Previous Issue
Volume 11, November-2
 
 
Due to planned maintenance work on our platforms, there might be short service disruptions on Saturday, December 3rd, between 15:00 and 16:00 (CET).

Electronics, Volume 11, Issue 23 (December-1 2022) – 174 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
Article
Eigenstructure through Matrix Adjugates and Admissible Pairs
Electronics 2022, 11(23), 4011; https://doi.org/10.3390/electronics11234011 (registering DOI) - 02 Dec 2022
Abstract
The traditional eigenstructure assignment method is reconsidered in this paper, shedding light on its nature and some of its properties. The approach is through matrix adjugates which enable a more eloquent decomposition compared to the lumped solution usually obtained through matrix null spaces. [...] Read more.
The traditional eigenstructure assignment method is reconsidered in this paper, shedding light on its nature and some of its properties. The approach is through matrix adjugates which enable a more eloquent decomposition compared to the lumped solution usually obtained through matrix null spaces. Based on the new approach, the admissible pair (w,z) is formalized. The new approach enables an alternative methodology to the determination of the permissible closed loop eigenvector subspaces and the might be termed the companion input-subspace. Such approach renders the method a formulae-based method as w and z are now obtained formula-wise as opposed to being extracted out of a lumped solution. Compared to the traditional method, the study reveals information such as w and z are independently and explicitly determined. Moreover, newly assigned eigenvalues always result in z0, the input matrix B does not influence z and a fundamental feature of the open loop characteristic polynomial is exposed. Furthermore, closed loop eigenvectors associated with repeated eigenvalues can be explicitly computed by means of differentiation as opposed to null space determination. A special form of system representation is highlighted, which considerably eases the calculations. The myriad concepts pointed out have been demonstrated and authenticated through carefully selected examples involving real, complex, repeated eigenvalues, and two practical systems of an electrical nature. Full article
(This article belongs to the Section Systems & Control Engineering)
Article
Hybrid Attention-Based 3D Object Detection with Differential Point Clouds
Electronics 2022, 11(23), 4010; https://doi.org/10.3390/electronics11234010 (registering DOI) - 02 Dec 2022
Abstract
Object detection based on point clouds has been widely used for autonomous driving, although how to improve its detection accuracy remains a significant challenge. Foreground points are more critical for 3D object detection than background points; however, most current detection frameworks cannot effectively [...] Read more.
Object detection based on point clouds has been widely used for autonomous driving, although how to improve its detection accuracy remains a significant challenge. Foreground points are more critical for 3D object detection than background points; however, most current detection frameworks cannot effectively preserve foreground points. Therefore, this work proposes a hybrid attention-based 3D object detection method with differential point clouds, which we name HA-RCNN. The method differentiates the foreground points from the background ones to preserve the critical information of foreground points. Extensive experiments conducted on the KITTI dataset show that the model outperforms the state-of-the-art methods, especially in recognizing large objects such as cars and cyclists. Full article
Article
Computer-Aided Diagnosis for Early Signs of Skin Diseases Using Multi Types Feature Fusion Based on a Hybrid Deep Learning Model
Electronics 2022, 11(23), 4009; https://doi.org/10.3390/electronics11234009 (registering DOI) - 02 Dec 2022
Abstract
According to medical reports and statistics, skin diseases have millions of victims worldwide. These diseases might affect the health and life of patients and increase the costs of healthcare services. Delays in diagnosing such diseases make it difficult to overcome the consequences of [...] Read more.
According to medical reports and statistics, skin diseases have millions of victims worldwide. These diseases might affect the health and life of patients and increase the costs of healthcare services. Delays in diagnosing such diseases make it difficult to overcome the consequences of these types of disease. Usually, diagnosis is performed using dermoscopic images, where specialists utilize certain measures to produce the results. This approach to diagnosis faces multiple disadvantages, such as overlapping infectious and inflammatory skin diseases and high levels of visual diversity, obstructing accurate diagnosis. Therefore, this article uses medical image analysis and artificial intelligence to present an automatic diagnosis system of different skin lesion categories using dermoscopic images. The addressed diseases are actinic keratoses (solar keratoses), benign keratosis (BKL), melanocytic nevi (NV), basal cell carcinoma (BCC), dermatofibroma (DF), melanoma (MEL), and vascular skin lesions (VASC). The proposed system consists of four main steps: (i) preprocessing the input raw image data and metadata; (ii) feature extraction using six pre-trained deep learning models (i.e., VGG19, InceptionV3, ResNet50, DenseNet201, and Xception); (iii) features concatenation; and (iv) classification/diagnosis using machine learning techniques. The evaluation results showed an average accuracy, sensitivity, specificity, precision, and disc similarity coefficient (DSC) of around 99.94%, 91.48%, 98.82%, 97.01%, and 94.00%, respectively. Full article
Article
A Lightweight CNN and Class Weight Balancing on Chest X-ray Images for COVID-19 Detection
Electronics 2022, 11(23), 4008; https://doi.org/10.3390/electronics11234008 (registering DOI) - 02 Dec 2022
Abstract
In many locations, reverse transcription polymerase chain reaction (RT-PCR) tests are used to identify COVID-19. It could take more than 48 h. It is a key factor in its seriousness and quick spread. Images from chest X-rays are utilized to diagnose COVID-19. Which [...] Read more.
In many locations, reverse transcription polymerase chain reaction (RT-PCR) tests are used to identify COVID-19. It could take more than 48 h. It is a key factor in its seriousness and quick spread. Images from chest X-rays are utilized to diagnose COVID-19. Which generally deals with the issue of imbalanced classification. The purpose of this paper is to improve CNN’s capacity to display Chest X-ray pictures when there is a class imbalance. CNN Training has come to an end while chastening the classes for using more examples. Additionally, the training data set uses data augmentation. The achievement of the suggested method is assessed on an image’s two data sets of chest X-rays. The suggested model’s efficiency was analyzed using criteria like accuracy, specificity, sensitivity, and F1 score. The suggested method attained an accuracy of 94% worst, 97% average, and 100% best cases, respectively, and an F1-score of 96% worst, 98% average and 100% best cases, respectively. Full article
(This article belongs to the Special Issue Medical Image Processing Using AI)
Show Figures

Figure 1

Article
Privacy-Enhanced Federated Learning: A Restrictively Self-Sampled and Data-Perturbed Local Differential Privacy Method
Electronics 2022, 11(23), 4007; https://doi.org/10.3390/electronics11234007 (registering DOI) - 02 Dec 2022
Abstract
As a popular distributed learning framework, federated learning (FL) enables clients to conduct cooperative training without sharing data, thus having higher security and enjoying benefits in processing large-scale, high-dimensional data. However, by sharing parameters in the federated learning process, the attacker can still [...] Read more.
As a popular distributed learning framework, federated learning (FL) enables clients to conduct cooperative training without sharing data, thus having higher security and enjoying benefits in processing large-scale, high-dimensional data. However, by sharing parameters in the federated learning process, the attacker can still obtain private information from the sensitive data of participants by reverse parsing. Local differential privacy (LDP) has recently worked well in preserving privacy for federated learning. However, it faces the inherent problem of balancing privacy, model performance, and algorithm efficiency. In this paper, we propose a novel privacy-enhanced federated learning framework (Optimal LDP-FL) which achieves local differential privacy protection by the client self-sampling and data perturbation mechanisms. We theoretically analyze the relationship between the model accuracy and client self-sampling probability. Restrictive client self-sampling technology is proposed which eliminates the randomness of the self-sampling probability settings in existing studies and improves the utilization of the federated system. A novel, efficiency-optimized LDP data perturbation mechanism (Adaptive-Harmony) is also proposed, which allows an adaptive parameter range to reduce variance and improve model accuracy. Comprehensive experiments on the MNIST and Fashion MNIST datasets show that the proposed method can significantly reduce computational and communication costs with the same level of privacy and model utility. Full article
(This article belongs to the Special Issue Artificial Intelligence Based on Data Mining)
Show Figures

Graphical abstract

Article
An Approach for Analyzing Cyber Security Threats and Attacks: A Case Study of Digital Substations in Norway
Electronics 2022, 11(23), 4006; https://doi.org/10.3390/electronics11234006 (registering DOI) - 02 Dec 2022
Viewed by 4
Abstract
In this paper, we provide an approach for analyzing cyber security threats and attacks in digital substations, which is based on several steps we performed within our work on two Research Council of Norway (RCN) projects. In the literature, there are various separate [...] Read more.
In this paper, we provide an approach for analyzing cyber security threats and attacks in digital substations, which is based on several steps we performed within our work on two Research Council of Norway (RCN) projects. In the literature, there are various separate or theoretical concepts to understand and follow a security analysis of smart grids in general, but none is focused specifically on digital substations. Moreover, none is showing real applicability on an existing use case, making the implementation difficult. The approach we propose here is a result of our attempts to create a comprehensive overview of the individual steps we have been taking to do the analysis. For that reason, firstly, we start with defining and explaining a digital substation and its concepts, and the security challenges related to digital substations. Afterwards, we present the main steps of the security analysis for digital substation. The first step is the security pyramid. The following steps are threat analysis, threat modeling, risk assessment and the simulation impact analysis, which are another contribution from our group presented in this paper. Considering that the main goal of a security analysis is to create awareness for the stakeholders of digital substations, such an impact simulation provides a flexible way for stakeholders to see and to understand the consequences of security threats and attacks. We summarize the paper with an illustration of the steps we are taking in the form of the approach for digital substation. Full article
(This article belongs to the Special Issue Simulation Modelling of Smart Grid Security and Dependability)
Article
Application of Skeletonization-Based Method in Solving Inverse Scattering Problems
Electronics 2022, 11(23), 4005; https://doi.org/10.3390/electronics11234005 (registering DOI) - 02 Dec 2022
Viewed by 118
Abstract
In electromagnetic inverse scattering problems, Scattered field commonly needs to be measured by a large number of receiving antennas to provide enough scattered information for image reconstruction, which may increase the cost of the experimental system and require a long testing time. In [...] Read more.
In electromagnetic inverse scattering problems, Scattered field commonly needs to be measured by a large number of receiving antennas to provide enough scattered information for image reconstruction, which may increase the cost of the experimental system and require a long testing time. In this paper, a skeletonization-based method was proposed to reduce the number of actual receiving antennas involved in an inverse scattering system. The skeleton points were obtained by performing a strong-rank-revealing QR factorization of Green’s function matrix. By measuring the scattered field only at the skeleton points, the number of receiving antennas could be effectively reduced, while the scattered field data at other receiving points could be accurately restored from the skeleton points. The numerical results show that, compared with the frequency domain zero-padding (FDZP) method, the skeletonization-based method was more accurate for antennas distributed in an elliptical shape (such as thorax imaging). In addition, the inverse scattering method using the skeletonization-based method was able to reduce the number of measurements while maintaining an image quality comparable to that of the actual full measurement system. The proposed method can serve as a guidance for building an experimental system for inverse scattering problems, especially for cases when the antennas are elliptically distributed. Full article
Show Figures

Figure 1

Article
Self-Decoupled MIMO Antenna Realized by Adjusting the Feeding Positions
Electronics 2022, 11(23), 4004; https://doi.org/10.3390/electronics11234004 (registering DOI) - 02 Dec 2022
Viewed by 80
Abstract
This paper proposes a novel decoupling technique achieved by adjusting the position of feeding probes of antennas. Two inherent radiation modes (patch mode and monopole mode), with different patterns and polarizations, are simultaneously excited by the same feeding probe. High isolation is realized [...] Read more.
This paper proposes a novel decoupling technique achieved by adjusting the position of feeding probes of antennas. Two inherent radiation modes (patch mode and monopole mode), with different patterns and polarizations, are simultaneously excited by the same feeding probe. High isolation is realized based on manipulating the relationship of two-mode couplings by moving the feeding positions. Since the two radiation modes are generated by the same antenna element, the proposed MIMO antenna features a simple structure and compact size. For verification, a two-element array with center-to-center spacing of 0.404 λ0 (λ0 is the wavelength in the air) is prototyped and characterized. Simulation and experimental results show that the proposed novel technique can offer higher port isolation (>18.1 dB), increased efficiency (>70%), and a lower envelope correlation coefficient (ECC < 0.1) in the operating frequency band (11.61–12.49 GHz). Full article
(This article belongs to the Special Issue CMOS Chips for Sensing and Communication)
Show Figures

Figure 1

Review
Survey of Credit Card Anomaly and Fraud Detection Using Sampling Techniques
Electronics 2022, 11(23), 4003; https://doi.org/10.3390/electronics11234003 (registering DOI) - 02 Dec 2022
Viewed by 80
Abstract
The rapid growth in e-commerce has resulted in an increasing number of people shopping online. These shoppers depend on credit cards as a payment method or use mobile wallets to pay for their purchases. Thus, credit cards have become the main payment method [...] Read more.
The rapid growth in e-commerce has resulted in an increasing number of people shopping online. These shoppers depend on credit cards as a payment method or use mobile wallets to pay for their purchases. Thus, credit cards have become the main payment method in the e-world. Given the billions of transactions that occur daily, criminals see tremendous opportunities to be gained from finding different ways of attacking and stealing credit card information. Fraudulent credit card transactions are a serious business issue, and such ‘scams’ can result in significant financial and personal losses. As a result, businesses are increasingly investing in the development of new ideas and methods for detecting and preventing fraud to secure their customers’ trust to protect their privacy. In recent years, learning algorithms have emerged as important in research areas aimed at developing optimal solutions to this issue. The core challenge currently facing researchers is that of the imbalanced credit card dataset, in which the data are highly skewed and the number of normal transactions is much higher than fraudulent transactions, which thus negatively affects the performance of credit card fraud detection. This paper reviews the sampling techniques and their importance in solving the imbalanced data problem. Past research is found to show that hybrid sampling techniques will produce excellent results that can improve the fraud detection system. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

Article
Analysis and Optimization Based on Factors Affecting the Spiral Climbing Locomotion of Snake-like Robot
Electronics 2022, 11(23), 4002; https://doi.org/10.3390/electronics11234002 (registering DOI) - 02 Dec 2022
Viewed by 80
Abstract
The snake-like robot is a limbless bionic robot widely used in unstructured environments to perform tasks with substantial functional flexibility and environmental adaptability in complex environments. In this paper, the spiral climbing motion of a snake-like robot on the outer surface of a [...] Read more.
The snake-like robot is a limbless bionic robot widely used in unstructured environments to perform tasks with substantial functional flexibility and environmental adaptability in complex environments. In this paper, the spiral climbing motion of a snake-like robot on the outer surface of a cylindrical object was studied based on the three-dimensional motion of a biological snake, and we carried out the analysis and optimization of the motion-influencing factors. First, the spiral climbing motion of the snake-like robot was implemented by the angle control method, and the target motion was studied and analyzed by combining numerical and environmental simulations. We integrated the influence of kinematics and dynamics factors on the spiral climbing motion. Based on this, we established a multi-objective optimization function that utilized the influence factors to optimize the joint module. In addition, through dynamics simulation analysis, the change of the general clamping force of the snake-like robot’s spiral climbing motion was transformed into the analysis of the contact force between the joint module and the cylinder. On the basis of the results, the effect of the control strategy adopted in this paper on the motion and change rule of the spiral climbing motion was analyzed. This paper presents the analysis of the spiral climbing motion, which is of great theoretical significance and engineering value for the realization of the three-dimensional motion of the snake-like robot. Full article
Show Figures

Figure 1

Article
Multitask Learning Based Intra-Mode Decision Framework for Versatile Video Coding
Electronics 2022, 11(23), 4001; https://doi.org/10.3390/electronics11234001 (registering DOI) - 02 Dec 2022
Viewed by 85
Abstract
In mid-2020, the new international video coding standard, namely versatile video coding (VVC), was officially released by the Joint Video Expert Team (JVET). As its name indicates, the VVC enables a higher level of versatility with better compression performance compared to its predecessor, [...] Read more.
In mid-2020, the new international video coding standard, namely versatile video coding (VVC), was officially released by the Joint Video Expert Team (JVET). As its name indicates, the VVC enables a higher level of versatility with better compression performance compared to its predecessor, high-efficiency video coding (HEVC). VVC introduces several new coding tools like multiple reference lines (MRL) and matrix-weighted intra-prediction (MIP), along with several improvements on the block-based hybrid video coding scheme such as quatree with nested multi-type tree (QTMT) and finer-granularity intra-prediction modes (IPMs). Because finding the best encoding decisions is usually preceded by optimizing the rate distortion (RD) cost, introducing new coding tools or enhancing existing ones requires additional computations. In fact, the VVC is 31 times more complex than the HEVC. Therefore, this paper aims to reduce the computational complexity of the VVC. It establishes a large database for intra-prediction and proposes a multitask learning (MTL)-based intra-mode decision framework. Experimental results show that our proposal enables up to 30% of complexity reduction while slightly increasing the Bjontegaard bit rate (BD-BR). Full article
(This article belongs to the Special Issue Video Coding, Processing, and Delivery for Future Applications)
Show Figures

Figure 1

Article
Design and Evaluation of a Personal Robot Playing a Self-Management for Children with Obesity
Electronics 2022, 11(23), 4000; https://doi.org/10.3390/electronics11234000 - 02 Dec 2022
Viewed by 118
Abstract
The preponderance of obesity and being overweight among children has increased significantly during the last two decades in Saudi Arabia and United Arab Emirates (UAE) with overwhelming consequences to public health. Most recommended approaches have paid attention to a healthier diet and physical [...] Read more.
The preponderance of obesity and being overweight among children has increased significantly during the last two decades in Saudi Arabia and United Arab Emirates (UAE) with overwhelming consequences to public health. Most recommended approaches have paid attention to a healthier diet and physical activity (PA) to reduce obesity. Recent research shows that the use of social robots could play a vital role in encouraging children to improve their skills in self-management. As children need to be surprised and feel a sense of enjoyment when involved in any activity where they can spend time and actively engage in activities, social robots could be an effective intervention for this purpose. In this context, the current project aimed to build an innovation social robot system to offer a set of activities to help obese children improve their capabilities to manage their selves properly and increase their obesity knowledge. This study aimed to determine the perceptions of obese children towards the NAO robot, a new medical technology, and analyze their responses to the robot’s advice and education-related activities. A proposed model of the intervention using the NAO robot is discussed in this study, and a pilot study was conducted to assess the performance of the proposed system. The obtained results showed an average acceptability of 89.37% for social robots to be involved in obesity management. Full article
(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)
Show Figures

Figure 1

Article
A Novel Ensemble Weight-Assisted Yolov5-Based Deep Learning Technique for the Localization and Detection of Malaria Parasites
Electronics 2022, 11(23), 3999; https://doi.org/10.3390/electronics11233999 - 02 Dec 2022
Viewed by 137
Abstract
The traditional way of diagnosing malaria takes time, as physicians have to check about 5000 cells to produce the final report. The accuracy of the final report also depends on the physician’s expertise. In the event of a malaria epidemic, a shortage of [...] Read more.
The traditional way of diagnosing malaria takes time, as physicians have to check about 5000 cells to produce the final report. The accuracy of the final report also depends on the physician’s expertise. In the event of a malaria epidemic, a shortage of qualified physicians can become a problem. In the manual method, the parasites are identified by visual identification; this technique can be automated with the use of new algorithms. There are numerous publicly available image datasets containing the intricate structure of parasites, and deep learning algorithms can recognize these complicated patterns in the images. This study aims to identify and localize malaria parasites in the photograph of blood cells using the YOLOv5 model. In this research, a publicly available malaria trophozoite dataset is utilized which contains 1182 data samples. YOLOv5, with the novel technique of weight ensemble and traditional transfer learning, is trained using this dataset, and the results were compared with the other object detection models—for instance, Faster RCNN, SSD net, and the hybrid model. It was observed that YOLOv5 with the ensemble weights yields better results in terms of precision, recall, and mAP values: 0.76, 0.78, and 0.79, respectively. The mAP score closer to 1 signifies a higher confidence in localizing the parasites. This study is the first implementation of ensemble YOLOv5 in the malaria parasite detection field. The proposed ensemble model can detect the presence of malaria parasites and localize them with bounding boxes better than previously used models. Full article
Show Figures

Figure 1

Article
Teacher–Student Behavior Recognition in Classroom Teaching Based on Improved YOLO-v4 and Internet of Things Technology
Electronics 2022, 11(23), 3998; https://doi.org/10.3390/electronics11233998 - 02 Dec 2022
Viewed by 137
Abstract
Based on the classroom teaching scenarios, an improved YOLO-v4 behavior detection algorithm is proposed to recognize the behaviors of teachers and students. With the development of CNN (Convolutional Neural Networks) and IoT (Internet of Things) technologies, target detection algorithms based on deep learning [...] Read more.
Based on the classroom teaching scenarios, an improved YOLO-v4 behavior detection algorithm is proposed to recognize the behaviors of teachers and students. With the development of CNN (Convolutional Neural Networks) and IoT (Internet of Things) technologies, target detection algorithms based on deep learning have become mainstream, and typical algorithms such as SSD (Single Shot Detection) and YOLO series have emerged. Based on the videos or images collected in the perception layer of the IoT paradigm, deep learning models are used in the processing layer to implement various intelligent applications. However, none of these deep learning-based algorithms are perfect, and there is room for improvement in terms of detection accuracy, computing speed, and multi-target detection capabilities. In this paper, by introducing the concept of cross-stage local network, embedded connection (EC) components are constructed and embedded at the end of the YOLO-v4 network to obtain an improved YOLO-v4 network. Aiming at the problem that it is difficult to quickly and effectively identify the students’ actions when they are occluded, the Repulsion loss function is connected in series on the basis of the original YOLO-v4 loss function. The newly added loss function consists of two parts: RepGT loss and RepBox loss. The RepGT loss function is used to calculate the loss values between the target prediction box and the adjacent ground truth boxes to reduce false positive detection results; the RepBox loss function is used to calculate the loss value between the target prediction box and other adjacent target prediction boxes to reduce false negative detection results. The training and testing are carried out on the classroom behavior datasets of teachers and students, respectively. The experimental results show that the average precision of identifying various classroom behaviors of different targets exceeds 90%, which verifies the effectiveness of the proposed method. The model performs well in sustainable classroom behavior recognition in educational context, accurate recognition of classroom behaviors can help teachers and students better understand classroom learning and promote the development of intelligent classroom model. Full article
(This article belongs to the Special Issue Recent Innovations in Computing and Electronics)
Show Figures

Figure 1

Article
An Optical Encoder Chip with Area Compensation
Electronics 2022, 11(23), 3997; https://doi.org/10.3390/electronics11233997 - 02 Dec 2022
Viewed by 143
Abstract
A photodiode area-compensation method based on light intensity distribution characteristics is introduced to solve the problem of the hybrid optical encoder’s inconsistent absolute code output signals. This method performs area compensation of different degrees according to the irradiance received by the photodiodes at [...] Read more.
A photodiode area-compensation method based on light intensity distribution characteristics is introduced to solve the problem of the hybrid optical encoder’s inconsistent absolute code output signals. This method performs area compensation of different degrees according to the irradiance received by the photodiodes at different positions, thus achieving the consistency of output signals and reducing the bit error rate of absolute code signals. Based on the 0.35 μmm CMOS process, a four-channel photodiode array chip for a reflective hybrid optical encoder was designed. Moreover, the absolute code photodiode arrays were designed with area compensation. The test results show that the square wave duty cycle error of the output signals is less than 2% when the LED light source works normally. When the LED working current changes by ±2.85 mA, the output signal’s square wave duty cycle error is less than 3.1%. In each case, the square wave duty cycle error of the output signals is small, so it can be seen that the area compensation method based on light intensity distribution can achieve good consistency of the output signal. The chip has been taped and packaged, and the chip area is 21.45 mm2. Full article
(This article belongs to the Section Semiconductor Devices)
Show Figures

Figure 1

Article
Deep Learning for Predicting Congestive Heart Failure
Electronics 2022, 11(23), 3996; https://doi.org/10.3390/electronics11233996 - 02 Dec 2022
Viewed by 161
Abstract
Congestive heart failure (CHF) is one of the most debilitating cardiac disorders. It is a costly disease in terms of both lives and financial outlays, given the high rate of hospital re-admissions and mortality. Heart failure (HF) is notoriously difficult to identify on [...] Read more.
Congestive heart failure (CHF) is one of the most debilitating cardiac disorders. It is a costly disease in terms of both lives and financial outlays, given the high rate of hospital re-admissions and mortality. Heart failure (HF) is notoriously difficult to identify on time, and is frequently accompanied by additional comorbidities that further complicate diagnosis. Many decision support systems (DSS) have been developed to facilitate diagnosis and to raise the standard of screening and monitoring operations, even for non-expert staff. This is confirmed in the literature by records of highly performing diagnosis-aid systems, which are unfortunately not very relevant to expert cardiologists. In order to assist cardiologists in predicting the trajectory of HF, we propose a deep learning-based system which predicts severity of disease progression by employing medical patient history. We tested the accuracy of four models on a labeled dataset, composed of 1037 records, to predict CHF severity and progression, achieving results comparable to studies based on much larger datasets, none of which used longitudinal multi-class prediction. The main contribution of this work is that it demonstrates that a fairly complicated approach can achieve good results on a medium size dataset, providing a reasonably accurate means of determining the evolution of CHF well in advance. This potentially constitutes a significant aid for healthcare managers and expert cardiologists in designing different therapies for medication, healthy lifestyle changes and quality of life (QoL) management, while also promoting allocation of resources with an evidence-based approach. Full article
(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)
Show Figures

Graphical abstract

Article
Study on Score Prediction Model with High Efficiency Based on Deep Learning
Electronics 2022, 11(23), 3995; https://doi.org/10.3390/electronics11233995 - 02 Dec 2022
Viewed by 138
Abstract
In the problem of unified classroom performance prediction, there is a certain lag in the prediction, and there are also problems such as the data sparsity and single feature in the data. In addition, feature engineering is often carried out manually in modeling, [...] Read more.
In the problem of unified classroom performance prediction, there is a certain lag in the prediction, and there are also problems such as the data sparsity and single feature in the data. In addition, feature engineering is often carried out manually in modeling, which highly depends on the professional knowledge and experience of engineers and affects the accuracy of the prediction to a certain extent. To solve the abovementioned gaps, we proposed an online course score prediction model with a high time efficiency that combines multiple features. The model uses a deep neural network, which can automatically carry out feature engineering and reduce the intervention of artificial feature engineering, thus significantly improving the time efficiency. Secondly, the model uses a factorization machine and two kinds of neural networks to consider the influence of first-order features, second-order features, and higher-order features at the same time, and it fully learns the relationship between the features and scores, which improves the prediction effect of the model compared to using only single feature learning. The performance of the model is evaluated on the learning analysis dataset from Fall 2015 to Spring 2021 and includes 412 courses with 600 students. The experimental results show that the performance of the prediction model based on the feature combination proposed in the present study is better than the previous performance prediction model. More importantly, our model has the best time efficiency of below 0.3 compared to the other models. Full article
(This article belongs to the Special Issue Efficient Machine Learning for the Internet of Things)
Show Figures

Figure 1

Article
Macro Model for Discrete-Time Sigma‒Delta Modulators
Electronics 2022, 11(23), 3994; https://doi.org/10.3390/electronics11233994 - 02 Dec 2022
Viewed by 160
Abstract
This work presents a macro model for discrete-time sigma‒delta modulators, which can significantly reduce the simulation time compared to transistor level circuits. The proposed macro model is realized by effectively combining active and passive ideal circuit components with Verilog-A modules. As such, since [...] Read more.
This work presents a macro model for discrete-time sigma‒delta modulators, which can significantly reduce the simulation time compared to transistor level circuits. The proposed macro model is realized by effectively combining active and passive ideal circuit components with Verilog-A modules. As such, since the macro model is a true representation of the actual transistor level circuit, a moderately good accuracy can be obtained. In addition, the proposed macro model includes the major amplifier, comparator, and switch‒capacitor non-idealities of the sigma‒delta modulator such as amplifier DC gain, GBW, slewrate, comparator bandwidth, hysteresis, parasitic capacitance, and switch-on resistance. The results show the simulation time of the proposed macro model sigma‒delta modulator is only 6.43% of the transistor level circuit with comparable accuracy. As a result, the proposed macro model can facilitate the circuit design and leverage non-ideality analysis of discrete-time sigma‒delta modulators. As a practical design example, a second order discrete-time sigma‒delta modulator with a five-level quantizer is realized using the propose macro model for GSM and WCDMA applications. Full article
Show Figures

Figure 1

Article
Industrial Fault Detection Based on Discriminant Enhanced Stacking Auto-Encoder Model
Electronics 2022, 11(23), 3993; https://doi.org/10.3390/electronics11233993 - 02 Dec 2022
Viewed by 163
Abstract
In the recent years, deep learning has been widely used in process monitoring due to its strong ability to extract features. However, with the increasing layers of the deep network, the compression of features by the deep model will lead to the loss [...] Read more.
In the recent years, deep learning has been widely used in process monitoring due to its strong ability to extract features. However, with the increasing layers of the deep network, the compression of features by the deep model will lead to the loss of some valuable information and affect the model’s performance. To solve this problem, a fault detection method based on a discriminant enhanced stacked auto-encoder is proposed. An enhanced stacked auto-encoder network structure is designed, and the original data is added to each hidden layer in the model pre-training process to solve the problem of information loss in the feature extraction process. Then the self-encoding network is combined with spectral regression kernel discriminant analysis. The fault category information is introduced into the features to optimize the features and enhance the discrimination of the extracted features. The Euclidean distance is used for fault detection based on the extracted features. From the Tennessee Eastman process experiment, it can be found that the detection accuracy of this method is about 9.4% higher than that of the traditional stacked auto-encoder method. Full article
Show Figures

Figure 1

Article
Hybrid Convolutional Network Combining 3D Depthwise Separable Convolution and Receptive Field Control for Hyperspectral Image Classification
Electronics 2022, 11(23), 3992; https://doi.org/10.3390/electronics11233992 - 01 Dec 2022
Viewed by 113
Abstract
Deep-learning-based methods have been widely used in hyperspectral image classification. In order to solve the problems of the excessive parameters and computational cost of 3D convolution, and loss of detailed information due to the excessive increase in the receptive field in pursuit of [...] Read more.
Deep-learning-based methods have been widely used in hyperspectral image classification. In order to solve the problems of the excessive parameters and computational cost of 3D convolution, and loss of detailed information due to the excessive increase in the receptive field in pursuit of multi-scale features, this paper proposes a lightweight hybrid convolutional network called the 3D lightweight receptive control network (LRCNet). The proposed network consists of a 3D depthwise separable convolutional network and a receptive field control network. The 3D depthwise separable convolutional network uses the depthwise separable technique to capture the joint features of spatial and spectral dimensions while reducing the number of computational parameters. The receptive field control network ensures the extraction of hyperspectral image (HSI) details by controlling the convolution kernel. In order to verify the validity of the proposed method, we test the classification accuracy of the LRCNet based on three public datasets, which exceeds 99.50% The results show that compare with state-of-the-art methods, the proposed network has competitive classification performance. Full article
Article
A Platform for Analysing Huge Amounts of Data from Households, Photovoltaics, and Electrical Vehicles: From Data to Information
Electronics 2022, 11(23), 3991; https://doi.org/10.3390/electronics11233991 - 01 Dec 2022
Viewed by 141
Abstract
Analytics is an essential procedure to acquire knowledge and support applications for determining electricity consumption in smart homes. Electricity variables measured by the smart meter (SM) produce a significant amount of data on consumers, making the data sets very sizable and the analytics [...] Read more.
Analytics is an essential procedure to acquire knowledge and support applications for determining electricity consumption in smart homes. Electricity variables measured by the smart meter (SM) produce a significant amount of data on consumers, making the data sets very sizable and the analytics complex. Data mining and emerging cloud computing technologies make collecting, processing, and analysing the so-called big data possible. The monitoring and visualization of information aid in personalizing applications that benefit both homeowners and researchers in analysing consumer profiles. This paper presents a smart meter for household (SMH) to obtain load profiles and a new platform that allows the innovative analysis of captured Internet of Things data from smart homes, photovoltaics, and electrical vehicles. We propose the use of cloud systems to enable data-based services and address the challenges of complexities and resource demands for online and offline data processing, storage, and classification analysis. The requirements and system design components are discussed. Full article
(This article belongs to the Topic IoT for Energy Management Systems and Smart Cities)
Article
Semi-Supervised Group Emotion Recognition Based on Contrastive Learning
Electronics 2022, 11(23), 3990; https://doi.org/10.3390/electronics11233990 - 01 Dec 2022
Viewed by 122
Abstract
The performance of all learning-based group emotion recognition (GER) methods depends on the number of labeled samples. Although there are lots of group emotion images available on the Internet, labeling them manually is a labor-intensive and cost-expensive process. For this reason, datasets for [...] Read more.
The performance of all learning-based group emotion recognition (GER) methods depends on the number of labeled samples. Although there are lots of group emotion images available on the Internet, labeling them manually is a labor-intensive and cost-expensive process. For this reason, datasets for GER are usually small in size, which limits the performance of GER. Considering labeling manually is challenging, using limited labeled images and a large number of unlabeled images in the network training is a potential way to improve the performance of GER. In this work, we propose a semi-supervised group emotion recognition framework based on contrastive learning to learn efficient features from both labeled and unlabeled images. In the proposed method, the unlabeled images are used to pretrain the backbone by a contrastive learning method, and the labeled images are used to fine-tune the network. The unlabeled images are then given pseudo-labels by the fine-tuned network and used for further training. In order to alleviate the uncertainty of the given pseudo-labels, we propose a Weight Cross-Entropy Loss (WCE-Loss) to suppress the influence of the samples with unreliable pseudo-labels in the training process. Experiment results on three prominent benchmark datasets for GER show the effectiveness of the proposed framework and its superiority compared with other competitive state-of-the-art methods. Full article
(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications, Volume II)
Article
A Novel Expert System for the Diagnosis and Treatment of Heart Disease
Electronics 2022, 11(23), 3989; https://doi.org/10.3390/electronics11233989 - 01 Dec 2022
Viewed by 173
Abstract
The diagnosis of diseases in their early stages can assist us in preventing life-threatening infections and caring for them better than in the last phase because prevention is better than cure. The death rate can be very high due to the unapproachability of [...] Read more.
The diagnosis of diseases in their early stages can assist us in preventing life-threatening infections and caring for them better than in the last phase because prevention is better than cure. The death rate can be very high due to the unapproachability of diagnosed patients at an early point. Expert systems help us to defeat the problem mentioned above and enable us to automatically diagnose diseases in their early phases. Expert systems use a fuzzy, rule-based inference engine to provide forward-chain methods for diagnosing the patient. In this research, data have been gathered from different sources, such as a hospital, by performing the test on the patients’ age, gender, blood sugar, heart rate, and ECG to calculate the values. The proposed expert system for medical diagnosis can be used to find minimum disease levels and demonstrate the predominant method for curing different medical diseases, such as heart diseases. In the next step, the diagnostic test at the hospital with the novel expert system, the crisp, fuzzy value is generated for input into the expert system. After taking the crisp input, the expert system starts working on fuzzification and compares it with the knowledge base processed by the inference engine. After the fuzzification, the next step starts with the expert system in the defuzzification process converting the fuzzy sets’ value into a crisp value that is efficient for human readability. Later, the expert physician system’s diagnosis calculates the value by using fuzzy sets, and gives an output to determine the patient’s heart disease. In one case, the diagnosis step was accomplished, and the expert system provided the yield with the heart disease risk level as “low”, “high”, or “risky”. After the expert system’s responsibilities have been completed, the physician decides on the treatment and recommends a proper dose of medicine according to the level the expert system provided after the diagnosis step. The findings indicate that this research achieves better performance in finding appropriate heart disease risk levels, while also fulfilling heart disease patient treatment due to the physicians shortfalls. Full article
(This article belongs to the Special Issue Future Prospects of IoMT for Smart Healthcare Systems (ICSCA2022))
Show Figures

Figure 1

Article
Implementation and Experimental Verification of Resistorless Fractional-Order Basic Filters
Electronics 2022, 11(23), 3988; https://doi.org/10.3390/electronics11233988 - 01 Dec 2022
Viewed by 165
Abstract
Novel structures of fractional-order differentiation and integration stages are presented in this work, where passive resistors are not required for their implementation. This has been achieved by considering the inherent resistive behavior of fractional-order capacitors. The implementation of the presented stages is performed [...] Read more.
Novel structures of fractional-order differentiation and integration stages are presented in this work, where passive resistors are not required for their implementation. This has been achieved by considering the inherent resistive behavior of fractional-order capacitors. The implementation of the presented stages is performed using a current feedback operational amplifier as active element and fractional-order capacitors based on multi-walled carbon nano-tubes. Basic filter and controller stages are realized using the introduced fundamental blocks, and their behavior is evaluated through experimental results. Full article
(This article belongs to the Special Issue Feature Papers in Circuit and Signal Processing)
Show Figures

Figure 1

Article
Automatic Knee Injury Identification through Thermal Image Processing and Convolutional Neural Networks
Electronics 2022, 11(23), 3987; https://doi.org/10.3390/electronics11233987 - 01 Dec 2022
Viewed by 154
Abstract
Knee injury is a common health problem that affects both people who practice sports and those who do not do it. The high prevalence of knee injuries produces a considerable impact on the health-related life quality of patients. For this reason, it is [...] Read more.
Knee injury is a common health problem that affects both people who practice sports and those who do not do it. The high prevalence of knee injuries produces a considerable impact on the health-related life quality of patients. For this reason, it is essential to develop procedures for an early diagnosis, allowing patients to receive timely treatment for preventing and correcting knee injuries. In this regard, this paper presents, as main contribution, a methodology based on infrared thermography (IT) and convolutional neural networks (CNNs) to automatically differentiate between a healthy knee and an injured knee, being an alternative tool to help medical specialists. In general, the methodology consists of three steps: (1) database generation, (2) image processing, and (3) design and validation of a CNN for automatically identifying a patient with an injured knee. In the image-processing stage, grayscale images, equalized images, and thermal images are obtained as inputs for the CNN, where 98.72% of accuracy is obtained by the proposed method. To test its robustness, different infrared images with changes in rotation angle and different brightness levels (i.e., possible conditions at the time of imaging) are used, obtaining 97.44% accuracy. These results demonstrate the effectiveness and robustness of the proposal for differentiating between a patient with a healthy knee and an injured knee, having the advantages of using a fast, low-cost, innocuous, and non-invasive technology. Full article
(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications, Volume II)
Show Figures

Figure 1

Article
SARIMA: A Seasonal Autoregressive Integrated Moving Average Model for Crime Analysis in Saudi Arabia
Electronics 2022, 11(23), 3986; https://doi.org/10.3390/electronics11233986 - 01 Dec 2022
Viewed by 164
Abstract
Crimes have clearly had a detrimental impact on a nation’s development, prosperity, reputation, and economy. The issue of crime has become one of the most pressing concerns in societies, thus reducing the crime rate has become an increasingly critical task. Recently, several studies [...] Read more.
Crimes have clearly had a detrimental impact on a nation’s development, prosperity, reputation, and economy. The issue of crime has become one of the most pressing concerns in societies, thus reducing the crime rate has become an increasingly critical task. Recently, several studies have been proposed to identify the causes and occurrences of crime in order to identify ways to reduce crime rates. However, few studies have been conducted in Saudi Arabia technological solutions based on crime analysis. The analysis of crime can help governments identify hotspots of crime and monitor crime distribution. This study aims to investigate which Saudi Arabian areas will experience increased crime rates in the coming years. This research helps law enforcement agencies to effectively utilize available resources in order to reduce crime rates. This paper proposes SARIMA model which focuses on identifying factors that affect crimes in Saudi Arabia, estimating a reasonable crime rate, and identifying the likelihood of crime distribution based on various locations. The dataset used in this study is obtained from Saudi Arabian official government channels. There is detailed information related to time and place along with crime statistics pertaining to different types of crimes. Furthermore, the new proposed method performs better than other traditional classifiers such as Linear Regression, XGB, and Random Forest. Finally, SARIMA model has an MAE score of 0.066559, which is higher than the other models. Full article
Show Figures

Figure 1

Article
A Survey on Citizens Broadband Radio Service (CBRS)
Electronics 2022, 11(23), 3985; https://doi.org/10.3390/electronics11233985 - 01 Dec 2022
Viewed by 144
Abstract
To leverage the existing spectrum and mitigate the global spectrum dearth, the Federal Communications Commission of the United States has recently opened the Citizens Broadband Radio Service (CBRS) spectrum, spanning 3550–3700 MHz, for commercial cognitive operations. The CBRS has a three-tier hierarchical architecture, [...] Read more.
To leverage the existing spectrum and mitigate the global spectrum dearth, the Federal Communications Commission of the United States has recently opened the Citizens Broadband Radio Service (CBRS) spectrum, spanning 3550–3700 MHz, for commercial cognitive operations. The CBRS has a three-tier hierarchical architecture, wherein the incumbents, including military radars, occupy the topmost tier. The priority access licenses (PAL) and general authorized access (GAA) are second and third tier, respectively, facilitating licensed and unlicensed access to the spectrum. This combination of licensed and unlicensed access to the spectrum in a three-tier model has opened novel research directions in optimal spectrum sharing as well as privacy preservation, and hence, several schemes have been proposed for the same. This article provides a detailed survey of the existing literature on the CBRS. We provide an overview of the CBRS ecosystem and discuss the regulation and standardization process and industrial developments on the CBRS. The existing schemes for optimal spectrum sharing and resource allocation in CBRS are discussed in detail. Further, an in-depth study of the existing literature on the privacy of incumbents, PAL devices, and GAA devices in CBRS is presented. Finally, we discuss the open issues in CBRS, which demand more attention and effort. Full article
Show Figures

Figure 1

Article
Design Optimization of an Efficient Bicolor LED Driving System
Electronics 2022, 11(23), 3984; https://doi.org/10.3390/electronics11233984 - 01 Dec 2022
Viewed by 222
Abstract
There are some challenges involved in the design of a multicolor LED driver, such as the precise control of color consistency, i.e., maintaining the correlated color temperature (CCT) and luminous intensity. CCT deviation causes a color shift of composite light. This paper approaches [...] Read more.
There are some challenges involved in the design of a multicolor LED driver, such as the precise control of color consistency, i.e., maintaining the correlated color temperature (CCT) and luminous intensity. CCT deviation causes a color shift of composite light. This paper approaches the method of nonlinear optimization of the LED currents of two LED sources to achieve the desired CCT. A bicolor blended-shade white LED system is formed by using a warm color LED source of 1000 K CCT and a cool color LED source of 6500 K CCT. By using a nonlinear optimization methodology, the reduced deviation of the blended CCT and optimum LED currents are obtained. The optimized currents in the two LED strings are maintained by the control circuit of the single-ended primary inductor converter (SEPIC). The obtained reduced deviation of the CCT is 43 K, and the precision is 99.15%. Again, harmonics in the input current hamper power quality, i.e., reduce the power factor and increase power loss. This paper proposes the harmonic reduction technique to achieve the lowest value of total harmonic distortion (THD) through the nonlinear parametric optimization of the SEPIC. Measured THD = 4.37%; PF = 0.96; and efficiency = 92.8%. The system stability was determined and found to be satisfactory. Full article
(This article belongs to the Topic Power Converters)
Show Figures

Figure 1

Article
Comparison between Piezoelectric Filter and Passive LC Filter in a Class L−Piezo Inverter
Electronics 2022, 11(23), 3983; https://doi.org/10.3390/electronics11233983 - 01 Dec 2022
Viewed by 191
Abstract
This paper presents a comparison between piezoelectric filtering and passive LC filtering integrated into an HF class L−Piezo inverter. This L−Piezo inverter is a variant of class φ2 where the filtering of the second harmonic is carried out by a piezoelectric resonator. Piezoelectric [...] Read more.
This paper presents a comparison between piezoelectric filtering and passive LC filtering integrated into an HF class L−Piezo inverter. This L−Piezo inverter is a variant of class φ2 where the filtering of the second harmonic is carried out by a piezoelectric resonator. Piezoelectric filters are well known in the signal domain (RF filtering), but their use in the field of power electronics, as a temporary energy storage element, is rather recent. In power electronics, piezoelectricity has mainly been used as a transformer, in particular, to greatly increase voltages (backlight applications). A class L−Piezo inverter with Lithium Niobate (LNO) piezoelectric resonator is designed for a switching frequency of 10.4 MHz, an input voltage of 30 V, and an output power of 15 W. To compare these two filtering methods, two prototypes are built, one with piezoelectric filtering and one with passive LC filtering. Measurements show a reduction of 60% of the losses in the filter, while the volume of the filter is reduced by a factor of 50. Full article
(This article belongs to the Topic Power Electronics Converters)
Show Figures

Figure 1

Article
Decentralized Blockchain Network for Resisting Side-Channel Attacks in Mobility-Based IoT
Electronics 2022, 11(23), 3982; https://doi.org/10.3390/electronics11233982 - 01 Dec 2022
Viewed by 270
Abstract
The inclusion of mobility-based Internet-of-Things (IoT) devices accelerates the data transmission process, thereby catering to IoT users’ demands; however, securing the data transmission in mobility-based IoT is one complex and challenging concern. The adoption of unified security architecture has been identified to prevent [...] Read more.
The inclusion of mobility-based Internet-of-Things (IoT) devices accelerates the data transmission process, thereby catering to IoT users’ demands; however, securing the data transmission in mobility-based IoT is one complex and challenging concern. The adoption of unified security architecture has been identified to prevent side-channel attacks in the IoT, which has been discussed extensively in developing security solutions. Despite blockchain’s apparent superiority in withstanding a wide range of security threats, a careful examination of the relevant literature reveals that some common pitfalls are associated with these methods. Therefore, the proposed scheme introduces a novel computational security framework wherein a branched and decentralized blockchain network is formulated to facilitate coverage from different variants of side-channel IoT attacks that are yet to be adequately reported. A unique blockchain-based authentication approach is designed to secure communication among mobile IoT devices using multiple stages of security implementation with Smart Agreement and physically unclonable functions. Analytical modeling with lightweight finite field encryption is used to create this framework in Python. The study’s benchmark results show that the proposed scheme offers 4% less processing time, 5% less computational overhead, 1% more throughput, 12% less latency, and 30% less energy consumption compared to existing blockchain methods. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

Previous Issue
Back to TopTop