Electronics

12 pages, 2532 KiB

Open AccessArticle

Application of Deep Dilated Convolutional Neural Network for Non-Flat Rough Surface

by Chien-Ching Chiu, Yang-Han Lee, Wei Chien, Po-Hsiang Chen and Eng Hock Lim

Electronics 2025, 14(6), 1236; https://doi.org/10.3390/electronics14061236 - 20 Mar 2025

Viewed by 235

In this paper, we propose a novel deep dilated convolutional neural network (DDCNN) architecture to reconstruct periodic rough surfaces, including their periodic length, dielectric constant, and shape. Historically, rough surface problems were addressed through optimization algorithms. However, these algorithms are computationally intensive, making [...] Read more.

In this paper, we propose a novel deep dilated convolutional neural network (DDCNN) architecture to reconstruct periodic rough surfaces, including their periodic length, dielectric constant, and shape. Historically, rough surface problems were addressed through optimization algorithms. However, these algorithms are computationally intensive, making the process very time-consuming. To resolve this issue, we provide measured scattered fields as training data for the DDCNN to reconstruct the periodic length, dielectric constant, and shape. The numerical results demonstrate that DDCNN can accurately reconstruct rough surface images under high noise levels. In addition, we also discuss the impacts of the periodic length and dielectric constant of the rough surface on the shape reconstruction. Notably, our method achieves excellent reconstruction results compared to DCNN even when the period and dielectric coefficient are unknown. Finally, it is worth mentioning that the trained network model completes the reconstruction process in less than one second, realizing efficient real-time imaging. Full article

(This article belongs to the Special Issue Advanced Machine Learning Technologies and Their Applications in Intelligent Imaging and Image Processing)

► Show Figures

Figure 1

22 pages, 819 KiB

Open AccessArticle

Detection-Aided Ordering for LMMSE-ISIC in MIMO Systems

by Sangjoon Park

Electronics 2025, 14(6), 1235; https://doi.org/10.3390/electronics14061235 - 20 Mar 2025

Viewed by 156

Abstract

In this paper, the detection-aided ordering schemes are proposed for linear minimum mean-squared-error (LMMSE) iterative soft interference cancellation (ISIC) in multiple-input multiple-output (MIMO) systems. Unlike the conventional LMMSE-ISIC ordering schemes that utilize the channel state information (CSI) only, the proposed ordering schemes utilize [...] Read more.

In this paper, the detection-aided ordering schemes are proposed for linear minimum mean-squared-error (LMMSE) iterative soft interference cancellation (ISIC) in multiple-input multiple-output (MIMO) systems. Unlike the conventional LMMSE-ISIC ordering schemes that utilize the channel state information (CSI) only, the proposed ordering schemes utilize the receive signal vector and CSI for the ordering procedure. Then, for each candidate symbol, the sum of the likelihoods except the largest likelihood is calculated to estimate the reliability of the candidate symbol, where the likelihoods are calculated by the LMMSE or LMMSE-ISIC detection-aided ordering procedure. Thus, the proposed ordering schemes can provide a significantly more accurate ordering result than the conventional ordering schemes. As the detection-aided ordering schemes, non-iterative and iterative ordering schemes are proposed, and the constrained iterative ordering scheme is also proposed to resolve the high computational complexity of the original iterative ordering scheme. Numerical simulation results verify that the proposed detection-aided ordering schemes outperform the conventional ordering schemes in terms of convergence speed and error performance. Full article

(This article belongs to the Special Issue Advancements in Signal Processing: Communications, Sensing and Imaging)

► Show Figures

Figure 1

21 pages, 2465 KiB

Open AccessArticle

DE-CLIP: Unsupervised Dense Counting Method Based on Multimodal Deep Sharing Prompts and Cross-Modal Alignment Ranking

by Xuebin Zi and Chunlei Wu

Electronics 2025, 14(6), 1234; https://doi.org/10.3390/electronics14061234 - 20 Mar 2025

Viewed by 176

Abstract

With the rapid development of multimodal prompt learning in unsupervised domains, prompt tuning has demonstrated significant potential for dense counting tasks. However, existing supervised methods heavily rely on annotated data, limiting their generalization capabilities. Additionally, unimodal prompt designs fail to fully leverage the [...] Read more.

With the rapid development of multimodal prompt learning in unsupervised domains, prompt tuning has demonstrated significant potential for dense counting tasks. However, existing supervised methods heavily rely on annotated data, limiting their generalization capabilities. Additionally, unimodal prompt designs fail to fully leverage the complementary advantages of multimodal data, compromising the accuracy and robustness of counting systems. To address these challenges, we propose DE-CLIP, an unsupervised dense counting method based on multimodal deep shared prompts and cross-modal alignment ranking. DE-CLIP constructs hierarchically ordered textual prompts and optimizes the image encoder via cross-modal alignment ranking loss, which enforces rank-aware embedding learning by aligning visual patches with incrementally scaled textual descriptions, thereby enhancing the model’s numerical perception. The text encoder recursively injects visual information across transformer layers, achieving the progressive fusion of textual and visual prompts to improve multimodal representation. Simultaneously, the image encoder interacts deeply with textual prompts at each transformer layer, strengthening the synergy between visual features and textual semantics. A multimodal collaborative fusion module further enables bidirectional interaction between modalities via self-attention and cross-attention mechanisms, enhancing the model’s capability to comprehend and process complex scenes. The experimental results demonstrate that DE-CLIP significantly outperforms the existing supervised and unsupervised methods across multiple dense counting benchmarks, achieving superior recognition accuracy and generalization ability. This validates its exceptional performance and broad applicability in unsupervised settings. Full article

► Show Figures

Figure 1

17 pages, 3964 KiB

Open AccessArticle

A Methodology for Efficient Antenna Deployment in Distributed Massive Multiple-Input Multiple-Output Systems

by Jesús R. Pérez, Rafael P. Torres, Luis Valle, Lorenzo Rubio, Vicent M. Rodrigo-Peñarrocha and Juan Reig

Electronics 2025, 14(6), 1233; https://doi.org/10.3390/electronics14061233 - 20 Mar 2025

Viewed by 138

Abstract

This paper, taking as reference channel data previously obtained by using a rigorous and well-tested ray-tracing method for a concentrated massive multiple-input multiple-output (mMIMO) system, focuses on the optimization of the set of potential antennas required in a distributed mMIMO system to achieve [...] Read more.

This paper, taking as reference channel data previously obtained by using a rigorous and well-tested ray-tracing method for a concentrated massive multiple-input multiple-output (mMIMO) system, focuses on the optimization of the set of potential antennas required in a distributed mMIMO system to achieve the same channel spectral efficiency as the concentrated system. Concerning the optimizer, a binary particle swarm optimization algorithm was considered to decide whether to activate or deactivate any of the antennas within the original mesh, taking into account, in order to direct the search, the total spectral efficiency, the equality between the spectral efficiency of users, and the number of receiver antennas at the distributed base station. The analysis was carried out in a large indoor environment at the 5G n258 frequency band (26 GHz), concentrating on the up-link and considering a set of 20 uniformly distributed active users. The results obtained show that, in the distributed mMIMO system, an arrangement with fewer than half the number of receiver antennas of the initial mesh is required to achieve a similar performance to that of the concentrated one taken as a reference. Full article

(This article belongs to the Collection MIMO Antennas)

► Show Figures

Figure 1

27 pages, 3412 KiB

Open AccessArticle

Efficient Clustering Method for Graph Images Using Two-Stage Clustering Technique

by Hyuk-Gyu Park, Kwang-Seong Shin and Jong-Chan Kim

Electronics 2025, 14(6), 1232; https://doi.org/10.3390/electronics14061232 - 20 Mar 2025

Viewed by 206

Abstract

Graphimages, which represent data structures through nodes and edges, present significant challenges for clustering due to their intricate topological properties. Traditional clustering algorithms, such as K-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), often struggle to effectively capture both spatial and [...] Read more.

Graphimages, which represent data structures through nodes and edges, present significant challenges for clustering due to their intricate topological properties. Traditional clustering algorithms, such as K-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), often struggle to effectively capture both spatial and structural relationships within graph images. To overcome these limitations, we propose a novel two-stage clustering approach that integrates conventional clustering techniques with graph-based methodologies to enhance both accuracy and efficiency. In the first stage, a distance- or density-based clustering algorithm (e.g., K-means or DBSCAN) is applied to generate initial cluster formations. In the second stage, these clusters are refined using spectral clustering or community detection techniques to better preserve and exploit topological features. We evaluate our approach using a dataset of 8118 graph images derived from depth measurements taken at various angles. The experimental results demonstrate that our method surpasses single-method clustering approaches in terms of the silhouette score, Calinski-Harabasz index (CHI), and modularity. The silhouette score measures how similar an object is to its own cluster compared to other clusters, while the CHI, also known as the Variance Ratio Criterion, evaluates cluster quality based on the ratio of between-cluster dispersion to within-cluster dispersion. Modularity, a metric commonly used in graph-based clustering, assesses the strength of division of a network into communities. Furthermore, qualitative analysis through visualization confirms that the proposed two-stage clustering approach more effectively differentiates structural similarities within graph images. These findings underscore the potential of hybrid clustering techniques for various applications, including three-dimensional (3D) measurement analysis, medical imaging, and social network analysis. Full article

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

► Show Figures

Figure 1

18 pages, 84247 KiB

Open AccessArticle

A Terrain Classification Method for Quadruped Robots with Proprioception

by Yinglong Zhang, Baoru Huang, Meng Hong, Chao Huang, Guan Wang and Min Guo

Electronics 2025, 14(6), 1231; https://doi.org/10.3390/electronics14061231 - 20 Mar 2025

Viewed by 265

Abstract

Acquiring terrain information during robot locomotion is essential for autonomous navigation, gait selection, and trajectory planning. Quadruped robots, due to their biomimetic structures, demonstrate enhanced traversability over complex terrains compared to other robotic platforms. Furthermore, the internal sensors of quadruped robots acquire rich [...] Read more.

Acquiring terrain information during robot locomotion is essential for autonomous navigation, gait selection, and trajectory planning. Quadruped robots, due to their biomimetic structures, demonstrate enhanced traversability over complex terrains compared to other robotic platforms. Furthermore, the internal sensors of quadruped robots acquire rich terrain-related data during locomotion across diverse terrains. This study investigates the relationship between terrain characteristics and quadruped robots based on proprioception sensor data, and proposes a simple, efficient, and motion-independent terrain classification method by integrating multiple sensor signals. The sensors referred to in the text only include the IMU sensor and joint encoders, which means that the method has a wide range of applicability while requiring sufficiently low hardware cost. The Convolutional Neural Network will serve as the backbone of the algorithm. In addition, the control command about its own control information will serve as supporting information to eliminate the impact of motion patterns on the results. Employing a multi-label classification algorithm, the complex terrains are classified by multiple physical feature labels like roughness, slippage, softness, and slope, which depict terrain attributes. A feature-labeled terrain dataset is established by abstracting diverse terrain features across various terrains. Unlike semantic labels (e.g., grassland, sand, gravel) that are comprehensible only to humans, feature labels provide a more helpful and precise terrain characterization, including broader terrain attributes. Full article

► Show Figures

Figure 1

26 pages, 1411 KiB

Open AccessArticle

Trandroid: An Android Mobile Threat Detection System Using Transformer Neural Networks

by Thabet Kacem and Sourou Tossou

Electronics 2025, 14(6), 1230; https://doi.org/10.3390/electronics14061230 - 20 Mar 2025

Viewed by 339

Abstract

In recent years, Android malware have been evolving and becoming more sophisticated at an alarming rate, highlighting the need for robust and evolving detection schemes. Despite the popularity of artificial intelligence-based approaches, they still struggle to generalize for various reasons. For instance, due [...] Read more.

In recent years, Android malware have been evolving and becoming more sophisticated at an alarming rate, highlighting the need for robust and evolving detection schemes. Despite the popularity of artificial intelligence-based approaches, they still struggle to generalize for various reasons. For instance, due to the reliance on handcrafted features for the machine learning approaches and the dependence on static datasets for the case of deep learning. In this paper, we bridge this gap by proposing Trandroid, an approach to detect diverse and real-world attack patterns targeting Android using transformers. This approach represents a major extension of our previous research to tackle this problem by developing a transformer-based Android attack detection system using the TUANDROMD dataset. Our choice of TUANDROMD was motivated by its wide coverage of Android attacks, support for metadata, and usage of feature extraction that makes it a good choice to build a holistic threat detection for Android using advanced AI models. We achieved a high accuracy rate of 99.25% with our state-of-the-art transformer model compared to the other classifiers we developed for comparison purposes, including Recurrent Neural Networks (RNNs), the Gated Recurrent Units (GRUs), Convolutional Neural Networks (CNNs), Long-Term Short-Term Memory (LSTM), and the hybrid CNN-LSTM model. Our Trandroid model also outperforms other approaches in the literature, considering all the performance indicators we used. These findings indicate the effectiveness of transformers in dealing with the evolving nature of Android malware and their promising potential for real-world deployment in mobile platforms. Full article

► Show Figures

Figure 1

29 pages, 1297 KiB

Open AccessArticle

Performance Modeling of Distributed Ledger-Based Authentication in Cyber–Physical Systems Using Colored Petri Nets

by Michał Jarosz, Konrad Wrona and Zbigniew Zieliński

Electronics 2025, 14(6), 1229; https://doi.org/10.3390/electronics14061229 - 20 Mar 2025

Viewed by 199

Abstract

Federated cyber–physical systems (CPSs) present unique security challenges due to their distributed nature and the need for secure communication between components from different administrative domains. Distributed ledger technology (DLT) offers a promising approach to implementing a resilient authentication and authorization mechanism and an [...] Read more.

Federated cyber–physical systems (CPSs) present unique security challenges due to their distributed nature and the need for secure communication between components from different administrative domains. Distributed ledger technology (DLT) offers a promising approach to implementing a resilient authentication and authorization mechanism and an immutable record of CPS identities and transactions in federated environments. However, using Distributed Ledger (DL) within a CPS raises some important questions regarding scalability, throughput, latency, and potential bottlenecks, which require effective modeling of DL performance. This paper proposes a novel approach to modeling distributed ledgers using Colored Timed Petri Nets (CPNs). We focus on the performance modeling of Hyperledger Fabric (HLF), a permissioned distributed ledger technology which provides a backbone for a Lightweight Authentication and Authorization Framework for Federated IoT (LAAFFI), a novel framework for secure communication between CPS devices. We implement our model using CPN Tools, a widely adopted CPN modeling software that provides advanced simulation, analysis, and performance monitoring features. Our model offers a robust framework for studying distributed ledger systems’ synchronization, throughput, and response time. It supports flexibility in modeling transaction validation and consensus algorithms, which provides an opportunity for adapting the model to future changes in HLF and modeling other DLs. We successfully validate our CPN model by comparing simulation results with experimental measurements obtained from a LAAFFI prototype. Full article

(This article belongs to the Special Issue Securing the Future: Challenges and Prospects in Emerging Cyber‒Physical Systems)

► Show Figures

Figure 1

12 pages, 4873 KiB

Open AccessArticle

Dual-Polarized Antenna with 2D Beam Steering Using Reconfigurable Double Square Loops

by Yuanming Cai, Guibin Zhang, Leyan Pan, Zhipeng Liu, Yuchen Luan, Feng Liu and Jiayin Guo

Electronics 2025, 14(6), 1228; https://doi.org/10.3390/electronics14061228 - 20 Mar 2025

Viewed by 235

Abstract

A novel dual-polarized 2D beam-steering antenna is proposed based on the reconfigurable double square loops (RDSLs). The antenna is composed of stacked patches with two ports and a beam-steering surface consisting of a 2 × 2 array of RDSLs. Varactor diodes are integrated [...] Read more.

A novel dual-polarized 2D beam-steering antenna is proposed based on the reconfigurable double square loops (RDSLs). The antenna is composed of stacked patches with two ports and a beam-steering surface consisting of a 2 × 2 array of RDSLs. Varactor diodes are integrated on the inner square loop of the RDSL. The steerable radiation beam of the antenna can be continuously controlled by tuning four biasing voltages applied on the beam-steering surface for both polarizations. The experimental results show that the scanning ranges are up to ±32° for both ports in two principal planes. The proposed antenna has an average gain of 7.87 dBi with a fluctuation of less than 0.5 dB during 2D beam scanning. The cross-polarization is less than −20 dB, and the isolation between the two ports is greater than 20 dB. The proposed antenna has scannable beams for dual polarizations, stable gains, compact size, and a simple structure, which makes it a good candidate for wireless communication systems. Full article

► Show Figures

Figure 1

25 pages, 7385 KiB

Open AccessArticle

Integrated Waveform Design and Signal Processing Based on Composite Noise Nimble Modulated Signals

by Xinquan Cao, Shiyuan Zhang, Ke Tan, Xingyu Lu, Jianchao Yang, Zheng Dai and Hong Gu

Electronics 2025, 14(6), 1227; https://doi.org/10.3390/electronics14061227 - 20 Mar 2025

Viewed by 161

Abstract

In modern radar operations, detection and jamming systems play a critical role. Integrated detection and jamming systems simultaneously fulfill both functions, thereby optimizing resource utilization. In this paper, we introduce a novel random noise frequency modulation nimble modulation integrated signal (RNFM-NMIS) that is [...] Read more.

In modern radar operations, detection and jamming systems play a critical role. Integrated detection and jamming systems simultaneously fulfill both functions, thereby optimizing resource utilization. In this paper, we introduce a novel random noise frequency modulation nimble modulation integrated signal (RNFM-NMIS) that is designed based on reconnaissance analysis of adversary linear frequency modulated (LFM) radar signal parameters. This waveform facilitates flexible adjustment of parameters, enabling adaptive detection and jamming functions. Furthermore, to address the challenge of direct-wave interference from adversary transmissions, we propose a signal processing method based on time-domain pre-cancellation (TDPC). Simulation and experimental results show that the proposed integrated waveform exhibits excellent and adjustable detection and jamming capabilities. Under the proposed processing method, interference suppression and target detection performance are significantly enhanced, achieving substantial improvements over traditional methods. Full article

(This article belongs to the Topic Innovations in AI and Signal Processing for Advanced Sensing, Radar, RFID, and Communication Systems)

► Show Figures

Figure 1

39 pages, 4693 KiB

Open AccessArticle

Exploring the Impact of Digital Transformation on Non-Financial Performance in Central and Eastern European Countries

by Alexandru Buglea, Irina Daniela Cișmașu, Delia Anca Gabriela Gligor and Cecilia Nicoleta Jurcuț

Electronics 2025, 14(6), 1226; https://doi.org/10.3390/electronics14061226 - 20 Mar 2025

Viewed by 313

Abstract

This article explores the intricate relationship between digital transformation and non-financial performance in Central and Eastern European (CEE) countries. As these nations navigate the complexities of post-communist economic landscapes, the role of digitalization emerges as a pivotal factor influencing various dimensions of organizational [...] Read more.

This article explores the intricate relationship between digital transformation and non-financial performance in Central and Eastern European (CEE) countries. As these nations navigate the complexities of post-communist economic landscapes, the role of digitalization emerges as a pivotal factor influencing various dimensions of organizational performance beyond mere financial outcomes. In this framework, our research aims to analyze the ways in which digital transformation (as proxied by DESI) impacts a range of non-financial performance metrics (ESG) in order to furnish a thorough comprehension of the intricate interplay within the specific context of CEE countries. With data collected over an 11-year timeframe, we performed a panel data analysis, relying on a robust regression. The main findings indicate that digital transformation profoundly impacts the environmental (CO₂ emissions, renewable energy consumption), social (ratio of female-to-male labor force participation rate, unemployment) and governance (government effectiveness) performance of CEE countries, although the effects vary significantly across different regions. The panel data highlight potential areas for policy emphasis, particularly in relation to reducing CO₂ emissions, improving regulatory quality, and advancing digital integration and connectivity. The disparities identified may inform targeted strategies aimed at uplifting underperforming regions, thereby contributing to enhanced economic growth and sustainability. Full article

(This article belongs to the Special Issue The Role of Digital Technologies in Sustainability Accounting and Reporting)

► Show Figures

Figure 1

26 pages, 15361 KiB

Open AccessArticle

DPCSANet: Dual-Path Convolutional Self-Attention for Small Ship Detection in Optical Remote Sensing Images

by Jiajie Chen, Xin Tian and Chong Du

Electronics 2025, 14(6), 1225; https://doi.org/10.3390/electronics14061225 - 20 Mar 2025

Viewed by 163

Abstract

Detecting small ships in optical RSIS is challenging. Due to resolution limitations, the texture and edge information of many ship targets are blurred, making feature extraction difficult and thereby reducing detection accuracy. To address this issue, we propose a novel dual-path convolutional self-attention [...] Read more.

Detecting small ships in optical RSIS is challenging. Due to resolution limitations, the texture and edge information of many ship targets are blurred, making feature extraction difficult and thereby reducing detection accuracy. To address this issue, we propose a novel dual-path convolutional self-attention network, DPCSANet, for ship detection. The model first incorporates a dual-path convolutional self-attention module to enhance its ability to extract local and global features and strengthen target features. This module integrates two parallel branches to process features extracted by convolution and attention mechanisms, respectively, thereby mitigating the potential conflicts between local and global information. Additionally, a high-dimensional hybrid spatial pyramid pooling module is introduced into the model to expand the scale range of feature extraction. This enables the model to fully utilize background contextual features to compensate for weak feature representations of the target. To further improve the detection accuracy for small ships, we developed a focal complete intersection over union loss function. This regression loss guides the model to focus on weak targets during training by increasing the contribution of low-accuracy prediction boxes to the loss. Experimental results demonstrate that the proposed method effectively enhances the model’s detection ability for small ships. On the LEVIR-ship, OSSD, and DOTA-ship datasets, DPCANet achieves an average precision improvement of 0.9% to 11.4% over the baseline, outperforming other state-of-the-art object detection models. Full article

► Show Figures

Figure 1

11 pages, 6274 KiB

Open AccessArticle

A Low-Cost, Wide-Band, High-Gain Mechanically Reconfigurable Multi-Polarization Antenna Based on a 3-D Printed Polarizer

by Wenjie Ding, Guoda Xie, Yang Hong, Hang Yu, Chao Wang, Siliang Wang and Zhixiang Huang

Electronics 2025, 14(6), 1224; https://doi.org/10.3390/electronics14061224 - 20 Mar 2025

Viewed by 159

Abstract

This paper proposes a mechanically reconfigurable multi-polarization antenna based on a 3D-printed anisotropic dielectric polarizer, offering wide bandwidth, high gain, and extremely low cost. The working mechanism of the dielectric polarizer is analyzed, demonstrating its ability to efficiently convert linear polarization (LP) to [...] Read more.

This paper proposes a mechanically reconfigurable multi-polarization antenna based on a 3D-printed anisotropic dielectric polarizer, offering wide bandwidth, high gain, and extremely low cost. The working mechanism of the dielectric polarizer is analyzed, demonstrating its ability to efficiently convert linear polarization (LP) to circular polarization (CP) over a wide frequency range. Furthermore, the polarizer exhibits subwavelength characteristics. For a given duty cycle, its phase response depends only on the height and is independent of the aperture size. This property enables miniaturized and customized designs of the polarizer’s aperture size. Subsequently, the polarizer is placed above a Ku band waveguide and standard horn antennas. The results show that by rotating the dielectric polarizer and adjusting the positions of the antennas, right-handed CP (RHCP), left-handed CP (LHCP), and dual LP radiation switching can be achieved in the 12.4–18.0 GHz band, verifying the quad-polarization reconfigurability. Additionally, the polarizer significantly enhances the gain of the waveguide antenna by approximately 9.5 dB. Furthermore, due to the low-cost 3D printing material, the manufacturing cost of the polarizer is exceptionally low, making it suitable for applications such as anechoic chamber measurements and wireless communications. Finally, the measurement results further validate the accuracy of the simulations. Full article

► Show Figures

Figure 1

16 pages, 5213 KiB

Open AccessArticle

Real-Time Temperature Prediction for Large-Scale Multi-Core Chips Based on Graph Convolutional Neural Networks

by Dengbao Miao, Gaoxiang Duan, Danyan Chen, Yongyin Zhu and Xiaoying Zheng

Electronics 2025, 14(6), 1223; https://doi.org/10.3390/electronics14061223 - 20 Mar 2025

Viewed by 202

Abstract

The real-time temperature prediction of chips is a critical issue in the semiconductor field. As chip designs evolve towards 3D and high integration, traditional analytical methods such as finite element software and HotSpot face bottlenecks such as high difficulty in modeling, costly computation, [...] Read more.

The real-time temperature prediction of chips is a critical issue in the semiconductor field. As chip designs evolve towards 3D and high integration, traditional analytical methods such as finite element software and HotSpot face bottlenecks such as high difficulty in modeling, costly computation, and slow inference speeds when dealing with large-scale, multi-hotspot chip thermal analysis. To address these challenges, this paper proposes a real-time temperature prediction model for multi-core chips based on Graph Convolutional Neural Networks (GCNs) that includes the following specific steps: First, the multi-core chip and its temperature power information are represented by a graph according to the physical pattern of heat transfer; Second, three strategies—full connection, setting a truncation radius, and clustering—are proposed to construct the adjacency matrix of the graph, thus supporting the model to balance between computational complexity and accuracy; Third, the GCN model is improved by assigning learnable weights to the adjacency matrix, thereby enhancing its representational power for the temperature distribution of multiple cores. Experimental results show that, under different node numbers and distributions, our proposed method can control the Mean Squared Error (MSE) error of temperature prediction within 0.5, while the single inference time is within 2 ms, which is at least an order of magnitude faster than traditional methods such as HotSpot, meeting the requirements for real-time prediction. Full article

► Show Figures

Figure 1

27 pages, 7966 KiB

Open AccessArticle

An Effective Path Planning Method Based on VDWF-MOIA for Multi-Robot Patrolling in Expo Parks

by Tianyi Guo, Li Huang and Hua Han

Electronics 2025, 14(6), 1222; https://doi.org/10.3390/electronics14061222 - 20 Mar 2025

Viewed by 194

Abstract

Expo parks are characterized by dense crowds and a high risk of accidents. A multi-robot patrolling system equipped with multiple sensors can provide personalized services to visitors and quickly locate emergencies, effectively accelerating response times. This study focuses on developing efficient patrolling strategies [...] Read more.

Expo parks are characterized by dense crowds and a high risk of accidents. A multi-robot patrolling system equipped with multiple sensors can provide personalized services to visitors and quickly locate emergencies, effectively accelerating response times. This study focuses on developing efficient patrolling strategies for multi-robot systems. In expo parks, this requires solving the multiple traveling salesman problem (MTSP) and addressing multi-robot obstacle avoidance in static environments. The main challenge is to plan paths and allocate tasks effectively while avoiding collisions and balancing workloads. Traditional methods often struggle to optimize task allocation and path planning at the same time. This can lead to an unbalanced distribution of patrol tasks. Some robots may have too much workload, while others are not fully utilized. In addition, poor path planning may increase the total patrol length and reduce overall efficiency. It can also affect the coordination of the multi-robot system, limiting its scalability and applicability. To solve these problems, this paper proposes a multi-objective immune optimization algorithm based on the Van der Waals force mechanism (VDWF-MOIA). It introduces an innovative double-antibody coding scheme that adapts well to environments with obstacles, making it easier to represent solutions more diversely. The algorithm has two levels. At the lower level, the path cost matrix based on vector rotation-angle-based obstacle avoidance (PCM-VRAOA) calculates path costs and detour nodes. It effectively reduces the total patrol path length and identifies optimal obstacle avoidance paths, facilitating collaborative optimization with subsequent task allocation. At the higher level, a crossover operator inspired by the Van der Waals force mechanism enhances solution diversity and convergence by enabling effective crossover between antibody segments, resulting in more effective offspring. The proposed algorithm improves performance by enhancing solution diversity, speeding up convergence, and reducing computational costs. Compared to other algorithms, experiments on test datasets in a static environment show that the VDWF-MOIA performs better in terms of total patrol path length, load balancing metrics, and the hypervolume (HV) indicator. Full article

► Show Figures

Figure 1

16 pages, 4162 KiB

Open AccessArticle

Dynamic Energy Cascading Model for Stock Price Prediction in Enterprise Association Networks

by Peijie Zhang, Saike He, Jun Luo, Yi Yang, Qiaoqiao Yuan, Yuqi Huang, Yichun Peng and Daniel Dajun Zeng

Electronics 2025, 14(6), 1221; https://doi.org/10.3390/electronics14061221 - 20 Mar 2025

Viewed by 178

Abstract

Enterprise performance in real-world markets is shaped by dynamic factors, including competitors, collaborators, and hidden associates. Existing models struggle to capture the interplay between time-varying network dynamics and financial asset price movements. Traditional energy cascading models rely on static network assumptions, while deep [...] Read more.

Enterprise performance in real-world markets is shaped by dynamic factors, including competitors, collaborators, and hidden associates. Existing models struggle to capture the interplay between time-varying network dynamics and financial asset price movements. Traditional energy cascading models rely on static network assumptions, while deep learning approaches lack the incorporation of key network science principles such as structural balance and assortativity degree. To address these gaps, we propose the Dynamic Energy Cascading Model (DECM), a framework that models the propagation of business influence within dynamic enterprise networks. This method first constructs a dynamic enterprise association network, then applies an energy cascading mechanism to this network, utilizing the propagated energy metrics as predictive indicators for stock price forecasting. Unlike existing approaches, DECM uniquely integrates dynamic network properties and knowledge structures, such as structural balance and assortativity degree, to model the cascading effects of business influences on stock prices. Through extensive evaluations using data from S&P 500 companies, we demonstrate that DECM significantly outperforms conventional models in predictive precision. A key innovation of our work lies in identifying the critical role of assortativity degree in predicting stock price movements, which surpasses the impact of structural balance. These findings not only advance the theoretical understanding of enterprise performance dynamics but also provide actionable insights for policymakers and practitioners from a network science perspective. Full article

(This article belongs to the Section Computer Science & Engineering)

► Show Figures

Figure 1

24 pages, 343 KiB

Open AccessArticle

An Automated Framework for Prioritizing Software Requirements

by Behnaz Jamasb, Seyed Raouf Khayami, Reza Akbari and Rahim Taheri

Electronics 2025, 14(6), 1220; https://doi.org/10.3390/electronics14061220 - 20 Mar 2025

Viewed by 213

Abstract

Requirement Engineering (RE) is a critical phase in software development, integral to the successful execution of projects. The initial stage of RE involves requirement elicitation and analysis, where the prioritization of requirements is critical. Traditional methods of requirement prioritization (RP) are diverse, each [...] Read more.

Requirement Engineering (RE) is a critical phase in software development, integral to the successful execution of projects. The initial stage of RE involves requirement elicitation and analysis, where the prioritization of requirements is critical. Traditional methods of requirement prioritization (RP) are diverse, each presenting unique challenges. In response to the challenges of traditional methods, this paper proposes an entirely automated framework designed to eliminate the disadvantages associated with excessive stakeholder involvement. This innovative framework processes raw natural language inputs directly, applying a three-phase approach to systematically assign priority numbers to each requirement. The first phase preprocesses the input to standardize and prepare the data, the second phase employs advanced machine learning algorithms to analyze and rank the requirements, and the third phase consolidates the results to produce a final prioritized list. The effectiveness of this method was tested using the RALIC (Replacement Access, Library, and ID Card) dataset, a well-known benchmark in the field of requirement engineering. The results confirm that our automated approach not only enhances the efficiency and objectivity of the prioritization process but also scales effectively across diverse and extensive sets of requirements. This framework represents a significant advancement in the field of software development, offering a robust alternative to traditional, subjective methods of requirement prioritization. Full article

(This article belongs to the Special Issue Software Engineering: Status and Perspectives)

► Show Figures

Graphical abstract

20 pages, 7771 KiB

Open AccessArticle

A Novel Fault Diagnosis and Accurate Localization Method for a Power System Based on GraphSAGE Algorithm

by Fang Wang and Zhijian Hu

Electronics 2025, 14(6), 1219; https://doi.org/10.3390/electronics14061219 - 20 Mar 2025

Viewed by 182

Abstract

Artificial intelligence (AI)-based fault diagnosis methods have been widely studied for power grids, with most research focusing on fault interval localization rather than precise fault point identification. In cases involving long-distance transmission lines or underground cables, merely locating the fault interval is insufficient. [...] Read more.

Artificial intelligence (AI)-based fault diagnosis methods have been widely studied for power grids, with most research focusing on fault interval localization rather than precise fault point identification. In cases involving long-distance transmission lines or underground cables, merely locating the fault interval is insufficient. This paper presents a novel fault diagnosis and precise localization method for power systems utilizing the Graph Sample and Aggregated (GraphSAGE) algorithm. A fault diagnosis and interval localization model are developed based on the system topology, identifying k-order adjacent nodes at both ends of the fault interval. This information is then used to construct an accurate fault point localization model. Leveraging the strong inductive learning capability of GraphSAGE, the proposed method effectively captures the impact of the fault point on surrounding nodes, enabling precise fault point localization. Experimental results demonstrate that the proposed method offers high fault diagnosis accuracy, precise localization, and robust performance. The model shows significant applicability in real-world fault scenarios, maintaining strong performance and economic value across varying network topologies and incomplete data collection. Full article

► Show Figures

Figure 1

23 pages, 1040 KiB

Open AccessArticle

Hardware-Aware Federated Learning: Optimizing Differential Privacy in Distributed Computing Architectures

by Vishnu Vardhan Baligodugula and Fathi Amsaad

Electronics 2025, 14(6), 1218; https://doi.org/10.3390/electronics14061218 - 20 Mar 2025

Viewed by 215

Abstract

This paper analyzes hardware-aware federated learning implementation with differential privacy optimization. Experiments across 10 distributed clients using MNIST show that DP-FedAvg achieves 89.2% accuracy with privacy guarantees (e = 0.20), representing only a 5% reduction compared to standard FedAvg. Our hardware analysis identifies [...] Read more.

This paper analyzes hardware-aware federated learning implementation with differential privacy optimization. Experiments across 10 distributed clients using MNIST show that DP-FedAvg achieves 89.2% accuracy with privacy guarantees (e = 0.20), representing only a 5% reduction compared to standard FedAvg. Our hardware analysis identifies 15–25% increased memory usage and 30–40% computational variation across devices, while communication costs scale linearly up to 1000 clients. Implementation across heterogeneous platforms demonstrates an effective balance between privacy and performance in resource-constrained environments, providing practical deployment guidelines for privacy-preserving federated learning systems. Full article

► Show Figures

Figure 1

19 pages, 7628 KiB

Open AccessTechnical Note

Distributed Event-Triggered Current Sharing Consensus-Based Adaptive Droop Control of DC Microgrid

by Jinhui Zeng, Tianqi Liu, Chengjie Xu and Zhifeng Sun

Electronics 2025, 14(6), 1217; https://doi.org/10.3390/electronics14061217 - 20 Mar 2025

Viewed by 208

Abstract

Conventional droop control (a decentralized method to regulate power sharing by adjusting voltage–current slopes) in DC microgrids faces challenges in balancing precise current distribution, bus voltage regulation, and communication pressure, especially in distributed energy management scenarios. To address these limitations, this paper proposes [...] Read more.

Conventional droop control (a decentralized method to regulate power sharing by adjusting voltage–current slopes) in DC microgrids faces challenges in balancing precise current distribution, bus voltage regulation, and communication pressure, especially in distributed energy management scenarios. To address these limitations, this paper proposes an adaptive control strategy combining three layers: (1) Primary control achieves power sharing and voltage stabilization via U-I droop characteristics for distributed energy resources (DERs); (2) Secondary control corrects voltage deviations and droop coefficient imbalances through multi-agent consensus algorithms, ensuring global equilibrium; (3) Event-triggered consensus control minimizes communication pressure via a novel protocol with time-varying coupling weights and a hybrid trigger function combining state variables and time-decaying terms rigorously proven to exclude Zeno behavior (i.e., infinite triggering in finite time) using Lyapunov stability theory. Full article

(This article belongs to the Special Issue IoT Applications for Renewable Energy Management and Control, 2nd Edition)

► Show Figures

Figure 1

14 pages, 2198 KiB

Open AccessArticle

Online Calibration Strategy for SF₆ Gas Density Relay Based on Weighing Pressure Measurement

by Wenjuan Dong, Xingang Wang, Yuwei Wang, Changao Ji and Chunwei Song

Electronics 2025, 14(6), 1216; https://doi.org/10.3390/electronics14061216 - 20 Mar 2025

Viewed by 150

Abstract

SF₆ gas has high electrical insulation strength and excellent arc-extinguishing properties, making it widely used in high-voltage equipment. However, gas leakage or liquefaction can reduce its performance, necessitating density monitoring. This paper presents an online calibration device based on balance pressure measurement [...] Read more.

SF₆ gas has high electrical insulation strength and excellent arc-extinguishing properties, making it widely used in high-voltage equipment. However, gas leakage or liquefaction can reduce its performance, necessitating density monitoring. This paper presents an online calibration device based on balance pressure measurement and outlines the calibration process. It also analyzes the impact of factors such as the measuring balance, gravitational acceleration, cylinder friction, and installation alignment on calibration accuracy. To address uncertainty in the stabilization time of the cylinder gas temperature, a simulation model was created to observe the temperature equilibrium. Furthermore, power consumption analysis of the test device was conducted under different calibration cycles. The experimental results confirm the effectiveness of this calibration strategy. Full article

► Show Figures

Figure 1

26 pages, 3184 KiB

Open AccessArticle

Enhancing the Resilience of a Federated Learning Global Model Using Client Model Benchmark Validation

by Algimantas Venčkauskas, Jevgenijus Toldinas, Nerijus Morkevičius, Ernestas Serkovas and Modestas Krištaponis

Electronics 2025, 14(6), 1215; https://doi.org/10.3390/electronics14061215 - 19 Mar 2025

Viewed by 303

Abstract

Federated learning (FL) makes it possible for users to share trained models with one another, thereby removing the necessity of publicly centralizing training data. One of the best and most cost-effective ways to connect users is through email. To steal sensitive information, spam [...] Read more.

Federated learning (FL) makes it possible for users to share trained models with one another, thereby removing the necessity of publicly centralizing training data. One of the best and most cost-effective ways to connect users is through email. To steal sensitive information, spam emails might trick users into visiting malicious websites or performing other fraudulent actions. The developed semantic parser creates email metadata datasets from multiple email corpuses and populates the email domain ontology to facilitate the privacy of the information contained in email messages. There is a new idea to make FL global models more resistant to Byzantine attacks. It involves accepting updates only from strong participants whose local model shows higher validation scores using benchmark datasets. The proposed approach integrates FL, the email domain-specific ontology, the semantic parser, and a collection of benchmark datasets from heterogeneous email corpuses. By giving meaning to the metadata of an email message, the email’s domain-specific ontology made it possible to create datasets for email benchmark corpuses and participant updates in a unified format with the same features. In order to avoid fraudulently modified client updates from being applied to the global model, the experimental results approved the proposed approach to strengthen the resiliency of an FL global model by utilizing client model benchmark validation. Full article

(This article belongs to the Special Issue Navigating the Digital Age: Security, Ethics and Trust in Emerging Technologies)

► Show Figures

Figure 1

24 pages, 1853 KiB

Open AccessArticle

FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL

by Guanyu Jiang, Weibin Li, Chenglong Yu, Zixuan Zhu and Wei Li

Electronics 2025, 14(6), 1214; https://doi.org/10.3390/electronics14061214 - 19 Mar 2025

Viewed by 325

Abstract

Recent advances in large language models have driven major breakthroughs in Text-to-SQL tasks. However, many challenges hinder the use of SQL parsers for cross-language tasks. In this article, we introduce FGCSQL, a novel three-stage pipeline framework to deal with three challenges: cross-language schema [...] Read more.

Recent advances in large language models have driven major breakthroughs in Text-to-SQL tasks. However, many challenges hinder the use of SQL parsers for cross-language tasks. In this article, we introduce FGCSQL, a novel three-stage pipeline framework to deal with three challenges: cross-language schema linking, SQL parsing potential of LLM, and error propagation in SQL parsers, in which the framework uniquely incorporates a filtering encoder to eliminate irrelevant database schema items, harnessing a pre-trained generative large language model fine-tuned on a carefully structured dataset for enhanced SQL parsing. Finally, a correcting decoder addresses error propagation, culminating in a robust system for semantic parsing tasks. Tested on the CSpider dataset, the FGCSQL showcases a substantial improvement in the exact-set-match (EM) accuracy and execution accuracy (EX) metrics, validating the pipeline’s architecture’s effectiveness in mitigating the challenges typically confronted in Text-to-SQL conversion, especially in cross-lingual contexts. FGCSQL outstrips existing methods in execution precision, indicating the validity of our proposed method. Full article

► Show Figures

Figure 1

23 pages, 1716 KiB

Open AccessArticle

Knowledge Translator: Cross-Lingual Course Video Text Style Transform via Imposed Sequential Attention Networks

by Jingyi Zhang, Bocheng Zhao, Wenxing Zhang and Qiguang Miao

Electronics 2025, 14(6), 1213; https://doi.org/10.3390/electronics14061213 - 19 Mar 2025

Cited by 1 | Viewed by 225

Abstract

Massive Online Open Courses (MOOCs) have been growing rapidly in the past few years. Video content is an important carrier for cultural exchange and education popularization, and needs to be translated into multiple language versions to meet the needs of learners from different [...] Read more.

Massive Online Open Courses (MOOCs) have been growing rapidly in the past few years. Video content is an important carrier for cultural exchange and education popularization, and needs to be translated into multiple language versions to meet the needs of learners from different countries and regions. However, current MOOC video processing solutions rely excessively on manual operations, resulting in low efficiency and difficulty in meeting the urgent requirement for large-scale content translation. Key technical challenges include the accurate localization of embedded text in complex video frames, maintaining style consistency across languages, and preserving text readability and visual quality during translation. Existing methods often struggle with handling diverse text styles, background interference, and language-specific typographic variations. In view of this, this paper proposes an innovative cross-language style transfer algorithm that integrates advanced techniques such as attention mechanisms, latent space mapping, and adaptive instance normalization. Specifically, the algorithm first utilizes attention mechanisms to accurately locate the position of each text in the image, ensuring that subsequent processing can be targeted at specific text areas. Subsequently, by extracting features corresponding to this location information, the algorithm can ensure accurate matching of styles and text features, achieving an effective style transfer. Additionally, this paper introduces a new color loss function aimed at ensuring the consistency of text colors before and after style transfer, further enhancing the visual quality of edited images. Through extensive experimental verification, the algorithm proposed in this paper demonstrated excellent performance on both synthetic and real-world datasets. Compared with existing methods, the algorithm exhibited significant advantages in multiple image evaluation metrics, and the proposed method achieved a 2% improvement in the FID metric and a 20% improvement in the IS metric on relevant datasets compared to SOTA methods. Additionally, both the proposed method and the introduced dataset, PTTEXT, will be made publicly available upon the acceptance of the paper. For additional details, please refer to the project URL, which will be made public after the paper has been accepted. Full article

(This article belongs to the Special Issue Applications of Computational Intelligence, 3rd Edition)

► Show Figures

Figure 1

18 pages, 9580 KiB

Open AccessArticle

Development and Implementation of an Autonomous Control System for a Micro-Turbogenerator Installed on an Unmanned Aerial Vehicle

by Tiberius-Florian Frigioescu, Daniel-Eugeniu Crunțeanu, Maria Căldărar, Mădălin Dombrovschi, Gabriel-Petre Badea and Alexandra Nistor

Electronics 2025, 14(6), 1212; https://doi.org/10.3390/electronics14061212 - 19 Mar 2025

Viewed by 229

Abstract

The field of unmanned aerial vehicles (UAVs) has experienced substantial growth, with applications expanding across diverse domains. Missions increasingly demand higher autonomy, reducing human intervention and relying more on advanced onboard systems. However, integrating hybrid power sources, especially micro-turboprop engines, into UAVs poses [...] Read more.

The field of unmanned aerial vehicles (UAVs) has experienced substantial growth, with applications expanding across diverse domains. Missions increasingly demand higher autonomy, reducing human intervention and relying more on advanced onboard systems. However, integrating hybrid power sources, especially micro-turboprop engines, into UAVs poses significant challenges due to their complexity, hindering the development of effective power management control systems. This research aims to design a control algorithm for dynamic power allocation based on UAV operational needs. A fuzzy logic-based control algorithm was implemented on the Single-Board Computer (SBC) of a micro-turbogenerator test bench, which was previously developed in an earlier study. After implementing and testing the algorithm, voltage stabilization was achieved at improved levels by tightening the membership function constraints of the fuzzy logic controller. Automating the throttle control of the Electric Ducted Fan (EDF), the test platform’s primary power consumer, enabled the electric generator’s maximum capacity to be reached. This result indicates the necessity of replacing the current electric motor with one that is capable of higher power outputs to support the system’s enhanced performance. Full article

(This article belongs to the Section Systems & Control Engineering)

► Show Figures

Figure 1

13 pages, 3561 KiB

Open AccessArticle

Research on Lightweight Facial Landmark Prediction Network

by Shangzhen Pang, Tzer Hwai Gilbert Thio, Fei Lu Siaw, Mingju Chen and Li Lin

Electronics 2025, 14(6), 1211; https://doi.org/10.3390/electronics14061211 - 19 Mar 2025

Viewed by 179

Abstract

Facial landmarks, as direct and reliable biometric features, are widely utilized in various fields, including information security, public safety, virtual reality, and augmented reality. Facial landmarks, which are discrete key points on the face, preserve expression features and maintain the topological structure between [...] Read more.

Facial landmarks, as direct and reliable biometric features, are widely utilized in various fields, including information security, public safety, virtual reality, and augmented reality. Facial landmarks, which are discrete key points on the face, preserve expression features and maintain the topological structure between facial organs. Fast and accurate facial landmark prediction is essential in solving computer vision problems involving facial analysis, particularly in occlusion scenarios. This research proposes a lightweight facial landmark prediction network for occluded faces using an improved depthwise separable convolutional neural network architecture. The model is trained using 30,000 images from the CelebA-HQ dataset. The model is then tested under different occlusion ratios, including 10–20%, 30–40%, 40–50%, and 50–60% random occlusion, as well as 25% center occlusion. Using 68 facial landmarks for occlusion prediction, the proposed method always achieved significant improvements. Experimental results show that the proposed lightweight facial landmark prediction method is 1.97 times faster than FAN* and 1.67 times faster than ESR*, while still achieving better prediction results with lower NMSE values across all tested occlusion ratios for both frontal and profile faces. Full article

► Show Figures

Figure 1

22 pages, 1669 KiB

Open AccessArticle

Empowering Education with Intelligent Systems: Exploring Large Language Models and the NAO Robot for Information Retrieval

by Nikos Fragakis, Georgios Trichopoulos and George Caridakis

Electronics 2025, 14(6), 1210; https://doi.org/10.3390/electronics14061210 - 19 Mar 2025

Viewed by 246

Abstract

To unlock more aspects of human cognitive structuring, human–AI and human–robot interactions require increasingly advanced communication skills on both the human and robot sides. This paper compares three methods of retrieving cultural heritage information in primary school education: search engines, large language models [...] Read more.

To unlock more aspects of human cognitive structuring, human–AI and human–robot interactions require increasingly advanced communication skills on both the human and robot sides. This paper compares three methods of retrieving cultural heritage information in primary school education: search engines, large language models (LLMs), and the NAO humanoid robot, which serves as a facilitator with programmed answering capabilities for convergent questions. Human–robot interaction has become a critical aspect of modern education, with robots like the NAO providing new opportunities for engaging and personalized learning experiences. The NAO, with its anthropomorphic design and ability to interact with students, presents a unique approach to fostering deeper connections with educational content, particularly in the context of cultural heritage. The paper includes an introduction, extensive literature review, methodology, research results from student questionnaires, and conclusions. The findings highlight the potential of intelligent and embodied technologies for enhancing knowledge retrieval and engagement, demonstrating the NAO’s ability to adapt to student needs and facilitate more dynamic learning interactions. Full article

(This article belongs to the Special Issue New Trends in Intelligent User Interfaces and Human-Computer Interactions with Large Language Models)

► Show Figures

Figure 1

19 pages, 8720 KiB

Open AccessArticle

High Step-Up Interleaved DC–DC Converter with Voltage-Lift Capacitor and Voltage Multiplier Cell

by Shin-Ju Chen, Sung-Pei Yang, Chao-Ming Huang and Po-Yuan Hu

Electronics 2025, 14(6), 1209; https://doi.org/10.3390/electronics14061209 - 19 Mar 2025

Viewed by 227

Abstract

In this article, a new high step-up interleaved DC–DC converter is presented for renewable energy systems. The converter circuit is based on the interleaved two-phase boost converter and integrates a voltage-lift capacitor and a voltage multiplier cell. A high voltage gain of the [...] Read more.

In this article, a new high step-up interleaved DC–DC converter is presented for renewable energy systems. The converter circuit is based on the interleaved two-phase boost converter and integrates a voltage-lift capacitor and a voltage multiplier cell. A high voltage gain of the converter can be achieved with a reasonable duty ratio and the voltage stresses of semiconductor devices are reduced. Because of low voltage stress, the switches with low on-resistance and the diodes with low forward voltage drops can be adopted to minimize the conduction losses. Additionally, the switching losses are reduced because the switches are turned on under zero-current switching (ZCS) conditions. Due to the existence of leakage inductances of the coupled inductors, the diode reverse-recovery problem is alleviated. Moreover, the leakage energy is recycled and the voltage spikes during switch turn-off are avoided. The parallel input architecture and interleaved operation reduce the input current ripple. The operating principles, steady-state characteristics, and design considerations of the presented converter are proposed in detail. Furthermore, a closed-loop control is designed to maintain a well-regulated output voltage despite variations in input voltage and output load. A prototype converter with a rated 1000 W output power is realized for demonstration. Finally, experimental results show the converter effectiveness and verify the theoretical analysis. Full article

(This article belongs to the Special Issue Efficient and Resilient DC Energy Distribution Systems)

► Show Figures

Figure 1

19 pages, 868 KiB

Open AccessArticle

Detecting Cryptojacking Containers Using eBPF-Based Security Runtime and Machine Learning

by Riyeong Kim, Jeongeun Ryu, Sumin Kim, Soomin Lee and Seongmin Kim

Electronics 2025, 14(6), 1208; https://doi.org/10.3390/electronics14061208 - 19 Mar 2025

Viewed by 361

Abstract

As the use of containers has become mainstream in the cloud environment, various security threats targeting containers have also been increasing. Among them, a notable malicious activity is a cryptojacking attack that steals resources without the consent of an instance owner to mine [...] Read more.

As the use of containers has become mainstream in the cloud environment, various security threats targeting containers have also been increasing. Among them, a notable malicious activity is a cryptojacking attack that steals resources without the consent of an instance owner to mine cryptocurrency. However, detecting such anomalies in a containerized environment is more complex because containers share the host kernel, making it challenging to pinpoint resource usage and anomalies at the container granularity without introducing significant overhead. To this end, this study proposes a runtime detection framework for identifying malicious mining behaviors in the cloud-native environment. By leveraging Tetragon, a runtime security tool based on the extended Berkeley Packet Filter (eBPF), we capture system call traces and flow-level information of cryptojacking containers to extract rich feature representations for training and evaluating various machine learning models. As a result of the experiment, our framework delivers up to 99.75% classification accuracy with moderate runtime monitoring overhead. Full article

(This article belongs to the Special Issue Machine Learning and Cybersecurity—Trends and Future Challenges)

► Show Figures

Figure 1

19 pages, 402 KiB

Open AccessArticle

From Vulnerability to Resilience: Securing Public Safety GPS and Location Services with Smart Radio, Blockchain, and AI-Driven Adaptability

by Swarnamouli Majumdar and Anjali Awasthi

Electronics 2025, 14(6), 1207; https://doi.org/10.3390/electronics14061207 - 19 Mar 2025

Viewed by 343

Abstract

In an era where public safety hinges on real-time intelligence and rapid response, this paper delves into the pivotal role of location-based services (LBSs) in empowering law enforcement and fire rescue operations. GPS tracking systems have revolutionized situational awareness and resource management, yet [...] Read more.

In an era where public safety hinges on real-time intelligence and rapid response, this paper delves into the pivotal role of location-based services (LBSs) in empowering law enforcement and fire rescue operations. GPS tracking systems have revolutionized situational awareness and resource management, yet they come with critical security and privacy challenges, including unauthorized access, real-time data interception, and insider threats. To address these vulnerabilities, this study introduces an innovative framework that combines blockchain, artificial intelligence (AI), and IoT technologies to redefine emergency management and public safety systems. Voice-command virtual assistants powered by AI enable hands-free operations, enhance hazard detection, and optimize resource allocation in real time, while blockchain’s decentralized and tamper-proof architecture ensures data integrity and security. By integrating these cutting-edge technologies, the research showcases a system design that not only secures sensitive information but also drives operational efficiency and resilience. With applications spanning smart cities, autonomous systems, and fire rescue operations, this study offers a transformative vision for public safety, emphasizing technology integration, digital innovation, and trust-building. These advancements promise not only to protect responders and communities but also to redefine the standards of security and efficiency in modern emergency management. Full article

(This article belongs to the Special Issue Security and Privacy in Location-Based Service)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 14, Issue 6 (March-2 2025) – 180 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI