Electronics

17 pages, 3994 KiB

Open AccessArticle

A Novel Day-Ahead Optimization-Oriented Low-Carbon Economic Scheduling Scheme for Integrated Energy Systems

by Youdong Liang, Peng Li, Zhiran Yu, Zhilong Yin, Feng Yu and Zhiguo Wang

Electronics 2024, 13(20), 4122; https://doi.org/10.3390/electronics13204122 (registering DOI) - 19 Oct 2024

Abstract

As the global energy structure undergoes transformation and the low-carbon development process continues to advance, integrated energy systems have progressively emerged as crucial technical support for achieving sustainable development. In this paper, a joint-day optimal scheduling model is put forward considering the existence [...] Read more.

As the global energy structure undergoes transformation and the low-carbon development process continues to advance, integrated energy systems have progressively emerged as crucial technical support for achieving sustainable development. In this paper, a joint-day optimal scheduling model is put forward considering the existence of dispatchable resources in community integrated energy systems (CIES). The aim is to cut down the system operation cost and enhance energy utilization efficiency. This model is founded on the concept of energy hubs and combines the shiftable, transferable, and reducible characteristics of demand-side flexible loads. It includes gas turbine power generation systems, energy storage, as well as wind and solar renewable resources. System operation cost and carbon trading cost are comprehensively taken into account, and ultimately, the CIES low-carbon economic dispatch model with the lowest total cost as the optimization objective is established. The Yalmip toolbox and Cplex solver are employed to solve the model. The optimization results of flexible electric and thermal loads participating in dispatching under different scenarios are analyzed through simulation. The economic benefits of electric and thermal independent dispatching are compared and analyzed, and the economic benefits of electric and thermal coupled dispatching are verified. The study reveals that the rational scheduling of user-side flexible loads can notably reduce operating costs, lower the load peak-to-valley difference and carbon emissions, and boost the comprehensive economic and environmental benefits of the system. Full article

► Show Figures

Figure 1

14 pages, 2370 KiB

Open AccessArticle

AMW-YOLOv8n: Road Scene Object Detection Based on an Improved YOLOv8

by Donghao Wu, Chao Fang, Xiaogang Zheng, Jue Liu, Shengchun Wang and Xinyu Huang

Electronics 2024, 13(20), 4121; https://doi.org/10.3390/electronics13204121 (registering DOI) - 19 Oct 2024

Abstract

This study introduces an improved YOLOv8 model tailored for detecting objects in road scenes. To overcome the limitations of standard convolution operations in adapting to varying targets, we introduce Adaptive Kernel Convolution (AKconv). AKconv dynamically adjusts the convolution kernel’s shape and size, enhancing [...] Read more.

This study introduces an improved YOLOv8 model tailored for detecting objects in road scenes. To overcome the limitations of standard convolution operations in adapting to varying targets, we introduce Adaptive Kernel Convolution (AKconv). AKconv dynamically adjusts the convolution kernel’s shape and size, enhancing the backbone network’s feature extraction capabilities and improving feature representation across different scales. Additionally, we employ a Multi-Scale Dilated Attention (MSDA) mechanism to focus on key target features, further enhancing feature representation. To address the challenge posed by YOLOv8’s large down sampling factor, which limits the learning of small target features in deeper feature maps, we add a small target detection layer. Finally, to improve model training efficiency, we introduce a regression loss function with a Wise-IoU dynamic non-monotonic focusing mechanism. With these enhancements, our improved YOLOv8 model excels in road scene object detection tasks, achieving a 5.6 percentage point improvement in average precision over the original YOLOv8n on real road datasets. Full article

► Show Figures

Figure 1

32 pages, 7028 KiB

Open AccessArticle

Detection of Faulty Energizations in High Voltage Direct Current Power Cables by Analyzing Leakage Currents

by Kumar Mahtani, Ricardo Granizo, José M. Guerrero and Carlos A. Platero

Electronics 2024, 13(20), 4120; https://doi.org/10.3390/electronics13204120 (registering DOI) - 19 Oct 2024

Abstract

The use of multi-terminal high voltage direct current (HVDC) power transmission systems is being adopted in many new links between different generation and consumption areas due to their high efficiency. In these systems, cable energization must be performed at the rated voltage. Healthy [...] Read more.

The use of multi-terminal high voltage direct current (HVDC) power transmission systems is being adopted in many new links between different generation and consumption areas due to their high efficiency. In these systems, cable energization must be performed at the rated voltage. Healthy energizations at the rated voltage result in large inrush currents, especially in long cables, primarily due to ground capacitance. State-of-the-art protection functions struggle to distinguish between transients caused by switching and those associated with ground faults, leading to potential unwanted tripping of the protection systems. To prevent this, tripping is usually blocked during the energization transient, which delays fault detection and clearing. This paper presents a novel method for prompt discrimination between healthy and faulty energizations. The proposed method outperforms conventional protection functions as this discrimination allows for earlier and more reliable tripping, thus avoiding extensive damage to the cable and the converter due to trip blocking. The method is based on the transient analysis of the current in the cable shields, therefore, another technical advantage is that high voltage-insulated measuring devices are not required. Two distinct tripping criteria are proposed: one attending to the change in current polarity, and the other to the change in current derivative sign. Extensive computer simulations and laboratory tests confirmed the correct operation in both cases. Full article

(This article belongs to the Special Issue High-Voltage Technology and Its Applications)

► Show Figures

Figure 1

17 pages, 1484 KiB

Open AccessArticle

Method for Noise Reduction by Averaging the Filtering Results on Circular Displacements Using Wavelet Transform and Local Binary Pattern

by Petrica Ciotirnae, Catalin Dumitrescu, Ionut Cosmin Chiva, Augustin Semenescu, Eduard Cristian Popovici and Diana Dranga

Electronics 2024, 13(20), 4119; https://doi.org/10.3390/electronics13204119 (registering DOI) - 18 Oct 2024

Abstract

Algorithms for noise reduction that use the translation invariant wavelet transform indirectly are spatially selective filtering algorithms in the wavelet domain. These al-gorithms use the undecimated wavelet transform to accurately determine the coeffi-cients corresponding to the contours in the images, these being processed [...] Read more.

Algorithms for noise reduction that use the translation invariant wavelet transform indirectly are spatially selective filtering algorithms in the wavelet domain. These al-gorithms use the undecimated wavelet transform to accurately determine the coeffi-cients corresponding to the contours in the images, these being processed differently from the other wavelet coefficients. The use of the undecimated wavelet transform in image noise reduction applications leads not only to an improvement in terms of Mean Square Error (MSE), but also in terms of the content quality of the processed images. In the case of noise reduction procedures by truncation of wavelet coefficients, artifacts appear, especially in the approximation of singularities, due to some pseudo-Gibbs phenomena. These artifacts, which appear locally, are troublesome in the case of object recognition applications from images acquired in conditions of nonuniform illumina-tion and low contrast. In this work we propose a method of feature extractor based on undecimated wavelet transform (UWT) and local binary pattern (LBP). The results ob-tained on images acquired from drones in adverse conditions show promising results in terms of accuracy. The authors show that the displacement-invariant wavelet transform is an very good method of compression and noise reduction in signals. Full article

11 pages, 2521 KiB

Open AccessArticle

Threshold Voltage Recovery Time Measurement Technique Post V_TH Instability in Normally-Off p-Gate GaN High Electron Mobility Transistors

by Karthick Murukesan and Florin Udrea

Electronics 2024, 13(20), 4118; https://doi.org/10.3390/electronics13204118 (registering DOI) - 18 Oct 2024

Abstract

In this study, we propose a simple measurement technique to quantitatively measure the time taken by threshold voltage of normally-off p-GaN AlGaN/GaN HEMTs to recover from a nominal operational gate stress-induced instability. The proposed technique eliminates the requirement to perform a full transfer [...] Read more.

In this study, we propose a simple measurement technique to quantitatively measure the time taken by threshold voltage of normally-off p-GaN AlGaN/GaN HEMTs to recover from a nominal operational gate stress-induced instability. The proposed technique eliminates the requirement to perform a full transfer characteristic sweep post-stress, thereby eliminating the measurement-induced instability effect, often colluding precise recovery time measurement. The rate of recovery and extracted recovery times hold significance in empirically correlating the location of traps in the p-GaN or AlGaN barrier region causing V_TH instability. The gate of the HEMT is stressed at nominal operational drive voltages 1.5 V, 2 V, and 4 V for various time intervals from 500 μs to 100 s, and the time taken for the drain current to recover to prestress levels measured at near-threshold voltage (~1.1 V_TH) is measured as the threshold voltage recovery time. With increasing gate stress voltages, 2DEG gets trapped at relatively deeper trap energy levels at the AlGaN/GaN interface requiring more emission time during the process of recovery, mandating larger recovery times. At higher stress voltage of 4 V, the Schottky gate leakage current is high enough enabling injected holes to cross the AlGaN barrier and counter-compensate for the deeply trapped 2DEG, requiring relatively the same recovery times as lower stress voltages where the gate leakage is negligibly small. With increasing stress time, the amount of 2DEG trapped increases, requiring more recovery time to de-trap and beyond a certain time, saturation of the trap density occurs causing the recovery time to plateau. Full article

(This article belongs to the Special Issue Research and Application of Wide Band Gap Semiconductors)

► Show Figures

Figure 1

20 pages, 7824 KiB

Open AccessArticle

Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning

by Shaopeng Kang, Hongbin Qiang, Jing Yang, Kailei Liu, Wenbin Qian, Wenpeng Li and Yanfei Pan

Electronics 2024, 13(20), 4117; https://doi.org/10.3390/electronics13204117 (registering DOI) - 18 Oct 2024

Abstract

Laser vision seam tracking enhances robotic welding by enabling external information acquisition, thus improving the overall intelligence of the welding process. However, camera images captured during welding often suffer from distortion due to strong noises, including arcs, splashes, and smoke, which adversely affect [...] Read more.

Laser vision seam tracking enhances robotic welding by enabling external information acquisition, thus improving the overall intelligence of the welding process. However, camera images captured during welding often suffer from distortion due to strong noises, including arcs, splashes, and smoke, which adversely affect the accuracy and robustness of feature point detection. To mitigate these issues, we propose a feature point extraction algorithm tailored for weld images, utilizing an improved Deeplabv3+ semantic segmentation network combined with EfficientDet. By replacing Deeplabv3+’s backbone with MobileNetV2, we enhance prediction efficiency. The DenseASPP structure and attention mechanism are implemented to focus on laser stripe edge extraction, resulting in cleaner laser stripe images and minimizing noise interference. Subsequently, EfficientDet extracts feature point positions from these cleaned images. Experimental results demonstrate that, across four typical weld types, the average feature point extraction error is maintained below 1 pixel, with over 99% of errors falling below 3 pixels, indicating both high detection accuracy and reliability. Full article

(This article belongs to the Special Issue Advanced Machine Learning, Pattern Recognition, and Deep Learning Technologies: Methodologies and Applications)

► Show Figures

Figure 1

14 pages, 9120 KiB

Open AccessArticle

Interpretable Mixture of Experts for Decomposition Network on Server Performance Metrics Forecasting

by Fang Peng, Xin Ji, Le Zhang, Junle Wang, Kui Zhang and Wenjun Wu

Electronics 2024, 13(20), 4116; https://doi.org/10.3390/electronics13204116 (registering DOI) - 18 Oct 2024

Abstract

The accurate forecasting of server performance metrics, such as CPU utilization, memory usage, and network bandwidth, is critical for optimizing resource allocation and ensuring system reliability in large-scale computing environments. In this paper, we introduce the Mixture of Experts for Decomposition Kolmogorov–Arnold Network [...] Read more.

The accurate forecasting of server performance metrics, such as CPU utilization, memory usage, and network bandwidth, is critical for optimizing resource allocation and ensuring system reliability in large-scale computing environments. In this paper, we introduce the Mixture of Experts for Decomposition Kolmogorov–Arnold Network (MOE-KAN), a novel approach designed to improve both the accuracy and interpretability of server performance prediction. The MOE-KAN framework employs a decomposition strategy that breaks down complex, nonlinear server performance patterns into simpler, more interpretable components, facilitating a clearer understanding of how predictions are made. By leveraging a Mixture of Experts (MOE) model, trend and residual components are learned by specialized experts, whose outputs are transparently combined to form the final prediction. The Kolmogorov–Arnold Network further enhances the model’s ability to capture intricate input–output relationships while maintaining transparency in its decision-making process. Experimental results on real-world server performance datasets demonstrate that MOE-KAN not only outperforms traditional models in terms of accuracy but also provides a more trustworthy and interpretable forecasting framework. This makes it particularly suitable for real-time server management and capacity planning, offering both reliability and interpretability in predictive models. Full article

(This article belongs to the Special Issue Trustworthy Deep Learning in Practice)

21 pages, 5545 KiB

Open AccessArticle

ESFuse: Weak Edge Structure Perception Network for Infrared and Visible Image Fusion

by Wuyang Liu, Haishu Tan, Xiaoqi Cheng and Xiaosong Li

Electronics 2024, 13(20), 4115; https://doi.org/10.3390/electronics13204115 (registering DOI) - 18 Oct 2024

Abstract

Infrared and visible image fusion (IVIF) fully integrates the complementary features of different modal images, and the fused image provides a more comprehensive and objective interpretation of the scene compared to each source image, thus attracting extensive attention in the field of computer [...] Read more.

Infrared and visible image fusion (IVIF) fully integrates the complementary features of different modal images, and the fused image provides a more comprehensive and objective interpretation of the scene compared to each source image, thus attracting extensive attention in the field of computer vision in recent years. However, current fusion methods usually center their attention on the extraction of prominent features, falling short of adequately safeguarding subtle and diminutive structures. To address this problem, we propose an end-to-end unsupervised IVIF method (ESFuse), which effectively enhances fine edges and small structures. In particular, we introduce a two-branch head interpreter to extract features from source images of different modalities. Subsequently, these features are fed into the edge refinement module with the detail injection module (DIM) to obtain the edge detection results of the source image, improving the network’s ability to capture and retain complex details as well as global information. Finally, we implemented a multiscale feature reconstruction module to obtain the final fusion results by combining the output of the DIM with the output of the head interpreter. Extensive IVIF fusion experiments on existing publicly available datasets show that the proposed ESFuse outperforms the state-of-the-art(SOTA) methods in both subjective vision and objective evaluation, and our fusion results perform well in semantic segmentation, target detection, pose estimation and depth estimation tasks. The source code has been availabled. Full article

16 pages, 1249 KiB

Open AccessArticle

A Distributed Algorithm for Reaching Average Consensus in Unbalanced Tree Networks

by Gianfranco Parlangeli

Electronics 2024, 13(20), 4114; https://doi.org/10.3390/electronics13204114 (registering DOI) - 18 Oct 2024

Abstract

In this paper, a distributed algorithm for reaching average consensus is proposed for multi-agent systems with tree communication graph, when the edge weight distribution is unbalanced. First, the problem is introduced as a key topic of core algorithms for several modern scenarios. Then, [...] Read more.

In this paper, a distributed algorithm for reaching average consensus is proposed for multi-agent systems with tree communication graph, when the edge weight distribution is unbalanced. First, the problem is introduced as a key topic of core algorithms for several modern scenarios. Then, the relative solution is proposed as a finite-time algorithm, which can be included in any application as a preliminary setup routine, and it is well-suited to be integrated with other adaptive setup routines, thus making the proposed solution useful in several practical applications. A special focus is devoted to the integration of the proposed method with a recent Laplacian eigenvalue allocation algorithm, and the implementation of the overall approach in a wireless sensor network framework. Finally, a worked example is provided, showing the significance of this approach for reaching a more precise average consensus in uncertain scenarios. Full article

(This article belongs to the Special Issue New Insights in Multi-Agent Systems and Intelligent Control)

► Show Figures

Figure 1

12 pages, 621 KiB

Open AccessArticle

Maximum Doppler Shift Identification Using Decision Feedback Channel Estimation

by Yudai Handa, Hiroya Hayakawa, Riku Tanaka, Kosuke Tamura, Jaesang Cha and Chang-Jun Ahn

Electronics 2024, 13(20), 4113; https://doi.org/10.3390/electronics13204113 (registering DOI) - 18 Oct 2024

Abstract

This paper introduces a new method for estimating the maximum Doppler shift using decision feedback channel estimation (DFCE). In highly mobile environments, which are expected to be covered beyond 5G and 6G systems, the relative movement between the transmitter and receiver causes Doppler [...] Read more.

This paper introduces a new method for estimating the maximum Doppler shift using decision feedback channel estimation (DFCE). In highly mobile environments, which are expected to be covered beyond 5G and 6G systems, the relative movement between the transmitter and receiver causes Doppler shifts. This leads to inter-carrier interference (ICI), significantly degrading communication quality. To mitigate this effect, systems that estimate the maximum Doppler shift and adaptively adjust communication parameters have been extensively studied. One of the most promising methods for maximum Doppler shift estimation involves inserting pilot signals at both the beginning and end of the packet. Although this method achieves high estimation accuracy, it introduces significant latency due to the insertion of the pilot signal at the packet’s end. To address this issue, this paper proposes a new method for rapid estimation using DFCE. The proposed approach compensates for faded signals using channel state information obtained from decision feedback. By treating the compensated signal as a reference, the Doppler shift can be accurately estimated without the need for pilot signals at the end of the packet. This method not only maintains high estimation accuracy but also significantly reduces the latency associated with conventional techniques, making it well-suited for the requirements of next-generation communication systems. Full article

(This article belongs to the Special Issue 5G and 6G Wireless Systems: Challenges, Insights, and Opportunities)

► Show Figures

Figure 1

16 pages, 8003 KiB

Open AccessArticle

AffectiVR: A Database for Periocular Identification and Valence and Arousal Evaluation in Virtual Reality

by Chaelin Seok, Yeongje Park, Junho Baek, Hyeji Lim, Jong-hyuk Roh, Youngsam Kim, Soohyung Kim and Eui Chul Lee

Electronics 2024, 13(20), 4112; https://doi.org/10.3390/electronics13204112 - 18 Oct 2024

Abstract

This study introduces AffectiVR, a dataset designed for periocular biometric authentication and emotion evaluation in virtual reality (VR) environments. To maximize immersion in VR environments, interactions must be seamless and natural, with unobtrusive authentication and emotion recognition technologies playing a crucial role. This [...] Read more.

This study introduces AffectiVR, a dataset designed for periocular biometric authentication and emotion evaluation in virtual reality (VR) environments. To maximize immersion in VR environments, interactions must be seamless and natural, with unobtrusive authentication and emotion recognition technologies playing a crucial role. This study proposes a method for user authentication by utilizing periocular images captured by a camera attached to a VR headset. Existing datasets have lacked periocular images acquired in VR environments, limiting their practical application. To address this, periocular images were collected from 100 participants using the HTC Vive Pro and Pupil Labs infrared cameras in a VR environment. Participants also watched seven emotion-inducing videos, and emotional evaluations for each video were conducted. The final dataset comprises 1988 monocular videos and corresponding self-assessment manikin (SAM) evaluations for each experimental video. This study also presents a baseline study to evaluate the performance of biometric authentication using the collected dataset. A deep learning model was used to analyze the performance of biometric authentication based on periocular data collected in a VR environment, confirming the potential for implicit and continuous authentication. The high-resolution periocular images collected in this study provide valuable data not only for user authentication but also for emotion evaluation research. The dataset developed in this study can be used to enhance user immersion in VR environments and as a foundational resource for advancing emotion recognition and authentication technologies in fields such as education, therapy, and entertainment. This dataset offers new research opportunities for non-invasive continuous authentication and emotion recognition in VR environments, and it is expected to significantly contribute to the future development of related technologies. Full article

(This article belongs to the Special Issue Biometric Recognition: Latest Advances and Prospects)

► Show Figures

Figure 1

18 pages, 847 KiB

Open AccessArticle

A Stock Prediction Method Based on Multidimensional and Multilevel Feature Dynamic Fusion

by Yuxin Dong and Yongtao Hao

Electronics 2024, 13(20), 4111; https://doi.org/10.3390/electronics13204111 - 18 Oct 2024

Abstract

Stock price prediction has long been a topic of interest in academia and the financial industry. Numerous factors influence stock prices, such as a company’s performance, industry development, national policies, and other macroeconomic factors. These factors are challenging to quantify, making predicting stock [...] Read more.

Stock price prediction has long been a topic of interest in academia and the financial industry. Numerous factors influence stock prices, such as a company’s performance, industry development, national policies, and other macroeconomic factors. These factors are challenging to quantify, making predicting stock price movements difficult. This paper presents a novel deep neural network framework that leverages the dynamic fusion of multi-dimensional and multi-level features for stock price prediction, which means we utilize fundamental trading data and technical indicators as multi-dimensional data and local and global multi-level information. Firstly, the model dynamically assigns weights to multi-dimensional features of stocks to capture the impact of each feature on stock prices. Next, it applies the Fourier transform to the global features to capture the long-term trends of the global environment and dynamically fuses these with local and global features of the stocks to capture the overall market environment’s impact on individual stocks. Finally, temporal features are captured using an attention layer and an RNN-based model, which incorporates historical price data to forecast future prices. Experiments on stocks from various industries within the Chinese CSI 300 index reveal that the proposed model outperforms traditional methods and other deep learning approaches in terms of stock price prediction. This paper proposes a method that facilitates the dynamic integration of multi-dimensional and multi-level features in an efficient manner and experimental results show that it improves the accuracy of stock price predictions. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

14 pages, 928 KiB

Open AccessArticle

Online Action Detection Incorporating an Additional Action Classifier

by Min-Hang Hsu, Chen-Chien Hsu, Yin-Tien Wang, Shao-Kang Huang and Yi-Hsing Chien

Electronics 2024, 13(20), 4110; https://doi.org/10.3390/electronics13204110 - 18 Oct 2024

Abstract

Most online action detection methods focus on solving a (K + 1) classification problem, where the additional category represents the ‘background’ class. However, training on the ‘background’ class and managing data imbalance are common challenges in online action detection. To address these [...] Read more.

Most online action detection methods focus on solving a (K + 1) classification problem, where the additional category represents the ‘background’ class. However, training on the ‘background’ class and managing data imbalance are common challenges in online action detection. To address these issues, we propose a framework for online action detection by incorporating an additional pathway between the feature extractor and online action detection model. Specifically, we present one configuration that retains feature distinctions for fusion with the final decision from the Long Short-Term Transformer (LSTR), enhancing its performance in the (K + 1) classification. Experimental results show that the proposed method achieves an accuracy of 71.2% in mean Average Precision (mAP) on the Thumos14 dataset, outperforming the 69.5% achieved by the original LSTR method. Full article

(This article belongs to the Special Issue Pattern Recognition and Image Processing: Latest Advances and Prospects)

► Show Figures

Figure 1

23 pages, 493 KiB

Open AccessArticle

Comparison of Large Language Models in Generating Machine Learning Curricula in High Schools

by Gjorgji Noveski, Mathis Jeroncic, Thomas Velard, Primož Kocuvan and Matjaž Gams

Electronics 2024, 13(20), 4109; https://doi.org/10.3390/electronics13204109 - 18 Oct 2024

Abstract

With the rapid advancement of artificial intelligence technologies, the integration of AI concepts into educational curricula represents an increasingly important issue. This paper presents a comparative analysis of four AI large language models, ChatGPT (now GPT-4o), Bard (now Gemini), Copilot, and Auto-GPT, in [...] Read more.

With the rapid advancement of artificial intelligence technologies, the integration of AI concepts into educational curricula represents an increasingly important issue. This paper presents a comparative analysis of four AI large language models, ChatGPT (now GPT-4o), Bard (now Gemini), Copilot, and Auto-GPT, in the last year, progressing from the previous into the newer versions, thus also revealing the progress over time. Tasks were selected from the Valence project, which aims to advance machine learning in high school education with material designed by human experts. The four LLMs were assessed across 13 topics, 35 units, and 12 code segments, focusing on their code generation, definition formulation, and textual task capabilities. The results were analyzed using various metrics to conduct a comprehensive evaluation. Each LLM was allowed up to five attempts to produce outputs closely aligned with human-written materials, with experts providing iterative feedback. This study evaluated the effectiveness and accuracy of these LLMs in educational content creation, offering insights into their potential roles in shaping current and future AI-centric education systems. Full article

► Show Figures

Figure 1

16 pages, 1815 KiB

Open AccessArticle

A Power Control and Intervention Algorithm for Co-Existing IMT Base Stations and Satellite Services

by Min Jia, Shiyao Meng, Hui Wang, Zhouhao Tang and Ziliang Jin

Electronics 2024, 13(20), 4108; https://doi.org/10.3390/electronics13204108 - 18 Oct 2024

Abstract

IMT-2020 (International Mobile Telecommunications-2020) is the prevailing mobile communication technology at the moment, significantly affecting societal progress. Nevertheless, the roll-out of the IMT-2020 system has introduced numerous interferences to existing services. The coexistence with fixed satellite services has become a topical issue currently [...] Read more.

IMT-2020 (International Mobile Telecommunications-2020) is the prevailing mobile communication technology at the moment, significantly affecting societal progress. Nevertheless, the roll-out of the IMT-2020 system has introduced numerous interferences to existing services. The coexistence with fixed satellite services has become a topical issue currently under consideration. This paper discusses the compatibility and interference issues between IMT-2020 and the 14 GHz FSS (fixed-satellite service) uplink, as well as the spectrum access issue solved by artificial intelligence methods. The study shows that the interference from IMT-2020 macro-base stations to FSS space stations exceeds the ITU standard by approximately 10 dB. To control the interference, a partition-based power control algorithm is proposed, which divides ground base stations into multiple areas and virtualizes each area’s base stations into a single large base station then applies power control to maximize the total transmission power of the base stations within the area. Furthermore, three intra-partition power control algorithms are introduced: average power allocation, power allocation based on channel gain, andna power allocation method based on the maximum intra-partition sum rate. Additionally, under the assumption that dynamic satellite nodes are available in the system for ground user access, a spectrum access algorithm utilizing deep reinforcement learning is designed. Simulation results confirm the effectiveness of the proposed scheme, which can reduce the interference from the IMT-2020 system to the FSS service below the threshold, ensuring harmonious coexistence of the two services. Full article

(This article belongs to the Special Issue Satellite Terrestrial Networks: Technologies, Security and Applications)

► Show Figures

Figure 1

16 pages, 2952 KiB

Open AccessArticle

A High-Performance FPGA-Based RoCE v2 RDMA Packet Parser and Generator

by Zezheng Sun, Zhichuan Guo, Jiandong Ma and Yipeng Pan

Electronics 2024, 13(20), 4107; https://doi.org/10.3390/electronics13204107 - 18 Oct 2024

Abstract

RDMA (Remote Direct Memory Access) technology has been widely applied due to its high-throughput and low-latency characteristics compared with traditional networks. Implementing RDMA with an FPGA (Field-Programmable Gate Array) is a feasible solution. This paper proposes an implementation method for the ROCE v2 [...] Read more.

RDMA (Remote Direct Memory Access) technology has been widely applied due to its high-throughput and low-latency characteristics compared with traditional networks. Implementing RDMA with an FPGA (Field-Programmable Gate Array) is a feasible solution. This paper proposes an implementation method for the ROCE v2 (Remote Direct Memory Access) protocol packet parser and generator based on an FPGA, capable of supporting various transaction packet types, such as RDMA READ, RDMA WRITE, and SEND, under the Reliable Connection service. The RDMA READ and RDMA WRITE performance of RDMA is close to 100 Gbps, which provides a feasible solution for the application of wide-area networks. Full article

(This article belongs to the Topic Advanced Integrated Circuit Design and Application)

► Show Figures

Figure 1

19 pages, 4224 KiB

Open AccessArticle

A Rigid–Flexible Supernumerary Robotic Arm/Leg: Design, Modeling, and Control

by Jiajun Xu, Mengcheng Zhao, Tianyi Zhang and Aihong Ji

Electronics 2024, 13(20), 4106; https://doi.org/10.3390/electronics13204106 - 18 Oct 2024

Abstract

As humans’ additional arms or legs, supernumerary robotic limbs (SRLs) have gained great application prospects in many fields. However, current SRLs lack both rigidity/flexibility adaptability and arm/leg function conversion. Inspired by the muscular hydrostat characteristics of octopus tentacles, fiber-reinforced actuators (FRAs) were employed [...] Read more.

As humans’ additional arms or legs, supernumerary robotic limbs (SRLs) have gained great application prospects in many fields. However, current SRLs lack both rigidity/flexibility adaptability and arm/leg function conversion. Inspired by the muscular hydrostat characteristics of octopus tentacles, fiber-reinforced actuators (FRAs) were employed to develop SRLs simultaneously realizing flexible operation and stable support. In this paper, an SRL with FRAs was designed and implemented. The analytic model of the FRA was established to formulate the movement trajectory and stiffness profile of the SRL. A hierarchical hidden Markov model (HHMM) was proposed to recognize the wearer’s motion intention and control the SRL to complete the specific working mode and motion type. Experiments were conducted to exhibit the feasibility and superiority of the proposed robot. Full article

(This article belongs to the Special Issue Advancements in Robotics: Perception, Manipulation, and Interaction)

► Show Figures

Figure 1

16 pages, 5772 KiB

Open AccessArticle

Optimizing Football Formation Analysis via LSTM-Based Event Detection

by Benjamin Orr, Ephraim Pan and Dah-Jye Lee

Electronics 2024, 13(20), 4105; https://doi.org/10.3390/electronics13204105 - 18 Oct 2024

Abstract

The process of manually annotating sports footage is a demanding one. In American football alone, coaches spend thousands of hours reviewing and analyzing videos each season. We aim to automate this process by developing a system that generates comprehensive statistical reports from full-length [...] Read more.

The process of manually annotating sports footage is a demanding one. In American football alone, coaches spend thousands of hours reviewing and analyzing videos each season. We aim to automate this process by developing a system that generates comprehensive statistical reports from full-length football game videos. Having previously demonstrated the proof of concept for our system, here, we present optimizations to our preprocessing techniques along with an inventive method for multi-person event detection in sports videos. Employing a long short-term memory (LSTM)-based architecture to detect the snap in American football, we achieve an outstanding LSI (Levenshtein similarity index) of 0.9445, suggesting a normalized difference of less than 0.06 between predictions and ground truth labels. We also illustrate the utility of snap detection as a means of identifying the offensive players’ assuming of formation. Our results exhibit not only the success of our unique approach and underlying optimizations but also the potential for continued robustness as we pursue the development of our remaining system components. Full article

(This article belongs to the Special Issue Deep Learning for Computer Vision Application)

► Show Figures

Graphical abstract

14 pages, 1578 KiB

Open AccessArticle

A Platform of Federated Learning Management for Enhanced Mobile Collaboration

by Farkhod Yusubov and KangYoon Lee

Electronics 2024, 13(20), 4104; https://doi.org/10.3390/electronics13204104 - 18 Oct 2024

Abstract

Federated learning (FL) has emerged as a crucial technology in today’s data-centric environment, enabling decentralized machine learning while safeguarding user privacy. This study introduces “Federated Learning ML Operations (FedOps) Mobile”, a novel FL framework optimized for the dynamic and heterogeneous ecosystem of mobile [...] Read more.

Federated learning (FL) has emerged as a crucial technology in today’s data-centric environment, enabling decentralized machine learning while safeguarding user privacy. This study introduces “Federated Learning ML Operations (FedOps) Mobile”, a novel FL framework optimized for the dynamic and heterogeneous ecosystem of mobile devices. FedOps Mobile addresses the inherent challenges of FL—such as system scalability, device heterogeneity, and operational efficiency—through advanced on-device training using TensorFlow Lite and CoreML. The framework’s innovative approach includes sophisticated client selection mechanisms that assess device readiness and capabilities, ensuring equitable and efficient participation across the network. Additionally, FedOps Mobile leverages remote device control for seamless task management and continuous learning, all without compromising the user experience. The main contribution of this study is the demonstration that federated learning across heterogeneous devices, especially those using different operating systems, can be both practical and efficient using the FedOps Mobile framework. This was validated through experiments that evaluated three key areas: operational efficiency, model personalization, and resource optimization in multi-device settings. The results showed that the proposed method excels in client selection, energy consumption, and model optimization, establishing a new benchmark for federated learning in diverse and complex environments. Full article

(This article belongs to the Special Issue Challenges and Opportunities Presented by Federated Learning in Mobile Computing)

► Show Figures

Figure 1

Journal Description

Electronics

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI