Next Issue
Volume 11, August-1
Previous Issue
Volume 11, July-1
 
 

Electronics, Volume 11, Issue 14 (July-2 2022) – 170 articles

Cover Story (view full-size image): With the growth in continuous energy demand, high-voltage multiterminal DC (MTDC) systems are technically and economically feasible to transmit bulk power and integrate additional energy sources. However, the development of DC fault ride-through techniques such as DC circuit breakers is still challenging due to their high cost and complex operation. This paper presents a DC fault clearance and isolation method for a modular multilevel converter (MMC)-based MTDC grid without adopting high-cost DC circuit breakers. Further, a restoration sequence is proposed to re-energize the DC grid upon clearing the fault. An MMC-based four-terminal DC grid is implemented in a control-hardware-in-loop (CHIL) environment based on Xilinx Virtex-7 FPGAs and real-time digital simulator (RTDS). 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 Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
15 pages, 4260 KiB  
Article
The Application of Adaptive Tolerance and Serialized Facial Feature Extraction to Automatic Attendance Systems
by Chun-Ling Lin and Yi-Huai Huang
Electronics 2022, 11(14), 2278; https://doi.org/10.3390/electronics11142278 - 21 Jul 2022
Cited by 4 | Viewed by 2895
Abstract
The aim of this study was to develop a real-time automatic attendance system (AAS) based on Internet of Things (IoT) technology and facial recognition. A Raspberry Pi camera built into a Raspberry Pi 3B is used to transfer facial images to a cloud [...] Read more.
The aim of this study was to develop a real-time automatic attendance system (AAS) based on Internet of Things (IoT) technology and facial recognition. A Raspberry Pi camera built into a Raspberry Pi 3B is used to transfer facial images to a cloud server. Face detection and recognition libraries are implemented on this cloud server, which thus can handle all the processes involved with the automatic recording of student attendance. In addition, this study proposes the application of data serialization processing and adaptive tolerance vis-à-vis Euclidean distance. The facial features encountered are processed using data serialization before they are saved in the SQLite database; such serialized data can easily be written and then read back from the database. When examining the differences between the facial features already stored in the SQLite databases and any new facial features, the proposed adaptive tolerance system can improve the performance of the facial recognition method applying Euclidean distance. The results of this study show that the proposed AAS can recognize multiple faces and so record attendance automatically. The AAS proposed in this study can assist in the detection of students who attempt to skip classes without the knowledge of their teachers. The problem of students being unintentionally marked present, though absent, and the problem of proxies is also resolved. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

11 pages, 4498 KiB  
Article
Enhanced Automatic Morphometry of Nerve Histological Sections Using Ensemble Learning
by Yazan Dweiri, Mousa Al-Zanina and Dominique Durand
Electronics 2022, 11(14), 2277; https://doi.org/10.3390/electronics11142277 - 21 Jul 2022
Viewed by 1475
Abstract
There is a need for an automated morphometry algorithm to facilitate the otherwise labor-intensive task of the quantitative histological analysis of neural microscopic images. A benchmark morphometry algorithm is the convolutional neural network Axondeepseg (ADS), which yields a high segmentation accuracy for scanning [...] Read more.
There is a need for an automated morphometry algorithm to facilitate the otherwise labor-intensive task of the quantitative histological analysis of neural microscopic images. A benchmark morphometry algorithm is the convolutional neural network Axondeepseg (ADS), which yields a high segmentation accuracy for scanning and transmission electron microscopy images. Nevertheless, it shows decreased accuracy when applied to optical microscopy images, and it has been observed to yield sizable false positives when identifying small-sized neurons within the slides. In this study, ensemble learning is used to enhance the performance of ADS by combining it with the paired image-to-image translation algorithm PairedImageTranslation (PIT). Here, 120 optical microscopy images of peripheral nerves were used to train and test the ensemble learning model and the two base models individually for comparison. The results showed weighted pixel-wise accuracy for the ensemble model of 95.5%, whereas the ADS and PIT yielded accuracies of 93.4% and 90%, respectively. The automated measurements of the axon diameters and myelin thicknesses from the manually marked ground truth images were not statistically different (p = 0.05) from the measurements taken from the same images when segmented using the developed ensemble model, while they were different when they were measured from the segmented images by the two base models individually. The automated measurement of the G ratios indicated a higher similarity to the ground truth testing images for the ensemble model in comparison with the individual base models. The proposed model yielded automated segmentation of the nerve slides, which were sufficiently equivalent to the manual annotations and could be employed for axon diameters and myelin thickness measurements for fully automated histological analysis of the neural images. Full article
Show Figures

Figure 1

15 pages, 681 KiB  
Article
Mindless Memorization Booster: A Method to Influence Memorization Power Using Attention Induction Phenomena Caused by Visual Interface Modulation and Its Application to Memorization Support for English Vocabulary Learning
by Kyosuke Futami, Daisuke Kawahigashi and Kazuya Murao
Electronics 2022, 11(14), 2276; https://doi.org/10.3390/electronics11142276 - 21 Jul 2022
Cited by 3 | Viewed by 2617
Abstract
Memorization is necessary for various fields, such as language learning in the field of education. While memorization learning is often tedious and demotivating due to requiring conscious effort, few support approaches improve memorization unconsciously with low conscious effort. In this study, we propose [...] Read more.
Memorization is necessary for various fields, such as language learning in the field of education. While memorization learning is often tedious and demotivating due to requiring conscious effort, few support approaches improve memorization unconsciously with low conscious effort. In this study, we propose a method, Mindless Memorization Booster, which improves users’ memorization unconsciously by visual stimuli of modulating the visual interface. This method is based on previous findings that the modulation of perceptual stimuli arouses attention/concentration. When the user looks at the memorization target, the proposed method presents a change in visual interface (e.g., changes in memorization target size, background color, and visual icon movement) to cause a psychological phenomenon of affecting the user’s attention and concentration, aiming at enhancing the memorization unconsciously. A prototype system of the proposed method was implemented for an English vocabulary memorization learning application. The evaluation results showed that the user’s memorization result was affected by the proposed method, and the speed of recall (i.e., outputs of the memorization word from the brain) increased by about 1 s per one memorization word without causing a negative affection on the number of correct answers for memorization. This result indicated the feasibility of the proposed method for memorization learning support. Our findings are helpful for designing visual information interfaces that consider the phenomena affecting the user’s memorization and promote memorization learning unconsciously. Full article
(This article belongs to the Special Issue Human–Computer Interaction: Latest Advances and Future Trends)
Show Figures

Figure 1

22 pages, 3468 KiB  
Article
Two Sound Field Control Methods Based on Particle Velocity
by Song Wang and Cong Zhang
Electronics 2022, 11(14), 2275; https://doi.org/10.3390/electronics11142275 - 21 Jul 2022
Cited by 1 | Viewed by 1718
Abstract
In recent years, a variety of sound field control methods have been proposed for the generation of separated sound regions. Different algorithms control the physical properties of the generated sound field to different degrees. The existing methods mainly focus on sound pressure restoration [...] Read more.
In recent years, a variety of sound field control methods have been proposed for the generation of separated sound regions. Different algorithms control the physical properties of the generated sound field to different degrees. The existing methods mainly focus on sound pressure restoration and its related improvement. When the loudspeaker array is non-uniformly placed, the reconstruction system is not stable enough. To solve this problem, this paper proposes two sound field control methods related to particle velocity. The first method regulates the reconstruction error of particle velocity in the bright zone and the square of particle velocity in the dark zone; the second method regulates the reconstruction error of sound pressure and particle velocity in the bright zone and the square of sound pressure and particle velocity in the dark zone. Five channel and twenty-two channel non-uniform loudspeaker systems were used for two-dimensional and three-dimensional computer simulation testing. Experimental results show that the two proposed methods have better tradeoffs in terms of acoustic contrast, reproduction error and array effort than traditional methods, especially the second proposed method. In the two-dimensional experiment, the maximum reductions of the average array efforts generated by the proposed methods were about 10 dB and 11 dB compared with the average array efforts generated by two traditional methods. In the three-dimensional experiment, the maximum reductions of the average array efforts generated by the proposed methods were about 8 dB and 2 dB compared with the average array efforts generated by two traditional methods. The smaller the array effort, the more stable the loudspeaker system. Therefore, the reconstruction systems produced by the proposed methods are more stable than those produced by the traditional methods. Full article
(This article belongs to the Special Issue Applications of Audio and Acoustic Signal)
Show Figures

Figure 1

17 pages, 5039 KiB  
Article
Development of a Virtual Object Weight Recognition Algorithm Based on Pseudo-Haptics and the Development of Immersion Evaluation Technology
by Eunjin Son, Hayoung Song, Seonghyeon Nam and Youngwon Kim
Electronics 2022, 11(14), 2274; https://doi.org/10.3390/electronics11142274 - 21 Jul 2022
Cited by 3 | Viewed by 2603
Abstract
In this work, we propose a qualitative immersion evaluation technique based on a pseudo-haptic-based user-specific virtual object weight recognition algorithm and an immersive experience questionnaire (IEQ). The proposed weight recognition algorithm is developed by considering the moving speed of a natural hand tracking-based, [...] Read more.
In this work, we propose a qualitative immersion evaluation technique based on a pseudo-haptic-based user-specific virtual object weight recognition algorithm and an immersive experience questionnaire (IEQ). The proposed weight recognition algorithm is developed by considering the moving speed of a natural hand tracking-based, user-customized virtual object using a camera in a VR headset and the realistic offset of the object’s weight when lifting it in real space. Customized speeds are defined to recognize customized weights. In addition, an experiment is conducted to measure the speed of lifting objects by weight in real space to obtain the natural object lifting speed weight according to the weight. In order to evaluate the weight and immersion of the developed simulation content, the participants’ qualitative immersion evaluation is conducted through three IEQ-based immersion evaluation surveys. Based on the analysis results of the experimental participants and the interview, this immersion evaluation technique shows whether it is possible to evaluate a realistic tactile experience in VR content. It is predicted that the proposed weight recognition algorithm and evaluation technology can be applied to various fields, such as content production and service support, in line with market demand in the rapidly growing VR, AR, and MR fields. Full article
Show Figures

Figure 1

17 pages, 953 KiB  
Article
Dynamic Feedback versus Varna-Based Techniques for SDN Controller Placement Problems
by Wael Hosny Fouad Aly, Hassan Kanj, Samer Alabed, Nour Mostafa and Khaled Safi
Electronics 2022, 11(14), 2273; https://doi.org/10.3390/electronics11142273 - 21 Jul 2022
Cited by 3 | Viewed by 1814
Abstract
During the past few years, software-defined networking (SDN) has become a successful architecture that decouples the control plane from the data plane. SDN has the capability to monitor and control the network in a central fashion through a softwarization process. The central element [...] Read more.
During the past few years, software-defined networking (SDN) has become a successful architecture that decouples the control plane from the data plane. SDN has the capability to monitor and control the network in a central fashion through a softwarization process. The central element is the controller. For the current SDN architectures, there is an essential need for multiple controllers. The process of placing the controllers efficiently in an SDN environment is called the controller placement problem (CPP). Earlier CPP solutions focused on improving the propagation delays through the capacity of the controllers and the dynamic load on the switches. In this paper, we develop a novel algorithm called dynamic feedback algorithm for controller placement for SDN (DFBCPSDN). DFBCPSDN is compared with the varna-based optimization (VBO) towards solving the CPP. We used the VBO as the reference model to this work since it is relatively a new algorithm. Moreover, the VBO extensively outperformed many other existing models. To the best of our knowledge, this is one of the first attempts to minimize the total average latency of SDN using feedback control theoretic techniques. Experimental results indicate that the DFBCPSDN outperforms the VBO algorithm implemented in two well-known topologies, namely Internet2 OS3E topology and EU-GÉANT topology. We observe that for uncapacitated CPP, the DFBCPSDN outperforms the VBO for Internet2 OS3E and EU-GÉANT topologies by 11% and 9%, respectively, in terms of total average latency. On the other hand, for capacitated CPP, the DFBCPSDN algorithm outperforms the VBO reference model by 10% and 8%, respectively. Full article
(This article belongs to the Special Issue Next Generation Networks and Systems Security)
Show Figures

Figure 1

20 pages, 4949 KiB  
Article
Sub-Synchronous Oscillation Suppression Strategy Based on Impedance Modeling by Attaching Virtual Resistance Controllers for Doubly-Fed Induction Generator
by Yingming Liu, Guoxian Guo, Xiaodong Wang, Hanbo Wang and Liming Wang
Electronics 2022, 11(14), 2272; https://doi.org/10.3390/electronics11142272 - 21 Jul 2022
Cited by 3 | Viewed by 2092
Abstract
A sub-synchronous oscillation (SSO) suppression strategy of attaching virtual resistance controllers to the rotor-side converter (RSC) of the doubly-fed induction generator (DFIG) is proposed in this study to suppress sub-synchronous oscillation (SSO) caused by series compensation and grid connection of DFIG. A DFIG-based [...] Read more.
A sub-synchronous oscillation (SSO) suppression strategy of attaching virtual resistance controllers to the rotor-side converter (RSC) of the doubly-fed induction generator (DFIG) is proposed in this study to suppress sub-synchronous oscillation (SSO) caused by series compensation and grid connection of DFIG. A DFIG-based frequency domain impedance model considering RSC control under small signal perturbations is developed in a three-phase stationary coordinate system. Subsequently, the factors and mechanisms of SSO in the system with different phase sequences are analyzed in combination with the equivalent RLC resonant circuit of a DFIG-based series-compensated grid-connected system (SCGCS). SSO occurs when RSC and rotor winding generate a large equivalent negative resistance at the SSO frequency, resulting in a negative total system resistance. Additionally, the influences of series compensation degree (SCD) of line and inner loop parameters (ILPs) of RSC related to the total impedance of the system on the SSO characteristics are analyzed to optimize the parameters and improve the system stability. Based on the causes of SSO, virtual resistance controllers are attached to RSC to provide positive resistance to the system and to offset the equivalent negative resistance of RSC and rotor winding at the SSO frequency, thereby avoiding SSO of the system. Finally, time-domain simulations using power system computer aided design/electromagnetic transients including dc (PSCAD/EMTDC) show that the SSO of the system is effectively suppressed. Full article
(This article belongs to the Topic Distributed Generation and Storage in Power Systems)
Show Figures

Figure 1

22 pages, 1401 KiB  
Systematic Review
Virtual/Augmented Reality for Rehabilitation Applications Using Electromyography as Control/Biofeedback: Systematic Literature Review
by Cinthya Lourdes Toledo-Peral, Gabriel Vega-Martínez, Jorge Airy Mercado-Gutiérrez, Gerardo Rodríguez-Reyes, Arturo Vera-Hernández, Lorenzo Leija-Salas and Josefina Gutiérrez-Martínez
Electronics 2022, 11(14), 2271; https://doi.org/10.3390/electronics11142271 - 20 Jul 2022
Cited by 30 | Viewed by 6860
Abstract
Virtual reality (VR) and augmented reality (AR) are engaging interfaces that can be of benefit for rehabilitation therapy. However, they are still not widely used, and the use of surface electromyography (sEMG) signals is not established for them. Our goal is to explore [...] Read more.
Virtual reality (VR) and augmented reality (AR) are engaging interfaces that can be of benefit for rehabilitation therapy. However, they are still not widely used, and the use of surface electromyography (sEMG) signals is not established for them. Our goal is to explore whether there is a standardized protocol towards therapeutic applications since there are not many methodological reviews that focus on sEMG control/feedback. A systematic literature review using the PRISMA (preferred reporting items for systematic reviews and meta-analyses) methodology is conducted. A Boolean search in databases was performed applying inclusion/exclusion criteria; articles older than 5 years and repeated were excluded. A total of 393 articles were selected for screening, of which 66.15% were excluded, 131 records were eligible, 69.46% use neither VR/AR interfaces nor sEMG control; 40 articles remained. Categories are, application: neurological motor rehabilitation (70%), prosthesis training (30%); processing algorithm: artificial intelligence (40%), direct control (20%); hardware: Myo Armband (22.5%), Delsys (10%), proprietary (17.5%); VR/AR interface: training scene model (25%), videogame (47.5%), first-person (20%). Finally, applications are focused on motor neurorehabilitation after stroke/amputation; however, there is no consensus regarding signal processing or classification criteria. Future work should deal with proposing guidelines to standardize these technologies for their adoption in clinical practice. Full article
Show Figures

Figure 1

14 pages, 2070 KiB  
Article
Adaptive Fuzzy Control for Flexible Robotic Manipulator with a Fixed Sampled Period
by Jiaming Zhang and Xisheng Dai
Electronics 2022, 11(14), 2270; https://doi.org/10.3390/electronics11142270 - 20 Jul 2022
Cited by 3 | Viewed by 1529
Abstract
In this paper, a backstepping sampled data control method is developed for a flexible robotic manipulator whose internal dynamic is completely unknown. To address the internal uncertainties, the fuzzy logical system (FLS) is considered. Moreover, considering the limited network bandwidth, the designed controller [...] Read more.
In this paper, a backstepping sampled data control method is developed for a flexible robotic manipulator whose internal dynamic is completely unknown. To address the internal uncertainties, the fuzzy logical system (FLS) is considered. Moreover, considering the limited network bandwidth, the designed controller and adaptive laws only contain the sampled data with a fixed sampled period. By invoking the Lyapunov stability theory, all signals of the flexible robotic manipulator are semi-global uniformly ultimately bounded (SGUUB). Ultimately, an application to a flexible robotic manipulator is given to verify the validity of the sampled data controller. Full article
Show Figures

Figure 1

20 pages, 6196 KiB  
Article
Practical Digital Twins Application to High Energy Systems: Thermal Protection for Multi-Detector
by Andrzej Wojtulewicz, Paweł D. Domański, Maciej Czarnynoga, Monika Kutyła, Maciej Ławryńczuk, Robert Nebeluk, Sebastian Plamowski, Krystian Rosłon and Krzysztof Zarzycki
Electronics 2022, 11(14), 2269; https://doi.org/10.3390/electronics11142269 - 20 Jul 2022
Cited by 1 | Viewed by 1979
Abstract
The digital twins concept brings a new perspective into the system design and maintenance practice. As any industrial process can be accurately simulated, its digital replica can be utilized to design a control system structure, evaluate its efficacy and investigate the properties of [...] Read more.
The digital twins concept brings a new perspective into the system design and maintenance practice. As any industrial process can be accurately simulated, its digital replica can be utilized to design a control system structure, evaluate its efficacy and investigate the properties of the real system and possible issues. Based on such an analysis, ideas for improvement may be formulated. This article reports the formulation of a digital twin system developed for a Thermal System (TS) maintaining proper thermal conditions for the operation of the Silicon Tracking Detectors (STDs) utilized for high-energy physics experiments. A thermal system digital twin is built for a full-scale target installation, which is right now during the construction phase. The emphasis is put on a proper control system design using the thermal system digital twins. Full article
Show Figures

Figure 1

16 pages, 3106 KiB  
Article
AGS-SSD: Attention-Guided Sampling for 3D Single-Stage Detector
by Hanxiang Qian, Peng Wu, Bei Sun and Shaojing Su
Electronics 2022, 11(14), 2268; https://doi.org/10.3390/electronics11142268 - 20 Jul 2022
Cited by 2 | Viewed by 2034
Abstract
3D object detection based on LiDAR point cloud has always been challenging. Existing point cloud downsampling approaches often use heuristic algorithms such as farthest point sampling (FPS) to extract the features from a massive raw point cloud. However, FPS has disadvantages such as [...] Read more.
3D object detection based on LiDAR point cloud has always been challenging. Existing point cloud downsampling approaches often use heuristic algorithms such as farthest point sampling (FPS) to extract the features from a massive raw point cloud. However, FPS has disadvantages such as low operating efficiency and inability to sample key areas. This paper presents an attention-guided downsampling method for point-cloud-based 3D object detection, named AGS-SSD. The method contains two modules: PEA (point external attention) and A-FPS (attention-guided FPS). PEA explores the correlation between the data and uses the external attention mechanism to extract the semantic features in the set abstraction stage. The semantic information, including the relationship between the samples, is sent to the candidate point generation module as context points. A-FPS weighs the point cloud according to the generated attention map and samples the foreground points with rich semantic information as candidate points. The experimental results show that our method achieves significant improvements with novel architectures against the baseline and runs at 24 frames per second for inference. Full article
(This article belongs to the Special Issue Autonomous Vehicle Perception: The Technology of Today and Tomorrow)
Show Figures

Figure 1

14 pages, 4623 KiB  
Article
A Robust Bayesian Optimization Framework for Microwave Circuit Design under Uncertainty
by Duygu De Witte, Jixiang Qing, Ivo Couckuyt, Tom Dhaene, Dries Vande Ginste and Domenico Spina
Electronics 2022, 11(14), 2267; https://doi.org/10.3390/electronics11142267 - 20 Jul 2022
Cited by 6 | Viewed by 2364
Abstract
In modern electronics, there are many inevitable uncertainties and variations of design parameters that have a profound effect on the performance of a device. These are, among others, induced by manufacturing tolerances, assembling inaccuracies, material diversities, machining errors, etc. This prompts wide interests [...] Read more.
In modern electronics, there are many inevitable uncertainties and variations of design parameters that have a profound effect on the performance of a device. These are, among others, induced by manufacturing tolerances, assembling inaccuracies, material diversities, machining errors, etc. This prompts wide interests in enhanced optimization algorithms that take the effect of these uncertainty sources into account and that are able to find robust designs, i.e., designs that are insensitive to the uncertainties early in the design cycle. In this work, a novel machine learning-based optimization framework that accounts for uncertainty of the design parameters is presented. This is achieved by using a modified version of the expected improvement criterion. Moreover, a data-efficient Bayesian Optimization framework is leveraged to limit the number of simulations required to find a robust design solution. Two suitable application examples validate that the robustness is significantly improved compared to standard design methods. Full article
(This article belongs to the Topic Artificial Intelligence Models, Tools and Applications)
Show Figures

Figure 1

18 pages, 15504 KiB  
Article
Design and Implementation of an Intelligent Assistive Cane for Visually Impaired People Based on an Edge-Cloud Collaboration Scheme
by Yuqi Ma, Yanqing Shi, Moyu Zhang, Wei Li, Chen Ma and Yu Guo
Electronics 2022, 11(14), 2266; https://doi.org/10.3390/electronics11142266 - 20 Jul 2022
Cited by 4 | Viewed by 4218
Abstract
Visually impaired people face many inconveniences in daily life, and there are problems such as high prices and single functions in the market of assistance tools for visually impaired people. In this work, we designed and implemented a low-cost intelligent assistance cane, particularly [...] Read more.
Visually impaired people face many inconveniences in daily life, and there are problems such as high prices and single functions in the market of assistance tools for visually impaired people. In this work, we designed and implemented a low-cost intelligent assistance cane, particularly for visually impaired individuals, based on computer vision, sensors, and an edge-cloud collaboration scheme. Obstacle detection, fall detection, and traffic light detection functions have been designed and integrated for the convenience of moving for visually impaired people. We have also designed an image captioning function and object detection function with high-speed processing capability based on an edge-cloud collaboration scheme to improve the user experience. Experiments show that the performance metrics have an aerial obstacle detection accuracy of 92.5%, fall detection accuracy of 90%, and average image retrieval period of 1.124 s. It proves the characteristics of low power consumption, strong real-time performance, adaptability to multiple scenarios, and convenience, which can ensure the safety of visually impaired people when moving and can help them better perceive and understand the surrounding environment. Full article
(This article belongs to the Special Issue Design, Development and Testing of Wearable Devices)
Show Figures

Figure 1

11 pages, 998 KiB  
Article
EEG-Based Schizophrenia Diagnosis through Time Series Image Conversion and Deep Learning
by Dong-Woo Ko and Jung-Jin Yang
Electronics 2022, 11(14), 2265; https://doi.org/10.3390/electronics11142265 - 20 Jul 2022
Cited by 22 | Viewed by 4281
Abstract
Schizophrenia, a mental disorder experienced by more than 20 million people worldwide, is emerging as a serious issue in society. Currently, the diagnosis of schizophrenia is based only on mental disorder diagnosis and/or diagnosis by a psychiatrist or mental health professional using DSM-5, [...] Read more.
Schizophrenia, a mental disorder experienced by more than 20 million people worldwide, is emerging as a serious issue in society. Currently, the diagnosis of schizophrenia is based only on mental disorder diagnosis and/or diagnosis by a psychiatrist or mental health professional using DSM-5, a diagnostic and statistical manual of mental disorders. Furthermore, patients in countries with insufficient access to healthcare are difficult to diagnose for schizophrenia and early diagnosis is even more problematic. While various studies are being conducted to solve the challenges of schizophrenia diagnosis, methodology is considered to be limited, and diagnostic accuracy needs to be improved. In this study, a new approach using EEG data and deep learning is proposed to increase objectivity and efficiency of schizophrenia diagnosis. Existing deep learning studies use EEG data to classify schizophrenic patients and healthy subjects by learning EEG in the form of graphs or tables. However, in this study, EEG, a time series data, was converted into an image to improve classification accuracy, and is then studied in deep learning models. This study used EEG data of 81 people, in which the difference in N100 EEG between schizophrenic patients and healthy patients had been analyzed in prior research. EEGs were converted into images using time series image conversion algorithms, Recurrence Plot (RP) and Gramian Angular Field (GAF), and converted EEG images were learned with Convolutional Neural Network (CNN) models built based on VGGNet. When the trained deep learning model was applied to the same data from prior research, it was demonstrated that classification accuracy improved when compared to previous studies. Among the two algorithms used for image conversion, the deep learning model that learned through GAF showed significantly higher classification accuracy. The results of this study suggest that the use of GAF and CNN models based on EEG results can be an effective way to increase objectivity and efficiency in diagnosing various mental disorders, including schizophrenia. Full article
(This article belongs to the Topic Machine and Deep Learning)
Show Figures

Figure 1

13 pages, 4383 KiB  
Article
A Coupling Analytical Method of a Fuel Control System under Electromagnetic Pulses
by Jie Cao, Minxiang Wei and Dong Zhou
Electronics 2022, 11(14), 2264; https://doi.org/10.3390/electronics11142264 - 20 Jul 2022
Cited by 1 | Viewed by 1568
Abstract
This study presents an electromagnetic coupling analytical method of a fuel control system under electromagnetic pulses. With the increasing complexity of the electromagnetic environment, improving the survivability of the aero-engine fuel control system is of great importance. By analyzing the electromagnetic interference of [...] Read more.
This study presents an electromagnetic coupling analytical method of a fuel control system under electromagnetic pulses. With the increasing complexity of the electromagnetic environment, improving the survivability of the aero-engine fuel control system is of great importance. By analyzing the electromagnetic interference of the aero-engine fuel control system under electromagnetic pulses, a coupling analytical method of an aero-engine fuel control system under electromagnetic pulses was proposed. The method tested the control system to obtain the coupling signal of the controller through the bulk current injection (BCI) test. Subsequently, the numerical model of the terminal coupling signal of the controller under an electromagnetic pulse was established, and the influence of the terminal coupling signal on the terminal circuit was investigated by numerical simulation. The method locates sensitive components of the control system and determines if the internal mechanism of the electromagnetic pulse effect is the interference of the pulse signal to control signal links. The coupling signal model is established to predict the coupling signal of the main fuel regulation control system. It identifies potential solutions to BCI method limitations that have an impact on reducing test costs. Full article
(This article belongs to the Section Systems & Control Engineering)
Show Figures

Figure 1

9 pages, 2245 KiB  
Article
Improved Performance and Bias Stability of Al2O3/IZO Thin-Film Transistors with Vertical Diffusion
by Se-Hyeong Lee, So-Young Bak and Moonsuk Yi
Electronics 2022, 11(14), 2263; https://doi.org/10.3390/electronics11142263 - 20 Jul 2022
Cited by 4 | Viewed by 2730
Abstract
Several studies on amorphous oxide semiconductor thin-film transistors (TFTs) applicable to next-generation display devices have been conducted. To improve the poor switching characteristics and gate bias stability of co-sputtered aluminum–indium–zinc oxide (AIZO) TFTs, we fabricate Al2O3/indium–zinc oxide (IZO) dual-active-layer [...] Read more.
Several studies on amorphous oxide semiconductor thin-film transistors (TFTs) applicable to next-generation display devices have been conducted. To improve the poor switching characteristics and gate bias stability of co-sputtered aluminum–indium–zinc oxide (AIZO) TFTs, we fabricate Al2O3/indium–zinc oxide (IZO) dual-active-layer TFTs. By varying the Al2O3 target power and oxygen partial pressure in the chamber during Al2O3 back-channel deposition, we optimize the electrical characteristics and gate bias stability of the Al2O3/IZO TFTs. The Al2O3/IZO TFTs, which are fabricated under 50 W Al2O3 target power and 13% oxygen partial pressure conditions, exhibit a high electron mobility of 23.34 cm2/V·s, a low threshold voltage of 0.96 V, an improved on–off current ratio of 6.8 × 107, and a subthreshold swing of 0.61 V/dec. Moreover, by increasing the oxygen partial pressure in the chamber, the positive and negative bias stress values improve to +0.32 V and −2.08 V, respectively. X-ray photoelectron spectroscopy is performed to reveal the cause of these improvements. Full article
(This article belongs to the Section Semiconductor Devices)
Show Figures

Figure 1

15 pages, 930 KiB  
Article
Modeling Acoustic Channel Variability in Underwater Network Simulators from Real Field Experiment Data
by Filippo Campagnaro, Nicola Toffolo and Michele Zorzi
Electronics 2022, 11(14), 2262; https://doi.org/10.3390/electronics11142262 - 20 Jul 2022
Cited by 7 | Viewed by 1798
Abstract
The underwater acoustic channel is remarkably dependent on the considered scenario and the environmental conditions. In fact, channel impairments differ significantly in shallow water with respect to deep water, and the presence of external factors such as snapping shrimps, bubbles, rain, or ships [...] Read more.
The underwater acoustic channel is remarkably dependent on the considered scenario and the environmental conditions. In fact, channel impairments differ significantly in shallow water with respect to deep water, and the presence of external factors such as snapping shrimps, bubbles, rain, or ships passing nearby, changes of temperature, and wind strength can change drastically the link quality in different seasons and even during the same day. Legacy mathematical models that consider these factors exist, but are either not very accurate, like the Urick model, or very computationally demanding, like the Bellhop ray tracer. Deterministic models based on lookup tables (LUTs) of sea trial measurements are widely used by the research community to simulate the acoustic channel in order to verify the functionalities of a network in certain water conditions before the actual deployment. These LUTs can characterize the link quality by observing, for instance, the average packet error rate or even a time varying packet error rate computed within a certain time window. While this procedure characterizes well the acoustic channel, the obtained simulation results are limited to a single channel realization, making it hard to fully evaluate the acoustic network in different conditions. In this paper, we discuss the development of a statistical channel model based on the analysis of real field experiment data, and compare its performance with the other channel models available in the DESERT Underwater network simulator. Full article
Show Figures

Figure 1

13 pages, 2416 KiB  
Article
Analysis of the Impact of Particulate Matter on Net Load and Behind-the-Meter PV Decoupling
by Yeuntae Yoo and Seokheon Cho
Electronics 2022, 11(14), 2261; https://doi.org/10.3390/electronics11142261 - 20 Jul 2022
Viewed by 1511
Abstract
With the increasing penetration of the photovoltaic (PV) generator, uncertainty surrounding the power system has increased simultaneously. The uncertainty of PV generation output has an impact on the load demand forecast due to the presence of behind-the-meter (BtM) PV generation. As it is [...] Read more.
With the increasing penetration of the photovoltaic (PV) generator, uncertainty surrounding the power system has increased simultaneously. The uncertainty of PV generation output has an impact on the load demand forecast due to the presence of behind-the-meter (BtM) PV generation. As it is hard to assess the amount of BtM PV generation, the load demand pattern can be distorted depending on the solar irradiation level. In several literature works, the influence of the load demand pattern from BtM PV generation is modeled using environmental data sets such as the level of solar irradiation, temperature, and past load demand data. The particulate matter is a severe meteorological event in several countries that can reduce the level of solar irradiation on the surface. The accuracy of the forecast model for PV generation and load demand can be exacerbated if the impact of the particulate matter is not properly considered. In this paper, the impact of particulate matter to load demand patterns is analyzed for the power system with high penetration of BtM PV generation. Actual meteorological data are gathered for the analysis and correlations between parameters are built using Gaussian process regression. Full article
Show Figures

Figure 1

16 pages, 3417 KiB  
Article
Convolution Neural Networks for the Automatic Segmentation of 18F-FDG PET Brain as an Aid to Alzheimer’s Disease Diagnosis
by Elena Pasini, Dario Genovesi, Carlo Rossi, Lisa Anita De Santi, Vincenzo Positano, Assuero Giorgetti and Maria Filomena Santarelli
Electronics 2022, 11(14), 2260; https://doi.org/10.3390/electronics11142260 - 20 Jul 2022
Cited by 3 | Viewed by 2416
Abstract
Our work aims to exploit deep learning (DL) models to automatically segment diagnostic regions involved in Alzheimer’s disease (AD) in 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) volumetric scans in order to provide a more objective diagnosis of this disease and to reduce the [...] Read more.
Our work aims to exploit deep learning (DL) models to automatically segment diagnostic regions involved in Alzheimer’s disease (AD) in 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) volumetric scans in order to provide a more objective diagnosis of this disease and to reduce the variability induced by manual segmentation. The dataset used in this study consists of 102 volumes (40 controls, 39 with established Alzheimer’s disease (AD), and 23 with established mild cognitive impairment (MCI)). The ground truth was generated by an expert user who identified six regions in original scans, including temporal lobes, parietal lobes, and frontal lobes. The implemented architectures are the U-Net3D and V-Net networks, which were appropriately adapted to our data to optimize performance. All trained segmentation networks were tested on 22 subjects using the Dice similarity coefficient (DSC) and other similarity indices, namely the overlapping area coefficient (AOC) and the extra area coefficient (EAC), to evaluate automatic segmentation. The results of each labeled brain region demonstrate an improvement of 50%, with DSC from about 0.50 for V-Net-based networks to about 0.77 for U-Net3D-based networks. The best performance was achieved by using U-Net3D, with DSC on average equal to 0.76 for frontal lobes, 0.75 for parietal lobes, and 0.76 for temporal lobes. U-Net3D is very promising and is able to segment each region and each class of subjects without being influenced by the presence of hypometabolic regions. Full article
(This article belongs to the Special Issue Machine Learning in Electronic and Biomedical Engineering, Volume II)
Show Figures

Figure 1

20 pages, 3035 KiB  
Article
An Efficient Real-Time FPGA-Based ORB Feature Extraction for an UHD Video Stream for Embedded Visual SLAM
by Mateusz Wasala, Hubert Szolc and Tomasz Kryjak
Electronics 2022, 11(14), 2259; https://doi.org/10.3390/electronics11142259 - 20 Jul 2022
Cited by 9 | Viewed by 3747
Abstract
The detection and description of feature points are important components of many computer vision systems. For example, in the field of autonomous unmanned aerial vehicles (UAV), these methods form the basis of so-called Visual Odometry (VO) and Simultaneous Localisation and Mapping (SLAM) algorithms. [...] Read more.
The detection and description of feature points are important components of many computer vision systems. For example, in the field of autonomous unmanned aerial vehicles (UAV), these methods form the basis of so-called Visual Odometry (VO) and Simultaneous Localisation and Mapping (SLAM) algorithms. In this paper, we present a hardware feature points detection system able to process a 4K video stream in real-time. We use the ORB algorithm—Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elementary Features)—to detect and describe feature points in the images. We make numerous modifications to the original ORB algorithm (among others, we use the RS-BRIEF instead of classic R-BRIEF) to adapt it to the high video resolution, make it computationally efficient, reduce the resource utilisation and achieve lower power consumption. Our hardware implementation supports a 4 ppc (pixels per clock) format (with simple adaptation to 2 ppc, 8 ppc, and more) and real-time processing of a 4K video stream (UHD—Ultra High Definition, 3840×2160 pixels) @ 60 frames per second (150 MHz clock). We verify our system using simulations in the Vivado IDE and implement it in hardware on the ZCU 104 evaluation board with the AMD Xilinx Zynq UltraScale+ MPSoC device. The proposed design consumes only 5 watts. Full article
(This article belongs to the Special Issue Embedded Systems: Fundamentals, Design and Practical Applications)
Show Figures

Figure 1

18 pages, 9131 KiB  
Article
Design of Miniaturized Antipodal Vivaldi Antennas for Wideband Microwave Imaging of the Head
by Farhana Parveen and Parveen Wahid
Electronics 2022, 11(14), 2258; https://doi.org/10.3390/electronics11142258 - 20 Jul 2022
Cited by 4 | Viewed by 2715
Abstract
Many wideband applications, e.g., microwave imaging of the head, require low-frequency (~1–6 GHz) operation using small antennas. Vivaldi antennas are extensively used in multifarious wideband applications; however, the physical dimensions of the antenna become very large for covering low-frequency bands. Hence, the miniaturization [...] Read more.
Many wideband applications, e.g., microwave imaging of the head, require low-frequency (~1–6 GHz) operation using small antennas. Vivaldi antennas are extensively used in multifarious wideband applications; however, the physical dimensions of the antenna become very large for covering low-frequency bands. Hence, the miniaturization of Vivaldi antennas, while maintaining proper matching and radiation characteristics, is essential for these applications. In this work, two miniaturized Vivaldi antennas are proposed, and several miniaturization techniques are presented for reducing the size of the antennas without the need for being immersed into any matching liquid, while maintaining desired performance. The novelty of the designs lies in the use of two half-cut superstrates, which help in achieving low-frequency operation with end-fire radiation. Two prototype antennas are fabricated, and the performances of the antennas are analyzed from both simulation and measurement results. The antennas show an FBW of 45.26% and 95.9% with a gain of ~1.9–5.2 dB and ~1.5–5.5 dB, respectively, while having a radiation efficiency above 80% within the resonant bandwidth. A comparison of the proposed antennas with several other state-of-the-art Vivaldi antennas is included to demonstrate the viability of the proposed antennas in achieving the desired performance with comparatively small dimensions. Full article
(This article belongs to the Special Issue New Generation Design of Antennas)
Show Figures

Figure 1

19 pages, 4511 KiB  
Article
Post-Flood UAV-Based Free Space Optics Recovery Communications with Spatial Mode Diversity
by Angela Amphawan, Norhana Arsad, Tse-Kian Neo, Muhammed Basheer Jasser and Athirah Mohd Ramly
Electronics 2022, 11(14), 2257; https://doi.org/10.3390/electronics11142257 - 19 Jul 2022
Cited by 7 | Viewed by 2506
Abstract
The deployment of unmanned aerial vehicles (UAVs) for free space optical communications is an attractive solution for forwarding the vital health information of victims from a flood-stricken area to neighboring ground base stations during rescue operations. A critical challenge to this is maintaining [...] Read more.
The deployment of unmanned aerial vehicles (UAVs) for free space optical communications is an attractive solution for forwarding the vital health information of victims from a flood-stricken area to neighboring ground base stations during rescue operations. A critical challenge to this is maintaining an acceptable signal quality between the ground base station and UAV-based free space optics relay. This is largely unattainable due to rapid UAV propeller and body movements, which result in fluctuations in the beam alignment and frequent link failures. To address this issue, linearly polarized Laguerre–Gaussian modes were leveraged for spatial mode diversity to prevent link failures over a 400 m link. Spatial mode diversity successfully improved the bit error rate by 38% to 55%. This was due to a 10% to 19% increase in the predominant mode power from spatial mode diversity. The time-varying channel matrix indicated the presence of nonlinear deterministic chaos. This opens up new possibilities for research on state-space reconstruction of the channel matrix. Full article
(This article belongs to the Special Issue Unmanned Aircraft Systems with Autonomous Navigation)
Show Figures

Figure 1

13 pages, 998 KiB  
Article
Assessing Artificial Intelligence Technology Acceptance in Managerial Accounting
by Anca Antoaneta Vărzaru
Electronics 2022, 11(14), 2256; https://doi.org/10.3390/electronics11142256 - 19 Jul 2022
Cited by 32 | Viewed by 11614
Abstract
The increasing expansion of digital technologies has significantly changed most economic activities and professions. As a result of the scientific and technological revolution 4.0, organizational structures and business models have changed, and new ones have emerged. Consequently, the accounting activities that record operations [...] Read more.
The increasing expansion of digital technologies has significantly changed most economic activities and professions. As a result of the scientific and technological revolution 4.0, organizational structures and business models have changed, and new ones have emerged. Consequently, the accounting activities that record operations and provide the necessary information to managers for decision making have faced threats, challenges, and opportunities, which have changed and will change the DNA of managerial accounting, determining a reinventing of it. As a result of the evolution of data collection and processing technologies, managerial accounting activities have become increasingly complex, encompassing increasing volumes of data. Resistance to change, organizational culture, lack of trust, and the high price of technology are the most critical barriers that interfere with adopting artificial intelligence technology in managerial accounting. This study aimed to assess the acceptance of artificial intelligence technology among accountants in Romanian organizations in the context of the modernization and digitization of managerial accounting. This research was quantitative, carried out through a survey based on a questionnaire. In total, 396 specialists in managerial accounting from Romanian organizations filled and returned the questionnaire. Using structural equation modeling, we tested the model of accepting artificial intelligence technology in managerial accounting. The results show that implementing artificial intelligence solutions in managerial accounting offers multiple options to managers through innovation and shortening processes, improves the use of accounting information, and is relatively easy to use, given the high degree of automation and customization. Full article
Show Figures

Figure 1

14 pages, 2978 KiB  
Article
A Cloud-Edge-Smart IoT Architecture for Speeding Up the Deployment of Neural Network Models with Transfer Learning Techniques
by Tz-Heng Hsu, Zhi-Hao Wang and Aaron Raymond See
Electronics 2022, 11(14), 2255; https://doi.org/10.3390/electronics11142255 - 19 Jul 2022
Cited by 6 | Viewed by 2884
Abstract
Existing edge computing architectures do not support the updating of neural network models, nor are they optimized for storing, updating, and transmitting different neural network models to a large number of IoT devices. In this paper, a cloud-edge smart IoT architecture for speeding [...] Read more.
Existing edge computing architectures do not support the updating of neural network models, nor are they optimized for storing, updating, and transmitting different neural network models to a large number of IoT devices. In this paper, a cloud-edge smart IoT architecture for speeding up the deployment of neural network models with transfer learning techniques is proposed. A new model deployment and update mechanism based on the share weight characteristic of transfer learning is proposed to address the model deployment issues associated with the significant number of IoT devices. The proposed mechanism compares the feature weight and parameter difference between the old and new models whenever a new model is trained. With the proposed mechanism, the neural network model can be updated on IoT devices with just a small quantity of data sent. Utilizing the proposed collaborative edge computing platform, we demonstrate a significant reduction in network bandwidth transmission and an improved deployment speed of neural network models. Subsequently, the service quality of smart IoT applications can be enhanced. Full article
(This article belongs to the Special Issue Advances of Future IoE Wireless Network Technology)
Show Figures

Figure 1

20 pages, 5378 KiB  
Article
Analyzing TCP Performance in High Bit Error Rate Using Simulation and Modeling
by Nurul I. Sarkar, Roman Ammann and Salahuddin Muhammad Salim Zabir
Electronics 2022, 11(14), 2254; https://doi.org/10.3390/electronics11142254 - 19 Jul 2022
Cited by 3 | Viewed by 3233
Abstract
While Transmission Control Protocol (TCP) works well with a low bit error rate (BER), the performance of TCP degrades significantly if the BER rises above a certain level. A study of the performance of TCP with high BER is required for [...] Read more.
While Transmission Control Protocol (TCP) works well with a low bit error rate (BER), the performance of TCP degrades significantly if the BER rises above a certain level. A study of the performance of TCP with high BER is required for the efficient design and deployment of such systems. In this paper, we address the problem of TCP performance in high BERs and analyze the issues by investigating the effect of BERs on system performance. We consider TCP Reno in our study to explore the system performance using extensive analysis of simulation and modeling. In the analysis, we consider the amount of datagram sent and retransmitted, mean throughput, link-layer overhead, TCP window size, FTP download response time, packet dropping and retransmission, and the TCP congestion avoidance mechanism. We validate simulation results by setting up a virtualized testbed using Linux hosts and a Linux router. The results obtained show that TCP throughput degrades significantly and eventually collapses at the packet drop probability of 10% (BER = 10−5). The FTP download response time is about 32 times longer than that of a perfect channel (no packet dropping). We found that TCP Reno cannot handle such a high BER to operate in wireless environments effectively. Finally, we provide recommendations for network researchers and engineers confronted with the challenge of operating TCP over noisy channels. Full article
Show Figures

Figure 1

14 pages, 410 KiB  
Article
Batch-Wise Permutation Feature Importance Evaluation and Problem-Specific Bigraph for Learn-to-Branch
by Yajie Niu, Chen Peng and Bolin Liao
Electronics 2022, 11(14), 2253; https://doi.org/10.3390/electronics11142253 - 19 Jul 2022
Cited by 4 | Viewed by 2106
Abstract
The branch-and-bound algorithm for combinatorial optimization typically relies on a plethora of handcraft expert heuristics, and a research direction, so-called learn-to-branch, proposes to replace the expert heuristics in branch-and-bound with machine learning models. Current studies in this area typically use an imitation learning [...] Read more.
The branch-and-bound algorithm for combinatorial optimization typically relies on a plethora of handcraft expert heuristics, and a research direction, so-called learn-to-branch, proposes to replace the expert heuristics in branch-and-bound with machine learning models. Current studies in this area typically use an imitation learning (IL) approach; however, in practice, IL often suffers from limited training samples. Thus, it has been emphasized that a small-dataset fast-training scheme for IL in learn-to-branch is worth studying, so that other methods, e.g., reinforcement learning, may be used for subsequent training. Thus, this paper focuses on the IL part of a mixed training approach, where a small-dataset fast-training scheme is considered. The contributions are as follows. First, to compute feature importance metrics so that the state-of-the-art bigraph representation can be effectively reduced for each problem type, a batch-wise permutation feature importance evaluation method is proposed, which permutes features within each batch in the forward pass. Second, based on the evaluated importance of the bigraph features, a reduced bigraph representation is proposed for each of the benchmark problems. The experimental results on four MILP benchmark problems show that our method improves branching accuracy by 8% and reduces solution time by 18% on average under the small-dataset fast-training scheme compared to the state-of-the-art bigraph-based learn-to-branch method. The source code is available online at GitHub. Full article
(This article belongs to the Special Issue Analog AI Circuits and Systems)
Show Figures

Figure 1

17 pages, 5883 KiB  
Article
Asymmetric Fault-Tolerant Control of 3-Phase Coupled Buck–Boost Converter
by Han Fu, Shanxu Duan, Junyang Bao, Dong Jiang, Hao Fu and Qiqi Li
Electronics 2022, 11(14), 2252; https://doi.org/10.3390/electronics11142252 - 19 Jul 2022
Cited by 1 | Viewed by 1494
Abstract
A coupled inductor can optimize the weight of a DC/DC converter while the performance characteristics are complicated. To reduce the influence of system fault and keep the stable operation of the coupled converter, a fault-tolerant strategy is proposed. Firstly, a mathematic model is [...] Read more.
A coupled inductor can optimize the weight of a DC/DC converter while the performance characteristics are complicated. To reduce the influence of system fault and keep the stable operation of the coupled converter, a fault-tolerant strategy is proposed. Firstly, a mathematic model is obtained to compare the difference between a coupled converter and a normal converter. Then, an open-circuit fault process is analyzed for fault detection. To design a proper fault-tolerant control system, transfer functions in asymmetric conditions are analyzed, and the operation of the mode switching is optimized for better a transition process. Finally, the method is verified by simulation and experiment. Full article
Show Figures

Figure 1

15 pages, 2795 KiB  
Article
Interference Signal Feature Extraction and Pattern Classification Algorithm Based on Deep Learning
by Jiangyi Qin, Fei Zhang, Kai Wang, Yuan Zuo and Chenxi Deng
Electronics 2022, 11(14), 2251; https://doi.org/10.3390/electronics11142251 - 19 Jul 2022
Cited by 4 | Viewed by 2908
Abstract
Aiming at the scarcity of Low Earth Orbit (LEO) satellite spectrum resources, this paper proposes an algorithm of interference signal feature extraction and pattern classification based on deep learning to further improve the stability of satellite–ground communication links. The algorithm can successfully predict [...] Read more.
Aiming at the scarcity of Low Earth Orbit (LEO) satellite spectrum resources, this paper proposes an algorithm of interference signal feature extraction and pattern classification based on deep learning to further improve the stability of satellite–ground communication links. The algorithm can successfully predict the interference signal pattern, start–stop time, frequency change range and other parameters, and has the advantages of excellent interference detection performance, high detection accuracy and small parameter prediction error, etc. It can be applied in the field of channel monitoring of communication satellite-to-ground communication links, and realize the repeated and efficient utilization of spectrum resources. Experiments show that the precision and recall of the algorithm for detecting five kinds of interference signals are all close to 100%, the prediction error of starting and ending time is less than 4 ms, and the prediction error of starting and ending frequency is less than 6 KHz. Full article
(This article belongs to the Special Issue Edge Computing for Urban Internet of Things)
Show Figures

Figure 1

21 pages, 3397 KiB  
Article
Real-Time Facemask Detection for Preventing COVID-19 Spread Using Transfer Learning Based Deep Neural Network
by Mona A. S. Ai, Anitha Shanmugam, Suresh Muthusamy, Chandrasekaran Viswanathan, Hitesh Panchal, Mahendran Krishnamoorthy, Diaa Salama Abd Elminaam and Rasha Orban
Electronics 2022, 11(14), 2250; https://doi.org/10.3390/electronics11142250 - 18 Jul 2022
Cited by 15 | Viewed by 3846
Abstract
The COVID-19 pandemic disrupted people’s livelihoods and hindered global trade and transportation. During the COVID-19 pandemic, the World Health Organization mandated that masks be worn to protect against this deadly virus. Protecting one’s face with a mask has become the standard. Many public [...] Read more.
The COVID-19 pandemic disrupted people’s livelihoods and hindered global trade and transportation. During the COVID-19 pandemic, the World Health Organization mandated that masks be worn to protect against this deadly virus. Protecting one’s face with a mask has become the standard. Many public service providers will encourage clients to wear masks properly in the foreseeable future. On the other hand, monitoring the individuals while standing alone in one location is exhausting. This paper offers a solution based on deep learning for identifying masks worn over faces in public places to minimize the coronavirus community transmission. The main contribution of the proposed work is the development of a real-time system for determining whether the person on a webcam is wearing a mask or not. The ensemble method makes it easier to achieve high accuracy and makes considerable strides toward enhancing detection speed. In addition, the implementation of transfer learning on pretrained models and stringent testing on an objective dataset led to the development of a highly dependable and inexpensive solution. The findings provide validity to the application’s potential for use in real-world settings, contributing to the reduction in pandemic transmission. Compared to the existing methodologies, the proposed method delivers improved accuracy, specificity, precision, recall, and F-measure performance in three-class outputs. These metrics include accuracy, specificity, precision, and recall. An appropriate balance is kept between the number of necessary parameters and the time needed to conclude the various models. Full article
(This article belongs to the Special Issue Big Data Analytics Using Artificial Intelligence)
Show Figures

Figure 1

18 pages, 8596 KiB  
Article
Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine
by Huajun Bai, Xianbiao Zhan, Hao Yan, Liang Wen, Yunbin Yan and Xisheng Jia
Electronics 2022, 11(14), 2249; https://doi.org/10.3390/electronics11142249 - 18 Jul 2022
Cited by 13 | Viewed by 2151
Abstract
Due to the relative insufficiencies of conventional time-domain waveform and spectrum analysis in fault diagnosis research, a diesel engine fault diagnosis method based on the Stacked Sparse Autoencoder and the Support Vector Machine is proposed in this study. The method consists of two [...] Read more.
Due to the relative insufficiencies of conventional time-domain waveform and spectrum analysis in fault diagnosis research, a diesel engine fault diagnosis method based on the Stacked Sparse Autoencoder and the Support Vector Machine is proposed in this study. The method consists of two main steps. The first step is to utilize the Stacked Sparse Autoencoder (SSAE) to reduce the feature dimension of the multi-sensor vibration information; when compared with other dimension reduction methods, this approach can better capture nonlinear features, so as to better cope with dimension reduction. The second step consists of diagnosing faults, implementing the grid search, and K-fold cross-validation to optimize the hyperparameters of the SVM method, which effectively improves the fault classification effect. By conducting a preset failure experiment for the diesel engine, the proposed method achieves an accuracy rate of more than 98%, better engineering application, and promising outcomes. Full article
(This article belongs to the Special Issue Deep Learning Algorithm Generalization for Complex Industrial Systems)
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop