Electronics

10 pages, 3921 KiB

Open AccessArticle

An Efficient and Low-Cost Design of Modular Reduction for CRYSTALS-Kyber

by Zhengwu Huang, Sizhe Chen, Pengyue Sun, Ding Deng and Guangfu Sun

Electronics 2025, 14(11), 2309; https://doi.org/10.3390/electronics14112309 - 5 Jun 2025

Viewed by 164

After being selected as a standard for Post-Quantum Cryptography Key Encapsulation Mechanisms by NIST, CRYSTALS-Kyber has driven the transformation of the information security field toward new standards. In CRYSTALS-Kyber, modular reduction is crucial for performance optimization. This paper proposes a bitwise modular reduction [...] Read more.

After being selected as a standard for Post-Quantum Cryptography Key Encapsulation Mechanisms by NIST, CRYSTALS-Kyber has driven the transformation of the information security field toward new standards. In CRYSTALS-Kyber, modular reduction is crucial for performance optimization. This paper proposes a bitwise modular reduction design based on Dadda tree compression arrays, achieving higher parallelism through a strategy that combines bitwise modular reduction with hybrid compression arrays. As our experiments show, it only costs 91 LUTs when implemented on Xilinx Artix-7 FPGA. Compared with the leading hardware implementations, the Area–Time Product (ATP) is reduced by 16.43%~87.69%. Full article

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

► Show Figures

Figure 1

21 pages, 11516 KiB

Open AccessArticle

Elevator Fault Diagnosis Based on a Graph Attention Recurrent Network

by Haokun Wu, Li Yin, Yufeng Chen, Zhiwu Li and Qiwei Tang

Electronics 2025, 14(11), 2308; https://doi.org/10.3390/electronics14112308 - 5 Jun 2025

Viewed by 238

Abstract

Elevator fault diagnosis is critical for ensuring operational safety and reliability in modern vertical transportation systems. Traditional approaches, which rely on time- and frequency-domain signal analysis, often struggle with the issues such as noise sensitivity, inadequate feature extraction, and limited adaptability to complex [...] Read more.

Elevator fault diagnosis is critical for ensuring operational safety and reliability in modern vertical transportation systems. Traditional approaches, which rely on time- and frequency-domain signal analysis, often struggle with the issues such as noise sensitivity, inadequate feature extraction, and limited adaptability to complex scenarios. To address these challenges, this paper proposes a Graph Attention Recurrent Network (GARN) which integrates graph-structured signal representation with spatiotemporal feature learning. The GARN employs a limited penetrable visibility graph to transform raw vibration signals into noise-robust graph topologies, preserving critical patterns while suppressing high-frequency noise through controlled edge penetration. An adaptive attention mechanism dynamically fuses triaxial features to prioritize the most relevant information for fault diagnosis. The GARN combines a graph convolutional network to extract spatial correlations and a gated recurrent unit to capture temporal fault progression, enabling holistic and accurate fault classification. Experimental results based on real-world elevator datasets demonstrate the superior performance of the GARN, showcasing its strong noise resistance, adaptability to complex fault conditions, and ability to provide reliable and timely fault diagnosis, making it a robust solution for modern elevator systems. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

24 pages, 14764 KiB

Open AccessArticle

Mechatronic Anticollision System for Electric Wheelchairs Based on a Time-of-Flight Sensor

by Wiesław Szaj, Michał Wanic, Wiktoria Wojnarowska and Sławomir Miechowicz

Electronics 2025, 14(11), 2307; https://doi.org/10.3390/electronics14112307 - 5 Jun 2025

Viewed by 187

Abstract

Electric wheelchairs significantly enhance mobility for individuals with disabilities, but navigating confined or crowded spaces remains a challenge. This paper presents a mechatronic anticollision system based on Time-of-Flight (ToF) sensors designed to improve wheelchair navigation in such environments. The system performs eight-plane 3D [...] Read more.

Electric wheelchairs significantly enhance mobility for individuals with disabilities, but navigating confined or crowded spaces remains a challenge. This paper presents a mechatronic anticollision system based on Time-of-Flight (ToF) sensors designed to improve wheelchair navigation in such environments. The system performs eight-plane 3D environmental scans in 214–358 ms, with a vertical field of view of 12.4° and a detection range of up to 4 m—sufficient for effective obstacle avoidance. Unlike existing solutions like the YDLIDAR T-mini Plus, which has a narrow vertical field of view and a longer detection range that may be excessive for indoor spaces, or the xLIDAR, which struggles with shorter detection ranges, our system balances an optimal detection range and vertical scanning area, making it especially suitable for wheelchair users. Preliminary tests confirm that our system achieves high accuracy, with a standard deviation as low as 0.003 m and a maximum deviation below 0.05 m at a 3-m range on high-reflectivity surfaces (e.g., white and light brown). Our solution offers low power consumption (140 mA) and USB communication, making it an energy-efficient and easy-to-integrate solution for electric wheelchairs. Future work will focus on enhancing angular precision and robustness for dynamic, real-world environments. Full article

► Show Figures

Figure 1

18 pages, 3509 KiB

Open AccessArticle

A Segmented Adaptive PID Temperature Control Method Suitable for Industrial Dispensing System

by Yuan Gao and Wanshan Zhu

Electronics 2025, 14(11), 2306; https://doi.org/10.3390/electronics14112306 - 5 Jun 2025

Viewed by 162

Abstract

Industrial dispensing systems consist of many components, and the temperature characteristics of these components vary significantly. To address this, a segmented adaptive PID temperature control method is proposed in this paper. This method integrates a segmented temperature control algorithm with a variable control [...] Read more.

Industrial dispensing systems consist of many components, and the temperature characteristics of these components vary significantly. To address this, a segmented adaptive PID temperature control method is proposed in this paper. This method integrates a segmented temperature control algorithm with a variable control coefficient algorithm based on output power, which not only ensures minimal overshoot in the system but also enhances its disturbance rejection capability. Experimental results demonstrate that, under identical conditions, compared with the traditional PID method, the proposed method reduces overshoot by 2–4 °C and decreases the amplitude of temperature fluctuations after disturbance by approximately 0.2 °C. Full article

(This article belongs to the Special Issue Advances in Autonomous Control Systems and Their Applications: 2nd Edition)

► Show Figures

Figure 1

25 pages, 7158 KiB

Open AccessArticle

Anti-Jamming Decision-Making for Phased-Array Radar Based on Improved Deep Reinforcement Learning

by Hang Zhao, Hu Song, Rong Liu, Jiao Hou and Xianxiang Yu

Electronics 2025, 14(11), 2305; https://doi.org/10.3390/electronics14112305 - 5 Jun 2025

Viewed by 173

Abstract

In existing phased-array radar systems, anti-jamming strategies are mainly generated through manual judgment. However, manually designing or selecting anti-jamming decisions is often difficult and unreliable in complex jamming environments. Therefore, reinforcement learning is applied to anti-jamming decision-making to solve the above problems. However, [...] Read more.

In existing phased-array radar systems, anti-jamming strategies are mainly generated through manual judgment. However, manually designing or selecting anti-jamming decisions is often difficult and unreliable in complex jamming environments. Therefore, reinforcement learning is applied to anti-jamming decision-making to solve the above problems. However, the existing anti-jamming decision-making models based on reinforcement learning often suffer from problems such as low convergence speeds and low decision-making accuracy. In this paper, a multi-aspect improved deep Q-network (MAI-DQN) is proposed to improve the exploration policy, the network structure, and the training methods of the deep Q-network. In order to solve the problem of the

ϵ

-greedy strategy being highly dependent on hyperparameter settings, and the Q-value being overly influenced by the action in other deep Q-networks, this paper proposes a structure that combines a noisy network, a dueling network, and a double deep Q-network, which incorporates an adaptive exploration policy into the neural network and increases the influence of the state itself on the Q-value. These enhancements enable a highly adaptive exploration strategy and a high-performance network architecture, thereby improving the decision-making accuracy of the model. In order to calculate the target value more accurately during the training process and improve the stability of the parameter update, this paper proposes a training method that combines n-step learning, target soft update, variable learning rate, and gradient clipping. Moreover, a novel variable double-depth priority experience replay (VDDPER) method that more accurately simulates the storage and update mechanism of human memory is used in the MAI-DQN. The VDDPER improves the decision-making accuracy by dynamically adjusting the sample size based on different values of experience during training, enhancing exploration during the early stages of training, and placing greater emphasis on high-value experiences in the later stages. Enhancements to the training method improve the model’s convergence speed. Moreover, a reward function combining signal-level and data-level benefits is proposed to adapt to complex jamming environments, which ensures a high reward convergence speed with fewer computational resources. The findings of a simulation experiment show that the proposed phased-array radar anti-jamming decision-making method based on MAI-DQN can achieve a high convergence speed and high decision-making accuracy in environments where deceptive jamming and suppressive jamming coexist. Full article

(This article belongs to the Special Issue Advanced Radar Waveform Design and Intelligent Countermeasures in Integrated Radar and Communication Systems)

► Show Figures

Figure 1

20 pages, 4598 KiB

Open AccessArticle

Feature Decoupling-Guided Annotation Framework for Surface Defects on Steel Strips

by Weiqi Yuan and Wentao Liu

Electronics 2025, 14(11), 2304; https://doi.org/10.3390/electronics14112304 - 5 Jun 2025

Viewed by 137

Abstract

Surface defect detection on steel strips is a critical step in quality control for industrial products. While existing research has made some progress in optimizing annotation strategies and improving efficiency, issues such as feature aliasing during the annotation process, the insufficient utilization of [...] Read more.

Surface defect detection on steel strips is a critical step in quality control for industrial products. While existing research has made some progress in optimizing annotation strategies and improving efficiency, issues such as feature aliasing during the annotation process, the insufficient utilization of boundary information, and the inaccurate representation of complex defect patterns remain inadequately addressed. To tackle these challenges, this paper proposes an annotation optimization framework from the perspective of feature analysis. The framework decomposes defect features into geometric features and grayscale distribution features and, based on feature decoupling theory, classifies defects into three typical patterns: block, linear, and textured defects. For each pattern, the minimum annotation units that preserved essential features were designed, enabling the standardized representation of complex defects and precise boundary localization. Experiments on the NEU-DET dataset showed that this annotation framework improves the average mAP of six mainstream detection models by 4.9 percentage points, validating its effectiveness in enhancing the detection performance. Additionally, this paper introduces an Efficiency–Cost Ratio (ECR) evaluation metric to quantify the relationship between the annotation cost and performance improvement. The study found that block and linear defect detection achieved optimal performance with only 50% annotation effort. This research not only improved the performance of defect detection models but also quantified the annotation resource utilization efficiency, providing robust theoretical support and practical guidance for efficient defect detection in complex industrial scenarios. Full article

► Show Figures

Figure 1

21 pages, 92256 KiB

Open AccessArticle

Recognition of Dense Goods with Cross-Layer Feature Fusion Based on Multi-Scale Dynamic Interaction

by Zhiyuan Wu, Bisheng Wu, Kai Xie, Junqin Yu, Banghui Xu, Chang Wen, Jianbiao He and Wei Zhang

Electronics 2025, 14(11), 2303; https://doi.org/10.3390/electronics14112303 - 5 Jun 2025

Viewed by 130

Abstract

To enhance the accuracy of product recognition in non-store retail sales and address misidentification and missed detection caused by occlusion in densely placed goods, we propose an improved YOLOv8-based network: Dense-YOLO. We first introduce an enhanced multi-scale feature extraction module (EMFE) in the [...] Read more.

To enhance the accuracy of product recognition in non-store retail sales and address misidentification and missed detection caused by occlusion in densely placed goods, we propose an improved YOLOv8-based network: Dense-YOLO. We first introduce an enhanced multi-scale feature extraction module (EMFE) in the feature extraction layer and employ a lightweight feature fusion strategy (LFF) in the feature fusion layer to improve the network’s performance. Next, to enhance the performance of dense product recognition, particularly when handling small and multi-scale objects in complex settings, we propose a novel multi-scale dynamic interaction attention mechanism (MDIAM). This mechanism combines dynamic channel weight adjustment and multi-scale spatial convolution to emphasize crucial features, while avoiding overfitting and enhancing model generalization. Finally, a cross-layer feature interaction mechanism is introduced to strengthen the interaction between low- and high-level features, further improving the model’s expressive power. Using the public COCO128 dataset and over 2000 daily smart retail cabinet product images compiled in our laboratory, we created a dataset covering 50 product categories for ablation and comparison experiments. The experimental results indicate that the accuracy under MDIAM is improved by 1.6% compared to other top-performing models. The proposed algorithm achieves an mAP of 94.9%, which is a 1.0% improvement over the original model. The enhanced algorithm not only significantly improves the recognition accuracy of individual commodities but also effectively addresses the issues of misdetection and missed detection when multiple commodities are recognized simultaneously. Full article

(This article belongs to the Special Issue Deep Learning-Based Object Detection/Classification)

► Show Figures

Figure 1

33 pages, 14789 KiB

Open AccessArticle

A Node-Degree Power-Law Distribution-Based Honey Badger Algorithm for Global and Engineering Optimization

by Shuangyu Song, Zhenyu Song, Xingqian Chen and Junkai Ji

Electronics 2025, 14(11), 2302; https://doi.org/10.3390/electronics14112302 - 5 Jun 2025

Viewed by 129

Abstract

The honey badger algorithm (HBA) has gained significant attention as a metaheuristic optimization method; however, despite these design strengths, it still faces challenges such as premature convergence, suboptimal exploration–exploitation balance, and low population diversity. To address these limitations, we integrate a power-law degree [...] Read more.

The honey badger algorithm (HBA) has gained significant attention as a metaheuristic optimization method; however, despite these design strengths, it still faces challenges such as premature convergence, suboptimal exploration–exploitation balance, and low population diversity. To address these limitations, we integrate a power-law degree distribution (PDD) topology into the HBA population structure. Three improved versions of the HBA are proposed, with each employing different population update strategies: PDDHBA-R, PDDHBA-B, and PDDHBA-H. In the PDDHBA-R strategy, individuals randomly select neighbours as references, promoting diversity and randomness. The PDDHBA-B strategy allows individuals to select the best neighbouring individual, speeding up convergence. The PDDHBA-H strategy combines both approaches, using random selection for elite individuals and best selection for non-elite individuals. These algorithms were tested on 30 benchmark functions from CEC2017, 21 real-world problems from CEC2011, and four constrained engineering problems. The experimental results show that all three improvements significantly improve the performance of the HBA, with PDDHBA-H delivering the best results across various tests. Further analysis of the parameter sensitivity, computational complexity, population diversity, and exploration–exploitation balance confirms the superiority of PDDHBA-H, highlighting its potential for use in complex optimization problems. Full article

(This article belongs to the Special Issue Applications of Edge Computing in Mobile Systems)

► Show Figures

Figure 1

20 pages, 9232 KiB

Open AccessArticle

Design, Fabrication, and Electromagnetic Characterization of a Feed Horn of the Linear-Polarized Multi-Beam Cryogenic S-Band Receiver for the Sardinia Radio Telescope

by Tonino Pisanu, Paolo Maxia, Alessandro Navarrini, Giuseppe Valente, Renzo Nesti, Luca Schirru, Pasqualino Marongiu, Pierluigi Ortu, Adelaide Ladu, Francesco Gaudiomonte, Silvio Pilia, Roberto Caocci, Paola Di Ninni, Luca Cresci and Aldo Sonnini

Electronics 2025, 14(11), 2301; https://doi.org/10.3390/electronics14112301 - 5 Jun 2025

Viewed by 127

Abstract

The S-band (i.e., 2–4 GHz) is essential in multiple fields of radio astronomy, ranging from pulsar and solar studies to investigations of the early universe. The Italian 64 m fully steerable Sardinia Radio Telescope (SRT) is a system designed to operate in a [...] Read more.

The S-band (i.e., 2–4 GHz) is essential in multiple fields of radio astronomy, ranging from pulsar and solar studies to investigations of the early universe. The Italian 64 m fully steerable Sardinia Radio Telescope (SRT) is a system designed to operate in a wide frequency band ranging from 300 MHz to 116 GHz. Recently, the Astronomical Observatory of Cagliari (OAC) has been developing a new cryogenic seven-beam S-band radio receiver. This paper describes the design, fabrication and electromagnetic characterization of the feed horn for this new receiver. It has been designed to observe the sky in the 3–4.5 GHz frequency range and it will be composed of seven feed horns arranged in a regular hexagonal layout with a central element. The feed horns are optimized for placement in the primary focus and consequently illuminate the 64 m primary mirror of the SRT. The electromagnetic characterization of the single feed horn is crucial to verify the receiver’s performance; for this reason, a single feed horn has been manufactured to compare the measured reflection coefficient and the radiated far-field diagram with the results of the electromagnetic simulations, performed using the CST^® Suite Studio 2024 and Ansys HFSS^® Electromagnetics Suite 2021 R1 (To make the S-parameters and the radiation diagram measurement procedure feasible, the single feed horn has been connected to two adapters: a circular-to-rectangular waveguide adapter and a coax-to-rectangular waveguide adapter. The results of the measurements performed in the anechoic chamber are in very good agreement with the simulated results. Additionally, the feed horn phase center position is evaluated, merging the measurements and simulations results for an optimal installation on the primary focus of the SRT. Full article

(This article belongs to the Special Issue Microwave Devices: Analysis, Design, and Application)

► Show Figures

Figure 1

10 pages, 28452 KiB

Open AccessArticle

Highly Linear 2.6 GHz Band InGaP/GaAs HBT Power Amplifier IC Using a Dynamic Predistorter

by Hyeongjin Jeon, Jaekyung Shin, Woojin Choi, Sooncheol Bae, Kyungdong Bae, Soohyun Bin, Sangyeop Kim, Yunhyung Ju, Minseok Ahn, Gyuhyeon Mun, Keum Cheol Hwang, Kang-Yoon Lee and Youngoo Yang

Electronics 2025, 14(11), 2300; https://doi.org/10.3390/electronics14112300 - 5 Jun 2025

Viewed by 175

Abstract

This paper presents a highly linear two-stage InGaP/GaAs power amplifier integrated circuit (PAIC) using a dynamic predistorter for 5G small-cell applications. The proposed predistorter, based on a diode-connected transistor, utilizes a supply voltage to accurately control the linearization characteristics by adjusting its dc [...] Read more.

This paper presents a highly linear two-stage InGaP/GaAs power amplifier integrated circuit (PAIC) using a dynamic predistorter for 5G small-cell applications. The proposed predistorter, based on a diode-connected transistor, utilizes a supply voltage to accurately control the linearization characteristics by adjusting its dc current. It is connected in parallel with an inter-stage of the two-stage PAIC through a series configuration of a resistor and an inductor, and features a shunt capacitor at the base of the transistor. These passive components have been optimized to enhance the linearization performance by managing the RF signal’s coupling to the diode. Using these optimized components, the AM−AM and AM−PM nonlinearities arising from the nonlinear resistance and capacitance in the diode can be effectively used to significantly flatten the AM−AM and AM−PM characteristics of the PAIC. The proposed predistorter was applied to the 2.6 GHz two-stage InGaP/GaAs HBT PAIC. The IC was tested using a 5 × 5 mm² module package based on a four-layer laminate. The load network was implemented off-chip on the laminate. By employing a continuous-wave (CW) signal, the AM−AM and AM−PM characteristics at 2.55–2.65 GHz were improved by approximately 0.05 dB and 3°, respectively. When utilizing the new radio (NR) signal, based on OFDM cyclic prefix (CP) with a signal bandwidth of 100 MHz and a peak-to-average power ratio (PAPR) of 9.7 dB, the power-added efficiency (PAE) reached at least 11.8%, and the average output power was no less than 24 dBm, achieving an adjacent channel leakage power ratio (ACLR) of −40.0 dBc. Full article

(This article belongs to the Section Microwave and Wireless Communications)

► Show Figures

Figure 1

26 pages, 7006 KiB

Open AccessArticle

Cross-Environment Device-Free Human Action Recognition via Wi-Fi Signals

by Sai Zhang, Yi Zhong, Haoge Jia, Xue Ding and Ting Jiang

Electronics 2025, 14(11), 2299; https://doi.org/10.3390/electronics14112299 - 5 Jun 2025

Viewed by 176

Abstract

Human action recognition (HAR) based on Wi-Fi signals has become a research hotspot due to its advantages of privacy protection, a comfortable experience, and a reliable recognition effect. However, the performance of existing Wi-Fi-based HAR systems is vulnerable to changes in environments and [...] Read more.

Human action recognition (HAR) based on Wi-Fi signals has become a research hotspot due to its advantages of privacy protection, a comfortable experience, and a reliable recognition effect. However, the performance of existing Wi-Fi-based HAR systems is vulnerable to changes in environments and shows poor system generalization capabilities. In this paper, we propose a cross-environment HAR system (CHARS) based on the channel state information (CSI) of Wi-Fi signals for the recognition of human activities in different indoor environments. To achieve good performance for cross-environment HAR, a two-stage action recognition method is proposed. In the first stage, an HAR adversarial network is designed to extract robust action features independent of environments. Through the maximum–minimum learning scheme, the aim is to narrow the distribution gap between action features extracted from the source and the target (i.e., new) environments without using any label information from the target environment, which is beneficial for the generalization of the cross-environment HAR system. In the second stage, a self-training strategy is introduced to further extract action recognition information from the target environment and perform secondary optimization, enhancing the overall performance of the cross-environment HAR system. The results of experiments show that the proposed system achieves more reliable performance in target environments, demonstrating the generalization ability of the proposed CHARS to environmental changes. Full article

(This article belongs to the Special Issue Advances in Wireless Communication for loT)

► Show Figures

Figure 1

17 pages, 2353 KiB

Open AccessArticle

Integration of Mobility-Assisting Technologies in the Rehabilitation of Drivers with Neurological Disorders: A Preliminary Study

by Jacek S. Tutak and Krzysztof Lew

Electronics 2025, 14(11), 2298; https://doi.org/10.3390/electronics14112298 - 5 Jun 2025

Viewed by 182

Abstract

This publication aims to present the preliminary results of research on an innovative device designed to support the rehabilitation of drivers with neurological disorders, developed as part of a multidisciplinary project. The device was designed for individuals recovering from neurological diseases, injuries, and [...] Read more.

This publication aims to present the preliminary results of research on an innovative device designed to support the rehabilitation of drivers with neurological disorders, developed as part of a multidisciplinary project. The device was designed for individuals recovering from neurological diseases, injuries, and COVID-19-related complications, who experience difficulties with coordination and the speed of performing motor exercises. Its goal is to improve the quality of life for patients and increase their chances of safely driving vehicles, which also contributes to the safety of all road users. The device allows for controlled upper limb exercises using a diagnostic module, exercise program, and biofeedback system. The main component is a mechatronic driving simulator, enhanced with dedicated software to support the rehabilitation of individuals with neurological disorders and older adults. Through driving simulations and rehabilitation tasks, patients perform exercises that improve their health, facilitating a faster recovery. The innovation of the solution is confirmed by a submitted patent application, and preliminary research results indicate its effectiveness in rehabilitation and improving mobility for individuals with neurological disorders. Full article

(This article belongs to the Special Issue Internet of Things, Artificial Intelligence, and Edge Computing for Smart Health)

► Show Figures

Figure 1

14 pages, 1343 KiB

Open AccessArticle

Comparative Analysis of Direct Inclined Irradiance Data Sources for Micro-Tracking Concentrator Photovoltaics

by Pedro Perez-Higueras, Maria A. Ceballos, Elmehdi Mouhib, Joao Gabriel Bessa, Jesus Montes-Romero and Raul Mata-Campos

Electronics 2025, 14(11), 2297; https://doi.org/10.3390/electronics14112297 - 5 Jun 2025

Viewed by 200

Abstract

In recent years, the scientific community has intensified its efforts to develop a new type of concentrator photovoltaic module that is competitive with conventional modules. These modules are based on internal tracking systems, known as micro-tracking concentrator photovoltaic modules, which generate electrical energy [...] Read more.

In recent years, the scientific community has intensified its efforts to develop a new type of concentrator photovoltaic module that is competitive with conventional modules. These modules are based on internal tracking systems, known as micro-tracking concentrator photovoltaic modules, which generate electrical energy proportional to the direct radiation on the inclined surface. There are several reviews, databases, and models for various components of solar radiation, particularly for global and direct normal radiation. However, readily available data on direct inclined irradiance remain scarce. This paper reviews several available sources of solar radiation data, finding that only the Photovoltaic Geographic Information System and Solar Radiation Database provide direct inclined irradiance data. A comparative statistical analysis was carried out, and a reasonable fit was obtained between both databases. In addition, direct inclined radiation data extracted from these databases were compared with the values calculated using a well-established mathematical model. In addition, worldwide maps were generated to determine areas of interest for this technology. Therefore, this paper presents an original comparative analysis of existing databases containing information on direct inclined irradiation. This information is of interest for the accurate design and performance analysis of micro-tracking concentrator modules. Full article

(This article belongs to the Special Issue Materials and Properties for Solar Cell Application)

► Show Figures

Figure 1

16 pages, 2979 KiB

Open AccessArticle

CNN-Assisted Effective Radar Active Jamming Suppression in Ultra-Low Signal-to-Jamming Ratio Conditions Using Bandwidth Enhancement

by Linbo Zhang, Xiuting Zou, Shaofu Xu, Mengmeng Chai, Wenbin Lu, Zhenbin Lv and Weiwen Zou

Electronics 2025, 14(11), 2296; https://doi.org/10.3390/electronics14112296 - 5 Jun 2025

Viewed by 193

Abstract

In complex scenarios, radar echoes are contaminated by strong jamming, which significantly degrades their detection. Target detection under ultra-low signal-to-jamming ratio (SJR) conditions has thus become a major challenge when confronted with active jamming represented by smeared spectrum (SMSP) noise. Traditional jamming suppression [...] Read more.

In complex scenarios, radar echoes are contaminated by strong jamming, which significantly degrades their detection. Target detection under ultra-low signal-to-jamming ratio (SJR) conditions has thus become a major challenge when confronted with active jamming represented by smeared spectrum (SMSP) noise. Traditional jamming suppression methods are often limited by model dependency and useful signal loss. Convolutional neural networks (CNNs) have gained significant attention as an effective method for jamming suppression. However, in an ultra-low SJR environment, CNNs would have difficulty in carrying out jamming suppression, resulting in poor signal quality. In this study, we utilize a bandwidth enhancement method to allow CNNs to perform effective radar active jamming suppression in ultra-low SJR environments. Specifically, the bandwidth enhancement method reduces the correlation between target and jamming signals, which yields higher-quality target range profiles. Consequently, a modified CNN featuring a dense connection module can effectively suppress jamming even in ultra-low SJR scenarios. The experimental results show that when the input SJR is −30 dB and the bandwidth is 1.2 GHz, the output SJR reaches 13.25 dB. Meanwhile, the improvement factor (IF) gradually increases and reaches saturation at ~15 dB. Building on the bandwidth enhancement method, the modified CNN further improves the IF by ~27 dB. This work is expected to offer a new technical pathway for suppressing radar active jamming in ultra-low SJR scenarios. Full article

(This article belongs to the Section Microwave and Wireless Communications)

► Show Figures

Figure 1

9 pages, 2547 KiB

Open AccessCommunication

Design of Orientation-Independent Non-Invasive Glucose Sensor Based on Meta-Structured Antenna

by Jae-Min Jeong, Franklin Bien and Jae-Gon Lee

Electronics 2025, 14(11), 2295; https://doi.org/10.3390/electronics14112295 - 5 Jun 2025

Viewed by 194

Abstract

This paper presents the design of an orientation-independent non-invasive glucose sensor based on a meta-structured antenna. The sensor is designed for blood glucose measurement through fingertip placement on the sensor and features a mushroom structure to generate zeroth-order resonance (ZOR). Moreover, the mushroom [...] Read more.

This paper presents the design of an orientation-independent non-invasive glucose sensor based on a meta-structured antenna. The sensor is designed for blood glucose measurement through fingertip placement on the sensor and features a mushroom structure to generate zeroth-order resonance (ZOR). Moreover, the mushroom structure has a hexagonal patch for orientation-independent non-invasive sensing. The operating frequency of the sensor is 4 GHz, and the overall size is 55 mm × 55 mm. In our study, the range of glucose concentration is from 50 to 250 mg/dL, with a step size of 50 mg/dL. The simulated and measured results show a linear relationship between the resonance frequency and the glucose concentration in the solution, and the linear shift of 0.352 MHz/mg/dL has been observed. On the other hand, the reflection coefficient level variation is a nonlinear function of the glucose concentration for the considered concentration ranges. Mathematical models describing the sensor response across all fingertip orientations are developed for the designed sensor using the regression analysis (R² ≥ 0.993) relating the glucose concentration to the measured resonance frequency and reflection coefficient level. While the reflection coefficient shows a nonlinear response, the resonance frequency exhibits a strong linear correlation with glucose concentration, making it a more reliable parameter for accurate prediction in the proposed sensing model. Full article

► Show Figures

Figure 1

25 pages, 2792 KiB

Open AccessArticle

Coupling Characteristic Analysis and Coordinated Planning Strategies for AC/DC Hybrid Transmission Systems with Multi-Infeed HVDC

by Hui Cai, Mingxin Yan, Song Gao, Ting Zhou, Guoteng Wang and Ying Huang

Electronics 2025, 14(11), 2294; https://doi.org/10.3390/electronics14112294 - 4 Jun 2025

Viewed by 204

Abstract

With the increasing penetration of renewable energy, the scale of AC/DC hybrid transmission systems continues to grow, intensifying risks such as line overloads under N-1 contingencies, short-circuit current violations, and operational stability challenges arising from multi-DC coupling. This paper explores the complex coupling [...] Read more.

With the increasing penetration of renewable energy, the scale of AC/DC hybrid transmission systems continues to grow, intensifying risks such as line overloads under N-1 contingencies, short-circuit current violations, and operational stability challenges arising from multi-DC coupling. This paper explores the complex coupling characteristics between AC/DC and multi-DC systems in hybrid configurations, proposing innovative evaluation indicators for coupling properties and a comprehensive assessment scheme for multi-DC coupling degrees. To enhance system stability, coordinated planning strategies are proposed for AC/DC hybrid transmission systems with multi-infeed High-voltage direct-current (HVDC) based on the AC/DC strong–weak balance principle. Specifically, planning schemes are developed for determining the locations, capacities, and converter configurations of newly added DC lines. Furthermore, to mitigate multi-DC simultaneous commutation failure risks, we propose an AC-to-DC conversion planning scheme and a strategy for adjusting the DC system technology route based on a through comprehensive multi-DC coupling strength assessment, yielding coordinated planning strategies applicable to the AC/DC hybrid transmission systems with multi-infeed HVDC. Finally, simulation studies on the IEEE two-area four-machine system validate the feasibility of the proposed hybrid transmission grid planning strategies. The results demonstrate its effectiveness in coordinating multi-DC coupling interactions, providing critical technical support for future hybrid grid development under scenarios with high renewable energy penetration. Full article

► Show Figures

Figure 1

27 pages, 3471 KiB

Open AccessArticle

Control of a Dumper Vehicle with a Trailer Using Partial Feedback Linearization

by Jaume Franch, Jose-Manuel Rodriguez-Fortun and Rafael Herguedas

Electronics 2025, 14(11), 2293; https://doi.org/10.3390/electronics14112293 - 4 Jun 2025

Viewed by 218

Abstract

The control of vehicles towing trailers is of significant interest to industry due to their wide-ranging applications across various sectors. Trailers play essential roles in logistics, mining, and other fields. This study focuses on the control of a dumper with a trailer specifically [...] Read more.

The control of vehicles towing trailers is of significant interest to industry due to their wide-ranging applications across various sectors. Trailers play essential roles in logistics, mining, and other fields. This study focuses on the control of a dumper with a trailer specifically used for the monitoring of terrain stability in mining operations. The trailer is equipped with a radar system for detecting potential ground shifts that could jeopardize fieldwork safety. While numerous studies have addressed the control of Ackerman vehicles and trailers, this dumper presents a unique challenge due to its rear-axle steering mechanism. Due to this configuration, which has not been extensively studied in the literature, although the differential flatness of the system is proven, computation of the flat outputs leads to a system of partial differential equations that cannot be solved analytically. For this reason, this paper examines partial feedback linearization to facilitate control and proposes a solution for trajectory tracking that also stabilizes jack-knifing tendencies between the vehicle and trailer. The designed control system was successfully validated in a virtual environment. Full article

(This article belongs to the Special Issue Control and Design of Intelligent Robots)

► Show Figures

Figure 1

21 pages, 14472 KiB

Open AccessArticle

RGD-DETR: Road Garbage Detection Based on Improved RT-DETR

by Zexing Luo, Meiqin Che, Qian Shao, Guoqing Yang, Changyong Xu and Yeqin Shao

Electronics 2025, 14(11), 2292; https://doi.org/10.3390/electronics14112292 - 4 Jun 2025

Viewed by 211

Abstract

Rapid urbanization in China has led to an increase in the volume of daily road garbage, posing challenges to municipal sanitation. Automatic garbage collection is thus essential for sustainable management. This paper proposes an improved RT-DETR-based (Real-Time Detection Transformer) detection model, RGD-DETR, to [...] Read more.

Rapid urbanization in China has led to an increase in the volume of daily road garbage, posing challenges to municipal sanitation. Automatic garbage collection is thus essential for sustainable management. This paper proposes an improved RT-DETR-based (Real-Time Detection Transformer) detection model, RGD-DETR, to improve road garbage detection performance. Firstly, an improved feature pyramid module that leverages multi-scale feature fusion techniques to enhance feature extraction effectiveness is designed. Secondly, a state space model is introduced to accurately capture long-range dependencies between image pixels with its spatial modeling capability, thus obtaining high-quality feature representation. Thirdly, a Dynamic Sorting-aware Decoder is adopted to embed a dynamic scoring module and a query-sorting module in adjacent decoder layers, enabling the model to focus on high-confidence predictions. Finally, the classification- and localization-oriented loss and matching cost are introduced to improve target localization accuracy. The experimental results on the road garbage dataset show that the RGD-DETR model improves detection accuracy (mAP) by 1.8% compared with the original RT-DETR, performing well for small targets and in occlusion scenarios. Full article

► Show Figures

Figure 1

19 pages, 8306 KiB

Open AccessArticle

Plant Sam Gaussian Reconstruction (PSGR): A High-Precision and Accelerated Strategy for Plant 3D Reconstruction

by Jinlong Chen, Yingjie Jiao, Fuqiang Jin, Xingguo Qin, Yi Ning, Minghao Yang and Yongsong Zhan

Electronics 2025, 14(11), 2291; https://doi.org/10.3390/electronics14112291 - 4 Jun 2025

Viewed by 220

Abstract

Plant 3D reconstruction plays a critical role in precision agriculture and plant growth monitoring, yet it faces challenges such as complex background interference, difficulties in capturing intricate plant structures, and a slow reconstruction speed. In this study, we propose PlantSamGaussianReconstruction (PSGR), a novel [...] Read more.

Plant 3D reconstruction plays a critical role in precision agriculture and plant growth monitoring, yet it faces challenges such as complex background interference, difficulties in capturing intricate plant structures, and a slow reconstruction speed. In this study, we propose PlantSamGaussianReconstruction (PSGR), a novel method that integrates Grounding SAM with 3D Gaussian Splatting (3DGS) techniques. PSGR employs Grounding DINO and SAM for accurate plant–background segmentation, utilizes algorithms such as Scale-Invariant Feature Transform (SIFT) for camera pose estimation and sparse point cloud generation, and leverages 3DGS for plant reconstruction. Furthermore, a 3D–2D projection-guided optimization strategy is introduced to enhance segmentation precision. The experimental results of various multi-view plant image datasets demonstrate that PSGR effectively removes background noise under diverse environments, accurately captures plant details, and achieves peak signal-to-noise ratio (PSNR) values exceeding 30 in most scenarios, outperforming the original 3DGS approach. Moreover, PSGR reduces training time by up to 26.9%, significantly improving reconstruction efficiency. These results suggest that PSGR is an efficient, scalable, and high-precision solution for plant modeling. Full article

► Show Figures

Figure 1

19 pages, 713 KiB

Open AccessArticle

LLM-Assisted Reinforcement Learning for U-Shaped and Circular Hybrid Disassembly Line Balancing in IoT-Enabled Smart Manufacturing

by Xiwang Guo, Chi Jiao, Jiacun Wang, Shujin Qin, Bin Hu, Liang Qi, Xianming Lang and Zhiwei Zhang

Electronics 2025, 14(11), 2290; https://doi.org/10.3390/electronics14112290 - 4 Jun 2025

Viewed by 226

Abstract

With the sharp increase in the number of products and the development of the remanufacturing industry, disassembly lines have become the mainstream recycling method. In view of the insufficient research on the layout of multi-form disassembly lines and human factors, we previously proposed [...] Read more.

With the sharp increase in the number of products and the development of the remanufacturing industry, disassembly lines have become the mainstream recycling method. In view of the insufficient research on the layout of multi-form disassembly lines and human factors, we previously proposed a linear-U-shaped hybrid layout considering the constraints of employee posture and a Duel-DQN algorithm assisted by Large Language Model (LLM). However, there is still room for improvement in the utilization efficiency of workstations. Based on this previous work, this study proposes an innovative layout of U-shaped and circular disassembly lines and retains the constraints of employee posture. The LLM is instruction-fine-tuned using the Quantized Low-Rank Adaptation (QLoRA) technique to improve the accuracy of disassembly sequence generation, and the Dueling Deep Q-Network(Duel-DQN) algorithm is reconstructed to maximize profits under posture constraints. Experiments show that in the more complex layout of U-shaped and circular disassembly lines, the iterative efficiency of this method can still be increased by about 26% compared with the traditional Duel-DQN, and the profit is close to the optimal solution of the traditional CPLEX solver, verifying the feasibility of this algorithm in complex scenarios. This study further optimizes the layout problem of multi-form disassembly lines and provides an innovative solution that takes into account both human factors and computational efficiency, which has important theoretical and practical significance. Full article

(This article belongs to the Special Issue Cybersecurity and Privacy in Internet-of-Things: Advances, Challenges, and Emerging Trends)

► Show Figures

Figure 1

22 pages, 1118 KiB

Open AccessArticle

Concatenation Augmentation for Improving Deep Learning Models in Finance NLP with Scarce Data

by César Vaca, Jesús-Ángel Román-Gallego, Verónica Barroso-García, Fernando Tejerina and Benjamín Sahelices

Electronics 2025, 14(11), 2289; https://doi.org/10.3390/electronics14112289 - 4 Jun 2025

Viewed by 249

Abstract

Nowadays, financial institutions increasingly leverage artificial intelligence to enhance decision-making and optimize investment strategies. A specific application is the automatic analysis of large volumes of unstructured textual data to extract relevant information through deep learning (DL) methods. However, the effectiveness of these methods [...] Read more.

Nowadays, financial institutions increasingly leverage artificial intelligence to enhance decision-making and optimize investment strategies. A specific application is the automatic analysis of large volumes of unstructured textual data to extract relevant information through deep learning (DL) methods. However, the effectiveness of these methods is often limited by the scarcity of high-quality labeled data. To address this, we propose a new data augmentation technique, Concatenation Augmentation (CA). This is designed to overcome the challenges of processing unstructured text, particularly in analyzing professional profiles from corporate governance reports. Based on Mixup and Label Smoothing Regularization principles, CA generates new text samples by concatenating inputs and applying a convex additive operator, preserving its spatial and semantic coherence. Our proposal achieved hit rates between 92.4% and 99.7%, significantly outperforming other data augmentation techniques. CA improved the precision and robustness of the DL models used for extracting critical information from corporate reports. This technique offers easy integration into existing models and incurs low computational costs. Its efficiency facilitates rapid model adaptation to new data and enhances overall precision. Hence, CA would be a potential and valuable data augmentation tool for boosting DL model performance and efficiency in analyzing financial and governance textual data. Full article

(This article belongs to the Collection Collaborative Artificial Systems)

► Show Figures

Figure 1

16 pages, 4344 KiB

Open AccessArticle

Ion-Induced Charge and Single-Event Burnout in Silicon Power UMOSFETs

by Saulo G. Alberton, Vitor A. P. Aguiar, Nemitala Added, Alexis C. Vilas-Bôas, Marcilei A. Guazzelli, Jeffery Wyss, Luca Silvestrin, Serena Mattiazzo, Matheus S. Pereira, Saulo Finco, Alessandro Paccagnella and Nilberto H. Medina

Electronics 2025, 14(11), 2288; https://doi.org/10.3390/electronics14112288 - 4 Jun 2025

Viewed by 207

Abstract

The U-shaped Metal-Oxide-Semiconductor Field-Effect Transistor (UMOS or trench FET) is one of the most widely used semiconductor power devices worldwide, increasingly replacing the traditional vertical double-diffused MOSFET (DMOSFET) in various applications due to its superior electrical performance. However, a detailed experimental comparison of [...] Read more.

The U-shaped Metal-Oxide-Semiconductor Field-Effect Transistor (UMOS or trench FET) is one of the most widely used semiconductor power devices worldwide, increasingly replacing the traditional vertical double-diffused MOSFET (DMOSFET) in various applications due to its superior electrical performance. However, a detailed experimental comparison of ion-induced Single-Event Burnout (SEB) in similarly rated silicon (Si) UMOS and DMOS devices remains lacking. This study presents a comprehensive experimental comparison of ion-induced charge collection mechanisms and SEB susceptibility in similarly rated Si UMOS and DMOS devices. Charge collection mechanisms due to alpha particles from ²⁴¹Am radiation source are analyzed, and SEB cross sections induced by heavy ions from particle accelerators are directly compared. The implications of the unique gate structure of Si UMOSFETs on their reliability in harsh radiation environments are discussed based on technology computer-aided design (TCAD) simulations. Full article

(This article belongs to the Special Issue Single-Event Effects: Modeling, Prediction, Testing and Radiation Hardening)

► Show Figures

Figure 1

28 pages, 4113 KiB

Open AccessArticle

Building Electricity Prediction Using BILSTM-RF-XGBOOST Hybrid Model with Improved Hyperparameters Based on Bayesian Algorithm

by Yuqing Liu, Binbin Li and Hejun Liang

Electronics 2025, 14(11), 2287; https://doi.org/10.3390/electronics14112287 - 4 Jun 2025

Viewed by 262

Abstract

Accurate building energy consumption prediction is essential for efficient energy management and energy optimization. This study utilizes bidirectional long short-term memory (BiLSTM) to automatically extract deep time series features. The nonlinear fitting and high-precision prediction capabilities of Random Forest (RF) and XGBoost models [...] Read more.

Accurate building energy consumption prediction is essential for efficient energy management and energy optimization. This study utilizes bidirectional long short-term memory (BiLSTM) to automatically extract deep time series features. The nonlinear fitting and high-precision prediction capabilities of Random Forest (RF) and XGBoost models are then utilized to develop a BiLSTM-RF-XGBoost stacked hybrid model. To enhance model generalization and reduce overfitting, a Bayesian algorithm with an early stopping mechanism is utilized to fine-tune hyperparameters, and strict K-fold time series cross-validation (TSCV) is implemented for performance evaluation. The hybrid model achieves a high TSCV average R² value of 0.989 during cross-validation. When evaluated on an independent test set, it yields a mean square error (MSE) of 0.00003, a root mean square error (RMSE) of 0.00548, a mean absolute error (MAE) of 0.00130, and a mean absolute percentage error (MAPE) of 0.26%. These values are significantly lower than those of comparison models, indicating a significant improvement in predictive performance. The study offers insights into the internal decision-making of the model through SHAP (SHapley Additive exPlanations) feature significance analysis, revealing the key roles of temperature and power lag features, and validating that the stacked model effectively utilizes the outputs of base models as meta-features. This study makes contributions by proposing a novel hybrid model trained with Bayesian optimization, analyzing the influence of various feature factors, and providing innovative technological solutions for building energy consumption prediction. It also provides theoretical value and guidance for low-carbon building energy management and application. Full article

► Show Figures

Graphical abstract

15 pages, 9452 KiB

Open AccessArticle

Thermal Fatigue Behaviors of BGA Packages with an Optimized Solder Joint Layout

by Mohammed Abdel Razzaq, Michael Meilunas, Xian A. Cao, Jim Wilcox and Abdallah Ramini

Electronics 2025, 14(11), 2286; https://doi.org/10.3390/electronics14112286 - 4 Jun 2025

Viewed by 272

Abstract

Ball Grid Array (BGA) failures are often dominated by stress concentrations at the outer solder joints, particularly under thermomechanical loading. To mitigate this issue, this study investigates the mechanical and reliability implications of optimizing the BGA solder joint array by removing the outermost [...] Read more.

Ball Grid Array (BGA) failures are often dominated by stress concentrations at the outer solder joints, particularly under thermomechanical loading. To mitigate this issue, this study investigates the mechanical and reliability implications of optimizing the BGA solder joint array by removing the outermost rows and columns, positioning all connections directly beneath the silicon die. Two commonly used solder alloys—SAC305 and Sn37Pb—were selected to evaluate the effects of this optimized array design. A combined experimental and numerical approach was employed, including accelerated thermal cycling (–40 °C to 125 °C), in situ resistance monitoring, cross-sectional failure analysis, and finite element modeling (FEM) to assess fatigue behavior under the altered layout. The optimized array significantly improved performance for SAC305, yielding a 1.67× increase in mean cycles-to-failure and a 29% reduction in peak von Mises stress, with failure locations shifting from the corners to more evenly distributed areas beneath the die. Sn37Pb assemblies showed only a 1.01× improvement despite an 11% stress reduction, attributed to persistent shear-dominated failures at second-row joints. These results highlight the critical influence of joint array architecture and solder alloy selection on reliability, offering design-level guidance for applications prioritizing thermomechanical robustness with reduced I/O counts. Full article

(This article belongs to the Section Electronic Materials, Devices and Applications)

► Show Figures

Figure 1

12 pages, 458 KiB

Open AccessArticle

Adversarial Robustness in Cognitive Systems: A Trustworthiness Assessment Perspective for 6G Networks

by Ilias Alexandropoulos, Harilaos Koumaras, Vasiliki Rentoula, Gerasimos Papanikolaou-Ntais, Spyridon Georgoulas and George Makropoulos

Electronics 2025, 14(11), 2285; https://doi.org/10.3390/electronics14112285 - 4 Jun 2025

Viewed by 208

Abstract

As B5G systems are evolving toward 6G, their coordination increasingly relies on AI-driven automation and orchestration actions, a process that is characterized as cognition. Therefore, a 6G system, through this cognitive process, acts as an intent-handling entity that comprehends sophisticated intent semantics from [...] Read more.

As B5G systems are evolving toward 6G, their coordination increasingly relies on AI-driven automation and orchestration actions, a process that is characterized as cognition. Therefore, a 6G system, through this cognitive process, acts as an intent-handling entity that comprehends sophisticated intent semantics from the users/tenants and calculates the ideal goal state for the specific intent, organizing the necessary adaptation actions that are needed for the transition of the system into that state. However, the use of cognitive-driven AI models to coordinate the purposes of a 6G system creates new risks, as a new surface of attack is born, where the whole 6G system operation may be maliciously affected by adversarial attacks within the user-intents. Focusing on this challenge, this paper realizes a prototype cognitive coordinator for 6G trustworthiness provision and investigates its adversarial robustness for different BERT-based quantification models, which are used for realizing the 6G cognitive system. Full article

(This article belongs to the Special Issue Recent Advances and Challenges in IoT, Cloud and Edge Coexistence)

► Show Figures

Figure 1

19 pages, 462 KiB

Open AccessArticle

Large Language Models for C Test Case Generation: A Comparative Analysis

by Alexandru Guzu, Georgian Nicolae, Horia Cucu and Corneliu Burileanu

Electronics 2025, 14(11), 2284; https://doi.org/10.3390/electronics14112284 - 4 Jun 2025

Viewed by 276

Abstract

Software testing is a crucial yet time-consuming aspect of software development. Writing comprehensive unit tests that accurately verify whether a function or an entire program behaves as intended requires considerable effort from developers, particularly when handling numerous edge cases. This study explores how [...] Read more.

Software testing is a crucial yet time-consuming aspect of software development. Writing comprehensive unit tests that accurately verify whether a function or an entire program behaves as intended requires considerable effort from developers, particularly when handling numerous edge cases. This study explores how Large Language Models (LLMs) can streamline this process by automatically generating effective unit tests. We evaluate various LLMs on their capability to interpret problem specifications, analyze source code across multiple programming languages, and generate suitable test cases. The effectiveness of these test cases is assessed using the Pass@1 and line coverage metrics. Our findings reveal that LLMs perform significantly better when provided with both the problem description and the corresponding solution code, particularly in the C programming language. Additionally, we observe substantial performance improvements when example test cases are included in the prompt, leading to higher Pass@1 scores and enhanced code coverage, particularly with more advanced LLMs. Full article

(This article belongs to the Special Issue Role of Artificial Intelligence in Natural Language Processing)

► Show Figures

Figure 1

21 pages, 2333 KiB

Open AccessArticle

Human-Centric Depth Estimation: A Hybrid Approach with Minimal Data

by Yuhyun Kim, Heejin Ahn, Taeseop Kim, Byungtae Ahn and Dong-Geol Choi

Electronics 2025, 14(11), 2283; https://doi.org/10.3390/electronics14112283 - 4 Jun 2025

Viewed by 256

Abstract

This study presents a novel system for accurate camera-to-person distance estimation in CCTV environments. To address the limitations of existing approaches—which often require extensive training data and lack object-level precision—we propose a hybrid framework that integrates SAM’s zero-shot segmentation with monocular depth estimation. [...] Read more.

This study presents a novel system for accurate camera-to-person distance estimation in CCTV environments. To address the limitations of existing approaches—which often require extensive training data and lack object-level precision—we propose a hybrid framework that integrates SAM’s zero-shot segmentation with monocular depth estimation. Our method isolates human subjects from complex backgrounds and incorporates Kernel Density Estimation (KDE), log-space learning, and linear residual blocks to improve prediction accuracy. This approach is designed to resolve the non-linear mapping between visual features and metric distances. Evaluations on a custom dataset demonstrate a mean absolute error (MAE) of 0.65 m on 1612 test images, using only 30 training samples. Notably, the use of SAM for fine-grained segmentation significantly outperforms conventional bounding box methods, reducing the MAE from 0.82 m to 0.65 m. The proposed system offers immediate applicability to security surveillance and disaster response scenarios, with its minimal data requirements enhancing its practical deployability. Full article

(This article belongs to the Collection Computer Vision and Pattern Recognition Techniques)

► Show Figures

Figure 1

20 pages, 1556 KiB

Open AccessArticle

Resilient Predefined-Time Flocking of Networked Agent Systems Against False Data Injection Attacks

by Boxian Lin, Meng Li, Yiru Liu, Zhiqiang Li, Kaiyu Qin and Mengji Shi

Electronics 2025, 14(11), 2282; https://doi.org/10.3390/electronics14112282 - 3 Jun 2025

Viewed by 170

Abstract

Flocking control in networked agent systems (NASs) has been extensively studied, yet many existing methods overlook two critical issues: the need for fast, predictable convergence, and resilience against false data injection (FDI) attacks. To tackle these challenges, this paper proposes a secure predefined-time [...] Read more.

Flocking control in networked agent systems (NASs) has been extensively studied, yet many existing methods overlook two critical issues: the need for fast, predictable convergence, and resilience against false data injection (FDI) attacks. To tackle these challenges, this paper proposes a secure predefined-time quasi-flocking control scheme leveraging neural networks. First, a predefined-time control protocol is formulated via a time-varying scaling function, which ensures that all agents achieve quasi-flocking behavior within a prescribed time, independent of their initial conditions. This design guarantees rapid and predictable convergence. Second, radial basis function (RBF) neural networks are employed to estimate the unknown disturbances induced by FDI attacks. A novel adaptive update law is developed to dynamically compensate for these uncertainties in real-time. Lyapunov-based analysis rigorously proves that the proposed control strategy achieves predefined-time quasi-flocking while preserving robustness against adversarial attacks. Finally, extensive simulation results demonstrate that the proposed approach ensures rapid convergence and robust performance in flocking control. Full article

► Show Figures

Figure 1

22 pages, 939 KiB

Open AccessArticle

Using Clustering Techniques to Design Learner Personas for GenAI Prompt Engineering and Adaptive Interventions

by Ivan Tudor, Martina Holenko Dlab, Gordan Đurović and Marko Horvat

Electronics 2025, 14(11), 2281; https://doi.org/10.3390/electronics14112281 - 3 Jun 2025

Viewed by 190

Abstract

Personalized learning in higher education aims to enhance student motivation, engagement, and academic outcomes. Learner personas as representations of students offer a promising approach to personalizing learning in technology-enhanced environments, particularly in combination with learning analytics (LA). This study explores how LA can [...] Read more.

Personalized learning in higher education aims to enhance student motivation, engagement, and academic outcomes. Learner personas as representations of students offer a promising approach to personalizing learning in technology-enhanced environments, particularly in combination with learning analytics (LA). This study explores how LA can be used to identify activity patterns based on data from the E-Learning Activities Recommender System (ELARS). The activity data of STEM students (N = 90) were analyzed using K-Means clustering. The analyses were based on timing, the percentage of task completion, and their combination to identify distinct engagement patterns. Based on these, six clusters (learner personas) were identified: consistent performers, overachievers, last-minute underperformers, low-engagement students, late moderate achievers, and early proactive performers. For each persona, GenAI prompts and personalized interventions based on motivational and instructional frameworks were proposed. These will inform further development of the ELARS system, with the goal of enabling personalization, promoting self-regulated learning, and encouraging students to integrate GenAI tools into their learning. The study shows how the combination of clustering techniques for learner persona development with GenAI prompt engineering and adaptive interventions has the potential to drive the design of personalized learning environments. Full article

(This article belongs to the Special Issue Techniques and Applications in Prompt Engineering and Generative AI)

► Show Figures

Figure 1

15 pages, 1900 KiB

Open AccessArticle

Research on Model Prediction of Remaining Service Life of Lithium-Ion Batteries Based on Chaotic Time Series

by Tongrui Zhang and Hao Sun

Electronics 2025, 14(11), 2280; https://doi.org/10.3390/electronics14112280 - 3 Jun 2025

Viewed by 191

Abstract

To address the conflicting demands of the energy crisis, environmental pollution, and economic growth, the electric vehicle (EV) industry has expanded rapidly, facilitating the widespread adoption of power batteries. This paper investigates the use of chaos theory and machine learning for predicting the [...] Read more.

To address the conflicting demands of the energy crisis, environmental pollution, and economic growth, the electric vehicle (EV) industry has expanded rapidly, facilitating the widespread adoption of power batteries. This paper investigates the use of chaos theory and machine learning for predicting the remaining useful life (RUL) of lithium-ion batteries. Firstly, the mutual information method determines the time delay of the monitoring sequence, while the improved false nearest neighbor method (Cao algorithm) establishes the embedding dimension, yielding the phase space reconstruction parameters. Secondly, the maximum Lyapunov exponent identifies the chaotic properties of the capacity decay time series, and a prediction dataset is constructed based on phase space reconstruction theory. Finally, leveraging the chaotic time-series features, a support vector machine (SVM) model is developed for lithium-ion battery RUL prediction. The algorithm is subsequently validated through simulation using the NASA battery dataset. The results demonstrate that the proposed method achieves high predictive accuracy and stability, providing reliable RUL estimates for the battery management system (BMS). Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 14, Issue 11 (June-1 2025) – 214 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI