algorithm is used to establish the attraction and repulsion functions of the robotic manipulator, and then the concepts of attraction and repulsion speed are introduced. The attraction and repulsion functions are converted into the attraction and repulsion speed functions, which mapped to the joint space. By using the Jacobian matrix and its inverse to establish the differential velocity function of joint motion, as well as comparing it with the set collision distance threshold between two robotic manipulators of robot, the collision avoidance can be solved. Meanwhile, after introducing a new repulsion function and adding virtual constraint points to eliminate existing limitations, APF is also improved. The correctness and effectiveness of the proposed method in the self-collision avoidance problem of a dual-arm robot are validated in MATLAB and Adams simulation environment. Full article

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement. Full article

Spin-transfer torque magnetic tunnel junction (STT-MTJ) based on double-barrier magnetic tunnel junction (DMTJ) has shown promising characteristics to define low-power non-volatile memories. This, along with the combination of tunnel FET (TFET) technology, could enable the design of ultralow-power/ultralow-energy STT magnetic RAMs (STT-MRAMs) for future Internet of Things (IoT) applications. This paper presents the comparison between FinFET- and TFET-based STT-MRAM bitcells operating at ultralow voltages. Our study is performed at the bitcell level by considering a DMTJ with two reference layers and exploiting either FinFET or TFET devices as cell selectors. Although ultralow-voltage operation occurs at the expense of reduced reading voltage sensing margins, simulations results show that TFET-based solutions are more resilient to process variations and can operate at ultralow voltages (<0.5 $\mathrm{V}$), while showing energy savings of 50% and faster write switching of 60%. Full article

Photoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging. Full article

Telecommunications have grown to be a pillar to a functional society and the urge for reliable and high throughput systems has become the main objective of researchers and engineers. State-of-the-art work considers massive Multiple-Input Multiple-Output (massive MIMO) as the key technology for 5G and beyond. Large spatial multiplexing and diversity gains are some of the major benefits together with an improved energy efficiency. Current works mostly assume the application of well-established techniques in a massive MIMO scenario, although there are still open challenges regarding hardware and computational complexities and energy efficiency. Fully digital, analog, and hybrid structures are analyzed and a multi-layer massive MIMO transmission technique is detailed. The purpose of this article is to describe the most acknowledged transmission techniques for massive MIMO systems and to analyze some of the most promising ones and identify existing problems and limitations. Full article

It is very important to make an objective evaluation of colorectal cancer histological images. Current approaches are generally based on the use of different combinations of textual features and classifiers to assess the classification performance, or transfer learning to classify different organizational types. However, since histological images contain multiple tissue types and characteristics, classification is still challenging. In this study, we proposed the best classification methodology based on the selected optimizer and modified the parameters of CNN methods. Then, we used deep learning technology to distinguish between healthy and diseased large intestine tissues. Firstly, we trained a neural network and compared the network architecture optimizers. Secondly, we modified the parameters of the network layer to optimize the superior architecture. Finally, we compared our well-trained deep learning methods on two different histological image open datasets, which comprised 5000 H&E images of colorectal cancer. The other dataset was composed of nine organizational categories of 100,000 images with an external validation of 7180 images. The results showed that the accuracy of the recognition of histopathological images was significantly better than that of existing methods. Therefore, this method is expected to have great potential to assist physicians to make clinical diagnoses and reduce the number of disparate assessments based on the use of artificial intelligence to classify colorectal cancer tissue. Full article

The millimeter-wave (mmWave) is expected to deliver a huge bandwidth to address the future demands for higher data rate transmissions. However, one of the major challenges in the mmWave band is the increase in signal loss as the operating frequency increases. This has attracted several research interests both from academia and the industry for indoor and outdoor mmWave operations. This paper focuses on the works that have been carried out in the study of the mmWave channel measurement in indoor environments. A survey of the measurement techniques, prominent path loss models, analysis of path loss and delay spread for mmWave in different indoor environments is presented. This covers the mmWave frequencies from 28 GHz to 100 GHz that have been considered in the last two decades. In addition, the possible future trends for the mmWave indoor propagation studies and measurements have been discussed. These include the critical indoor environment, the roles of artificial intelligence, channel characterization for indoor devices, reconfigurable intelligent surfaces, and mmWave for 6G systems. This survey can help engineers and researchers to plan, design, and optimize reliable 5G wireless indoor networks. It will also motivate the researchers and engineering communities towards finding a better outcome in the future trends of the mmWave indoor wireless network for 6G systems and beyond. Full article

The YOLOv4 neural network is employed for underwater target recognition. To improve the accuracy and speed of recognition, the structure of YOLOv4 is modified by replacing the upsampling module with a deconvolution module and by incorporating depthwise separable convolution into the network. Moreover, the training set used in the YOLO network is preprocessed by using a modified mosaic augmentation, in which the gray world algorithm is used to derive two images when performing mosaic augmentation. The recognition results and the comparison with the other target detectors demonstrate the effectiveness of the proposed YOLOv4 structure and the method of data preprocessing. According to both subjective and objective evaluation, the proposed target recognition strategy can effectively improve the accuracy and speed of underwater target recognition and reduce the requirement of hardware performance as well. Full article

Car accidents are one of the top ten causes of death and are produced mainly by driver distractions. ADAS (Advanced Driver Assistance Systems) can warn the driver of dangerous scenarios, improving road safety, and reducing the number of traffic accidents. However, having a system that is continuously sounding alarms can be overwhelming or confusing or both, and can be counterproductive. Using the driver’s attention to build an efficient ADAS is the main contribution of this work. To obtain this “attention value” the use of a Gaze tracking is proposed. Driver’s gaze direction is a crucial factor in understanding fatal distractions, as well as discerning when it is necessary to warn the driver about risks on the road. In this paper, a real-time gaze tracking system is proposed as part of the development of an ADAS that obtains and communicates the driver’s gaze information. The developed ADAS uses gaze information to determine if the drivers are looking to the road with their full attention. This work gives a step ahead in the ADAS based on the driver, building an ADAS that warns the driver only in case of distraction. The gaze tracking system was implemented as a model-based system using a Kinect v2.0 sensor and was adjusted on a set-up environment and tested on a suitable-features driving simulation environment. The average obtained results are promising, having hit ratios between 96.37% and 81.84%. Full article

This paper presents a single-pole 32-throw (SP32T) switch with an operating frequency of up to 6 GHz for 5G communication applications. Compared to the traditional SP32T module implemented by the waveguide package with large volume and power, the proposed switch can significantly simplify the system with a smaller size and light weight. The proposed SP32T scheme utilizing tree structure can dramatically reduce the dc power and enhance isolation between different output ports, which makes it suitable for low-power 5G communication. A design methodology of a novel transmission (ABCD) matrix is proposed to optimize the switch, which can achieve low insertion loss and high isolation simultaneously. The average insertion loss and the isolations are 1.5 and 35 dB at 6 GHz operating frequency, respectively. The switch exhibits the measured input return loss which is better than 10 dB at 6 GHz. The 1 dB input compression point of SP32T is 15 dBm. The prototype is designed in 5 V 0.25 μm GaAs technology and occupies a small area of 12 mm². Full article

Herein, a novel cavity design of racetrack integrated circular cavity established on metal-insulator-metal (MIM) waveguide is suggested for refractive index sensing application. Over the past few years, we have witnessed several unique cavity designs to improve the sensing performance of the plasmonic sensors created on the MIM waveguide. The optimized cavity design can provide the best sensing performance. In this work, we have numerically analyzed the device design by utilizing the finite element method (FEM). The small variations in the geometric parameter of the device can bring a significant shift in the sensitivity and the figure of merit (FOM) of the device. The best sensitivity and FOM of the anticipated device are 1400 nm/RIU and ~12.01, respectively. We believe that the sensor design analyzed in this work can be utilized in the on-chip detection of biochemical analytes. Full article

We propose a spiking neural network (SNN) approach for radar-based hand gesture recognition (HGR), using frequency modulated continuous wave (FMCW) millimeter-wave radar. After pre-processing the range-Doppler or micro-Doppler radar signal, we use a signal-to-spike conversion scheme that encodes radar Doppler maps into spike trains. The spike trains are fed into a spiking recurrent neural network, a liquid state machine (LSM). The readout spike signal from the SNN is then used as input for different classifiers for comparison, including logistic regression, random forest, and support vector machine (SVM). Using liquid state machines of less than 1000 neurons, we achieve better than state-of-the-art results on two publicly available reference datasets, reaching over 98% accuracy on 10-fold cross-validation for both data sets. Full article

The timely identification and early prevention of crop diseases are essential for improving production. In this paper, deep convolutional-neural-network (CNN) models are implemented to identify and diagnose diseases in plants from their leaves, since CNNs have achieved impressive results in the field of machine vision. Standard CNN models require a large number of parameters and higher computation cost. In this paper, we replaced standard convolution with depth=separable convolution, which reduces the parameter number and computation cost. The implemented models were trained with an open dataset consisting of 14 different plant species, and 38 different categorical disease classes and healthy plant leaves. To evaluate the performance of the models, different parameters such as batch size, dropout, and different numbers of epochs were incorporated. The implemented models achieved a disease-classification accuracy rates of 98.42%, 99.11%, 97.02%, and 99.56% using InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNetB0, respectively, which were greater than that of traditional handcrafted-feature-based approaches. In comparison with other deep-learning models, the implemented model achieved better performance in terms of accuracy and it required less training time. Moreover, the MobileNetV2 architecture is compatible with mobile devices using the optimized parameter. The accuracy results in the identification of diseases showed that the deep CNN model is promising and can greatly impact the efficient identification of the diseases, and may have potential in the detection of diseases in real-time agricultural systems. Full article

Fault detection/diagnosis has become a crucial function of the battery management system (BMS) due to the increasing application of lithium-ion batteries (LIBs) in highly sophisticated and high-power applications to ensure the safe and reliable operation of the system. The application of Machine Learning (ML) in the BMS of LIB has long been adopted for efficient, reliable, accurate prediction of several important states of LIB such as state of charge, state of health and remaining useful life. Inspired by some of the promising features of ML-based techniques over the conventional LIB fault detection/diagnosis methods such as model-based, knowledge-based and signal processing-based techniques, ML-based data-driven methods have been a prime research focus in the last few years. This paper provides a comprehensive review exclusively on the state-of-the-art ML-based data-driven fault detection/diagnosis techniques to provide a ready reference and direction to the research community aiming towards developing an accurate, reliable, adaptive and easy to implement fault diagnosis strategy for the LIB system. Current issues of existing strategies and future challenges of LIB fault diagnosis are also explained for better understanding and guidance. Full article

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings. Full article

This article proposes an energy-efficiency strategy based on the optimization of driving patterns for an electric vehicle (EV). The EV studied in this paper is a commercial vehicle only driven by a traction motor. The motor drives the front wheels indirectly through the differential drive. The electrical inverter model and the power-train efficiency are established by lookup tables determined by power tests in a dynamometric bank. The optimization problem is focused on maximizing energy-efficiency between the wheel power and battery pack, not only to maintain but also to improve its value by modifying the state of charge (SOC). The solution is found by means of a Particle Swarm Optimization (PSO) algorithm. The optimizer simulation results validate the increasing efficiency with the speed setpoint variations, and also show that the battery SOC is improved. The best results are obtained when the speed variation is between 5% and 6%. Full article

Fog computing is an emerging computing paradigm that has come into consideration for the deployment of Internet of Things (IoT) applications amongst researchers and technology industries over the last few years. Fog is highly distributed and consists of a wide number of autonomous end devices, which contribute to the processing. However, the variety of devices offered across different users are not audited. Hence, the security of Fog devices is a major concern that should come into consideration. Therefore, to provide the necessary security for Fog devices, there is a need to understand what the security concerns are with regards to Fog. All aspects of Fog security, which have not been covered by other literature works, need to be identified and aggregated. On the other hand, privacy preservation for user’s data in Fog devices and application data processed in Fog devices is another concern. To provide the appropriate level of trust and privacy, there is a need to focus on authentication, threats and access control mechanisms as well as privacy protection techniques in Fog computing. In this paper, a survey along with a taxonomy is proposed, which presents an overview of existing security concerns in the context of the Fog computing paradigm. Moreover, the Blockchain-based solutions towards a secure Fog computing environment is presented and various research challenges and directions for future research are discussed. Full article

Accomplishing multi-level programming in resistive random access memory (RRAM) arrays with truly discrete and linearly spaced conductive levels is crucial in order to implement synaptic weights in hardware-based neuromorphic systems. In this paper, we implemented this feature on 4-kbit 1T1R RRAM arrays by tuning the programming parameters of the multi-level incremental step pulse with verify algorithm (M-ISPVA). The optimized set of parameters was assessed by comparing its results with a non-optimized one. The optimized set of parameters proved to be an effective way to define non-overlapped conductive levels due to the strong reduction of the device-to-device variability as well as of the cycle-to-cycle variability, assessed by inter-levels switching tests and during 1 k reset-set cycles. In order to evaluate this improvement in real scenarios, the experimental characteristics of the RRAM devices were captured by means of a behavioral model, which was used to simulate two different neuromorphic systems: an 8 × 8 vector-matrix-multiplication (VMM) accelerator and a 4-layer feedforward neural network for MNIST database recognition. The results clearly showed that the optimization of the programming parameters improved both the precision of VMM results as well as the recognition accuracy of the neural network in about 6% compared with the use of non-optimized parameters. Full article

This work pursues the potential of extending “Industry 4.0” practices to farming toward achieving “Agriculture 4.0”. Our interest is in fruit harvesting, motivated by the problem of addressing the shortage of seasonal labor. In particular, here we present an integrated system architecture of an Autonomous Robot for Grape harvesting (ARG). The overall system consists of three interdependent units: (1) an aerial unit, (2) a remote-control unit and (3) the ARG ground unit. Special attention is paid to the ARG; the latter is designed and built to carry out three viticultural operations, namely harvest, green harvest and defoliation. We present an overview of the multi-purpose overall system, the specific design of each unit of the system and the integration of all subsystems. In addition, the fully sensory-based sensing system architecture and the underlying vision system are analyzed. Due to its modular design, the proposed system can be extended to a variety of different crops and/or orchards. Full article

The development of distributed generation, mainly based on renewable energies, requires the design of control strategies to allow the regulation of electrical variables, such as power, voltage (V), and frequency (f), and the coordination of multiple generation units in microgrids or islanded systems. This paper presents a strategy to control the active and reactive power flow in the Point of Common Connection (PCC) of a renewable generation system operating in islanded mode. Voltage Source Converters (VSCs) are connected between individual generation units and the PCC to control the voltage and frequency. The voltage and frequency reference values are obtained from the P–V and Q–f droop characteristics curves, where P and Q are the active and reactive power supplied to the load, respectively. Proportional–Integral (PI) controllers process the voltage and frequency errors and set the reference currents (in the dq frame) to be imposed by each VSC. Simulation results considering high-power solar and wind generation systems are presented to validate the proposed control strategy. Full article

Human facial emotion recognition (FER) has attracted the attention of the research community for its promising applications. Mapping different facial expressions to the respective emotional states are the main task in FER. The classical FER consists of two major steps: feature extraction and emotion recognition. Currently, the Deep Neural Networks, especially the Convolutional Neural Network (CNN), is widely used in FER by virtue of its inherent feature extraction mechanism from images. Several works have been reported on CNN with only a few layers to resolve FER problems. However, standard shallow CNNs with straightforward learning schemes have limited feature extraction capability to capture emotion information from high-resolution images. A notable drawback of the most existing methods is that they consider only the frontal images (i.e., ignore profile views for convenience), although the profile views taken from different angles are important for a practical FER system. For developing a highly accurate FER system, this study proposes a very Deep CNN (DCNN) modeling through Transfer Learning (TL) technique where a pre-trained DCNN model is adopted by replacing its dense upper layer(s) compatible with FER, and the model is fine-tuned with facial emotion data. A novel pipeline strategy is introduced, where the training of the dense layer(s) is followed by tuning each of the pre-trained DCNN blocks successively that has led to gradual improvement of the accuracy of FER to a higher level. The proposed FER system is verified on eight different pre-trained DCNN models (VGG-16, VGG-19, ResNet-18, ResNet-34, ResNet-50, ResNet-152, Inception-v3 and DenseNet-161) and well-known KDEF and JAFFE facial image datasets. FER is very challenging even for frontal views alone. FER on the KDEF dataset poses further challenges due to the diversity of images with different profile views together with frontal views. The proposed method achieved remarkable accuracy on both datasets with pre-trained models. On a 10-fold cross-validation way, the best achieved FER accuracies with DenseNet-161 on test sets of KDEF and JAFFE are 96.51% and 99.52%, respectively. The evaluation results reveal the superiority of the proposed FER system over the existing ones regarding emotion detection accuracy. Moreover, the achieved performance on the KDEF dataset with profile views is promising as it clearly demonstrates the required proficiency for real-life applications. Full article

The breakthrough of deep learning has started a technological revolution in various areas such as object identification, image/video recognition and semantic segmentation. Neural network, which is one of representative applications of deep learning, has been widely used and developed many efficient models. However, the edge implementation of neural network inference is restricted because of conflicts between the high computation and storage complexity and resource-limited hardware platforms in applications scenarios. In this paper, we research neural networks which are involved in the acceleration on FPGA-based platforms. The architecture of networks and characteristics of FPGA are analyzed, compared and summarized, as well as their influence on acceleration tasks. Based on the analysis, we generalize the acceleration strategies into five aspects—computing complexity, computing parallelism, data reuse, pruning and quantization. Then previous works on neural network acceleration are introduced following these topics. We summarize how to design a technical route for practical applications based on these strategies. Challenges in the path are discussed to provide guidance for future work. Full article

Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. These applications belong to the civilian and the military fields. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Reconnaissance (ISTAR) operations. However, the use of UAVs in these applications needs a substantial level of autonomy. In other words, UAVs should have the ability to accomplish planned missions in unexpected situations without requiring human intervention. To ensure this level of autonomy, many artificial intelligence algorithms were designed. These algorithms targeted the guidance, navigation, and control (GNC) of UAVs. In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. We made a detailed description of them, and we deduced the current limitations in this area. We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. We realized that further research efforts are needed to address the challenges that restrain their deployment in real-life scenarios. Full article

The execution of a quantum algorithm typically requires various classical pre- and post-processing tasks. Hence, workflows are a promising means to orchestrate these tasks, benefiting from their reliability, robustness, and features, such as transactional processing. However, the implementations of the tasks may be very heterogeneous and they depend on the quantum hardware used to execute the quantum circuits of the algorithm. Additionally, today’s quantum computers are still restricted, which limits the size of the quantum circuits that can be executed. As the circuit size often depends on the input data of the algorithm, the selection of quantum hardware to execute a quantum circuit must be done at workflow runtime. However, modeling all possible alternative tasks would clutter the workflow model and require its adaptation whenever a new quantum computer or software tool is released. To overcome this problem, we introduce an approach to automatically select suitable quantum hardware for the execution of quantum circuits in workflows. Furthermore, it enables the dynamic adaptation of the workflows, depending on the selection at runtime based on reusable workflow fragments. We validate our approach with a prototypical implementation and a case study demonstrating the hardware selection for Simon’s algorithm. Full article

This paper deals with a single-stage single-ended inverter-based Operational Transconductance Amplifiers (OTA) with improved composite transistors for ultra-low-voltage supplies, while maintaining a small-area, high power-efficiency and low output signal distortion. The improved composite transistor is a combination of the conventional composite transistor and forward-body-biasing to further increase voltage gain. The impact of the proposed technique on performance is demonstrated through post-layout simulations referring to the TSMC 180 nm technology process. The proposed OTA achieves 54 dB differential voltage gain, 210 Hz gain–bandwidth product for a 10 pF capacitive load, with a power consumption of 273 pW with a 0.3 V power supply, and occupies an area of 1026 μm². For a 0.6 V voltage supply, the proposed OTA improves its voltage gain to 73 dB, and achieves a 15 kHz gain–bandwidth product with a power consumption of 41 nW. Full article

Embedded intelligence (EI) is an emerging research field and has the objective to incorporate machine learning algorithms and intelligent decision-making capabilities into mobile and embedded devices or systems. There are several challenges to be addressed to realize efficient EI implementations in hardware such as the need for: (1) high computational processing; (2) low power consumption (or high energy efficiency); and (3) scalability to accommodate different network sizes and topologies. In recent years, an emerging hardware technology which has demonstrated strong potential and capabilities for EI implementations is the FPGA (field programmable gate array) technology. This paper presents an overview and review of embedded intelligence on FPGA with a focus on applications, platforms and challenges. There are four main classification and thematic descriptors which are reviewed and discussed in this paper for EI: (1) EI techniques including machine learning and neural networks, deep learning, expert systems, fuzzy intelligence, swarm intelligence, self-organizing map (SOM) and extreme learning; (2) applications for EI including object detection and recognition, indoor localization and surveillance monitoring, and other EI applications; (3) hardware and platforms for EI; and (4) challenges for EI. The paper aims to introduce interested researchers to this area and motivate the development of practical FPGA solutions for EI deployment. Full article

With the extensive application of 3D maps, acquiring high-quality images with unmanned aerial vehicles (UAVs) for precise 3D reconstruction has become a prominent topic of study. In this research, we proposed a coverage path planning method for UAVs to achieve full coverage of a target area and to collect high-resolution images while considering the overlap ratio of the collected images and energy consumption of clustered UAVs. The overlap ratio of the collected image set is guaranteed through a map decomposition method, which can ensure that the reconstruction results will not get affected by model breaking. In consideration of the small battery capacity of common commercial quadrotor UAVs, ray-scan-based area division was adopted to segment the target area, and near-optimized paths in subareas were calculated by a simulated annealing algorithm to find near-optimized paths, which can achieve balanced task assignment for UAV formations and minimum energy consumption for each UAV. The proposed system was validated through a site experiment and achieved a reduction in path length of approximately 12.6% compared to the traditional zigzag path. Full article

Deep learning models have improved cutting-edge technologies in many research areas, but their black-box structure makes it difficult to understand their inner workings and the rationale behind their predictions. This may lead to unintended effects, such as being susceptible to adversarial attacks or the reinforcement of biases. There is still a lack of research in the audio domain, despite the increasing interest in developing deep learning models that provide explanations of their decisions. To reduce this gap, we propose a novel interpretable deep learning model for automatic sound classification, which explains its predictions based on the similarity of the input to a set of learned prototypes in a latent space. We leverage domain knowledge by designing a frequency-dependent similarity measure and by considering different time-frequency resolutions in the feature space. The proposed model achieves results that are comparable to that of the state-of-the-art methods in three different sound classification tasks involving speech, music, and environmental audio. In addition, we present two automatic methods to prune the proposed model that exploit its interpretability. Our system is open source and it is accompanied by a web application for the manual editing of the model, which allows for a human-in-the-loop debugging approach. Full article

The rapid outbreak of COVID-19 has caused serious harm and infected tens of millions of people worldwide. Since there is no specific treatment, wearing masks has become an effective method to prevent the transmission of COVID-19 and is required in most public areas, which has also led to a growing demand for automatic real-time mask detection services to replace manual reminding. However, few studies on face mask detection are being conducted. It is urgent to improve the performance of mask detectors. In this paper, we proposed the Properly Wearing Masked Face Detection Dataset (PWMFD), which included 9205 images of mask wearing samples with three categories. Moreover, we proposed Squeeze and Excitation (SE)-YOLOv3, a mask detector with relatively balanced effectiveness and efficiency. We integrated the attention mechanism by introducing the SE block into Darknet53 to obtain the relationships among channels so that the network can focus more on the important feature. We adopted GIoUloss, which can better describe the spatial difference between predicted and ground truth boxes to improve the stability of bounding box regression. Focal loss was utilized for solving the extreme foreground-background class imbalance. Besides, we performed corresponding image augmentation techniques to further improve the robustness of the model on the specific task. Experimental results showed that SE-YOLOv3 outperformed YOLOv3 and other state-of-the-art detectors on PWMFD and achieved a higher 8.6% mAP compared to YOLOv3 while having a comparable detection speed. Full article