Next Issue
Volume 11, December-1
Previous Issue
Volume 11, November-1
 
 

Electronics, Volume 11, Issue 22 (November-2 2022) – 196 articles

Cover Story (view full-size image): Electrically conductive paths and elements in 3D-printed electronics are usually prepared from polymer composites with carbon or metal additives or silver pastes. Here, we propose a new approach to implement fusible alloys for fabricating conductive paths inside 3D-printed polymer structures and mounting electronic components using Fused Deposition Modeling for metals (FDMm). A comparison of solder wires is discussed to determine whether the solder alloys exhibit adequate wettability and adhesion to the polymer substrate. The symmetrical astable multivibrator circuit based on bipolar junction transistors (BJT) was fabricated with the FDMm technique. Additional perspectives for applying this technique to 3D-printed structural electronic circuits are also discussed. View this paper
  • 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
Artificial Intelligence Algorithms for Detecting and Classifying MQTT Protocol Internet of Things Attacks
Electronics 2022, 11(22), 3837; https://doi.org/10.3390/electronics11223837 - 21 Nov 2022
Viewed by 546
Abstract
The Internet of Things (IoT) grew in popularity in recent years, becoming a crucial component of industrial, residential, and telecommunication applications, among others. This innovative idea promotes communication between physical components, such as sensors and actuators, to improve process flexibility and efficiency. Smart [...] Read more.
The Internet of Things (IoT) grew in popularity in recent years, becoming a crucial component of industrial, residential, and telecommunication applications, among others. This innovative idea promotes communication between physical components, such as sensors and actuators, to improve process flexibility and efficiency. Smart gadgets in IoT contexts interact using various message protocols. Message queuing telemetry transfer (MQTT) is a protocol that is used extensively in the IoT context to deliver sensor or event data. The aim of the proposed system is to create an intrusion detection system based on an artificial intelligence algorithm, which is becoming essential in the defense of the IoT networks against cybersecurity threats. This study proposes using a k-nearest neighbors (KNN) algorithm, linear discriminant analysis (LDA), a convolutional neural network (CNN), and a convolutional long short-term memory neural network (CNN-LSTM) to identify MQTT protocol IoT intrusions. A cybersecurity system based on artificial intelligence algorithms was examined and evaluated using a standard dataset retrieved from the Kaggle repository. The dataset was injected by five attacks, namely brute-force, flooding, malformed packet, SlowITe, and normal packets. The deep learning algorithm achieved high performance compared with the developing security system using machine learning algorithms. The performance accuracy of the KNN method was 80.82%, while the accuracy of the LDA algorithm was 76.60%. The CNN-LSTM model attained a high level of precision (98.94%) and is thus very effective at detecting intrusions in IoT settings. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

Article
Deep-COVID: Detection and Analysis of COVID-19 Outcomes Using Deep Learning
Electronics 2022, 11(22), 3836; https://doi.org/10.3390/electronics11223836 - 21 Nov 2022
Viewed by 406
Abstract
The coronavirus epidemic (COVID-19) is growing quickly around the globe. The first acute atypical respiratory illness was reported in December 2019, in Wuhan, China. This quickly spread from Wuhan city to other locations. Deep learning (DL) algorithms are one of the greatest solutions [...] Read more.
The coronavirus epidemic (COVID-19) is growing quickly around the globe. The first acute atypical respiratory illness was reported in December 2019, in Wuhan, China. This quickly spread from Wuhan city to other locations. Deep learning (DL) algorithms are one of the greatest solutions for consistently and readily recognizing COVID-19. Previously, many researchers used state-of-the-art approaches for the classification of COVID-19. In this paper, we present a deep learning approach with the EfficientnetB4 model, centered on transfer learning, for the classification of COVID-19. Transfer learning is a popular technique that uses pre-trained models that have been trained on the ImageNet database and employed on a new problem to increase generalization. We presented an in-depth training approach to extract the visual properties of COVID-19 in exchange for providing a medical assessment before infection testing. The proposed methodology is assessed on a publicly accessible X-ray imaging dataset. The proposed framework achieves an accuracy of 97%. Our model’s experimental findings demonstrate that it is extremely successful at identifying COVID-19 and that it may be supplied to health organizations as a precise, quick, and successful decision support system for COVID-19 identification. Full article
Show Figures

Figure 1

Article
Building Security Awareness of Interdependent Services, Business Processes, and Systems in Cyberspace
Electronics 2022, 11(22), 3835; https://doi.org/10.3390/electronics11223835 - 21 Nov 2022
Viewed by 302
Abstract
Protection against a growing number of increasingly sophisticated and complex cyberattacks requires the real-time acquisition of up-to-date information on identified threats and their potential impact on an enterprise’s operation. However, the complexity and variety of IT/OT infrastructure interdependencies and the business processes and [...] Read more.
Protection against a growing number of increasingly sophisticated and complex cyberattacks requires the real-time acquisition of up-to-date information on identified threats and their potential impact on an enterprise’s operation. However, the complexity and variety of IT/OT infrastructure interdependencies and the business processes and services it supports significantly complicate this task. Hence, we propose a novel solution here that provides security awareness of critical infrastructure entities. Appropriate measures and methods for comprehensively managing cyberspace security and resilience in an enterprise are provided, and these take into account the aspects of confidentiality, availability, and integrity of the essential services offered across the underlying business processes and IT infrastructure. The abstraction of these entities as business objects is proposed to uniformly address them and their interdependencies. In this paper, the concept of modeling the cyberspace of interdependent services, business processes, and systems and the procedures for assessing and predicting their attributes and dynamic states are depicted. The enterprise can build a model of its operation with the proposed formalism, which takes it to the first level of security awareness. Through dedicated simulation procedures, the enterprise can anticipate the evolution of actual or hypothetical threats and related risks, which is the second level of awareness. Finally, simulation-driven analyses can serve in guiding operations toward improvement with respect to resilience and threat protection, bringing the enterprise to the third level of awareness. The solution is also applied in the case study of an essential service provider. Full article
(This article belongs to the Special Issue Cybersecurity and Data Science, Volume II)
Show Figures

Figure 1

Article
Research on Short-Term Load Forecasting Based on Optimized GRU Neural Network
Electronics 2022, 11(22), 3834; https://doi.org/10.3390/electronics11223834 - 21 Nov 2022
Viewed by 367
Abstract
Accurate short-term load forecasting can ensure the safe and stable operation of power grids, but the nonlinear load increases the complexity of forecasting. In order to solve the problem of modal aliasing in historical data, and fully explore the relationship between time series [...] Read more.
Accurate short-term load forecasting can ensure the safe and stable operation of power grids, but the nonlinear load increases the complexity of forecasting. In order to solve the problem of modal aliasing in historical data, and fully explore the relationship between time series characteristics in load data, this paper proposes a gated cyclic network model (SSA–GRU) based on sparrow algorithm optimization. Firstly, the complementary sets and empirical mode decomposition (EMD) are used to decompose the original data to obtain the characteristic components. The SSA–GRU combined model is used to predict the characteristic components, and finally obtain the prediction results, and complete the short-term load forecasting. Taking the real data of a company as an example, this paper compares the combined model CEEMD–SSA–GRU with EMD–SSA–GRU, SSA–GRU, and GRU models. Experimental results show that this model has better prediction effect than other models. Full article
(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)
Show Figures

Figure 1

Article
GPGCN: A General-Purpose Graph Convolution Neural Network Accelerator Based on RISC-V ISA Extension
Electronics 2022, 11(22), 3833; https://doi.org/10.3390/electronics11223833 - 21 Nov 2022
Viewed by 329
Abstract
In the past two years, various graph convolution neural networks (GCNs) accelerators have emerged, each with their own characteristics, but their common disadvantage is that the hardware architecture is not programmable and it is optimized for a specific network and dataset. They may [...] Read more.
In the past two years, various graph convolution neural networks (GCNs) accelerators have emerged, each with their own characteristics, but their common disadvantage is that the hardware architecture is not programmable and it is optimized for a specific network and dataset. They may not support acceleration for different GCNs and may not achieve optimal hardware resource utilization for datasets of different sizes. Therefore, given the above shortcomings, and according to the development trend of traditional neural network accelerators, this paper proposes and implements GPGCN: a general-purpose GCNs accelerator architecture based on RISC-V instruction set extension, providing the software programming freedom to support acceleration for various GCNs, and achieving the best acceleration efficiency for different GCNs with different datasets. Compared with traditional CPU, and traditional CPU with vector expansion, GPGCN achieves above 1001×, 267× speedup for GCN with the Cora dataset. Compared with dedicated accelerators, GPGCN has software programmability and supports the acceleration of more GCNs. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

Article
A Hierarchical Searchable Encryption Scheme Using Blockchain-Based Indexing
Electronics 2022, 11(22), 3832; https://doi.org/10.3390/electronics11223832 - 21 Nov 2022
Viewed by 351
Abstract
Focusing on the fine-grained access control challenge of multi-user searchable encryption, we propose a hierarchical searchable encryption scheme using blockchain-based indexing (HSE-BI). First, we propose a hierarchical search index structure based on a DAG-type access policy and a stepwise hierarchical key derivation mechanism; [...] Read more.
Focusing on the fine-grained access control challenge of multi-user searchable encryption, we propose a hierarchical searchable encryption scheme using blockchain-based indexing (HSE-BI). First, we propose a hierarchical search index structure based on a DAG-type access policy and a stepwise hierarchical key derivation mechanism; which we outsourced to the blockchain network to achieve reliable hierarchical search. We design a dynamic append-only update protocol for the blockchain-based index to deal with adding and deleting files. Secondly, we propose a hierarchical authorization mechanism based on broadcast encryption to achieve fine-grained search permission granting and revoking, which can prevent a malicious server from colluding with corrupted users. The security and complexity analysis shows that HSE-BI achieves optimal search time while satisfying adaptive secure and revocation secure. Our experimental results are encouraging, e.g., compared with the traditional multi-user searchable encryption schemes, HSE-BI’s hierarchical search policy does not impact the search performance visually. The growth rate of the search latency decreases with the increasing number of hierarchical users, which can act as an efficient crypto tool to open up venues for other applications. We demonstrate that HSE-BI is more suitable for actual applications with fine-grained access requirements and can act as an efficient crypto tool to open up venues for other applications. Full article
(This article belongs to the Special Issue Privacy and Security in Blockchain-Based Internet of Things (IoT))
Show Figures

Figure 1

Article
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
Electronics 2022, 11(22), 3831; https://doi.org/10.3390/electronics11223831 - 21 Nov 2022
Viewed by 390
Abstract
Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are [...] Read more.
Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire. Full article
(This article belongs to the Special Issue Applications of Neural Networks for Speech and Language Processing)
Show Figures

Figure 1

Article
Evaluation Index for IVIS Integration Test under a Closed Condition Based on the Analytic Hierarchy Process
Electronics 2022, 11(22), 3830; https://doi.org/10.3390/electronics11223830 - 21 Nov 2022
Viewed by 437
Abstract
The intelligent vehicle infrastructure system (IVIS) requires systematic testing before being put into large-scale applications. IVIS testing under closed conditions includes stress tests for typical scenarios and extreme scenario strength testing. To extract IVIS integration test indicators under closed conditions, this article constructed [...] Read more.
The intelligent vehicle infrastructure system (IVIS) requires systematic testing before being put into large-scale applications. IVIS testing under closed conditions includes stress tests for typical scenarios and extreme scenario strength testing. To extract IVIS integration test indicators under closed conditions, this article constructed a hierarchical framework of IVIS’s evaluation indexes in the stress tests and the strength tests. The hierarchical framework of IVIS stress test evaluation indicators reflect the highway construction area under typical scenarios, and the hierarchical framework of IVIS strength test evaluation indicators reflect the highway merging area under extreme scenarios. Both are based on the test requirements of the stress test and strength test, with safety as the evaluation objective. Second, the analytic hierarchy process (AHP) was used to calculate the weights of the test evaluation indicators of the two scenarios. Finally, the activity-based classification (ABC) method was used after ranking the weight results in order to extract the key factors that have the maximum impact on safety in the scenarios. In this paper, we proved the practicality and feasibility of the AHP-ABC extraction method in the IVIS integration testing evaluation index and guided the development and testing of the IVIS. Full article
(This article belongs to the Special Issue Recent Advances in Intelligent Transportation Systems)
Show Figures

Figure 1

Article
3D Printed Electronic Circuits from Fusible Alloys
Electronics 2022, 11(22), 3829; https://doi.org/10.3390/electronics11223829 - 21 Nov 2022
Viewed by 450
Abstract
This work aims to evaluate the possibility of fabricating conductive paths for printed circuit boards from low-temperature melting metal alloys on low-temperature 3D printed substrates and mounting through-hole electronic components using the fused deposition modeling for metals (FDMm) for structural electronics applications. The [...] Read more.
This work aims to evaluate the possibility of fabricating conductive paths for printed circuit boards from low-temperature melting metal alloys on low-temperature 3D printed substrates and mounting through-hole electronic components using the fused deposition modeling for metals (FDMm) for structural electronics applications. The conductive materials are flux-cored solder wires Sn60Pb40 and Sn99Ag0.3Cu0.7. The deposition was achieved with a specially adapted nozzle. A comparison of solder wires with and without flux cores is discussed to determine whether the solder alloys exhibit adequate wettability and adhesion to the polymer substrate. The symmetrical astable multivibrator circuit based on bipolar junction transistors (BJT) was fabricated to demonstrate the possibility of simultaneous production of conductive tracks and through-hole mountings with this additive technique. Additional perspectives for applying this technique to 3D-printed structural electronic circuits are also discussed. Full article
(This article belongs to the Special Issue New Trends in 3D Printing for Novel Materials)
Show Figures

Figure 1

Article
A Lightweight Border Patrol Object Detection Network for Edge Devices
Electronics 2022, 11(22), 3828; https://doi.org/10.3390/electronics11223828 - 21 Nov 2022
Viewed by 322
Abstract
Border patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out [...] Read more.
Border patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out its tasks. In this paper, we designed a detection algorithm TP-ODA for the border patrol object detection task in order to improve the UAV and portable reconnaissance equipment for the task of border patrol object detection, which is mostly performed in embedded devices with limited computing power and the detection frame imbalance problem is improved; finally, the PDOEM structure is designed in the neck network to optimize the feature fusion module of the algorithm. In order to verify the improvement effect of the algorithm in this paper, the Border Patrol object dataset BDP is constructed. The experiments show that, compared to the baseline model, the TP-ODA algorithm improves mAP by 2.9%, reduces GFLOPs by 65.19%, reduces model volume by 63.83% and improves FPS by 8.47%. The model comparison experiments were then combined with the requirements of the border patrol tasks, and it was concluded that the TP-ODA model is more suitable for UAV and portable reconnaissance equipment to carry and can better fulfill the task of border patrol object detection. Full article
(This article belongs to the Special Issue Advanced Machine Learning Applications in Big Data Analytics)
Show Figures

Figure 1

Article
Classification of Task Types in Software Development Projects
Electronics 2022, 11(22), 3827; https://doi.org/10.3390/electronics11223827 - 21 Nov 2022
Viewed by 359
Abstract
Managing software development processes is still a serious challenge and offers the possibility of introducing improvements that will reduce the resources needed to successfully complete projects. The article presents the original concept of classification of types of project tasks, which will allow for [...] Read more.
Managing software development processes is still a serious challenge and offers the possibility of introducing improvements that will reduce the resources needed to successfully complete projects. The article presents the original concept of classification of types of project tasks, which will allow for more beneficial use of the collected data in management support systems in the IT industry. The currently used agile management methods—described in the article—and the fact that changes during the course of projects are inevitable, were the inspiration for creating sets of tasks that occur in software development. Thanks to statistics for generating tasks and aggregating results in an iterative and incremental way, the analysis is more accurate and allows planning the further course of work in the project, selecting the optimal number of employees in task teams, and identifying bottlenecks that may decide on faster completion of the project with success. The use of data from actual software projects in the IT industry made it possible to classify the types of tasks and the necessary values for further work planning, depending on the nature of the planned software development project. Full article
(This article belongs to the Special Issue Knowledge Engineering and Data Mining)
Show Figures

Figure 1

Article
Application of Artificial Intelligent Techniques for Power Quality Improvement in Hybrid Microgrid System
Electronics 2022, 11(22), 3826; https://doi.org/10.3390/electronics11223826 - 21 Nov 2022
Viewed by 356
Abstract
The hybrid AC-DC microgrid (MG) has gained popularity recently as it offers the benefits of AC and DC systems. Interconnecting AC-DC converters are necessary since the MG has both DC and AC sub-grids. Adding an extra harmonic adjustment mechanism to the interlinking converters [...] Read more.
The hybrid AC-DC microgrid (MG) has gained popularity recently as it offers the benefits of AC and DC systems. Interconnecting AC-DC converters are necessary since the MG has both DC and AC sub-grids. Adding an extra harmonic adjustment mechanism to the interlinking converters is promising because non-linear AC loads can worsen the quality of the voltage on the AC bus. The interlinking converters’ primary function is to interchange real and reactive power between DC and AC sub-grids, so the typical harmonic controlling approach implemented for active power filters (APFs) might not be appropriate for them. When the MG’s capacity is high, it is desirable that the switching frequency be lesser than the APFs. The performance of harmonic correction or even system stability may suffer at low switching frequencies. In this study, a harmonic compensating technique appropriate for hybrid AC-DC interlinking converters with lower switching frequencies is planned. The suggested strategy, modeling techniques, stability analysis, and a thorough virtual impedance design are discussed in this work. Full article
Show Figures

Figure 1

Article
A Novel MOGNDO Algorithm for Security-Constrained Optimal Power Flow Problems
Electronics 2022, 11(22), 3825; https://doi.org/10.3390/electronics11223825 - 21 Nov 2022
Viewed by 368
Abstract
The current research investigates a new and unique Multi-Objective Generalized Normal Distribution Optimization (MOGNDO) algorithm for solving large-scale Optimal Power Flow (OPF) problems of complex power systems, including renewable energy sources and Flexible AC Transmission Systems (FACTS). A recently reported single-objective generalized normal [...] Read more.
The current research investigates a new and unique Multi-Objective Generalized Normal Distribution Optimization (MOGNDO) algorithm for solving large-scale Optimal Power Flow (OPF) problems of complex power systems, including renewable energy sources and Flexible AC Transmission Systems (FACTS). A recently reported single-objective generalized normal distribution optimization algorithm is transformed into the MOGNDO algorithm using the nondominated sorting and crowding distancing mechanisms. The OPF problem gets even more challenging when sources of renewable energy are integrated into the grid system, which are unreliable and fluctuating. FACTS devices are also being used more frequently in contemporary power networks to assist in reducing network demand and congestion. In this study, a stochastic wind power source was used with different FACTS devices, including a static VAR compensator, a thyristor- driven series compensator, and a thyristor—driven phase shifter, together with an IEEE-30 bus system. Positions and ratings of the FACTS devices can be intended to reduce the system’s overall fuel cost. Weibull probability density curves were used to highlight the stochastic character of the wind energy source. The best compromise solutions were obtained using a fuzzy decision-making approach. The results obtained on a modified IEEE-30 bus system were compared with other well-known optimization algorithms, and the obtained results proved that MOGNDO has improved convergence, diversity, and spread behavior across PFs. Full article
Show Figures

Figure 1

Article
Collaborative Gold Mining Algorithm: An Optimization Algorithm Based on the Natural Gold Mining Process
Electronics 2022, 11(22), 3824; https://doi.org/10.3390/electronics11223824 - 21 Nov 2022
Viewed by 277
Abstract
In optimization algorithms, there are some challenges, including lack of optimal solution, slow convergence, lack of scalability, partial search space, and high computational demand. Inspired by the process of gold exploration and exploitation, we propose a new meta-heuristic and stochastic optimization algorithm called [...] Read more.
In optimization algorithms, there are some challenges, including lack of optimal solution, slow convergence, lack of scalability, partial search space, and high computational demand. Inspired by the process of gold exploration and exploitation, we propose a new meta-heuristic and stochastic optimization algorithm called collaborative gold mining (CGM). The proposed algorithm has several iterations; in each of these, the center of mass of points with the highest amount of gold is calculated for each miner (agent), with this process continuing until the point with the highest amount of gold or when the optimal solution is found. In an n-dimensional geographic space, the CGM algorithm can locate the best position with the highest amount of gold in the entire search space by collaborating with several gold miners. The proposed CGM algorithm was applied to solve several continuous mathematical functions and several practical problems, namely, the optimal placement of resources, the traveling salesman problem, and bag-of-tasks scheduling. In order to evaluate its efficiency, the CGM results were compared with the outputs of some famous optimization algorithms, such as the genetic algorithm, simulated annealing, particle swarm optimization, and invasive weed optimization. In addition to determining the optimal solutions for all the evaluated problems, the experimental results show that the CGM mechanism has an acceptable performance in terms of optimal solution, convergence, scalability, search space, and computational demand for solving continuous and discrete problems. Full article
Show Figures

Figure 1

Article
Simultaneous Beam Forming and Focusing Using a Checkerboard Anisotropic Surface
Electronics 2022, 11(22), 3823; https://doi.org/10.3390/electronics11223823 - 21 Nov 2022
Viewed by 341
Abstract
A novel design method of simultaneous beam forming and focusing using a checkerboard anisotropic surface is proposed and verified in this paper. The proposed multibeam control regardless of far and near regions can easily be achieved through a rearrangement of the checkerboard structure. [...] Read more.
A novel design method of simultaneous beam forming and focusing using a checkerboard anisotropic surface is proposed and verified in this paper. The proposed multibeam control regardless of far and near regions can easily be achieved through a rearrangement of the checkerboard structure. The unit cell of the utilized anisotropic surface consists of two identical metallic structures divided by a dielectric material. When the EM wave with a circular polarization (CP) is incident on the unit cell, the maximum transmission phase variation of the unit cell is 360 degrees by half rotation of the unit cell. A microstrip patch antenna with trimmed corners is used to launch the CP wave and the distance between the microstrip patch antenna and anisotropic surface is about 2 wavelengths considering the optimized spillover and taper efficiencies. After designing each anisotropic surface for beam forming and focusing, the unit cells of the surface are rearranged in the form of a checkerboard. The feasibility of the proposed method is confirmed by full-wave simulation and measurement for anisotropic surface with a beam forming angle of 30 degrees and beam focusing point 60 mm away from center at 5.8 GHz. The forming angle and focal length are simulated and measured to be 28 degrees and about 65 mm, respectively. Full article
(This article belongs to the Section Microwave and Wireless Communications)
Show Figures

Figure 1

Article
Contrast-Controllable Image Enhancement Based on Limited Histogram
Electronics 2022, 11(22), 3822; https://doi.org/10.3390/electronics11223822 - 21 Nov 2022
Viewed by 374
Abstract
To address the technical shortcomings of conventional histogram equalization (HE), such as over-enhancement and artifacts, we propose a histogram-constrained and contrast-tunable HE technique for digital image enhancement. Firstly, the input image histogram is partitioned into two parts, the main histogram and the constrained [...] Read more.
To address the technical shortcomings of conventional histogram equalization (HE), such as over-enhancement and artifacts, we propose a histogram-constrained and contrast-tunable HE technique for digital image enhancement. Firstly, the input image histogram is partitioned into two parts, the main histogram and the constrained histogram, by a cumulative probability density threshold; second, the main histogram is redistributed equally in the whole grayscale range; and finally, the nonlinearity of the constrained histogram is mapped to the main histogram. The experimental averages show that the values of the two metrics, information entropy and MS-SSIM, processed by the algorithms in this paper, are more accurate compared to the other six excellent algorithms. Full article
Show Figures

Graphical abstract

Communication
Robust Phase Bias Estimation Method for Azimuth Multi-Channel HRWS SAR System Based on Maximum Modified Kurtosis
Electronics 2022, 11(22), 3821; https://doi.org/10.3390/electronics11223821 - 20 Nov 2022
Viewed by 421
Abstract
The azimuth multi-channel synthetic aperture radar (MC-SAR) systems can simultaneously realize high-resolution and wide-swath (HRWS) earth observations. However, channel phase bias inevitably exists in the practical work of the azimuth MC-SAR system, which is the main factor for the “virtual target” in SAR [...] Read more.
The azimuth multi-channel synthetic aperture radar (MC-SAR) systems can simultaneously realize high-resolution and wide-swath (HRWS) earth observations. However, channel phase bias inevitably exists in the practical work of the azimuth MC-SAR system, which is the main factor for the “virtual target” in SAR images. To accurately estimate the phase bias, a channel phase bias estimation approach based on modified kurtosis maximization (MMK) is proposed in this paper. By analyzing the echo characteristics of multi-channel SAR, the proposed approach constructs the objective optimization function of MMK of the reconstructed Doppler spectrum (RDS), and the channel phase bias can be accurately estimated. Simulation experiments and real raw data processing verify the effectiveness and robustness of the proposed approach, which is not limited by the scene and has a good estimation performance at a low signal-to-noise ratio (SNR). Full article
(This article belongs to the Special Issue Advancements in Radar Signal Processing)
Show Figures

Figure 1

Communication
HfOx/Ge RRAM with High ON/OFF Ratio and Good Endurance
Electronics 2022, 11(22), 3820; https://doi.org/10.3390/electronics11223820 - 20 Nov 2022
Viewed by 470
Abstract
A trade-off between the memory window and the endurance exists for transition-metal-oxide RRAM. In this work, we demonstrated that HfOx/Ge-based metal-insulator-semiconductor RRAM devices possess both a larger memory window and longer endurance compared with metal-insulator-metal (MIM) RRAM devices. Under DC cycling, [...] Read more.
A trade-off between the memory window and the endurance exists for transition-metal-oxide RRAM. In this work, we demonstrated that HfOx/Ge-based metal-insulator-semiconductor RRAM devices possess both a larger memory window and longer endurance compared with metal-insulator-metal (MIM) RRAM devices. Under DC cycling, HfOx/Ge devices exhibit a 100× larger memory window compared to HfOx MIM devices, and a DC sweep of up to 20,000 cycles was achieved with the devices. The devices also realize low static power down to 1 nW as FPGA’s pull-up/pull-down resistors. Thus, HfOx/Ge devices act as a promising candidates for various applications such as FPGA or compute-in-memory, in which both a high ON/OFF ratio and decent endurance are required. Full article
(This article belongs to the Special Issue Advanced CMOS Devices and Applications)
Show Figures

Figure 1

Article
Analysis of Impulse Responses Measured in Motion in a Towing Tank
Electronics 2022, 11(22), 3819; https://doi.org/10.3390/electronics11223819 - 20 Nov 2022
Viewed by 382
Abstract
The growing interest in developing autonomous underwater vehicles (AUVs) and creating underwater sensor networks (USNs) has led to a need for communication tools in underwater environments. For obvious reasons, wireless means of communication are the most desirable. However, conducting research in real conditions [...] Read more.
The growing interest in developing autonomous underwater vehicles (AUVs) and creating underwater sensor networks (USNs) has led to a need for communication tools in underwater environments. For obvious reasons, wireless means of communication are the most desirable. However, conducting research in real conditions is troublesome and costly. Moreover, as hydroacoustic propagation conditions change very significantly, even during the day, the assessment of proposed underwater wireless communication methods is very difficult. Therefore, in the literature, there are considered simulators based on real measurements of underwater acoustic (UWA) channels. However, these simulators make an assumption that, during the transmission of elementary signals, the impulse response does not change. In this article, the authors present the results of the measurements realized in a towing tank where the transmitter could move with a precisely set velocity and show that the analyzed channel was non-stationary, even during the time of the transmission of a single chirp signal. The article presents an evaluation method of channel stationarity at the time of the chirp transmission, which should be treated as novelty. There is also an analysis of the impulse responses measured in motion in a towing tank. Full article
Show Figures

Figure 1

Review
Emerging Technologies’ Contribution to the Digital Transformation in Accountancy Firms
Electronics 2022, 11(22), 3818; https://doi.org/10.3390/electronics11223818 - 20 Nov 2022
Viewed by 445
Abstract
Digitalization becomes a key strategy for the success of businesses, which in today’s critical times, are under remarkable pressures and diffused uncertainty. The rapid pace of digitization is forcing deep changes in the modus operandi of organizations. This phenomenon is even more so [...] Read more.
Digitalization becomes a key strategy for the success of businesses, which in today’s critical times, are under remarkable pressures and diffused uncertainty. The rapid pace of digitization is forcing deep changes in the modus operandi of organizations. This phenomenon is even more so true for accounting organizations considering that, by implementing blockchain, RPA, cloud, big data, cybersecurity, and AI, accountants might have the most digitized workplace of all. The purpose of this paper is to explore how these emergent technologies are contributing to the digital transformation of accounting firms. Based on a qualitative approach, the methodology consists of a thematic analysis of the academic literature to reveal the synergic effect of the most disruptive emergent technologies for accountancy firms. In addition to the topic of research, the originality of this study is ensured by the fact that it presents both technical and conceptual information, easily digestible for academicians and practitioners skilled in the ICT field, or not. The paper is intended to be a building brick for the literature related to this topic. Full article
Show Figures

Figure 1

Article
Denial of Service Attack Classification Using Machine Learning with Multi-Features
Electronics 2022, 11(22), 3817; https://doi.org/10.3390/electronics11223817 - 20 Nov 2022
Viewed by 439
Abstract
The exploitation of internet networks through denial of services (DoS) attacks has experienced a continuous surge over the past few years. Despite the development of advanced intrusion detection and protection systems, network security remains a challenging problem and necessitates the development of efficient [...] Read more.
The exploitation of internet networks through denial of services (DoS) attacks has experienced a continuous surge over the past few years. Despite the development of advanced intrusion detection and protection systems, network security remains a challenging problem and necessitates the development of efficient and effective defense mechanisms to detect these threats. This research proposes a machine learning-based framework to detect distributed DOS (DDoS)/DoS attacks. For this purpose, a large dataset containing the network traffic of the application layer is utilized. A novel multi-feature approach is proposed where the principal component analysis (PCA) features and singular value decomposition (SVD) features are combined to obtain higher performance. The validation of the multi-feature approach is determined by extensive experiments using several machine learning models. The performance of machine learning models is evaluated for each class of attack and results are discussed regarding the accuracy, recall, and F1 score, etc., in the context of recent state-of-the-art approaches. Experimental results confirm that using multi-feature increases the performance and RF obtains a 100% accuracy. Full article
(This article belongs to the Special Issue New Advances and Challenges in Communication Networks)
Show Figures

Figure 1

Article
A Generic Preprocessing Architecture for Multi-Modal IoT Sensor Data in Artificial General Intelligence
Electronics 2022, 11(22), 3816; https://doi.org/10.3390/electronics11223816 - 20 Nov 2022
Viewed by 431
Abstract
A main barrier for autonomous and general learning systems is their inability to understand and adapt to new environments—that is, to apply previously learned abstract solutions to new problems. Supervised learning system functions such as classification require data labeling from an external source [...] Read more.
A main barrier for autonomous and general learning systems is their inability to understand and adapt to new environments—that is, to apply previously learned abstract solutions to new problems. Supervised learning system functions such as classification require data labeling from an external source and do not have the ability to learn feature representation autonomously. This research details an unsupervised learning method for multi-modal feature detection and evaluation to be used for preprocessing in general learning systems. The learning method details a clustering algorithm that can be applied to any generic IoT sensor data, and a seeded stimulus labeling algorithm impacted and evolved by cross-modal input. The method is implemented and tested in two agents consuming audio and image data, each with varying innate stimulus criteria. Their run-time stimulus changes over time depending on their experiences, while newly experienced features become meaningful without preprogrammed labeling of distinct attributes. The architecture provides interfaces for higher-order cognitive processes to be built on top of the unsupervised preprocessor. This method is unsupervised and modular, in contrast to the highly constrained and pretrained learning systems that exist, making it extendable and well-disposed for use in artificial general intelligence. Full article
Show Figures

Figure 1

Article
Knowledge Distillation for Image Signal Processing Using Only the Generator Portion of a GAN
Electronics 2022, 11(22), 3815; https://doi.org/10.3390/electronics11223815 - 20 Nov 2022
Viewed by 312
Abstract
Knowledge distillation, in which the parameter values learned in a large teacher network are transferred to a smaller student network, is a popular and effective network compression method. Recently, researchers have proposed methods to improve the performance of a student network by using [...] Read more.
Knowledge distillation, in which the parameter values learned in a large teacher network are transferred to a smaller student network, is a popular and effective network compression method. Recently, researchers have proposed methods to improve the performance of a student network by using a Generative Adverserial Network (GAN). However, because a GAN is an architecture that is ideally used to create realistic synthetic images, a pure GAN architecture may not be ideally suited for knowledge distillation. In knowledge distillation for image signal processing, synthetic images do not need to be realistic, but instead should include features that help the training of the student network. In the proposed Generative Image Processing (GIP) method, this is accomplished by using only the generator portion of a GAN and utilizing special techniques to capture the distinguishing feature capability of the teacher network. Experimental results show that the GIP method outperforms knowledge distillation using GANs as well as training using only knowledge distillation. Full article
(This article belongs to the Special Issue Feature Papers in Circuit and Signal Processing)
Show Figures

Figure 1

Article
Differential Optimization Federated Incremental Learning Algorithm Based on Blockchain
Electronics 2022, 11(22), 3814; https://doi.org/10.3390/electronics11223814 - 20 Nov 2022
Viewed by 432
Abstract
Federated learning is a hot area of concern in the field of privacy protection. There are local model parameters that are difficult to integrate, poor model timeliness, and local model training security issues. This paper proposes a blockchain-based differential optimization federated incremental learning [...] Read more.
Federated learning is a hot area of concern in the field of privacy protection. There are local model parameters that are difficult to integrate, poor model timeliness, and local model training security issues. This paper proposes a blockchain-based differential optimization federated incremental learning algorithm, First, we apply differential privacy to the weighted random forest and optimize the parameters in the weighted forest to reduce the impact of adding differential privacy on the accuracy of the local model. Using different ensemble algorithms to integrate the local model parameters can improve the accuracy of the global model. At the same time, the risk of a data leakage caused by gradient update is reduced; then, incremental learning is applied to the framework of federated learning to improve the timeliness of the model; finally, the model parameters in the model training phase are uploaded to the blockchain and synchronized quickly, which reduces the cost of data storage and model parameter transmission. The experimental results show that the accuracy of the stacking ensemble model in each period is above 83.5% and the variance is lower than 104 for training on the public data set. The accuracy of the model has been improved, and the security and privacy of the model have been improved. Full article
(This article belongs to the Topic Machine Learning in Internet of Things)
Show Figures

Figure 1

Article
Multi-Task Learning for Scene Text Image Super-Resolution with Multiple Transformers
Electronics 2022, 11(22), 3813; https://doi.org/10.3390/electronics11223813 - 20 Nov 2022
Viewed by 342
Abstract
Scene text image super-resolution aims to improve readability by recovering text shapes from low-resolution degraded text images. Although recent developments in deep learning have greatly improved super-resolution (SR) techniques, recovering text images with irregular shapes, heavy noise, and blurriness is still challenging. This [...] Read more.
Scene text image super-resolution aims to improve readability by recovering text shapes from low-resolution degraded text images. Although recent developments in deep learning have greatly improved super-resolution (SR) techniques, recovering text images with irregular shapes, heavy noise, and blurriness is still challenging. This is because networks with Convolutional Neural Network (CNN)-based backbones cannot sufficiently capture the global long-range correlations of text images or detailed sequential information about the text structure. In order to address this issue, this paper proposes a Multi-task learning-based Text Super-resolution (MTSR) Network to approach this problem. MTSR is a multi-task architecture for image reconstruction and SR. It uses transformer-based modules to transfer complementary features of the reconstruction model, such as noise removal capability and text structure information, to the SR model. In addition, another transformer-based module using 2D positional encoding is used to handle irregular deformations of the text. The feature maps generated from these two transformer-based modules are fused to attempt improvement of the visual quality of images with heavy noise, blurriness, and irregular deformations. Experimental results on the TextZoom dataset and several scene text recognition benchmarks show that our MTSR significantly improves the accuracy of existing text recognizers. Full article
(This article belongs to the Special Issue Deep Learning in Image Processing and Pattern Recognition)
Show Figures

Graphical abstract

Article
An Empirical Framework for Assessment of the Effects of Digital Technologies on Sustainability Accounting and Reporting in the European Union
Electronics 2022, 11(22), 3812; https://doi.org/10.3390/electronics11223812 - 20 Nov 2022
Viewed by 405
Abstract
Sustainability accounting and reporting is an emerging area of accounting that is receiving increasing attention as a result of sustainability requirements. In this paper, we examine the effects of implementing digital technology on sustainability accounting and reporting. This research consists of an empirical [...] Read more.
Sustainability accounting and reporting is an emerging area of accounting that is receiving increasing attention as a result of sustainability requirements. In this paper, we examine the effects of implementing digital technology on sustainability accounting and reporting. This research consists of an empirical study at the level of 21 European Union countries using data provided by Eurostat. Transversal research emphasizes the impact of digital technologies (cloud computing, Big Data, the Internet of things, and artificial intelligence) on sustainability accounting and reporting. In this paper, we highlight the relationships between variables using artificial neural network analysis and cluster analysis. The study findings indicate that digital technologies significantly influence the sustainability accounting and reporting and sustainability-oriented culture of the countries included in the empirical study. A cluster analysis reveals a group of countries at the top of the sustainability reporting rankings as a result of advances in digital technologies. This study demonstrates that the digital transformation produced by Industry 4.0 contributes to the potential improvement of sustainability accounting and reporting, with significant links between sustainability and digitization. Full article
Show Figures

Figure 1

Article
Artificial Intelligence Model for the Identification of the Personality of Twitter Users through the Analysis of Their Behavior in the Social Network
Electronics 2022, 11(22), 3811; https://doi.org/10.3390/electronics11223811 - 19 Nov 2022
Viewed by 442
Abstract
Currently, social networks have become one of the most used channels by society to share their ideas, their status, generate trends, etc. By applying artificial intelligence techniques and sentiment analysis to the large volume of data found in social networks, it is possible [...] Read more.
Currently, social networks have become one of the most used channels by society to share their ideas, their status, generate trends, etc. By applying artificial intelligence techniques and sentiment analysis to the large volume of data found in social networks, it is possible to predict the personality of people. In this work, the development of a data analysis model with machine learning algorithms with the ability to predict the personality of a user based on their activity on Twitter is proposed. To do this, a data collection and transformation process is carried out to be analyzed with sentiment analysis techniques and the linguistic analysis of tweets. Very successful results were obtained by developing a training process for the machine learning algorithm. By generating comparisons of this model, with the related literature, it is shown that social networks today house a large volume of data that contains significant value if your approach is appropriate. Through the analysis of tweets, retweets, and other factors, there is the possibility of creating a virtual profile on the Internet for each person; the uses can vary, from creating marketing campaigns to optimizing recruitment processes. Full article
(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)
Show Figures

Figure 1

Article
DEF-Net: A Dual-Encoder Fusion Network for Fundus Retinal Vessel Segmentation
Electronics 2022, 11(22), 3810; https://doi.org/10.3390/electronics11223810 - 19 Nov 2022
Viewed by 379
Abstract
The deterioration of numerous eye diseases is highly related to the fundus retinal structures, so the automatic retinal vessel segmentation serves as an essential stage for efficient detection of eye-related lesions in clinical practice. Segmentation methods based on encode-decode structures exhibit great potential [...] Read more.
The deterioration of numerous eye diseases is highly related to the fundus retinal structures, so the automatic retinal vessel segmentation serves as an essential stage for efficient detection of eye-related lesions in clinical practice. Segmentation methods based on encode-decode structures exhibit great potential in retinal vessel segmentation tasks, but have limited feature representation ability. In addition, they don’t effectively consider the information at multiple scales when performing feature fusion, resulting in low fusion efficiency. In this paper, a newly model, named DEF-Net, is designed to segment retinal vessels automatically, which consists of a dual-encoder unit and a decoder unit. Fused with recurrent network and convolution network, a dual-encoder unit is proposed, which builds a convolutional network branch to extract detailed features and a recurrent network branch to accumulate contextual features, and it could obtain richer features compared to the single convolution network structure. Furthermore, to exploit the useful information at multiple scales, a multi-scale fusion block used for facilitating feature fusion efficiency is designed. Extensive experiments have been undertaken to demonstrate the segmentation performance of our proposed DEF-Net. Full article
(This article belongs to the Special Issue Recent Advanced Applications of Rehabilitation and Medical Robotics)
Show Figures

Figure 1

Article
Epistemic-Uncertainty-Based Divide-and-Conquer Network for Single-Image Super-Resolution
Electronics 2022, 11(22), 3809; https://doi.org/10.3390/electronics11223809 - 19 Nov 2022
Viewed by 288
Abstract
The introduction of convolutional neural networks (CNNs) into single-image super-resolution (SISR) has resulted in remarkable performance in the last decade. There is a contradiction in SISR between indiscriminate processing and the different processing difficulties in different regions, leading to the need for locally [...] Read more.
The introduction of convolutional neural networks (CNNs) into single-image super-resolution (SISR) has resulted in remarkable performance in the last decade. There is a contradiction in SISR between indiscriminate processing and the different processing difficulties in different regions, leading to the need for locally differentiated processing of SR networks. In this paper, we propose an epistemic-uncertainty-based divide-and-conquer network (EU-DC) in order to address this problem. Firstly, we build an image-gradient-based divide-and-conquer network (IG-DC) that utilizes gradient-based division to separate degraded images into easy and hard processing regions. Secondly, we model the IG-DC’s epistemic uncertainty map (EUM) by using Monte Carlo dropout and, thus, measure the output confidence of the IG-DC. The lower the output confidence is, the more difficult the IG-DC is to process. The EUM-based division is generated by quantizing the EUM into two levels. Finally, the IG-DC is transformed into an EU-DC by substituting the gradient-based division with EUM-based division. Our extensive experiments demonstrate that the proposed EU-DC achieves better reconstruction performance than that of multiple state-of-the-art SISR methods in terms of both quantitative and visual quality. Full article
Show Figures

Figure 1

Article
Methodology for Improving High-Power Harmonic Measurement Accuracy and Stability
Electronics 2022, 11(22), 3808; https://doi.org/10.3390/electronics11223808 - 19 Nov 2022
Viewed by 276
Abstract
With continued dimension scaling of the semiconductor devices, the parasitic parameters become increasingly obvious and it affects the device performance directly. The harmonic distortion is one of the key factors to limit the RF system bandwidth resource and channel capability. Therefore, it is [...] Read more.
With continued dimension scaling of the semiconductor devices, the parasitic parameters become increasingly obvious and it affects the device performance directly. The harmonic distortion is one of the key factors to limit the RF system bandwidth resource and channel capability. Therefore, it is crucial to precisely extract the nonlinear index of the device and system. High-precision harmonic distortion extraction on a device’s intrinsic characteristics could be beneficial not only to device modeling but also to circuit design. However, the harmonic distortion measurement is highly sensitive to the peripheral circuit and instrumentations, especially in high power stimulus; its repeatability and stability are also hard to control. This paper aims to contribute to the subject by extending the measurement methodology, combining isolation compensation with a dual trace phase tuning (DTPT) technique to obtain the optimal harmonic value. As shown by the experiment results, the optimized approach could achieve high measurements of both accuracy and stability. The proposed methodology is validated with measurement data and compared with conventional measurement architecture. The assessment results prove that the proposed methodology could improve 30.66% and 28.84% measurement accuracy both on second and third harmonics. Simultaneously, the proposed methodology decreases gauge repeatability and reproducibility (GRR) from 56.49% to 7.13%. Full article
(This article belongs to the Section Microelectronics)
Show Figures

Figure 1

Previous Issue
Back to TopTop