Next Issue
Volume 13, December-1
Previous Issue
Volume 13, November-1
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Volume 13
Issue 22
share announcement

Electronics, Volume 13, Issue 22 (November-2 2024) – 245 articles

Cover Story (view full-size image): This study quantifies the interaction between remote drivers of teleoperation systems and Level 4 automated vehicles in real-world settings, focusing on how both disengagement and distraction affect performance. Key findings reveal that mental disengagement caused by distraction delays a remote driver's reaction times by 5.3 seconds and decision-making by 4.2 seconds during critical interventions. Disengagement also reduces attention and increased cognitive workload. The study underscores the need to design teleoperation systems that keep remote drivers engaged and which minimise distractions to ensure safe and effective operation of Level 4 automated vehicles. 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
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
19 pages, 5047 KiB  
Article
A Convolutional Neural Network for the Removal of Simultaneous Ocular and Myogenic Artifacts from EEG Signals
by Maryam Azhar, Tamoor Shafique and Anas Amjad
Electronics 2024, 13(22), 4576; https://doi.org/10.3390/electronics13224576 - 20 Nov 2024
Viewed by 787
Abstract
Electroencephalography (EEG) is a non-invasive technique widely used in neuroscience to diagnose neural disorders and analyse brain activity. However, ocular and myogenic artifacts from eye movements and facial muscle activity often contaminate EEG signals, compromising signal analysis accuracy. While deep learning models are [...] Read more.
Electroencephalography (EEG) is a non-invasive technique widely used in neuroscience to diagnose neural disorders and analyse brain activity. However, ocular and myogenic artifacts from eye movements and facial muscle activity often contaminate EEG signals, compromising signal analysis accuracy. While deep learning models are a popular choice for denoising EEG signals, most focus on removing either ocular or myogenic artifacts independently. This paper introduces a novel EEG denoising model capable of handling the simultaneous occurrence of both artifacts. The model uses convolutional layers to extract spatial features and a fully connected layer to reconstruct clean signals from learned features. The model integrates the Adam optimiser, average pooling, and ReLU activation to effectively capture and restore clean EEG signals. It demonstrates superior performance, achieving low training and validation losses with a significantly reduced RRMSE value of 0.35 in both the temporal and spectral domains. A high cross-correlation coefficient of 0.94 with ground-truth EEG signals confirms the model’s fidelity. Compared to the existing architectures and models (FPN, UNet, MCGUNet, LinkNet, MultiResUNet3+, Simple CNN, Complex CNN) across a range of signal-to-noise ratio values, the model shows superior performance for artifact removal. It also mitigates overfitting, underscoring its robustness in artifact suppression. Full article
►▼ Show Figures

Figure 1

15 pages, 402 KiB  
Article
Adaptive Dynamic Programming-Based Spacecraft Attitude Control Under a Tube-Based Framework
by Shiyi Li, Kerun Liu and Ming Liu
Electronics 2024, 13(22), 4575; https://doi.org/10.3390/electronics13224575 - 20 Nov 2024
Viewed by 454
Abstract
This paper investigates the control problem of a spacecraft attitude manoeuvrer with external disturbances. Firstly, the spacecraft attitude dynamical model is introduced; then, the tube-based framework is constructed, which includes a nominal system and an error system. Based on that, the control law [...] Read more.
This paper investigates the control problem of a spacecraft attitude manoeuvrer with external disturbances. Firstly, the spacecraft attitude dynamical model is introduced; then, the tube-based framework is constructed, which includes a nominal system and an error system. Based on that, the control law design would be a two-step process. To start with, the nominal control law is developed via an adaptive dynamic programming technique and a neural network approximation in order to provide a nominal trajectory to the desired attitude. Moreover, based on the nonsingular terminal sliding mode control scheme, the error controller is derived to lead the actual system to track the nominal trajectory and suppress disturbances. The stability of the closed-loop system is analyzed via the Lyapunov approach and the simulation results could verify the effectiveness of the proposed control scheme. Full article
(This article belongs to the Section Systems & Control Engineering)
►▼ Show Figures

Figure 1

19 pages, 7944 KiB  
Article
Method for Reconstructing Velocity Field Images of the Internal Structures of Bridges Based on Group Sparsity
by Jian Li, Jin Li, Chenli Guo, Hongtao Wu, Chuankun Li, Rui Liu and Lujun Wei
Electronics 2024, 13(22), 4574; https://doi.org/10.3390/electronics13224574 - 20 Nov 2024
Viewed by 418
Abstract
Non-destructive testing (NDT) enables the determination of internal defects and flaws in concrete structures without damaging them, making it a common application in current bridge concrete inspections. However, due to the complexity of the internal structure of this type of concrete, limitations regarding [...] Read more.
Non-destructive testing (NDT) enables the determination of internal defects and flaws in concrete structures without damaging them, making it a common application in current bridge concrete inspections. However, due to the complexity of the internal structure of this type of concrete, limitations regarding measurement point placement, and the extensive detection area, accurate defect detection cannot be guaranteed. This paper proposes a method that combines the Simultaneous Algebraic Reconstruction Technique with Group Sparsity Regularization (SART-GSR) to achieve tomographic imaging of bridge concrete under sparse measurement conditions. Firstly, a mathematical model is established based on the principles of the tomographic imaging of bridge concrete; secondly, the SART algorithm is used to solve for its velocity values; thirdly, on the basis of the SART results, GSR is applied for optimized solution processing; finally, simulation experiments are conducted to verify the reconstruction effects of the SART-GSR algorithm compared with those of the SART and ART algorithms. The results show that the SART-GSR algorithm reduced the relative error to 1.5% and the root mean square error to 89.76 m/s compared to the SART and ART algorithms. This improvement in accuracy makes it valuable for the tomographic imaging of bridge concrete and provides a reference for defect detection in bridge concrete. Full article
(This article belongs to the Topic Visual Computing and Understanding: New Developments and Trends)
►▼ Show Figures

Figure 1

26 pages, 14487 KiB  
Article
Accelerating Die Bond Quality Detection Using Lightweight Architecture DSGβSI-Yolov7-Tiny
by Bao Rong Chang, Hsiu-Fen Tsai and Wei-Shun Chang
Electronics 2024, 13(22), 4573; https://doi.org/10.3390/electronics13224573 - 20 Nov 2024
Viewed by 434
Abstract
The die bonding process is one of the most critical steps in the front-end semiconductor packaging process, as it significantly affects the yield of the entire IC packaging process. This research aims to find an efficient, intelligent vision detection model to identify whether [...] Read more.
The die bonding process is one of the most critical steps in the front-end semiconductor packaging process, as it significantly affects the yield of the entire IC packaging process. This research aims to find an efficient, intelligent vision detection model to identify whether each chip correctly adheres to the IC substrate; by utilizing the detection model to classify the type of defects occurring in the die bond images, the engineers can analyze the leading causes, enabling timely adjustments to key machine parameters in real-time, improving the yield of the die bond process, and significantly reducing manufacturing cost losses. This study proposes the lightweight Yolov7-tiny model using Depthwise-Separable and Ghost Convolutions and Sigmoid Linear Unit with β parameter (DSGβSI-Yolov7-tiny), which we can apply for real-time and efficient detection and prediction of die bond quality. The model achieves a maximum FPS of 192.3, a precision of 99.1%, and an F1-score of 0.97. Therefore, the performance of the proposed DSGβSI-Yolov7-tiny model outperforms other methods. Full article
(This article belongs to the Special Issue Novel Methods for Object Detection and Segmentation)
►▼ Show Figures

Figure 1

15 pages, 14638 KiB  
Article
Control Strategy for Disc Coreless Permanent Magnet Synchronous Motor with LC Filter
by Hong Tian and Min Kang
Electronics 2024, 13(22), 4572; https://doi.org/10.3390/electronics13224572 - 20 Nov 2024
Viewed by 535
Abstract
The disc coreless permanent magnet synchronous motor has the advantages of a short axial size, high power density, and small volume. Due to the coreless structure, its inductance is very small, which results in a serious current ripple and an unacceptable torque ripple [...] Read more.
The disc coreless permanent magnet synchronous motor has the advantages of a short axial size, high power density, and small volume. Due to the coreless structure, its inductance is very small, which results in a serious current ripple and an unacceptable torque ripple if driven from a conventional inverter. This can be solved by installing an LC filter between the inverter and the motor. However, an undesirable resonance phenomenon is induced by the LC filter. In this paper, a new capacitive current feedback active damping (CCFAD) strategy is proposed. Instead of current sensors in the capacitor branch, a state observer is introduced to estimate the capacitance current. The observer is designed with double sliding mode surfaces, which reduces the order of the system. Compared to conventional capacitive current feedback, no additional current sensors are required, reducing the system cost. Besides the resonant harmonics, the phase current contains obvious fifth and seventh harmonics due to the special plane structure of the rotor. The proportional-integral-resonance (PIR) controller, instead of the traditional PI controller, is designed to suppress lower order harmonics. The experiment results show that current ripples due to resonance and rotor structure are suppressed significantly. Full article
►▼ Show Figures

Figure 1

23 pages, 3093 KiB  
Article
SLDPSO-TA: Track Assignment Algorithm Based on Social Learning Discrete Particle Swarm Optimization
by Huayang Cai, Ruping Zhou, Pengcheng Huang, Yidan Jing and Genggeng Liu
Electronics 2024, 13(22), 4571; https://doi.org/10.3390/electronics13224571 - 20 Nov 2024
Viewed by 540
Abstract
In modern circuit design, the short-circuit problem is one of the key factors affecting routability. With the continuous reduction in feature sizes, the short-circuit problem grows significantly in detailed routing. Track assignment, as a crucial intermediary phase between global routing and detailed routing, [...] Read more.
In modern circuit design, the short-circuit problem is one of the key factors affecting routability. With the continuous reduction in feature sizes, the short-circuit problem grows significantly in detailed routing. Track assignment, as a crucial intermediary phase between global routing and detailed routing, plays a vital role in preprocessing the short-circuit problem. However, existing track assignment algorithms face the challenge of easily falling into local optimality. As a typical swarm intelligence technique, particle swarm optimization (PSO) is a powerful tool with excellent optimization ability to solve large-scale problems. To address the above issue, we propose an effective track assignment algorithm based on social learning discrete particle swarm optimization (SLDPSO-TA). First, an effective wire model that considers the local nets is proposed. By considering the pin distribution of local nets, this model extracts and allocates more segments to fully leverage the role of track assignment. Second, an integer encoding strategy is employed to ensure that particles within the encoding space range correspond one-to-one with the assignment scheme, effectively expanding the search space. Third, a social learning mode based on the example pool is introduced to PSO, which is composed of other particles that are superior to the current particle. By learning from various objects in the example pool, the diversity of the population is improved. Fourth, a negotiation-based refining strategy is utilized to further reduce overlap. This strategy intelligently transfers and redistributes wire segments in congested areas to reduce congestion across the entire routing panel. Experimental results on multiple benchmarks demonstrate that the proposed SLDPSO-TA can achieve the best overlap cost optimization among all the existing methods, effectively reducing congestion in critical routing areas. Full article
(This article belongs to the Section Computer Science & Engineering)
►▼ Show Figures

Figure 1

18 pages, 4942 KiB  
Article
Unsupervised Anomaly Detection and Explanation in Network Traffic with Transformers
by André Kummerow, Esrom Abrha, Markus Eisenbach and Dennis Rösch
Electronics 2024, 13(22), 4570; https://doi.org/10.3390/electronics13224570 - 20 Nov 2024
Viewed by 758
Abstract
Deep learning-based autoencoders represent a promising technology for use in network-based attack detection systems. They offer significant benefits in managing unknown network traces or novel attack signatures. Specifically, in the context of critical infrastructures, such as power supply systems, AI-based intrusion detection systems [...] Read more.
Deep learning-based autoencoders represent a promising technology for use in network-based attack detection systems. They offer significant benefits in managing unknown network traces or novel attack signatures. Specifically, in the context of critical infrastructures, such as power supply systems, AI-based intrusion detection systems must meet stringent requirements concerning model accuracy and trustworthiness. For the intrusion response, the activation of suitable countermeasures can greatly benefit from additional transparency information (e.g., attack causes). Transformers represent the state of the art for learning from sequential data and provide important model insights through the widespread use of attention mechanisms. This paper introduces a two-stage transformer-based autoencoder for learning meaningful information from network traffic at the packet and sequence level. Based on this, we present a sequential attention weight perturbation method to explain benign and malicious network packets. We evaluate our method against benchmark models and expert-based explanations using the CIC-IDS-2017 benchmark dataset. The results show promising results in terms of detecting and explaining FTP and SSH brute-force attacks, highly outperforming the results of the benchmark model. Full article
(This article belongs to the Special Issue Applications of Deep Learning in Cyber Threat Detection)
►▼ Show Figures

Figure 1

21 pages, 9594 KiB  
Article
On the Lateral Stability System of Four-Wheel Driven Electric Vehicles Based on Phase Plane Method
by Yu-Jie Ma, Chih-Keng Chen and Xiao-Dong Zhang
Electronics 2024, 13(22), 4569; https://doi.org/10.3390/electronics13224569 - 20 Nov 2024
Viewed by 513
Abstract
To improve the handling and stability of four-wheel independent drive electric vehicles (FWID EVs), this paper introduces a hierarchical architecture lateral stability control system. The upper-level controller is responsible for generating the additional yaw moment required by the vehicle. This includes a control [...] Read more.
To improve the handling and stability of four-wheel independent drive electric vehicles (FWID EVs), this paper introduces a hierarchical architecture lateral stability control system. The upper-level controller is responsible for generating the additional yaw moment required by the vehicle. This includes a control strategy based on feedforward control and a Linear Quadratic Regulator (LQR) for handling assistance control, an LQR-based stability control, a PID controller-based speed-following control, and a stability assessment method. The lower-level controller uses Quadratic Programming (QP) to optimally distribute the additional yaw moment to the four wheels. A “normalized” method was proposed to determine vehicle stability. After comparing it with the existing double-line method, diamond method, and curved boundary method through the open-loop Sine with Dwell test and the closed-loop Double Lane Change (DLC)test simulation, the results demonstrate that this method is more sensitive and accurate in determining vehicle stability, significantly enhancing vehicle handling and stability. Full article
(This article belongs to the Special Issue Control Systems for Autonomous Vehicles)
►▼ Show Figures

Figure 1

29 pages, 8399 KiB  
Article
Automatic Modulation Recognition Based on Multimodal Information Processing: A New Approach and Application
by Wenna Zhang, Kailiang Xue, Aiqin Yao and Yunqiang Sun
Electronics 2024, 13(22), 4568; https://doi.org/10.3390/electronics13224568 - 20 Nov 2024
Viewed by 634
Abstract
Automatic modulation recognition (AMR) has wide applications in the fields of wireless communications, radar systems, and intelligent sensor networks. The existing deep learning-based modulation recognition models often focus on temporal features while overlooking the interrelations and spatio-temporal relationships among different types of signals. [...] Read more.
Automatic modulation recognition (AMR) has wide applications in the fields of wireless communications, radar systems, and intelligent sensor networks. The existing deep learning-based modulation recognition models often focus on temporal features while overlooking the interrelations and spatio-temporal relationships among different types of signals. To overcome these limitations, a hybrid neural network based on a multimodal parallel structure, called the multimodal parallel hybrid neural network (MPHNN), is proposed to improve the recognition accuracy. The algorithm first preprocesses the data by parallelly processing the multimodal forms of the modulated signals before inputting them into the network. Subsequently, by combining Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU) models, the CNN is used to extract spatial features of the received signals, while the Bi-GRU transmits previous state information of the time series to the current state to capture temporal features. Finally, the Convolutional Block Attention Module (CBAM) and Multi-Head Self-Attention (MHSA) are introduced as two attention mechanisms to handle the temporal and spatial correlations of the signals through an attention fusion mechanism, achieving the calibration of the signal feature maps. The effectiveness of this method is validated using various datasets, with the experimental results demonstrating that the proposed approach can fully utilize the information of multimodal signals. The experimental results show that the recognition accuracy of MPHNN on multiple datasets reaches 93.1%, and it has lower computational complexity and fewer parameters than other models. Full article
(This article belongs to the Section Artificial Intelligence)
►▼ Show Figures

Figure 1

15 pages, 3115 KiB  
Article
Anti-Jamming Power Control Algorithm for Wireless Communication Systems Based on MPC
by Kefeng Yu, Yingtao Niu, Hang Yao and Kai Zhang
Electronics 2024, 13(22), 4567; https://doi.org/10.3390/electronics13224567 - 20 Nov 2024
Viewed by 452
Abstract
In complex electromagnetic environments, wireless communication system reliability can be compromised by various types of jamming. To improve reliability in the presence of malicious jamming, this paper introduces an anti-jamming power control algorithm for wireless communication systems, grounded in model predictive control (MPC) [...] Read more.
In complex electromagnetic environments, wireless communication system reliability can be compromised by various types of jamming. To improve reliability in the presence of malicious jamming, this paper introduces an anti-jamming power control algorithm for wireless communication systems, grounded in model predictive control (MPC) principles. The algorithm models the Yescommunication system as a linear control system, using the current signal-to-jamming-and-noise ratio (SJNR) to predict future system states and transmission power over a defined time horizon. Only the first element of the optimal control sequence is then applied to manage system power. Simulation results indicate that, compared to traditional adaptive power control algorithms, the proposed algorithm responds more swiftly to jamming variations, significantly enhancing communication reliability in high-jamming environments. Full article
►▼ Show Figures

Figure 1

22 pages, 2388 KiB  
Article
DeFFace: Deep Face Recognition Unlocked by Illumination Attributes
by Xiangling Zhou, Zhongmin Gao, Huanji Gong and Shenglin Li
Electronics 2024, 13(22), 4566; https://doi.org/10.3390/electronics13224566 - 20 Nov 2024
Viewed by 594
Abstract
General face recognition is currently one of the key technologies in the field of computer vision, and it has achieved tremendous success with the support of deep-learning technology. General face recognition models currently exhibit extremely high accuracy on some high-quality face datasets. However, [...] Read more.
General face recognition is currently one of the key technologies in the field of computer vision, and it has achieved tremendous success with the support of deep-learning technology. General face recognition models currently exhibit extremely high accuracy on some high-quality face datasets. However, their performance decreases in challenging environments, such as low-light scenes. To enhance the performance of face recognition models in low-light scenarios, we propose a face recognition approach based on feature decoupling and fusion (DeFFace). Our main idea is to extract facial-related features from images that are not influenced by illumination. First, we introduce a feature decoupling network (D-Net) to decouple the image into facial-related features and illumination-related features. By incorporating the illumination triplet loss optimized with unpaired identity IDs, we regulate illumination-related features to minimize the impact of lighting conditions on the face recognition system. However, the decoupled features are relatively coarse. Therefore, we introduce a feature fusion network (F-Net) to further extract the residual facial-related features from the illumination-related features and fuse them with the initial facial-related features. Finally, we introduce a lighting-facial correlation loss to reduce the correlation between the two decoupled features in the specific space. We demonstrate the effectiveness of our method on four real-world low-light datasets and three simulated low-light datasets. We retrain multiple general face recognition methods using our proposed low-light training sets to further validate the advanced performance of our method. Compared to general face recognition methods, our approach achieves an average improvement of more than 2.11 percentage points on low-light face datasets. In comparison with image enhancement-based solutions, our method shows an average improvement of around 16 percentage points on low-light datasets, and it also delivers an average improvement of approximately 5.67 percentage points when compared to illumination normalization-based methods. Full article
►▼ Show Figures

Figure 1

38 pages, 13063 KiB  
Review
Power Converters for Green Hydrogen: State of the Art and Perspectives
by Gianpaolo Vitale
Electronics 2024, 13(22), 4565; https://doi.org/10.3390/electronics13224565 - 20 Nov 2024
Viewed by 613
Abstract
This paper provides a comprehensive review and outlook on power converters devised for supplying polymer electrolyte membrane (PEM) electrolyzers from photovoltaic sources. The produced hydrogen, known as green hydrogen, is a promising solution to mitigate the dependence on fossil fuels. The main topologies [...] Read more.
This paper provides a comprehensive review and outlook on power converters devised for supplying polymer electrolyte membrane (PEM) electrolyzers from photovoltaic sources. The produced hydrogen, known as green hydrogen, is a promising solution to mitigate the dependence on fossil fuels. The main topologies of power conversion systems are discussed and classified; a loss analysis emphasizes the issues concerning the electrolyzer supply. The attention is focused on power converters of rated power up to a tenth of a kW, since it is a promising field for a short-term solution implementing green hydrogen production as a decentralized. It is also encouraged by the proliferation of relatively cheap photovoltaic low-power plants. The main converters proposed by the literature in the last few years and realized for practical applications are analyzed, highlighting their key characteristics and focusing on the parameters useful for designers. Future perspectives are addressed concerning the availability of new wide-bandgap devices and hard-to-abate sectors with reference to the whole conversion chain. Full article
(This article belongs to the Special Issue Advances in Power Converter Design, Control and Applications)
►▼ Show Figures

Figure 1

20 pages, 19180 KiB  
Article
Leveraging Multi-Source Data for the Trustworthy Evaluation of the Vibrancy of Child-Friendly Cities: A Case Study of Tianjin, China
by Di Zhang, Kun Song and Di Zhao
Electronics 2024, 13(22), 4564; https://doi.org/10.3390/electronics13224564 - 20 Nov 2024
Viewed by 447
Abstract
The vitality of a city is shaped by its social structure, environmental quality, and spatial form, with child-friendliness being an essential component of urban vitality. While there are numerous qualitative studies on the relationship between child-friendliness and various indicators of urban vitality, quantitative [...] Read more.
The vitality of a city is shaped by its social structure, environmental quality, and spatial form, with child-friendliness being an essential component of urban vitality. While there are numerous qualitative studies on the relationship between child-friendliness and various indicators of urban vitality, quantitative research remains relatively scarce, leading to a lack of sufficient objective and trustworthy data to guide urban planning and the development of child-friendly cities. This paper presents an analytical framework, using Heping District in Tianjin, China, as a case study. It defines four main indicators—social vitality, environmental vitality, spatial vitality, and urban scene perception—for a trustworthy and transparent quantitative evaluation. The study integrates multi-source data, including primary education (POI) data, street view image (SVI) data, spatiotemporal big data, normalized difference vegetation index (NDVI), and large visual language models (LVLMs) for the trustworthy analysis. These data are visualized using corresponding big data and weighted analysis methods, ensuring transparent and accurate assessments of the child-friendliness of urban blocks. This research introduces an innovative and trustworthy method for evaluating the child-friendliness of urban blocks, addressing gaps in the quantitative theory of child-friendliness in urban planning. It also provides a practical and reliable tool for urban planners, offering a solid theoretical foundation to create environments that better meet the needs of children in a trustworthy manner. Full article
(This article belongs to the Special Issue Adversarial Attacks and Defenses in AI Safety/Reliability)
►▼ Show Figures

Figure 1

30 pages, 2746 KiB  
Article
Optimizing Microgrid Performance: Integrating Unscented Transformation and Enhanced Cheetah Optimization for Renewable Energy Management
by Ali S. Alghamdi
Electronics 2024, 13(22), 4563; https://doi.org/10.3390/electronics13224563 - 20 Nov 2024
Viewed by 442
Abstract
The increased integration of renewable energy sources (RESs), such as photovoltaic and wind turbine systems, in microgrids poses significant challenges due to fluctuating weather conditions and load demands. To address these challenges, this study introduces an innovative approach that combines Unscented Transformation (UT) [...] Read more.
The increased integration of renewable energy sources (RESs), such as photovoltaic and wind turbine systems, in microgrids poses significant challenges due to fluctuating weather conditions and load demands. To address these challenges, this study introduces an innovative approach that combines Unscented Transformation (UT) with the Enhanced Cheetah Optimization Algorithm (ECOA) for optimal microgrid management. UT, a robust statistical technique, models nonlinear uncertainties effectively by leveraging sigma points, facilitating accurate decision-making despite variable renewable generation and load conditions. The ECOA, inspired by the adaptive hunting behaviors of cheetahs, is enhanced with stochastic leaps, adaptive chase mechanisms, and cooperative strategies to prevent premature convergence, enabling improved exploration and optimization for unbalanced three-phase distribution networks. This integrated UT-ECOA approach enables simultaneous optimization of continuous and discrete decision variables in the microgrid, efficiently handling uncertainty within RESs and load demands. Results demonstrate that the proposed model significantly improves microgrid performance, achieving a 10% reduction in voltage deviation, a 10.63% decrease in power losses, and an 83.32% reduction in operational costs, especially when demand response (DR) is implemented. These findings validate the model’s efficacy in enhancing microgrid reliability and efficiency, positioning it as a viable solution for optimized performance under uncertain renewable inputs. Full article
(This article belongs to the Special Issue Control and Optimization Technologies in Renewable Energy and Integrated Energy Systems)
►▼ Show Figures

Figure 1

18 pages, 2568 KiB  
Article
ATGT3D: Animatable Texture Generation and Tracking for 3D Avatars
by Fei Chen and Jaeho Choi
Electronics 2024, 13(22), 4562; https://doi.org/10.3390/electronics13224562 - 20 Nov 2024
Viewed by 401
Abstract
We propose the ATGT3D an Animatable Texture Generation and Tracking for 3D Avatars, featuring the innovative design of the Eye Diffusion Module (EDM) and Pose Tracking Diffusion Module (PTDM), which are dedicated to high-quality eye texture generation and synchronized tracking of dynamic poses [...] Read more.
We propose the ATGT3D an Animatable Texture Generation and Tracking for 3D Avatars, featuring the innovative design of the Eye Diffusion Module (EDM) and Pose Tracking Diffusion Module (PTDM), which are dedicated to high-quality eye texture generation and synchronized tracking of dynamic poses and textures, respectively. Compared to traditional GAN and VAE methods, ATGT3D significantly enhances texture consistency and generation quality in animated scenes using the EDM, which produces high-quality full-body textures with detailed eye information using the HUMBI dataset. Additionally, the Pose Tracking and Diffusion Module (PTDM) monitors human motion parameters utilizing the BEAT2 and AMASS mesh-level animatable human model datasets. The EDM, in conjunction with a basic texture seed featuring eyes and the diffusion model, restores high-quality textures, whereas the PTDM, by integrating MoSh++ and SMPL-X body parameters, models hand and body movements from 2D human images, thus providing superior 3D motion capture datasets. This module maintains the synchronization of textures and movements over time to ensure precise animation texture tracking. During training, the ATGT3D model uses the diffusion model as the generative backbone to produce new samples. The EDM improves the texture generation process by enhancing the precision of eye details in texture images. The PTDM involves joint training for pose generation and animation tracking reconstruction. Textures and body movements are generated individually using encoded prompts derived from masked gestures. Furthermore, ATGT3D adaptively integrates texture and animation features using the diffusion model to enhance both fidelity and diversity. Experimental results show that ATGT3D achieves optimal texture generation performance and can flexibly integrate predefined spatiotemporal animation inputs to create comprehensive human animation models. Our experiments yielded unexpectedly positive outcomes. Full article
(This article belongs to the Special Issue AI for Human Collaboration)
►▼ Show Figures

Figure 1

16 pages, 1589 KiB  
Article
A Two-Phase Deep Learning Approach to Link Quality Estimation for Multiple-Beam Transmission
by Mun-Suk Kim
Electronics 2024, 13(22), 4561; https://doi.org/10.3390/electronics13224561 - 20 Nov 2024
Viewed by 424
Abstract
In the multi-user multiple-input-multiple-output (MU-MIMO) beamforming (BF) training defined by the 802.11ay standard, since a single initiator transmits a significant number of action frames to multiple responders, inefficient configuration of the transmit antenna arrays when sending these action frames increases the signaling and [...] Read more.
In the multi-user multiple-input-multiple-output (MU-MIMO) beamforming (BF) training defined by the 802.11ay standard, since a single initiator transmits a significant number of action frames to multiple responders, inefficient configuration of the transmit antenna arrays when sending these action frames increases the signaling and latency overheads of MU-MIMO BF training. To configure appropriate transmit antenna arrays for transmitting action frames, the initiator needs to accurately estimate the signal to noise ratios (SNRs) measured at the responders for each configuration of the transmit antenna arrays. In this paper, we propose a two-phase deep learning approach to improve the accuracy of SNR estimation for multiple concurrent beams by reducing the measurement errors of the SNRs for individual single beams when each action frame is transmitted through multiple concurrent beams. Through simulations, we demonstrated that our proposed scheme enabled more responders to successfully receive action frames during MU-MIMO BF training compared to existing schemes. Full article
(This article belongs to the Special Issue Digital Signal Processing and Wireless Communication)
►▼ Show Figures

Figure 1

17 pages, 852 KiB  
Article
Boosting Few-Shot Network Intrusion Detection with Adaptive Feature Fusion Mechanism
by Jue Bo, Kai Chen, Shenghui Li and Pengyi Gao
Electronics 2024, 13(22), 4560; https://doi.org/10.3390/electronics13224560 - 20 Nov 2024
Viewed by 490
Abstract
In network security, intrusion detection systems (IDSs) are essential for maintaining network integrity. Traditional IDSs primarily use supervised learning, relying on extensive datasets for effective training, which limits their ability to address rapidly evolving cyber threats, especially with limited data samples. To overcome [...] Read more.
In network security, intrusion detection systems (IDSs) are essential for maintaining network integrity. Traditional IDSs primarily use supervised learning, relying on extensive datasets for effective training, which limits their ability to address rapidly evolving cyber threats, especially with limited data samples. To overcome this, prior research has applied meta-learning methods to distinguish between normal and malicious network traffic, showing promising results mainly in binary classification scenarios. However, challenges remain in model information acquisition within few-shot learning (FSL) frameworks. This study introduces a metric-based meta-learning strategy that constructs prototypes for each sample category, improving the model’s ability to manage multi-class scenarios. Additionally, we propose an Adaptive Feature Fusion (AFF) mechanism that dynamically integrates statistical features and binary data streams to extract meaningful insights from limited datasets, thereby enhancing the effectiveness of IDSs in few-shot learning contexts. By introducing a metric-based meta-learning method and the Adaptive Feature Fusion mechanism, this study provides a feasible solution for developing a high-accuracy, multi-class few-shot intrusion detection system. A series of experiments show that this approach significantly improves the effectiveness of the intrusion detection system, achieving an impressive accuracy of 97.78% in multi-class tasks, even when the sample size is reduced to just one. Full article
(This article belongs to the Special Issue Large Language Models for Software Engineering and Software Applications)
►▼ Show Figures

Figure 1

22 pages, 1667 KiB  
Article
Enhancing Keystroke Dynamics Authentication with Ensemble Learning and Data Resampling Techniques
by Xiaofei Wang and Daqing Hou
Electronics 2024, 13(22), 4559; https://doi.org/10.3390/electronics13224559 - 20 Nov 2024
Viewed by 614
Abstract
Background: Keystroke dynamics authentication is a behavioral biometric method that verifies user identity by analyzing typing patterns. While traditional machine learning methods (e.g., decision trees, SVM) have shown potential in this field, their performance suffers in real-world scenarios due to data imbalance and [...] Read more.
Background: Keystroke dynamics authentication is a behavioral biometric method that verifies user identity by analyzing typing patterns. While traditional machine learning methods (e.g., decision trees, SVM) have shown potential in this field, their performance suffers in real-world scenarios due to data imbalance and limited recognition of certain classes, undermining system security and reliability. Methods: To address these issues, this study combines the Synthetic Minority Over-sampling Technique (SMOTE) with ensemble learning methods to improve classification accuracy. A Django-based platform was developed for standardized keystroke data collection, generating a balanced dataset to evaluate various classifiers. Experiments: Experiments were conducted using both the Django-collected dataset and the CMU benchmark dataset to compare traditional classifiers with SMOTE-enhanced ensemble learning models, such as Random Forest, XGBoost, and Bagging, on metrics like accuracy, recall, G-mean, and F1-score. Conclusions: The results show that SMOTE-enhanced ensemble learning models significantly outperform traditional classifiers, particularly in detecting minority classes. This approach effectively addresses data imbalance, improving model robustness and security, and provides a practical reference for building more reliable keystroke dynamics authentication systems. Full article
►▼ Show Figures

Figure 1

18 pages, 439 KiB  
Article
Optimization of Reclaiming–Loading Scheduling in Dry Bulk Terminals Based on Knowledge-Driven Memetic Algorithm
by Qiang Liu, Xiaodong Ni, Huashi Liu, Jingjing Wang and Kang Wang
Electronics 2024, 13(22), 4558; https://doi.org/10.3390/electronics13224558 - 20 Nov 2024
Viewed by 476
Abstract
Reclaiming–loading operations in dry bulk terminals often face conflicts and delays due to limitations in equipment processing capacity and operational line accessibility, which significantly compromise the safety and efficiency of these operations. This paper aims to optimize the reclaiming–loading schedule for each incoming [...] Read more.
Reclaiming–loading operations in dry bulk terminals often face conflicts and delays due to limitations in equipment processing capacity and operational line accessibility, which significantly compromise the safety and efficiency of these operations. This paper aims to optimize the reclaiming–loading schedule for each incoming vessel by considering parallel equipment operations and potential conflicts, with the goal of enhancing both the safety and efficiency of the loading processes. Through a detailed analysis of bulk reclaiming and reclaiming–loading mechanisms, we formulate the dry bulk terminal loading scheduling problem to minimize the total operational time for all loading tasks, taking into account constraints such as parallel reclaiming, collaborative loading, operational conflicts, and line accessibility. In order to obtain a good solution, including task execution sequences and allocation of reclaimers and shiploaders, a knowledge-driven memetic algorithm is developed by integrating knowledge-driven mechanisms with problem-specific operators within a memetic computing framework. Finally, numerical experiments for various scales are conducted using the layout and operational data from the Huanghua Port’s coal port area. The experimental results demonstrate the effectiveness of the proposed optimization algorithm. Full article
►▼ Show Figures

Figure 1

14 pages, 4252 KiB  
Article
Vector Reconfiguration on a Bidirectional Multilevel LCL-T Resonant Converter
by Jie Shi, Zhongyi Zhang, Yi Xu, Dandan Zou and Hui Cao
Electronics 2024, 13(22), 4557; https://doi.org/10.3390/electronics13224557 - 20 Nov 2024
Viewed by 314
Abstract
With the development of distributed energy technology, the establishment of the energy internet has become a general trend, and relevant research about the core component, energy router, has also become a hotspot. Therefore, the bidirectional isolated DC–DC converter (BIDC) is widely used in [...] Read more.
With the development of distributed energy technology, the establishment of the energy internet has become a general trend, and relevant research about the core component, energy router, has also become a hotspot. Therefore, the bidirectional isolated DC–DC converter (BIDC) is widely used in AC–DC–AC energy router systems, because it can flexibly support the DC bus voltage ratio and achieve bidirectional power flow. This paper proposes a novel vector reconfiguration on a bidirectional multilevel LCL-T resonant converter in which an NPC (neutral-point clamped) multilevel structure with a flying capacitor is introduced to form a novel active bridge, and a coupling transformer is specially added into the active bridge to achieve multilevel voltage output under hybrid modulation. In addition, an LCL-T two-port vector analysis is adopted to elaborate bidirectional power flow which can generate some reactive power to realize zero-voltage switching (ZVS) on active bridges to improve the efficiency of the converter. Meanwhile, due to the symmetry of the LCL-T structure, the difficulty of the bidirectional operation analysis of the power flow is reduced. Finally, a simulation study is designed with a rated voltage of 200 V on front and rear input sources which has a rated power of 450 W with an operational efficiency of 93.8%. Then, the feasibility of the proposed converter is verified. Full article
►▼ Show Figures

Figure 1

15 pages, 2546 KiB  
Article
Intelligent Analysis and Prediction of Computer Network Security Logs Based on Deep Learning
by Zhiwei Liu, Xiaoyu Li and Dejun Mu
Electronics 2024, 13(22), 4556; https://doi.org/10.3390/electronics13224556 - 20 Nov 2024
Viewed by 558
Abstract
Since the beginning of the 21st century, the development of computer networks has been advancing rapidly, and the world has gradually entered a new era of digital connectivity. While enjoying the convenience brought by digitization, people are also facing increasingly serious threats from [...] Read more.
Since the beginning of the 21st century, the development of computer networks has been advancing rapidly, and the world has gradually entered a new era of digital connectivity. While enjoying the convenience brought by digitization, people are also facing increasingly serious threats from network security (NS) issues. Due to the significant shortcomings in accuracy and efficiency of traditional Long Short-Term Memory (LSTM) neural networks (NN), different scholars have conducted research on computer NS situation prediction methods to address the aforementioned issues of traditional LSTM based NS situation prediction algorithms. Although these algorithms can improve the accuracy of NS situation prediction to a certain extent, there are still some limitations, such as low computational efficiency, low accuracy, and high model complexity. To address these issues, new methods and techniques have been proposed, such as using NN and machine learning techniques to improve the accuracy and efficiency of prediction models. This article referred to the Bidirectional Gated Recurrent Unit (BiGRU) improved by Gated Recurrent Unit (GRU), and introduced a multi model NS situation prediction algorithm with attention mechanism. In addition, the improved Particle Swarm Optimization (PSO) algorithm can be utilized to optimize hyperparameters and improve the training efficiency of the GRU NN. The experimental results on the UNSW-NB15 dataset show that the algorithm had an average absolute error of 0.0843 in terms of NS prediction accuracy. The RMSE was 0.0932, which was lower than traditional prediction algorithms LSTM and GRU, and significantly improved prediction accuracy. Full article
(This article belongs to the Section Networks)
►▼ Show Figures

Figure 1

16 pages, 15336 KiB  
Article
An Innovative Nonlinear Bounded Component Analysis Algorithm Based on Multivariate Nonlinear Chirp Mode Decomposition
by Mingyang Tang and Yafeng Wu
Electronics 2024, 13(22), 4555; https://doi.org/10.3390/electronics13224555 - 20 Nov 2024
Viewed by 380
Abstract
In complex and diverse practical application scenarios, the challenge of blind source separation under underdetermined and nonlinear conditions is often encountered. To address this challenge, this paper proposes an innovative underdetermined nonlinear bounded component analysis method. This method first employs Multivariate Nonlinear Chirp [...] Read more.
In complex and diverse practical application scenarios, the challenge of blind source separation under underdetermined and nonlinear conditions is often encountered. To address this challenge, this paper proposes an innovative underdetermined nonlinear bounded component analysis method. This method first employs Multivariate Nonlinear Chirp Mode Decomposition (MNCMD) to process and reconstruct the observed signals, transforming the original underdetermined problem into a positive definite problem. Subsequently, Gaussianization techniques are introduced as a means of nonlinear compensation, successfully converting the nonlinear model into an analyzable linear model, laying a solid foundation for subsequent signal separation. Finally, the signal is separated by the bounded component analysis method, which does not require the source signals to be independent of each other. To validate the effectiveness and superiority of the proposed algorithm, detailed simulation experiments were designed and implemented. The experimental results demonstrate that compared to traditional underdetermined blind source separation algorithms, the algorithm presented in this paper exhibits significant advantages in terms of universality, convergence speed, separation accuracy, and robustness. Furthermore, this paper successfully applies the algorithm to the blind extraction of fetal electrocardiogram (FECG) signals from real datasets. The experimental results show that the algorithm can rapidly and effectively extract clearer and more accurate FECG signals, demonstrating its great potential and value in practical applications. Full article
(This article belongs to the Section Circuit and Signal Processing)
►▼ Show Figures

Figure 1

15 pages, 403 KiB  
Article
Guaranteed Cost Control of Singular Fuzzy Time-Delay Systems Based on Proportional Plus Derivative Feedback
by Huayang Zhang, Hebin Wang and Xin Wang
Electronics 2024, 13(22), 4554; https://doi.org/10.3390/electronics13224554 - 20 Nov 2024
Viewed by 441
Abstract
This paper explores the guaranteed cost control issue for singular Takagi-Sugeno (T-S) fuzzy systems with time delay. An augmented Lyapunov-Krasovskii functional (LKF) is adopted to analyze the system’s stabilization, and sufficient conditions are established based on Lyapunov stability theory. The method of free [...] Read more.
This paper explores the guaranteed cost control issue for singular Takagi-Sugeno (T-S) fuzzy systems with time delay. An augmented Lyapunov-Krasovskii functional (LKF) is adopted to analyze the system’s stabilization, and sufficient conditions are established based on Lyapunov stability theory. The method of free weight matrices is employed to provide a systematic approach for determining the controller parameters. Additionally, two compelling examples are presented to demonstrate the viability of the proposed methods. Full article
►▼ Show Figures

Figure 1

19 pages, 4398 KiB  
Article
Research on Steering-by-Wire System Motor Control Based on an Improved Sparrow Search Proportional–Integral–Derivative Algorithm
by Kai Jin, Ping Xiao, Dongde Yang, Zhanyu Fang, Rongyun Zhang and Aixi Yang
Electronics 2024, 13(22), 4553; https://doi.org/10.3390/electronics13224553 - 20 Nov 2024
Viewed by 493
Abstract
To enhance the control performance of a wire-controlled steering system, an improved sparrow search algorithm for fine-tuning the gains of a proportional–integral–derivative (SSA-PID) steering motor control algorithm is proposed. Mathematical models of the steering system and motor were derived based on an analysis [...] Read more.
To enhance the control performance of a wire-controlled steering system, an improved sparrow search algorithm for fine-tuning the gains of a proportional–integral–derivative (SSA-PID) steering motor control algorithm is proposed. Mathematical models of the steering system and motor were derived based on an analysis of the system’s structure and dynamics. A PID controller was developed with the aim of facilitating the precise control of the steering angle by targeting the angle of the steering motor. The population diversity in the sparrow algorithm was enhanced through the integration of a human learning mechanism along with a Cauchy–Gaussian variation strategy. Furthermore, an adaptive warning strategy was implemented, which employed spiral exploration to modify the ratio of early warning indicators, thereby augmenting the algorithm’s capacity to evade local optima. Following these enhancements, an SSA-PID steering motor control algorithm was developed. Joint simulations were performed using the CarSim software 2019.1 and MATLAB/Simulink R2022a, and subsequent tests were conducted on a wire-controlled steering test rig. The outcomes of the simulations and bench tests demonstrate that the proposed SSA-PID regulation algorithm is capable of adapting effectively to variations and disturbances within the system, facilitating precise motor angle control and enhancing the overall reliability of the steering system. Full article
►▼ Show Figures

Figure 1

10 pages, 4572 KiB  
Article
Multimodal Food Image Classification with Large Language Models
by Jun-Hwa Kim, Nam-Ho Kim, Donghyeok Jo and Chee Sun Won
Electronics 2024, 13(22), 4552; https://doi.org/10.3390/electronics13224552 - 20 Nov 2024
Viewed by 625
Abstract
In this study, we leverage advancements in large language models (LLMs) for fine-grained food image classification. We achieve this by integrating textual features extracted from images using an LLM into a multimodal learning framework. Specifically, semantic textual descriptions generated by the LLM are [...] Read more.
In this study, we leverage advancements in large language models (LLMs) for fine-grained food image classification. We achieve this by integrating textual features extracted from images using an LLM into a multimodal learning framework. Specifically, semantic textual descriptions generated by the LLM are encoded and combined with image features obtained from a transformer-based architecture to improve food image classification. Our approach employs a cross-attention mechanism to effectively fuse visual and textual modalities, enhancing the model’s ability to extract discriminative features beyond what can be achieved with visual features alone. Full article
(This article belongs to the Special Issue AI Synergy: Vision, Language, and Modality)
►▼ Show Figures

Figure 1

11 pages, 6298 KiB  
Article
Impact of Titanium Cranial Implants on the Electric Field and SAR Distribution Induced by Mobile Phones Within the User’s Head
by Dragana Živaljević, Dejan Jovanović, Dragan Krasić, Nenad Cvetković and Bojana Petković
Electronics 2024, 13(22), 4551; https://doi.org/10.3390/electronics13224551 - 20 Nov 2024
Viewed by 718
Abstract
The purpose of this study was to determine the impact of a titanium cranial implant on the electric field distribution and the amount of energy absorbed from a cell phone within the human head. Three-dimensional lifelike models of the head of the mobile [...] Read more.
The purpose of this study was to determine the impact of a titanium cranial implant on the electric field distribution and the amount of energy absorbed from a cell phone within the human head. Three-dimensional lifelike models of the head of the mobile phone user, a titanium cranial implant, and a smartphone model was built. The head model consisted of sixteen homogeneous, isotropic domains, with permittivity and conductivity parameters taken from the literature. Numerical calculations were performed at the mobile communication frequency of 2600 MHz for a head model with and without a titanium cranial implant, in order to determine a field perturbation introduced by the implant. Our results show that in the presence of a titanium cranial implant, the electric field amplitude and SAR (Specific Absorption Rate) are increased within the layers close to the outer surface of the model (skin, fat tissue, and muscle). On the other hand, a cranial implant leads to a lower penetration depth, decreasing the electric field amplitude and SAR inside the skull, cerebrospinal fluid, and brain. Full article
►▼ Show Figures

Figure 1

34 pages, 85423 KiB  
Article
Lightweight, Post-Quantum Secure Cryptography Based on Ascon: Hardware Implementation in Automotive Applications
by Hai Phong Nguyen and Yuhua Chen
Electronics 2024, 13(22), 4550; https://doi.org/10.3390/electronics13224550 - 19 Nov 2024
Viewed by 1064
Abstract
With the rapid growth of connected vehicles and the vulnerability of embedded systems against cyber attacks in an era where quantum computers are becoming a reality, post-quantum cryptography (PQC) is a crucial solution. Yet, by nature, automotive sensors are limited in power, processing [...] Read more.
With the rapid growth of connected vehicles and the vulnerability of embedded systems against cyber attacks in an era where quantum computers are becoming a reality, post-quantum cryptography (PQC) is a crucial solution. Yet, by nature, automotive sensors are limited in power, processing capability, memory in implementing secure measures. This study presents a pioneering approach to securing automotive systems against post-quantum threats by integrating the Ascon cipher suite—a lightweight cryptographic protocol—into embedded automotive environments. By combining Ascon with the Controller Area Network (CAN) protocol on an Artix-7 Field Programmable Gate Array (FPGA), we achieve low power consumption while ensuring high performance in post-quantum-resistant cryptographic tasks. The Ascon module is designed to optimize computational efficiency through bitwise Boolean operations and logic gates, avoiding resource-intensive look-up tables and achieving superior processing speed. Our hardware design delivers significant speed improvements of 100 times over software implementations and operates effectively within a 100 MHz clock while demonstrating low resource usage. Furthermore, a custom digital signal processing block supports CAN protocol integration, handling message alignment and synchronization to maintain signal integrity under automotive environmental noise. Our work provides a power-efficient, robust cryptographic solution that prepares automotive systems for quantum-era security challenges, emphasizing lightweight cryptography’s readiness for real-world deployment in automotive industries. Full article
(This article belongs to the Special Issue Advanced IoT Security Solutions for Healthcare and Critical Infrastructures)
►▼ Show Figures

Figure 1

19 pages, 18572 KiB  
Article
MSG-YOLO: A Lightweight Detection Algorithm for Clubbing Finger Detection
by Zhijie Wang, Qiao Meng, Feng Tang, Yuelin Qi, Bingyu Li, Xin Liu, Siyuan Kong and Xin Li
Electronics 2024, 13(22), 4549; https://doi.org/10.3390/electronics13224549 - 19 Nov 2024
Viewed by 637
Abstract
Clubbing finger is a significant clinical indicator, and its early detection is essential for the diagnosis and treatment of associated diseases. However, traditional diagnostic methods rely heavily on the clinician’s subjective assessment, which can be prone to biases and may lack standardized tools. [...] Read more.
Clubbing finger is a significant clinical indicator, and its early detection is essential for the diagnosis and treatment of associated diseases. However, traditional diagnostic methods rely heavily on the clinician’s subjective assessment, which can be prone to biases and may lack standardized tools. Unlike other diagnostic challenges, the characteristic changes of clubbing finger are subtle and localized, necessitating high-precision feature extraction. Existing models often fail to capture these delicate changes accurately, potentially missing crucial diagnostic features or generating false positives. Furthermore, these models are often not suited for accurate clinical diagnosis in resource-constrained settings. To address these challenges, we propose MSG-YOLO, a lightweight clubbing finger detection model based on YOLOv8n, designed to enhance both detection accuracy and efficiency. The model first employs a multi-scale dilated residual module, which expands the receptive field using dilated convolutions and residual connections, thereby improving the model’s ability to capture features across various scales. Additionally, we introduce a Selective Feature Fusion Pyramid Network (SFFPN) that dynamically selects and enhances critical features, optimizing the flow of information while minimizing redundancy. To further refine the architecture, we reconstruct the YOLOv8 detection head with group normalization and shared-parameter convolutions, significantly reducing the model’s parameter count and increasing computational efficiency. Experimental results indicate that the model maintains high detection accuracy with reduced parameter and computational requirements. Compared to YOLOv8n, MSG-YOLO achieves a 48.74% reduction in parameter count and a 24.17% reduction in computational load, while improving the mAP0.5 score by 2.86%, reaching 93.64%. This algorithm strikes a balance between accuracy and lightweight design, offering efficient and reliable clubbing finger detection even in resource-constrained environments. Full article
►▼ Show Figures

Figure 1

16 pages, 29661 KiB  
Article
6.5 kV SiC PiN and JBS Diodes’ Comparison in Hybrid and Full SiC Switch Topologies
by Lucas Barroso Spejo, Lars Knoll and Renato Amaral Minamisawa
Electronics 2024, 13(22), 4548; https://doi.org/10.3390/electronics13224548 - 19 Nov 2024
Viewed by 560
Abstract
This work investigates the performance of state-of-the-art non-commercial 6.5 kV Silicon Carbide (SiC) PiN and Junction Barrier Schottky (JBS) diodes in hybrid (Si IGBT with SiC diode) and full SiC (SiC MOSFET with SiC diode) switch topologies. The static and dynamic performance has [...] Read more.
This work investigates the performance of state-of-the-art non-commercial 6.5 kV Silicon Carbide (SiC) PiN and Junction Barrier Schottky (JBS) diodes in hybrid (Si IGBT with SiC diode) and full SiC (SiC MOSFET with SiC diode) switch topologies. The static and dynamic performance has been systematically evaluated at distinct temperatures, gate resistances and currents for each configuration. The SiC PiN diode presented higher current density capability and lower leakage current density than the JBS diode. Moreover, in most cases, the SiC PiN diode-based topologies demonstrated slightly higher total switching losses compared to the SiC JBS diode-based equivalent configurations. A loadability analysis in a three-level NPC converter is presented to evaluate the potential of each configuration in a converter application. The SiC PiN technology presented a 25% power extension compared to the SiC JBS technology with similar efficiency at typical industrial drives switching frequency operation when comparing same-active-area diode technologies. Finally, a long-term reliability test (H3TRB) is presented to demonstrate the SiC PiN diode technology’s potential for operation in harsh environments. Such characteristics show the advantage of the 6.5 kV SiC PiN diode when a high current density (>100 A/cm2), high efficiency and reliability are required. Full article
(This article belongs to the Special Issue Advances in Power Converter Design, Control and Applications)
►▼ Show Figures

Figure 1

20 pages, 458 KiB  
Article
Neural Architecture Search via Trainless Pruning Algorithm: A Bayesian Evaluation of a Network with Multiple Indicators
by Yiqi Lin, Yuki Endo, Jinho Lee and Shunsuke Kamijo
Electronics 2024, 13(22), 4547; https://doi.org/10.3390/electronics13224547 - 19 Nov 2024
Viewed by 505
Abstract
Neural Architecture Search (NAS) has found applications in various areas of computer vision, including image recognition and object detection. An increasing number of algorithms, such as ENAS (Efficient Neural Architecture Search via Parameter Sharing) and DARTS (Differentiable Architecture Search), have been applied to [...] Read more.
Neural Architecture Search (NAS) has found applications in various areas of computer vision, including image recognition and object detection. An increasing number of algorithms, such as ENAS (Efficient Neural Architecture Search via Parameter Sharing) and DARTS (Differentiable Architecture Search), have been applied to NAS. Nevertheless, the current Training-free NAS methods continue to exhibit unreliability and inefficiency. This paper introduces a training-free prune-based algorithm called TTNAS (True-Skill Training-Free Neural Architecture Search), which utilizes a Bayesian method (true-skill algorithm) to combine multiple indicators for evaluating neural networks across different datasets. The algorithm demonstrates highly competitive accuracy and efficiency compared to state-of-the-art approaches on various datasets. Specifically, it achieves 93.90% accuracy on CIFAR-10, 71.91% accuracy on CIFAR-100, and 44.96% accuracy on ImageNet 16-120, using 1466 GPU seconds in NAS-Bench-201. Additionally, the algorithm exhibits improved adaptation to other datasets and tasks. Full article
(This article belongs to the Special Issue Computational Imaging and Its Application)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-245
Previous Issue
Next Issue
Back to TopTop