Previous Issue
Volume 14, June-1
 
 

Electronics, Volume 14, Issue 12 (June-2 2025) – 21 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
16 pages, 996 KiB  
Article
An Arduino-Based, Portable Weather Monitoring System, Remotely Usable Through the Mobile Telephony Network
by Ioannis Michailidis, Petros Mountzouris, Panagiotis Triantis, Gerasimos Pagiatakis, Andreas Papadakis and Leonidas Dritsas
Electronics 2025, 14(12), 2330; https://doi.org/10.3390/electronics14122330 - 6 Jun 2025
Abstract
The article describes an Arduino-based, portable, remotely usable weather monitoring station capable of measuring temperature, relative humidity, pressure, and carbon monoxide (CO) concentration and transmitting the collected data to the Cloud through the mobile telephony network. The main modules of the station are [...] Read more.
The article describes an Arduino-based, portable, remotely usable weather monitoring station capable of measuring temperature, relative humidity, pressure, and carbon monoxide (CO) concentration and transmitting the collected data to the Cloud through the mobile telephony network. The main modules of the station are as follows: a DHT11 sensor for temperature and relative humidity sensing, a BMP180 sensor for pressure monitoring (with temperature compensation), a MQ7 sensor for the monitoring of the CO concentration, an Arduino Uno board, a GSM SIM900 module, and a buzzer, which is activated when the temperature exceeds 35 °C. The station operates as follows: the Arduino Uno board gathers the data collected by the sensors and, by means of the GSM SIM900 module, it transmits the data to the Cloud by using the mobile telephony network as well as the ThingSpeak software which is an open-code IoT application that, among others, enables saving and recovering of sensing and monitoring data. The main novelty of this work is the combined use of the GSM network and the Cloud which enhances the portability and usability of the proposed system and enables remote collection of data in a straightforward way. Additional merits of the system are the easiness and the low cost of its development (owing to the easily available, low-cost hardware combined with an open-code software) as well as its modularity and scalability which allows its customization depending on specific application it is intended for. The system could be used for real-time, remote monitoring of essential environmental parameters in spaces such as farms, warehouses, rooms etc. Full article
36 pages, 6049 KiB  
Article
Machine Learning Innovations in Renewable Energy Systems with Integrated NRBO-TXAD for Enhanced Wind Speed Forecasting Accuracy
by Zhiwen Hou, Jingrui Liu, Ziqiu Shao, Qixiang Ma and Wanchuan Liu
Electronics 2025, 14(12), 2329; https://doi.org/10.3390/electronics14122329 - 6 Jun 2025
Abstract
In the realm of renewable energy, harnessing wind power efficiently is crucial for establishing a low-carbon power system. However, the intermittent and uncertain nature of wind speed poses significant challenges for accurate prediction, which is essential for effective grid integration and dispatch management. [...] Read more.
In the realm of renewable energy, harnessing wind power efficiently is crucial for establishing a low-carbon power system. However, the intermittent and uncertain nature of wind speed poses significant challenges for accurate prediction, which is essential for effective grid integration and dispatch management. To address this challenge, this paper introduces a novel hybrid model, NRBO-TXAD, which integrates a Newton–Raphson-based optimizer (NRBO) with a Transformer and XGBoost, further enhanced by adaptive denoising techniques. The interquartile range–adaptive moving average filter (IQR-AMAF) method is employed to preprocess the data by removing outliers and smoothing the data, thereby improving the quality of the input. The NRBO efficiently optimizes the hyperparameters of the Transformer, thereby enhancing its learning performance. Meanwhile, XGBoost is utilized to compensate for any residual prediction errors. The effectiveness of the proposed model was validated using two real-world wind speed datasets. Among eight models, including LSTM, Informer, and hybrid baselines, NRBO-TXAD demonstrated superior performance. Specifically, for Case 1, NRBO-TXAD achieved a mean absolute percentage error (MAPE) of 11.24% and a root mean square error (RMSE) of 0.2551. For Case 2, the MAPE was 4.90%, and the RMSE was 0.2976. Under single-step forecasting, the MAPE for Case 2 was as low as 2.32%. Moreover, the model exhibited remarkable robustness across multiple time steps. These results confirm the model’s effectiveness in capturing wind speed fluctuations and long-range dependencies, making it a reliable solution for short-term wind forecasting. This research not only contributes to the field of signal analysis and machine learning but also highlights the potential of hybrid models in addressing complex prediction tasks within the context of artificial intelligence. Full article
18 pages, 1055 KiB  
Article
Privacy-Preserving and Interpretable Grade Prediction: A Differential Privacy Integrated TabNet Framework
by Yuqi Zhao, Jinheng Wang, Xiaoqing Tan, Linyan Wen, Qingru Gao and Wenjing Wang
Electronics 2025, 14(12), 2328; https://doi.org/10.3390/electronics14122328 - 6 Jun 2025
Abstract
The increasing digitization of educational data poses critical challenges in balancing predictive accuracy with privacy protection for sensitive student information. This study introduces DP-TabNet, a pioneering framework that integrates the interpretable deep learning architecture of TabNet with differential privacy (DP) techniques to enable [...] Read more.
The increasing digitization of educational data poses critical challenges in balancing predictive accuracy with privacy protection for sensitive student information. This study introduces DP-TabNet, a pioneering framework that integrates the interpretable deep learning architecture of TabNet with differential privacy (DP) techniques to enable secure and effective student grade prediction. By incorporating the Laplace Mechanism with a carefully calibrated privacy budget (ϵ = 0.7) and sensitivity (Δf = 0.1), DP-TabNet ensures robust protection of individual data while maintaining analytical utility. Experimental results on real-world educational datasets demonstrate that DP-TabNet achieves an accuracy of 80%, only 4% lower than the non-private TabNet model (84%), and outperforms privacy-preserving baselines such as DP-Random Forest (78%), DP-XGBoost (78%), DP-MLP (69%), and DP-SGD (69%). Furthermore, its interpretable feature importance analysis highlights key predictors like resource engagement and attendance metrics, offering actionable insights for educators under strict privacy constraints. This work advances privacy-preserving educational technology by demonstrating that high predictive performance and strong privacy guarantees can coexist, providing a practical and responsible framework for educational data analytics. Full article
Show Figures

Figure 1

20 pages, 13952 KiB  
Article
MSO-DETR: A Lightweight Detection Transformer Model for Small Object Detection in Maritime Search and Rescue
by Jing Li, Yun Hua and Mei Xue
Electronics 2025, 14(12), 2327; https://doi.org/10.3390/electronics14122327 - 6 Jun 2025
Abstract
In maritime search and rescue small object detection, existing high-accuracy detection models face deployment challenges on UAV platforms due to limited computational capabilities, while existing lightweight models often fail to meet performance requirements, reducing the overall effectiveness of rescue operations. To overcome the [...] Read more.
In maritime search and rescue small object detection, existing high-accuracy detection models face deployment challenges on UAV platforms due to limited computational capabilities, while existing lightweight models often fail to meet performance requirements, reducing the overall effectiveness of rescue operations. To overcome the difficulty of balancing lightweight design and detection accuracy, we propose Maritime Small Object Detection Transformer (MSO-DETR), a lightweight detection transformer model for small object detection in maritime search and rescue, based on an improved Real-Time Detection Transformer (RT-DETR) architecture. MSO-DETR employs StarNet as its backbone to reduce the computational cost with a slight drop in detection accuracy. In addition, the Dynamic-range Histogram Self-Attention (DHSA) mechanism is integrated with the Attention-based Intra-scale Feature Interaction (AIFI) module to construct DHAIFI, which enhances the model’s ability to perceive object features under challenging conditions such as sea surface reflections and wave interference. During the feature fusion phase, we propose the Scale-Tuned Enhanced Feature Fusion (STEFF) module, which integrates the improved Attentional Scale Sequence Fusion (ASF) structure with the newly designed Multi-Dilated Convolution Cross-Stage Partial (MDC_CSP) and Parallel Aggregation Downsampling (PAD) to enhance multi-scale aggregation and small object recognition while maintaining computational efficiency. Experimental results demonstrate that, in contrast to the baseline, MSO-DETR achieves significant model lightweighting, reducing parameters by 67.3% and GFLOPs by 46.5%, while maintaining detection accuracy on the SeaDronesSee dataset, with only a 0.1% decrease in mAP50 and a 0.5% improvement in mAP50:95. It also delivers comparable performance to the baseline on the AFO dataset. Full article
Show Figures

Figure 1

22 pages, 1657 KiB  
Article
Wind Power Prediction Using a Dynamic Neuro-Fuzzy Model
by George Kandilogiannakis, Paris Mastorocostas, Athanasios Voulodimos, Constantinos Hilas and Dimitrios Varsamis
Electronics 2025, 14(12), 2326; https://doi.org/10.3390/electronics14122326 - 6 Jun 2025
Abstract
A Dynamic Neuro-fuzzy Model (Dynamic Neuro-fuzzy Wind Predictor, DNFWP) is proposed for wind power prediction. The fuzzy rules in DNFWP consist of a typical antecedent part with static inputs, while the consequent part is a small three-layer neural network, incorporating unit feedback connections [...] Read more.
A Dynamic Neuro-fuzzy Model (Dynamic Neuro-fuzzy Wind Predictor, DNFWP) is proposed for wind power prediction. The fuzzy rules in DNFWP consist of a typical antecedent part with static inputs, while the consequent part is a small three-layer neural network, incorporating unit feedback connections at the outputs of the neurons of the hidden layer. The inclusion of internal feedback targets to capture the intrinsic temporal relations of the dataset, while maintaining the local modeling approach of traditional fuzzy models. Each rule in DNFWP represents a local model, and the fuzzy rules operate cooperatively through the defuzzification process. The fuzzy rule base is extracted employing the Fuzzy C-means clustering algorithm, and the consequent neural networks’ weights are tuned by the use of Dynamic Resilient Propagation. Two cases with datasets of different volumes are tested and the performance of DNFWP is very promising, according to the results attained using a series of metrics like Root Mean Squared Error, Mean Absolute Error, and the r-squared statistic. The dynamic nature of the predictor allows it to operate effectively with a single input, thus rendering a feature selection phase unnecessary. DNFWP is compared to Machine Learning-based and Deep Learning-based counterparts, such that its prediction capabilities along with its reduced parametric complexity are highlighted. Full article
Show Figures

Figure 1

20 pages, 1653 KiB  
Article
Reconfigurable Wideband Bandpass Filter Using Stepped Impedance Resonator Based on Liquid Crystals
by Jin-Young Choi, Jun-Seok Ma and Wook-Sung Kim
Electronics 2025, 14(12), 2325; https://doi.org/10.3390/electronics14122325 - 6 Jun 2025
Abstract
In this paper, a capacitively coupled-fed reconfigurable wideband bandpass filter (BPF) is proposed based on liquid crystal (LC) technology, which achieved three transmission poles across varying bias voltages (VB). An open-ended stepped impedance resonator configuration enables multi-mode resonance, offering significantly [...] Read more.
In this paper, a capacitively coupled-fed reconfigurable wideband bandpass filter (BPF) is proposed based on liquid crystal (LC) technology, which achieved three transmission poles across varying bias voltages (VB). An open-ended stepped impedance resonator configuration enables multi-mode resonance, offering significantly wider bandwidth compared to uniform-impedance resonators. The fractional bandwidth (FBW) and transmission pole positions are determined by the impedance ratio of the two resonators, allowing the filter to meet specific design requirements. An analytical methodology employing multilayer transmission line formulations and resonant frequency ratios was used to predict the modal stability of transmission poles under dielectric constant variation, which was subsequently validated through simulation. Experimental results show that the center frequency can be adjusted from 10.76 to 9.47 GHz with a maximum VB of 30 V, achieving a tuning range of 12.71%. The normalized 3 dB FBW exceeds 64.66%, and the return loss remains above 10 dB from 0 to 30 V, offering the widest FBW among the reported LC BPFs without pole merging or mode collapse. The frequency response of the fabricated filter shows good agreement with the simulation results. Full article
(This article belongs to the Section Electronic Materials, Devices and Applications)
23 pages, 10395 KiB  
Article
Data-Driven Estimation of End-to-End Delay Probability Density Function for Time-Sensitive WiFi Networks
by Jianyu Cao, Yujun Dai, Shuping Huang and Minghe Zhang
Electronics 2025, 14(12), 2324; https://doi.org/10.3390/electronics14122324 - 6 Jun 2025
Abstract
Time-sensitive applications require the End-to-End (E2E) delay of wireless networks to be deterministic. For example, control signals in industrial automation, intelligent transportation, and telemedicine must be transmitted to their destinations within the millisecond range, with delay jitter controlled within the microsecond range. To [...] Read more.
Time-sensitive applications require the End-to-End (E2E) delay of wireless networks to be deterministic. For example, control signals in industrial automation, intelligent transportation, and telemedicine must be transmitted to their destinations within the millisecond range, with delay jitter controlled within the microsecond range. To formulate effective policies for maintaining E2E delay within a small deterministic range, it is essential to estimate the probability density function (PDF) of E2E delay. Data-driven methods based on mixture density networks have been employed to estimate the PDF of E2E delay in wireless networks. However, in WiFi networks, the estimation results produced by existing methods exhibit significant discrepancies and fluctuations when compared to actual measurements. Motivated by this, an improved estimation method is proposed, where the delay PDF is divided into three segments with different functional expressions that are coupled together. Moreover, the parameter estimation process is implemented in two stages. First, the two division thresholds for the three segments of the PDF are calculated based on the variation trend of E2E delay measurements. Second, the remaining parameters are obtained through training using an improved mixture density network. Experimental results indicate that the E2E delay PDF obtained by the proposed method exhibits a smaller gap compared to actual measurements than existing methods. Specifically, the mean absolute errors and average fluctuation amplitudes of tail probabilities at certain delay values decrease by at least one order of magnitude. Moreover, the multiple-segmentation feature of the proposed method enhances its robustness in situations where measurement data are affected by low levels of Gaussian noise. Full article
Show Figures

Figure 1

14 pages, 2408 KiB  
Article
Backpack Client Selection Keeping Swarm Learning in Industrial Digital Twins for Wireless Mapping
by Xingjia Wei, Ning Su, Yikai Guo and Pengcheng Zhao
Electronics 2025, 14(12), 2323; https://doi.org/10.3390/electronics14122323 - 6 Jun 2025
Abstract
Digital twin virtual–real mapping and precise modeling require the synchronization of large amounts of data, which leads to high communication overhead in wireless channels in industrial Internet of Things (IoT). To solve this problem, this study proposes an architecture of Digital Twin–Swarm learning [...] Read more.
Digital twin virtual–real mapping and precise modeling require the synchronization of large amounts of data, which leads to high communication overhead in wireless channels in industrial Internet of Things (IoT). To solve this problem, this study proposes an architecture of Digital Twin–Swarm learning (DT-SL) for industrial IoT digital twins. SL is an emerging distributed federated learning (FL) method that eliminates the need for centralized servers completely. However, it faces the problem of wireless channel congestion caused by high concurrent parameter transmission. In view of the above architecture, a novel KSL scheme based on the backpack model is used to construct the DT model. The backpack optimization problem is used to select the client with the largest contribution to participate in Keeping SL twin modeling. In addition, the experimental results evaluated the performance of the proposed method. The absolute value of the client’s updated parameter quantity decreased by 23.6% on average. The convergence rate of the aggregation model increased by 34.1%, and the model aggregation MSE value decreased to 0.03. Full article
Show Figures

Graphical abstract

14 pages, 4931 KiB  
Article
State-of-the-Art VCO with Eight-Shaped Resonator-Type Transmission Line
by Sheng-Lyang Jang, Zi-Jun Lin and Miin-Horng Juang
Electronics 2025, 14(12), 2322; https://doi.org/10.3390/electronics14122322 - 6 Jun 2025
Abstract
A closed-loop transmission line (TL) coupled to an LCR resonator is used in this study for a fully-integrated CMOS rotary traveling wave oscillator (RTWO) based on the rotary traveling wave principle. A technique for the suppression of magnetic coupling noise is presented with [...] Read more.
A closed-loop transmission line (TL) coupled to an LCR resonator is used in this study for a fully-integrated CMOS rotary traveling wave oscillator (RTWO) based on the rotary traveling wave principle. A technique for the suppression of magnetic coupling noise is presented with eight-shaped inductors. The design and measurement of an 8.53 GHz oscillator in the TSMC 0.18 μm CMOS technology are discussed. The fully-integrated chip occupies a die area of 1.2 × 1.2 mm2. The oscillator consists of four sub-oscillators and uses four 1:1 symmetric twisted transformers, with the secondary inductors connected to form a twisted closed-loop transmission line for coupling the sub-oscillators. The transformers are configured as eight-shaped structures to minimize the far-field magnetic field radiation from each transformer and the whole transformer. At a supply voltage of 1.7 V, the power consumption is 5.84 mW. The free-running oscillation frequency of the RTWO is tunable from 8.53 GHz to 10.0 GHz. The measured phase noise at a 1 MHz frequency offset is −122.4 dBc/Hz at an oscillation frequency of 8.53 GHz, and the figure of merit (FOM) of the proposed VCO with a specific inductor layout is −193.4 dBc/Hz, surpassing other similar RTWOs. The FOM with a tuning range (FOMT) is −195.96 dBc/Hz. Full article
(This article belongs to the Special Issue Advances in Frontend Electronics for Millimeter-Wave Systems)
Show Figures

Figure 1

26 pages, 19159 KiB  
Article
Development of a Pipeline-Cleaning Robot for Heat-Exchanger Tubes
by Qianwen Liu, Canlin Li, Guangfei Wang, Lijuan Li, Jinrong Wang, Jianping Tan and Yuxiang Wu
Electronics 2025, 14(12), 2321; https://doi.org/10.3390/electronics14122321 - 6 Jun 2025
Abstract
Cleaning operations in narrow pipelines are often hindered by limited maneuverability and low efficiency, necessitating the development of a high-performance and highly adaptable robotic solution. To address this challenge, this study proposes a pipeline-cleaning robot specifically designed for the heat-exchange tubes of industrial [...] Read more.
Cleaning operations in narrow pipelines are often hindered by limited maneuverability and low efficiency, necessitating the development of a high-performance and highly adaptable robotic solution. To address this challenge, this study proposes a pipeline-cleaning robot specifically designed for the heat-exchange tubes of industrial heat exchangers. The robot features a dual-wheel cross-drive configuration to enhance motion stability and integrates a gear–rack-based alignment mechanism with a cam-based propulsion system to enable autonomous deployment and cleaning via a flexible arm. The robot adopts a modular architecture with a separated body and cleaning arm, allowing for rapid assembly and maintenance through bolted connections. A vision-guided control system is implemented to support accurate positioning and task scheduling within the primary pipeline. Experimental results demonstrate that the robot can stably execute automatic navigation and sub-pipe cleaning, achieving pipe-switching times of less than 30 s. The system operates reliably and significantly improves cleaning efficiency. The proposed robotic system exhibits strong adaptability and generalizability, offering an effective solution for automated cleaning in confined pipeline environments. Full article
(This article belongs to the Special Issue Intelligent Mobile Robotic Systems: Decision, Planning and Control)
Show Figures

Figure 1

21 pages, 1108 KiB  
Article
Transformer-Based Abstractive Summarization of Legal Texts in Low-Resource Languages
by Salman Masih, Mehdi Hassan, Labiba Gillani Fahad and Bilal Hassan
Electronics 2025, 14(12), 2320; https://doi.org/10.3390/electronics14122320 - 6 Jun 2025
Abstract
The emergence of large language models (LLMs) has revolutionized the trajectory of NLP research. Transformers, combined with attention mechanisms, have increased computational power, and massive datasets have led to the emergence of pre-trained large language models (PLLMs), which offer promising possibilities for multilingual [...] Read more.
The emergence of large language models (LLMs) has revolutionized the trajectory of NLP research. Transformers, combined with attention mechanisms, have increased computational power, and massive datasets have led to the emergence of pre-trained large language models (PLLMs), which offer promising possibilities for multilingual applications in low-resource settings. However, the scarcity of annotated resources and suitably pre-trained models continues to pose a significant hurdle for the low-resource abstractive text summarization of legal texts, particularly in Urdu. This study presents a transfer learning approach using pre-trained multilingual large models (the mBART and mT5, Small, Base, and Large) to generate abstractive summaries of Urdu legal texts. A curated dataset was developed with legal experts, who produced ground-truth summaries. The models were fine-tuned on this domain-specific corpus to adapt them for low-resource legal summarization. The experimental results demonstrated that the mT5-Large, fine-tuned on Urdu legal texts, outperforms all other evaluated models across standard summarization metrics, achieving ROUGE-1 scores of 0.7889, ROUGE-2 scores of 0.5961, and ROUGE-L scores of 0.7813. This indicates its strong capacity to generate fluent, coherent, and legally accurate summaries. The mT5-Base model closely follows with ROUGE-1 = 0.7774, while the mT5-Small shows moderate performance (ROUGE-1 = 0.6406), with reduced fidelity in capturing legal structure. The mBART50 model, despite being fine-tuned on the same legal corpus, performs lower (ROUGE-1 = 0.5914), revealing its relative limitations in this domain. Notably, models trained or fine-tuned on non-legal, out-of-domain data, such as the urT5 (ROUGE-1 = 0.3912), the mT5-XLSUM (ROUGE-1 = 0.0582), and the mBART50 (XLSUM) (ROUGE-1 = 0.0545), exhibit poor generalization to legal summaries, underscoring the necessity of domain adaptation when working in low-resource legal contexts. These findings highlight the effectiveness of fine-tuning multilingual LLMs for domain-specific tasks. The gains in legal summarization demonstrate the practical value of transfer learning in low-resource settings and the broader potential of AI-driven tools for legal document processing, information retrieval, and decision support. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

21 pages, 951 KiB  
Article
Bit Synchronization-Assisted Frequency Correction in Low-SNR Wireless Systems
by Junfeng Gao, Peiji Yang, Shaoxiang Chen, Zhenghua Luo, Yilin Zhang and Tao Liu
Electronics 2025, 14(12), 2319; https://doi.org/10.3390/electronics14122319 - 6 Jun 2025
Abstract
In wireless communication systems, traditional frequency synchronization methods struggle to effectively track carrier frequency in low signal-to-noise ratio (SNR) environments, leading to degraded demodulation performance and severely impacting the stability and reliability of communication systems. To address this challenge, an innovative frequency synchronization [...] Read more.
In wireless communication systems, traditional frequency synchronization methods struggle to effectively track carrier frequency in low signal-to-noise ratio (SNR) environments, leading to degraded demodulation performance and severely impacting the stability and reliability of communication systems. To address this challenge, an innovative frequency synchronization framework is introduced, enhancing frequency synchronization accuracy and robustness in low-SNR environments through bit synchronization techniques. Specifically, the approach constructs a “bit synchronization-frequency synchronization” joint correction mechanism, where clock offset information extracted during the bit synchronization process is utilized to estimate frequency offset. This method enables an indirect measurement and compensation of carrier frequency offset, forming a hierarchical error compensation system. Furthermore, to overcome the limited convergence speed of the classical Gardner algorithm under significant phase offset conditions, an improved error feedback structure is proposed, accelerating bit synchronization convergence and reducing timing synchronization errors, thereby enhancing overall system performance. The effectiveness of the proposed method is validated through theoretical analysis and simulation experiments. Simulation results demonstrate that, compared to conventional frequency synchronization schemes, the proposed method achieves higher frequency correction accuracy in low-SNR scenarios, thereby improving the robustness and anti-interference capability of wireless communication systems in complex environments. Full article
(This article belongs to the Section Microwave and Wireless Communications)
Show Figures

Figure 1

17 pages, 1594 KiB  
Article
Research on Path Planning for Mobile Charging Robots Based on Improved A* and DWA Algorithms
by Wenliang Zhu and Zhufan Chen
Electronics 2025, 14(12), 2318; https://doi.org/10.3390/electronics14122318 - 6 Jun 2025
Abstract
Driven by rapid growth in the new-energy vehicle (NEV) market and advances in automation, mobile charging robots are increasingly deployed in parking facilities. In complex environments featuring both static and dynamic obstacles, conventional trajectory plans often exhibit insufficient safety margins and poor smoothness. [...] Read more.
Driven by rapid growth in the new-energy vehicle (NEV) market and advances in automation, mobile charging robots are increasingly deployed in parking facilities. In complex environments featuring both static and dynamic obstacles, conventional trajectory plans often exhibit insufficient safety margins and poor smoothness. This paper proposes a hybrid path-planning strategy that combines an improved A* algorithm with an enhanced dynamic window approach (DWA). The enhanced A* algorithm incorporates obstacle influence factors and adaptive weighting during global search, enabling proactive avoidance of obstacle-dense regions and employing segmented Bezier curves for path smoothing. In local planning, the modified DWA integrates a global guidance term and distance-dependent heading weights to mitigate issues of local minima and target loss. Simulation results indicate that the proposed method substantially improves path safety, continuity, and adaptability to complex scenarios while maintaining computational efficiency. Specifically, under high-obstacle-density conditions (e.g., a 20 × 20 grid map), the collision rate is reduced by 66.7% compared to the standard A* algorithm (from 30% to 10%), and the minimum safety distance increases to 0.5 m. Current validation is conducted in simulations; future work will involve real-robot experiments to evaluate real-time performance and robustness in practical environments. Full article
Show Figures

Figure 1

21 pages, 1525 KiB  
Article
Fuzzy-Based Composite Nonlinear Feedback Cruise Control for Heavy-Haul Trains
by Qian Zhang, Jia Wang, Zhiqiang Chen, Yougen Xu, Zhiguo Zhou and Zhiwen Liu
Electronics 2025, 14(12), 2317; https://doi.org/10.3390/electronics14122317 - 6 Jun 2025
Abstract
To improve the transient performance of speed tracking control while ensuring stability and considering actuator constraints in heavy-haul train systems, this paper proposes a novel cruise control method based on a nonparallel distributed compensation (non-PDC) fuzzy-based composite nonlinear feedback (CNF) technique. First, a [...] Read more.
To improve the transient performance of speed tracking control while ensuring stability and considering actuator constraints in heavy-haul train systems, this paper proposes a novel cruise control method based on a nonparallel distributed compensation (non-PDC) fuzzy-based composite nonlinear feedback (CNF) technique. First, a low-dimensional nonlinear multi-particle error dynamics model is established based on the fencing concept, simplifying the model significantly. To facilitate controller design, a Takagi–Sugeno (T-S) fuzzy model is derived from the nonlinear model. Subsequently, sufficient conditions for the non-PDC fuzzy-based CNF controller are provided in terms of linear matrix inequalities (LMIs), with the controller design addressing asymmetric constraints on control inputs due to differing maximums of traction and braking forces. Simulations based on MATLAB/Simulink are conducted under different maneuvers to validate the effectiveness and superiority of the proposed method. The simulation results demonstrate a notable enhancement in transient performance (over 22.3% improvement in settling time) and steady-state cruise control performance for heavy-haul trains using the proposed strategy. Full article
Show Figures

Figure 1

21 pages, 4117 KiB  
Article
Polyp Segmentation Algorithm Based on the Dual Attention and Fusion Mechanism
by Xiang Xie and Xizhong Shen
Electronics 2025, 14(12), 2316; https://doi.org/10.3390/electronics14122316 - 6 Jun 2025
Abstract
Polyp segmentation plays a critical role in enhancing the accuracy of colorectal cancer screening and reducing polyp miss rates. The segmentation accuracy of existing algorithms is significantly limited due to challenges such as polyp morphological diversity, complex mucosal attachments, and boundary ambiguity. To [...] Read more.
Polyp segmentation plays a critical role in enhancing the accuracy of colorectal cancer screening and reducing polyp miss rates. The segmentation accuracy of existing algorithms is significantly limited due to challenges such as polyp morphological diversity, complex mucosal attachments, and boundary ambiguity. To address the limitations of insufficient feature extraction, information redundancy, and imbalance between global and local information fusion, a Dual Attention and Fusion Mechanism Network (DAFM-Net) is proposed, which achieves complementary feature fusion through multi-module collaborative optimization. Firstly, the Multi-scale Convolutional Patch Aware module (MCPA) employs multi-branch convolution and local attention mechanisms to extract multi-granular features, improving the characterization of irregular polyps. Secondly, the Cross-layer Aware Selective Fusion module (CASF) adaptively weights deep and shallow features to reduce redundant information and enhance semantic complementarity. Finally, the Dual Context Enhanced Attention module (DCEA) integrates global and local attention mechanisms to synergistically optimize global structure perception and local boundary details. Experimental results demonstrate the effectiveness of the algorithm, which outperforms state-of-the-art models on five publicly available polyp datasets. The proposed network exhibits superior segmentation accuracy and robustness, particularly in complex backgrounds, irregular morphologies, and multi-scale polyp scenarios. Full article
Show Figures

Figure 1

27 pages, 17572 KiB  
Article
Optimal Design of a Fractional Order PIDD2 Controller for an AVR System Using Hybrid Black-Winged Kite Algorithm
by Fei Dai, Tianli Ma and Song Gao
Electronics 2025, 14(12), 2315; https://doi.org/10.3390/electronics14122315 - 6 Jun 2025
Abstract
This study addresses the optimization of control performance for automatic voltage regulator systems by proposing a fractional-order PIDD2 (FOPIDD2) controller design method based on the hybrid Black-winged Kite Algorithm (BWOA). To overcome the challenges of complex parameter tuning and adaptability [...] Read more.
This study addresses the optimization of control performance for automatic voltage regulator systems by proposing a fractional-order PIDD2 (FOPIDD2) controller design method based on the hybrid Black-winged Kite Algorithm (BWOA). To overcome the challenges of complex parameter tuning and adaptability to high-dimensional nonlinear optimization in PID controllers, the BWOA integrates the precise search mechanism of the Black-winged Kite Algorithm (BKA) with the spiral encircling strategy of the Whale Optimization Algorithm (WOA). By dividing high-fitness individuals into subgroups for parallel optimization, combined with an elitism preservation mechanism and Levy flight perturbation, the BWOA effectively balances global exploration and local exploitation capabilities, preventing premature convergence. Furthermore, a multi-factor objective function is adopted to optimize the six parameters of the FOPIDD2 controller. Numerical simulations in MATLAB evaluate the controller’s performance across multiple dimensions, including transient response, frequency-domain stability, trajectory tracking, parameter uncertainty, and disturbance rejection, with comparisons to other recent controllers. Simulation results demonstrate that the BWOA-FOPIDD2 controller achieves superior performance in most metrics. Therefore, the proposed method provides an efficient hybrid optimization framework for AVR system controller design. Full article
Show Figures

Graphical abstract

36 pages, 4241 KiB  
Review
Global Research Trends in AI and Blockchain for Smart Grids: A Bibliometric Analysis with a Focus on Morocco (2014–2024)
by Anass Betouil, Samia El Haddouti and Habiba Chaoui
Electronics 2025, 14(12), 2314; https://doi.org/10.3390/electronics14122314 - 6 Jun 2025
Abstract
As Information and Communication Technologies (ICTs) are increasingly incorporated into energy systems, smart grids are becoming essential parts of modern energy infrastructures. However, this integration exposes them to significant cybersecurity risks, highlighting the need for effective prevention and mitigation strategies to enhance resilience. [...] Read more.
As Information and Communication Technologies (ICTs) are increasingly incorporated into energy systems, smart grids are becoming essential parts of modern energy infrastructures. However, this integration exposes them to significant cybersecurity risks, highlighting the need for effective prevention and mitigation strategies to enhance resilience. Due to their promising implications, blockchain and artificial intelligence (AI) have emerged as key technologies to strengthen security, improve data analysis, and optimize processes in smart grids. This bibliometric study investigates key trends, opportunities, and evolving dynamics within the field, analyzing a dataset of 9611 articles from the Scopus database, covering the period 2014–2024. To evaluate the research, we utilized a range of bibliometric tools, including Bibliometrix R, VOSviewer, and Python. We used these tools to identify impactful articles. We also analyzed country and institutional productivity, assessed prolific authors, and uncovered emerging trends. The findings highlight a shift towards advanced smart grids incorporating AI and blockchain, with significant progress in Morocco’s research since 2016. Morocco ranks 36th globally and 3rd in Africa, contributing to the National Digital Morocco 2030 Strategy, which promotes digital transition and innovation, particularly in smart grids, to bolster the country’s energy system. Full article
Show Figures

Figure 1

17 pages, 2816 KiB  
Article
Research on a Neural Network-Based Method for Detecting the Concentration and Particle Size of Suspended Solids Based on Multi-Frequency Acoustic Information
by Xuejin Zhao, Zhijian Lin, Ruojun Xiao and Gengxin Ning
Electronics 2025, 14(12), 2313; https://doi.org/10.3390/electronics14122313 - 6 Jun 2025
Abstract
Suspended solids (SS) composed of micrometer-to-nanometer-scale particles, including silt and organic matter, significantly impact aquatic ecosystems through physicochemical interactions. Accurate monitoring of SS concentration and particle size is critical for environmental protection and pollution prevention. We constructed multiple datasets using received signals after [...] Read more.
Suspended solids (SS) composed of micrometer-to-nanometer-scale particles, including silt and organic matter, significantly impact aquatic ecosystems through physicochemical interactions. Accurate monitoring of SS concentration and particle size is critical for environmental protection and pollution prevention. We constructed multiple datasets using received signals after propagation through different aqueous environments. Analysis of the performance of neural networks across different datasets revealed that high-frequency signals with rich spectra have high potential for detecting suspended solid information in complex aqueous environments. Our study explores the performance of two neural networks (Conv1dBGRU and TCN) in combination with channel attention mechanisms in classification tasks focused on the concentration of suspended solids and particle size. We also constructed neural networks for multi-task learning using both hard and soft parameter-sharing methods to simultaneously complete the classification tasks for concentration and particle size. The results show that multi-frequency acoustic signals in combination with neural networks can achieve simultaneous and accurate estimation of the concentration of suspended solids and particle size. Full article
Show Figures

Figure 1

23 pages, 809 KiB  
Article
Towards Smarter Assessments: Enhancing Bloom’s Taxonomy Classification with a Bayesian-Optimized Ensemble Model Using Deep Learning and TF-IDF Features
by Ali Alammary and Saeed Masoud
Electronics 2025, 14(12), 2312; https://doi.org/10.3390/electronics14122312 - 6 Jun 2025
Abstract
Bloom’s taxonomy provides a well-established framework for categorizing the cognitive complexity of assessment questions, ensuring alignment with course learning outcomes (CLOs). Achieving this alignment is essential for constructing meaningful and valid assessments that accurately measure student learning. However, in higher education, the large [...] Read more.
Bloom’s taxonomy provides a well-established framework for categorizing the cognitive complexity of assessment questions, ensuring alignment with course learning outcomes (CLOs). Achieving this alignment is essential for constructing meaningful and valid assessments that accurately measure student learning. However, in higher education, the large volume of questions that instructors must develop each semester makes manual classification of cognitive levels a time-consuming and error-prone process. Despite various attempts to automate this classification, the highest accuracy reported in existing research has not exceeded 93.5%, highlighting the need for further advancements in this area. Furthermore, the best-performing deep learning models only reached an accuracy of 86%. These results emphasize the need for improvement, particularly in the application of deep learning models, which have not been fully exploited for this task. In response to these challenges, our study explores a novel approach to enhance the accuracy of cognitive level classification. We leverage a combination of augmentation through synonym substitution, advanced feature extraction techniques utilizing DistilBERT and TF-IDF, and a robust ensemble model incorporating soft voting. These methods were selected to capture both semantic meaning and term frequency, allowing the model to benefit from contextual depth and statistical relevance. Additionally, Bayesian optimization is employed for hyperparameter tuning to refine the model’s performance further. The novelty of our approach lies in the fusion of sparse TF-IDF features with dense DistilBERT embeddings, optimized through Bayesian search across multiple classifiers. This hybrid design captures both term-level salience and deep contextual semantics, something not fully exploited in prior models focused solely on transformer architectures. Our soft-voting ensemble capitalizes on classifier diversity, yielding more stable and accurate results. Through this integrated approach outperformed previous configurations with an accuracy of 96%, surpassing the current state-of-the-art results and setting a new benchmark for automated cognitive level classification. These findings have significant implications for the development of high-quality, scalable assessments in educational settings. Full article
Show Figures

Figure 1

18 pages, 10378 KiB  
Article
A Compact Monopole Wideband Antenna Based on DGS
by Assefa Tsegaye, Xian-Qi Lin, Hao Liu and Hassan Sani Abubakar
Electronics 2025, 14(12), 2311; https://doi.org/10.3390/electronics14122311 - 6 Jun 2025
Abstract
This paper presents a compact monopole wideband antenna based on DGS. The ultimate geometry of the designed antenna is obtained after many design modifications and optimizations. A commercially available Taconic TLY substrate with a dielectric constant (εr) = 2.2, loss tangent [...] Read more.
This paper presents a compact monopole wideband antenna based on DGS. The ultimate geometry of the designed antenna is obtained after many design modifications and optimizations. A commercially available Taconic TLY substrate with a dielectric constant (εr) = 2.2, loss tangent (tan δ) = 0.0009, and thickness (h) of 1.524 mm is used. The dimension of the substrate is 34 mm × 28 mm. A 50Ω microstrip transmission line of size 12 mm × 3 mm is used to feed the antenna. Simulation results demonstrate a bandwidth from 4.08 to 18.92 GHz, a percentage bandwidth of 129% for S11 < −10 dB, and a peak gain of 7.4 dB. The DGS slots are embedded into the ground plane to enhance the antenna’s bandwidth, impedance matching, gain, and efficiency. For verification, the proposed antenna is fabricated and measured. Good agreement between measured and simulated results is observed. Thus, this antenna is appropriate for various modern wireless communication systems. Full article
Show Figures

Figure 1

17 pages, 439 KiB  
Article
MultiAVSR: Robust Speech Recognition via Supervised Multi-Task Audio–Visual Learning
by Shad Torrie, Kimi Wright and Dah-Jye Lee
Electronics 2025, 14(12), 2310; https://doi.org/10.3390/electronics14122310 - 6 Jun 2025
Abstract
Speech recognition approaches typically fall into three categories: audio, visual, and audio–visual. Visual speech recognition, or lip reading, is the most difficult because visual cues are ambiguous and data is scarce. To address these challenges, we present a new multi-task audio–visual speech recognition, [...] Read more.
Speech recognition approaches typically fall into three categories: audio, visual, and audio–visual. Visual speech recognition, or lip reading, is the most difficult because visual cues are ambiguous and data is scarce. To address these challenges, we present a new multi-task audio–visual speech recognition, or MultiAVSR, framework for training a model on all three types of speech recognition simultaneously primarily to improve visual speech recognition. Unlike prior works which use separate models or complex semi-supervision, our framework employs a supervised multi-task hybrid Connectionist Temporal Classification/Attention loss cutting training exaFLOPs to just 18% of that required by semi-supervised multitask models. MultiAVSR achieves state-of-the-art visual speech recognition word error rate of 21.0% on the LRS3-TED dataset. Furthermore, it exhibits robust generalization capabilities, achieving a remarkable 44.7% word error rate on the WildVSR dataset. Our framework also demonstrates reduced dependency on external language models, which is critical for real-time visual speech recognition. For the audio and audio–visual tasks, our framework improves the robustness under various noisy environments with average relative word error rate improvements of 16% and 31%, respectively. These improvements across the three tasks illustrate the robust results our supervised multi-task speech recognition framework enables. Full article
(This article belongs to the Special Issue Advances in Information, Intelligence, Systems and Applications)
Show Figures

Figure 1

Previous Issue
Back to TopTop