Electronics

23 pages, 998 KB

Open AccessArticle

A SIEM-Integrated Cybersecurity Prototype for Insider Threat Anomaly Detection Using Enterprise Logs and Behavioural Biometrics

by Mohamed Salah Mohamed and Abdullahi Arabo

Electronics 2026, 15(1), 248; https://doi.org/10.3390/electronics15010248 - 5 Jan 2026

Cited by 5 | Viewed by 3516

Abstract

Insider threats remain a serious concern for organisations in both public and private sectors. Detecting anomalous behaviour in enterprise environments is critical for preventing insider incidents. While many prior studies demonstrate promising results using deep learning on offline datasets, few address real-time operationalisation [...] Read more.

Insider threats remain a serious concern for organisations in both public and private sectors. Detecting anomalous behaviour in enterprise environments is critical for preventing insider incidents. While many prior studies demonstrate promising results using deep learning on offline datasets, few address real-time operationalisation or calibrated alert control within a Security Information and Event Management (SIEM) workflow. This paper presents a SIEM-integrated prototype that fuses the Computer Emergency Response Team Insider Threat Test Dataset (CERT) enterprise logs (Logon, Device, HTTP, and Email) with behavioural biometrics from the Balabit mouse dynamics dataset. Per-modality one-dimensional convolutional neural network (1D CNN) branches are trained independently using imbalance-aware strategies, including downsampling, class weighting, and focal loss. A unified 20 × N feature schema ensures train–serve parity and consistent feature validation during live inference. Post-training calibration using Platt and isotonic regression enables analyst-controlled threshold tuning and stable alert budgeting inside the SIEM. The models are deployed in Splunk’s Machine Learning Toolkit (MLTK), where dashboards visualise anomaly timelines, risky users or hosts, and cross-stream overlaps. Evaluation emphasises operational performance, precision–recall balance, calibration stability, and throughput rather than headline accuracy. Results show calibrated, controllable alert volumes: for Device, precision ≈0.70 at recall ≈0.30 (PR-AUC = 0.468, ROC-AUC = 0.949); for Logon, ROC-AUC = 0.936 with an ultra-low false-positive rate at a conservative threshold. Batch CPU inference sustains ≈70.5 k windows/s, confirming real-time feasibility. This study’s main contribution is to demonstrate a calibrated, multi-modal CNN framework that integrates directly within a live SIEM pipeline. It provides a reproducible path from offline anomaly detection research to Security Operations Centre (SOC)-ready deployment, bridging the gap between academic models and operational Cybersecurity practice. Full article

(This article belongs to the Special Issue AI in Cybersecurity, 2nd Edition)

► Show Figures

Figure 1

18 pages, 1213 KB

Open AccessArticle

Energy-Balanced and Stability-Oriented Clustering Algorithm for Fragment Velocity Measurement Networks

by Lirong Ma, Yonghong Ding and Wenbin You

Electronics 2026, 15(1), 247; https://doi.org/10.3390/electronics15010247 - 5 Jan 2026

Cited by 1 | Viewed by 654

Abstract

To address the energy limitations, long-term operation demands, and load imbalance in fragment velocity measurement wireless sensor networks, this paper proposes an Energy-Balanced and Stability-Oriented Grey Wolf Optimization (EBSIGWO) algorithm. The algorithm employs a multi-objective fitness function that jointly considers residual energy, intra-cluster [...] Read more.

To address the energy limitations, long-term operation demands, and load imbalance in fragment velocity measurement wireless sensor networks, this paper proposes an Energy-Balanced and Stability-Oriented Grey Wolf Optimization (EBSIGWO) algorithm. The algorithm employs a multi-objective fitness function that jointly considers residual energy, intra-cluster load balance, and long-term communication cost, ensuring both energy efficiency and clustering stability. A dynamic elite ratio strategy is further introduced to adaptively balance global exploration and local exploitation, thereby mitigating cluster-head overload and slowing energy depletion. Simulation results show that EBSIGWO significantly extends network lifetime compared with LEACH, HEED, GWO, and FIGWO, improving the half-node-death (HND) round by 518.0%, 200.1%, 111.2%, and 30.5%, respectively. Moreover, EBSIGWO reduces energy variance and slows energy consumption, demonstrating superior energy balance and overall efficiency. These results indicate that EBSIGWO provides an effective solution for reliable fragment velocity measurement applications. Full article

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

► Show Figures

Figure 1

19 pages, 950 KB

Open AccessArticle

Edge Microservice Deployment and Management Using SDN-Enabled Whitebox Switches

by Mohamad Rahhal, Lluis Gifre, Pablo Armingol Robles, Javier Mateos Najari, Aitor Zabala, Manuel Angel Jimenez, Rafael Leira Osuna, Raul Muñoz, Oscar González de Dios and Ricard Vilalta

Electronics 2026, 15(1), 246; https://doi.org/10.3390/electronics15010246 - 5 Jan 2026

Cited by 1 | Viewed by 985

Abstract

This work advances a 6G-ready, micro-granular SDN fabric that unifies high-performance edge data planes with intent-driven, multi-domain orchestration and cloud offloading. First, edge and cell-site whiteboxes are upgraded with Smart Network Interface Cards and embedded AI accelerators, enabling line-rate processing of data flows [...] Read more.

This work advances a 6G-ready, micro-granular SDN fabric that unifies high-performance edge data planes with intent-driven, multi-domain orchestration and cloud offloading. First, edge and cell-site whiteboxes are upgraded with Smart Network Interface Cards and embedded AI accelerators, enabling line-rate processing of data flows and on-box learning/inference directly in the data plane. This pushes functions such as traffic classification, telemetry, and anomaly mitigation to the point of ingress, reducing latency and backhaul load. Second, an SDN controller, i.e., ETSI TeraFlowSDN, is extended to deliver multi-domain SDN orchestration with native lifecycle management (LCM) for whitebox Network Operating Systems—covering onboarding, configuration-drift control, rolling upgrades/rollbacks, and policy-guarded compliance—so operators can reliably manage heterogeneous edge fleets at scale. Third, the SDN controller incorporates a new NFV-O client that seamlessly offloads network services—such as ML pipelines or NOS components—to telco clouds via an NFV orchestrator (e.g., ETSI Open Source MANO), enabling elastic placement and scale-out across the edge–cloud continuum. Together, these contributions deliver an open, programmable platform that couples in-situ acceleration with closed-loop, intent-based orchestration and elastic cloud resources, targeting demonstrable gains in end-to-end latency, throughput, operational agility, and energy efficiency for emerging 6G services. Full article

(This article belongs to the Special Issue Optical Networking and Computing)

► Show Figures

Figure 1

25 pages, 3879 KB

Open AccessArticle

Robust Occluded Object Detection in Multimodal Autonomous Driving: A Fusion-Aware Learning Framework

by Zhengqing Li and Baljit Singh

Electronics 2026, 15(1), 245; https://doi.org/10.3390/electronics15010245 - 5 Jan 2026

Cited by 5 | Viewed by 1973

Abstract

Reliable occluded object detection remains a persistent core challenge for autonomous driving perception systems, particularly in complex urban scenarios where targets are predominantly partially or fully obscured by static obstacles or dynamic agents. Conventional single-modality detectors often fail to capture adequate discriminative cues [...] Read more.

Reliable occluded object detection remains a persistent core challenge for autonomous driving perception systems, particularly in complex urban scenarios where targets are predominantly partially or fully obscured by static obstacles or dynamic agents. Conventional single-modality detectors often fail to capture adequate discriminative cues for robust recognition, while existing multimodal fusion strategies typically lack explicit occlusion modeling and effective feature completion mechanisms, ultimately degrading performance in safety-critical operating conditions. To address these limitations, we propose a novel Fusion-Aware Occlusion Detection (FAOD) framework that integrates explicit visibility reasoning with implicit cross-modal feature reconstruction. Specifically, FAOD leverages synchronized red–green–blue (RGB), light detection and ranging (LiDAR), and optional radar/infrared inputs, employs a visibility-aware attention mechanism to infer target occlusion states, and embeds a cross-modality completion module to reconstruct missing object features via complementary non-occluded modal information; it further incorporates an occlusion-aware data augmentation and annotation strategy to enhance model generalization across diverse occlusion patterns. Extensive evaluations on four benchmark datasets demonstrate that FAOD achieves state-of-the-art performance, including a +8.75% occlusion-level mean average precision (OL-mAP) improvement over existing methods on heavily occluded objects

O = 2

in the nuScenes dataset, while maintaining real-time efficiency. These findings confirm FAOD’s potential to advance reliable multimodal perception for next-generation autonomous driving systems in safety-critical environments. Full article

(This article belongs to the Special Issue Celebrating the 70th Anniversary of Beijing University of Posts and Telecommunications—Computer Science and Engineering)

► Show Figures

Figure 1

16 pages, 3532 KB

Open AccessArticle

A Fast Method for Estimating Generator Matrixes of BCH Codes

by Shunan Han, Yuanzheng Ge, Yu Shi and Renjie Yi

Electronics 2026, 15(1), 244; https://doi.org/10.3390/electronics15010244 - 5 Jan 2026

Cited by 2 | Viewed by 679

Abstract

The existing methods used for estimating generator matrixes of BCH codes, which are based on Galois Field Fourier transforms, need to exhaustively test all the possible codeword lengths and corresponding primitive polynomials. With the increase of codeword length, the search space exponentially expands. [...] Read more.

The existing methods used for estimating generator matrixes of BCH codes, which are based on Galois Field Fourier transforms, need to exhaustively test all the possible codeword lengths and corresponding primitive polynomials. With the increase of codeword length, the search space exponentially expands. Consequently, the computational complexity of the estimation scheme becomes very high. To overcome this limitation, a fast estimation method is proposed based on Gaussian elimination. Firstly, the encoded bit stream is reshaped into a matrix according to the assumed codeword length. Then, by using Gaussian elimination, the bit matrix is simplified as the upper triangle form. By testing the independent columns of the upper triangle matrix, the assumed codeword length is judged to be right or not. Simultaneously, by using an augmented matrix, the parity check matrix of a BCH code can be estimated from the simplification result in the procedure of Gaussian elimination. Furthermore, the generator matrix is estimated by using the orthogonality between the generator matrix and parity check matrix. To improve the performance of the proposed method in resisting bit errors, soft-decision data is adopted to evaluate the reliability of received bits, and reliable bits are selected to construct the matrix to be analyzed. Experimental results indicate that the proposed method can recognize BCH codes effectively. The robustness of our method is acceptable for application, and the computation required is much less than the existing methods. Full article

► Show Figures

Figure 1

19 pages, 778 KB

Open AccessArticle

GALR: Graph-Based Root Cause Localization and LLM-Assisted Recovery for Microservice Systems

by Wenya Zhang, Zhi Yang, Fang Peng, Le Zhang, Yiting Chen and Ruibo Chen

Electronics 2026, 15(1), 243; https://doi.org/10.3390/electronics15010243 - 5 Jan 2026

Cited by 3 | Viewed by 3271

Abstract

With the rapid evolution of cloud-native platforms, microservice-based systems have become increasingly large-scale and complex, making fast and accurate root cause localization and recovery a critical challenge. Runtime signals in such systems are inherently multimodal—combining metrics, logs, and traces—and are intertwined through deep, [...] Read more.

With the rapid evolution of cloud-native platforms, microservice-based systems have become increasingly large-scale and complex, making fast and accurate root cause localization and recovery a critical challenge. Runtime signals in such systems are inherently multimodal—combining metrics, logs, and traces—and are intertwined through deep, dynamic service dependencies, which often leads to noisy alerts, ambiguous fault propagation paths, and brittle, manually curated recovery playbooks. To address these issues, we propose GALR, a graph- and LLM-based framework for root cause localization and recovery in microservice-based business middle platforms. GALR first constructs a multimodal service call graph by fusing time-series metrics, structured logs, and trace-derived topology, and employs a GAT-based root cause analysis module with temporal-aware edge attention to model failure propagation. On top of this, an LLM-based node enhancement mechanism infers anomaly, normal, and uncertainty scores from log contexts and injects them into node representations and attention bias terms, improving robustness under noisy or incomplete signals. Finally, GALR integrates a retrieval-augmented LLM agent that retrieves similar historical cases and generates executable recovery strategies, with consistency checking against expert-standard playbooks to ensure safety and reproducibility. Extensive experiments on three representative microservice datasets demonstrate that GALR consistently achieves superior Top-k accuracy and mean reciprocal rank for root cause localization, while the retrieval-augmented agent yields substantially more accurate and actionable recovery plans compared with graph-only and LLM-only baselines, providing a practical closed-loop solution from anomaly perception to recovery execution. Full article

(This article belongs to the Special Issue Advanced Techniques for Multi-Agent Systems)

► Show Figures

Figure 1

15 pages, 3153 KB

Open AccessEditor’s ChoiceArticle

Decentralized Q-Learning for Multi-UAV Post-Disaster Communication: A Robotarium-Based Evaluation Across Urban Environments

by Udhaya Mugil Damodarin, Cristian Valenti, Sergio Spanò, Riccardo La Cesa, Luca Di Nunzio and Gian Carlo Cardarilli

Electronics 2026, 15(1), 242; https://doi.org/10.3390/electronics15010242 - 5 Jan 2026

Cited by 8 | Viewed by 1036

Abstract

Large-scale disasters such as earthquakes and floods often cause the collapse of terrestrial communication networks, isolating affected communities and disrupting rescue coordination. Unmanned aerial vehicles (UAVs) can serve as rapid-deployment aerial relays to restore connectivity in such emergencies. This work presents a decentralized [...] Read more.

Large-scale disasters such as earthquakes and floods often cause the collapse of terrestrial communication networks, isolating affected communities and disrupting rescue coordination. Unmanned aerial vehicles (UAVs) can serve as rapid-deployment aerial relays to restore connectivity in such emergencies. This work presents a decentralized Q-learning framework in which each UAV operates as an independent agent that learns to maintain reliable two-hop links between mobile ground users. The framework integrates user mobility, UAV–user assignment, multi-UAV coordination, and failure tracking to enhance adaptability under dynamic conditions. The system is implemented and evaluated on the Robotarium platform, with propagation modeled using the Al-Hourani air-to-ground path loss formulation. Experiments conducted across Suburban, Dense Urban, and Highrise Urban environments show throughput gains of up to 20% compared with random placement baselines while maintaining failure rates below 5%. These results demonstrate that decentralized learning offers a scalable and resilient foundation for UAV-assisted emergency communication in environments where conventional infrastructure is unavailable. Full article

(This article belongs to the Special Issue New Trends in Mobile Networks and Wireless Sensor Networks for Smart City IoT)

► Show Figures

Figure 1

18 pages, 3115 KB

Open AccessArticle

A Novel Reactive Power Decoupling Strategy for VSG Inverter Systems Using Adaptive Dynamic Virtual Impedance

by Wei Luo, Chenwei Zhang, Weizhong Chen, Bin Zhang and Zhenyu Lv

Electronics 2026, 15(1), 241; https://doi.org/10.3390/electronics15010241 - 5 Jan 2026

Cited by 3 | Viewed by 713

Abstract

Virtual synchronous machine (VSG) technology provides a robust framework for integrating electric vehicle energy storage into modern microgrids. Nonetheless, conventional VSG control often suffers from intense interaction between active and reactive power flows, which can trigger persistent steady-state errors, power fluctuations, and potential [...] Read more.

Virtual synchronous machine (VSG) technology provides a robust framework for integrating electric vehicle energy storage into modern microgrids. Nonetheless, conventional VSG control often suffers from intense interaction between active and reactive power flows, which can trigger persistent steady-state errors, power fluctuations, and potential system collapse. This research addresses these challenges by developing a 5th-order electromagnetic dynamic model tailored for a two-stage cascaded bridge inverter. By synthesizing a 3rd-order power regulation loop with a 2nd-order output stage, the proposed model captures stability boundaries across an extensive parameter spectrum. Unlike traditional 3rd-order “quasi-steady-state” approaches—which overlook essential dynamics under weak-damping or low-inertia conditions—this study utilizes the 5th-order model to derive an adaptive dynamic virtual impedance decoupling technique. This strategy facilitates real-time compensation of the cross-coupling between active and reactive channels, significantly boosting the inverter’s damping ratio. Quantitative analysis confirms that this approach curtails overshoot by 85.6% and accelerates the stabilization process by 42%, markedly enhancing the overall dynamic performance of the grid-connected system. Full article

(This article belongs to the Special Issue Intelligent Control Strategies for Power Electronics)

► Show Figures

Figure 1

28 pages, 1463 KB

Open AccessArticle

PUF-Based Secure Authentication Protocol for Cloud-Assisted Wireless Medical Sensor Networks

by Minsu Kim, Taehun Kim, Deokkyu Kwon and Youngho Park

Electronics 2026, 15(1), 240; https://doi.org/10.3390/electronics15010240 - 5 Jan 2026

Cited by 2 | Viewed by 1210

Abstract

Wireless medical sensor networks (WMSNs) have evolved alongside the development of communication systems, and the integration of cloud computing has enabled scalable and efficient medical data management. However, since the messages in WMSNs are transmitted over open channels, they are vulnerable to eavesdropping, [...] Read more.

Wireless medical sensor networks (WMSNs) have evolved alongside the development of communication systems, and the integration of cloud computing has enabled scalable and efficient medical data management. However, since the messages in WMSNs are transmitted over open channels, they are vulnerable to eavesdropping, replay, impersonation, and other various attacks. In response to these security concerns, Keshta et al. suggested an authentication protocol to establish secure communication in the cloud-assisted WMSNs. However, our analysis reveals their protocol cannot prevent session key disclosure, impersonation of the user and sensor node, and denial of service (DoS) attacks. Moreover, Keshta et al.’s protocol cannot support user untraceability due to fixed hidden identity. To address these weaknesses, we propose a physical unclonable function (PUF) based secure authentication protocol for cloud-assisted WMSNs. The protocol uses lightweight operations, provides mutual authentication between user, cloud server, and sensor node, and supports user anonymity and untraceability. We validate the proposed protocol’s security through informal analysis on various security attacks and formal analysis including “Burrows–Abadi–Needham (BAN) logic”, “Real-or-Random (RoR) model” for session key security, and “Automated Validation of Internet Security Protocols and Application (AVISPA) simulations”. Performance evaluation demonstrates lower communication cost and computation overhead compared with existing protocols, making the proposed protocol suitable for WMSN environments. Full article

(This article belongs to the Special Issue Trends in Information Systems and Security)

► Show Figures

Graphical abstract

14 pages, 1392 KB

Open AccessArticle

AirSpeech: Lightweight Speech Synthesis Framework for Home Intelligent Space Service Robots

by Xiugong Qin, Fenghu Pan, Jing Gao, Shilong Huang, Yichen Sun and Xiao Zhong

Electronics 2026, 15(1), 239; https://doi.org/10.3390/electronics15010239 - 5 Jan 2026

Viewed by 1071

Abstract

Text-to-Speech (TTS) methods typically employ a sequential approach with an Acoustic Model (AM) and a vocoder, using a Mel spectrogram as an intermediate representation. However, in home environments, TTS systems often struggle with issues such as inadequate robustness against environmental noise and limited [...] Read more.

Text-to-Speech (TTS) methods typically employ a sequential approach with an Acoustic Model (AM) and a vocoder, using a Mel spectrogram as an intermediate representation. However, in home environments, TTS systems often struggle with issues such as inadequate robustness against environmental noise and limited adaptability to diverse speaker characteristics. The quality of the Mel spectrogram directly affects the performance of TTS systems, yet existing methods overlook the potential of enhancing Mel spectrogram quality through more comprehensive speech features. To address the complex acoustic characteristics of home environments, this paper introduces AirSpeech, a post-processing model for Mel-spectrogram synthesis. We adopt a Generative Adversarial Network (GAN) to improve the accuracy of Mel spectrogram prediction and enhance the expressiveness of synthesized speech. By incorporating additional conditioning extracted from synthesized audio using specified speech feature parameters, our method significantly enhances the expressiveness and emotional adaptability of synthesized speech in home environments. Furthermore, we propose a global normalization strategy to stabilize the GAN training process. Through extensive evaluations, we demonstrate that the proposed method significantly improves the signal quality and naturalness of synthesized speech, providing a more user-friendly speech interaction solution for smart home applications. Full article

► Show Figures

Figure 1

41 pages, 829 KB

Open AccessReview

Personalized Learning Path Recommendation Based on Knowledge Graphs: A Survey

by Aili Li, Yong Li and Xiyu Gao

Electronics 2026, 15(1), 238; https://doi.org/10.3390/electronics15010238 - 5 Jan 2026

Cited by 13 | Viewed by 8970

Abstract

The rapid development of artificial intelligence is reshaping learning concepts and instructional practices. Online learning overcomes temporal and spatial constraints, providing flexible and autonomous learning environments, and has become a central component of educational digitalization. However, the physical separation of teachers and learners [...] Read more.

The rapid development of artificial intelligence is reshaping learning concepts and instructional practices. Online learning overcomes temporal and spatial constraints, providing flexible and autonomous learning environments, and has become a central component of educational digitalization. However, the physical separation of teachers and learners makes it difficult to monitor learning progress effectively, while the abundance of learning resources often leads to learner disorientation and reduced learning efficiency. Consequently, effective planning of personalized learning paths is essential for reducing learning costs and improving learning outcomes. Traditional one-size-fits-all instructional models are insufficient to meet learners’ needs. In this context, designing transparent, adaptive, and personalized learning paths for individual learners has become an urgent research challenge. This study presents a comprehensive review of personalized learning path recommendation based on knowledge graphs. It analyzes existing methods from interdisciplinary perspectives, with particular emphasis on the theoretical role of Bloom’s taxonomy in guiding the design of learning paths. The review further summarizes core algorithm approaches, examines the characteristics and applicability of commonly used public datasets, and identifies major limitations and challenges in current research. Finally, it outlines future research directions aimed at enhancing transparency, adaptability, and explainability to support educational digital transformation and the realization of individualized instruction. Full article

► Show Figures

Figure 1

23 pages, 1543 KB

Open AccessArticle

Jailbreaking MLLMs via Attention Redirection and Entropy Regularization

by Jiayu Du, Fangxu Dong and Fan Zhang

Electronics 2026, 15(1), 237; https://doi.org/10.3390/electronics15010237 - 5 Jan 2026

Viewed by 1883

Abstract

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across vision–language tasks, yet their safety alignment remains vulnerable to adversarial manipulation. Existing jailbreak attacks typically optimize adversarial perturbations using negative log-likelihood loss alone, which often leads to overfitting on target affirmative tokens and [...] Read more.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across vision–language tasks, yet their safety alignment remains vulnerable to adversarial manipulation. Existing jailbreak attacks typically optimize adversarial perturbations using negative log-likelihood loss alone, which often leads to overfitting on target affirmative tokens and fails to elicit substantive harmful content. We propose Attention-Enhancement and Targeted Entropy Regularization for Adversarial Optimization (AERO), a novel jailbreak framework addressing these limitations through two complementary mechanisms. First, an attention enhancement loss strategically redirects cross-modal attention toward perturbed visual tokens, distracting safety-aligned features from scrutinizing malicious queries. Second, a targeted entropy regularization scheme maximizes output diversity over non-refusal tokens during initial generation, creating a permissive context that improves cross-query generalization and enables responses that genuinely address malicious requests. Extensive experiments on multiple state-of-the-art MLLMs demonstrate that AERO significantly outperforms existing methods, achieving Attack Success Rates (ASRs) of 65.8–70.7% on MM-SafetyBench and 71.0–84.5% on HarmBench. Our approach surpasses the strongest baselines by margins of up to 16.2% in success rate while consistently generating higher-quality harmful content. Full article

(This article belongs to the Special Issue Artificial Intelligence Safety and Security)

► Show Figures

Figure 1

23 pages, 1682 KB

Open AccessArticle

An Improved Adaptive NSGA-II with Multiple Filtering for High-Dimensional Feature Selection

by Ying Wang, Renjie Fan, Lei Cheng, Bo Gong and Jiahao Liu

Electronics 2026, 15(1), 236; https://doi.org/10.3390/electronics15010236 - 5 Jan 2026

Cited by 3 | Viewed by 1598

Abstract

As the number of feature dimensions increases, the decision-making space exhibits extensive and discrete characteristics, which poses a severe challenge to multi-objective (MO) evolutionary algorithms when searching for the optimal feature subset. Many existing algorithms face the difficulty of slow convergence speed and [...] Read more.

As the number of feature dimensions increases, the decision-making space exhibits extensive and discrete characteristics, which poses a severe challenge to multi-objective (MO) evolutionary algorithms when searching for the optimal feature subset. Many existing algorithms face the difficulty of slow convergence speed and may fall into local optimal solutions. This study proposes AF-NSGA-II (an adaptive filtering-nondominated sorting genetic algorithm II), an improved MO evolutionary algorithm for high-dimensional feature selection, in which a novel sparse generation scheme for the solution set and an innovative adaptive crossover mechanism are introduced. This sparse initialization strategy, based on three distinct filter feature selection methods, produces initial solutions closer to the optimal Pareto solution set, which is beneficial for convergence. The adaptive crossover mechanism dynamically selects between geometric crossover operators (fostering convergence) and non-geometric crossover operators (enhancing diversity) based on parent similarity, effectively balancing both aspects and helping the algorithm to escape local optima. The algorithm is compared against six renowned multi-objective evolutionary algorithms across ten complex and publicly available datasets. The comparison results demonstrate the superiority of AF-NSGA-II over other algorithms, as well as its effectiveness in identifying the optimal feature subset. Full article

(This article belongs to the Special Issue Artificial Intelligence and Advanced Signal Processing Techniques and Their Applications)

► Show Figures

Figure 1

25 pages, 4045 KB

Open AccessArticle

A Hybrid Intrusion Detection Framework for Imbalanced AMI Traffic Using GAN-Based Data Augmentation and Lightweight CNN

by Shunjiang Wang, Yang Shi, Guiping Zhou and Peng Yu

Electronics 2026, 15(1), 235; https://doi.org/10.3390/electronics15010235 - 5 Jan 2026

Cited by 1 | Viewed by 1439

Abstract

With the widespread deployment of the Advanced Metering Infrastructure (AMI) in Power Industrial Control Systems (PICS), a significant and inherent property of network traffic data is its pronounced class imbalance. The continuous emergence of new types of cyberattacks significantly limits the detection accuracy [...] Read more.

With the widespread deployment of the Advanced Metering Infrastructure (AMI) in Power Industrial Control Systems (PICS), a significant and inherent property of network traffic data is its pronounced class imbalance. The continuous emergence of new types of cyberattacks significantly limits the detection accuracy of Intrusion Detection Systems (IDS). To overcome the limitations of traditional methods—particularly their poor adaptability in complex conditions and vulnerability to emerging threats—this paper introduces a novel hybrid intrusion detection framework. This framework synergistically combines data augmentation and a discriminative classification model for improved performance. Within this framework, a Multi-feature Constrained Conditional Generative Adversarial Network (MC-CGAN) is proposed. Its multi-feature constraint module (MC) preserves protocol-related invariant features, while the CGAN is responsible for conditionally generating the remaining continuous features based on class labels. By preserving the core semantic information of samples, this method reduces the risk of generating unrealistic data and decreases computational overhead. Furthermore, we develop ADS-Net, a lightweight Convolutional Neural Network that not only replaces traditional convolutions with depth-wise separable ones for efficiency, but also incorporates an attention mechanism to adaptively weight feature channels, thus improving discriminative focus. Extensive experiments demonstrate that, under conditions of extreme data imbalance, the proposed hybrid framework can generate industrially valid synthetic data while achieving accurate intrusion detection with an accuracy of 98.35%. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

12 pages, 6822 KB

Open AccessArticle

Design of Low-Pass Corrugated Filters Based on Half-Mode Groove Gap Waveguide Technology

by Stephan Marini, Antonio Seller Rueda, Pablo Soto, Encarnación Gimeno Nieves and Vicente E. Boria

Electronics 2026, 15(1), 234; https://doi.org/10.3390/electronics15010234 - 5 Jan 2026

Cited by 2 | Viewed by 1522

Abstract

In this paper, low-pass corrugated filters based on half-mode groove gap waveguide (HMGGW) technology are proposed for the first time. The design process starts from the equivalent classical low-pass implementation in corrugated rectangular waveguide. Then, the final response is achieved after a slight [...] Read more.

In this paper, low-pass corrugated filters based on half-mode groove gap waveguide (HMGGW) technology are proposed for the first time. The design process starts from the equivalent classical low-pass implementation in corrugated rectangular waveguide. Then, the final response is achieved after a slight re-optimization of groove widths and lengths. As a proof of concept, two corrugated low-pass filters with upper cutoff frequencies at 27 and 29.5 GHz, and maximum attenuation rejection at 34.5 and 39 GHz, respectively, have been designed and manufactured. In spite of the frequency range of operation, the return losses are better than 19.5 dB for both tuning-less filter prototypes, while measured insertion losses are lower than 0.25 dB and 0.3 dB, respectively, in almost the entire passband. The very good agreement between simulations and measurements fully validates the use of this new emerging technology for the implementation of low-pass filters at high frequency bands. Full article

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

► Show Figures

Figure 1

23 pages, 2090 KB

Open AccessArticle

Fault Section Localization in Distribution Networks Based on the Integration of Node Classification Matrix and an Improved Binary Particle Swarm Algorithm

by Kui Chen, Wen Xu and Yuheng Yang

Electronics 2026, 15(1), 233; https://doi.org/10.3390/electronics15010233 - 4 Jan 2026

Viewed by 632

Abstract

Single-phase-to-ground faults occur frequently in distribution networks, while traditional localization methods have limitations such as insufficient feature extraction and poor topological adaptability. To address these issues, this paper proposes a two-stage localization method that integrates the Node Classification Matrix (NCM) and an Improved [...] Read more.

Single-phase-to-ground faults occur frequently in distribution networks, while traditional localization methods have limitations such as insufficient feature extraction and poor topological adaptability. To address these issues, this paper proposes a two-stage localization method that integrates the Node Classification Matrix (NCM) and an Improved Binary Particle Swarm Optimization (IBPSO) algorithm. The NCM achieves rapid initial localization, and the IBPSO performs error correction. This paper employs an IEEE 33-node standard distribution network model to design simulations covering scenarios with varying fault locations, multiple fault resistances, and different numbers of node distortions for validation. The results demonstrate that the proposed method achieves a fault location accuracy of 96%, which is 19% higher than that of the NCM alone and 2% higher than that of the IBPSO alone. Moreover, it maintains an accuracy of over 95% under scenarios of 1–3 node distortions, topological switching, and high-impedance faults, and is compatible with existing Feeder Terminal Unit (FTU) devices. This method effectively balances localization speed and robustness, providing a reliable solution for the rapid fault isolation of distribution network. Full article

(This article belongs to the Topic Power System Protection)

► Show Figures

Figure 1

26 pages, 2431 KB

Open AccessArticle

Multi-Objective Deep Reinforcement Learning for Dynamic Task Scheduling Under Time-of-Use Electricity Price in Cloud Data Centers

by Xiao Liao, Yiqian Li, Luyao Liu, Lihao Deng, Jinlong Hu and Xiaofei Wu

Electronics 2026, 15(1), 232; https://doi.org/10.3390/electronics15010232 - 4 Jan 2026

Viewed by 1971

Abstract

The high energy consumption and substantial electricity costs of cloud data centers pose significant challenges related to carbon emissions and operational expenses for service providers. The temporal variability of electricity pricing in real-world scenarios adds complexity to this problem while simultaneously offering novel [...] Read more.

The high energy consumption and substantial electricity costs of cloud data centers pose significant challenges related to carbon emissions and operational expenses for service providers. The temporal variability of electricity pricing in real-world scenarios adds complexity to this problem while simultaneously offering novel opportunities for mitigation. This study addresses the task scheduling optimization problem under time-of-use pricing conditions in cloud computing environments by proposing an innovative task scheduling approach. To balance the three competing objectives of electricity cost, energy consumption, and task delay, we formulate a price-aware, multi-objective task scheduling optimization problem and establish a Markov decision process model. By integrating prioritized experience replay with a multi-objective preference vector selection mechanism, we design a dynamic, multi-objective deep reinforcement learning algorithm named TEPTS. The simulation results demonstrate that TEPTS achieves superior convergence and diversity compared to three other multi-objective optimization methods while exhibiting excellent scalability across varying test durations and system workload intensities. Specifically, under the TOU pricing scenario, the task migration rate during peak periods exceeds 33.90%, achieving a 13.89% to 36.89% reduction in energy consumption and a 14.09% to 45.33% reduction in electricity costs. Full article

► Show Figures

Figure 1

16 pages, 1561 KB

Open AccessArticle

TSAformer: A Traffic Flow Prediction Model Based on Cross-Dimensional Dependency Capture

by Haoning Lv, Xi Chen and Weijie Xiu

Electronics 2026, 15(1), 231; https://doi.org/10.3390/electronics15010231 - 4 Jan 2026

Cited by 3 | Viewed by 952

Abstract

Accurate multivariate traffic flow forecasting is critical for intelligent transportation systems yet remains challenging due to the complex interplay of temporal dynamics and spatial interactions. While Transformer-based models have shown promise in capturing long-range temporal dependencies, most existing approaches compress multidimensional observations into [...] Read more.

Accurate multivariate traffic flow forecasting is critical for intelligent transportation systems yet remains challenging due to the complex interplay of temporal dynamics and spatial interactions. While Transformer-based models have shown promise in capturing long-range temporal dependencies, most existing approaches compress multidimensional observations into flattened sequences—thereby neglecting explicit modeling of cross-dimensional (i.e., spatial or inter-variable) relationships, which are essential for capturing traffic propagation, network-wide congestion, and node-specific behaviors. To address this limitation, we propose TSAformer, a novel Transformer architecture that explicitly preserves and jointly models time and dimension as dual structural axes. TSAformer begins with a multimodal input embedding layer that encodes raw traffic values alongside temporal context (time-of-day and day-of-week) and node-specific positional features, ensuring rich semantic representation. The core of TSAformer is the Two-Stage Attention (TSA) module, which first models intra-dimensional temporal evolution via time-axis self-attention then captures inter-dimensional spatial interactions through a lightweight routing mechanism—avoiding quadratic complexity while enabling all-to-all cross-node communication. Built upon TSA, a hierarchical encoder–decoder (HED) structure further enhances forecasting by modeling traffic patterns across multiple temporal scales, from fine-grained fluctuations to macroscopic trends, and fusing predictions via cross-scale attention. Extensive experiments on three real-world traffic datasets—including urban road networks and highway systems—demonstrate that TSAformer consistently outperforms state-of-the-art baselines across short-term and long-term forecasting horizons. Notably, it achieves top-ranked performance in 36 out of 58 critical evaluation scenarios, including peak-hour and event-driven congestion prediction. By explicitly modeling both temporal and dimensional dependencies without structural compromise, TSAformer provides a scalable, interpretable, and high-performance solution for spatiotemporal traffic forecasting. Full article

(This article belongs to the Special Issue Artificial Intelligence for Traffic Understanding and Control)

► Show Figures

Figure 1

23 pages, 5200 KB

Open AccessArticle

Real-Time Visual Perception and Explainable Fault Diagnosis for Railway Point Machines at the Edge

by Yu Zhai and Lili Wei

Electronics 2026, 15(1), 230; https://doi.org/10.3390/electronics15010230 - 4 Jan 2026

Cited by 3 | Viewed by 1309

Abstract

Existing inspection systems for railway point machines often suffer from high latency and poor interpretability, which impedes the real-time detection of critical mechanical anomalies, thereby increasing the risks of derailment and leading to cascading schedule delays. Addressing these challenges, this study proposes a [...] Read more.

Existing inspection systems for railway point machines often suffer from high latency and poor interpretability, which impedes the real-time detection of critical mechanical anomalies, thereby increasing the risks of derailment and leading to cascading schedule delays. Addressing these challenges, this study proposes a lightweight computer vision-based detection framework deployed on the RK3588S edge platform. First, to overcome the accuracy degradation of segmentation networks on constrained edge NPUs, a Sensitivity-Aware Mixed-Precision Quantization and Heterogeneous Scheduling (SMPQ-HS) strategy is proposed. Second, a Multimodal Semantic Diagnostic Framework is constructed. By integrating geometric engagement depths—calculated via perspective rectification—with visual features, a Hard-Constrained Knowledge Embedding Paradigm is designed for the Qwen2.5-VL model. This approach constrains the stochastic reasoning of the Qwen2.5-VL model into standardized diagnostic conclusions. Experimental results demonstrate that the optimized model achieves an inference speed of 38.5 FPS and an mIoU of 0.849 on the RK3588S, significantly outperforming standard segmentation models in inference speed while maintaining high precision. Furthermore, the average depth-estimation error remains approximately 3%, and the VLM-based fault identification accuracy reaches 88%. Overall, this work provides a low-cost, deployable, and interpretable solution for intelligent point machine maintenance under edge-computing constraints. Full article

► Show Figures

Figure 1

14 pages, 4161 KB

Open AccessArticle

Influences of Leakage Inductances in Integrated Transformer of Input-Series Flyback Converter

by Shengze Liu, Wentao Huang, Tao Meng, Hongqi Ben and Chunyan Li

Electronics 2026, 15(1), 229; https://doi.org/10.3390/electronics15010229 - 4 Jan 2026

Viewed by 971

Abstract

In this paper, the influences of leakage inductances are investigated for the integrated transformer of an input-series flyback converter, in which each input-series circuit is based on the single-switch flyback topology. First, the configuration of this converter is introduced, and a novel multiple-inductor [...] Read more.

In this paper, the influences of leakage inductances are investigated for the integrated transformer of an input-series flyback converter, in which each input-series circuit is based on the single-switch flyback topology. First, the configuration of this converter is introduced, and a novel multiple-inductor coupling model is proposed for its flyback integrated transformer. Second, the operational process of this converter is analyzed by considering the leakage inductances between the primary and secondary windings of its integrated transformer. Third, the influences of these leakage inductances are analyzed; on this basis, the essential design considerations of the flyback integrated transformer are summarized. Finally, an experimental prototype of this input-series converter is built. Based on this, the analysis is verified by the experimental comparisons among three flyback integrated transformers with various winding layouts. Full article

(This article belongs to the Section Power Electronics)

► Show Figures

Figure 1

12 pages, 440 KB

Open AccessArticle

Symmetrized Extrinsic Information Transfer Chart Analysis for Joint Decoding Between LDPC Codes and CCDMs

by Gang Yang, Fei Yang and Yanan Luo

Electronics 2026, 15(1), 228; https://doi.org/10.3390/electronics15010228 - 4 Jan 2026

Viewed by 632

Abstract

This paper proposes a symmetrized extrinsic information transfer (S-EXIT) chart analysis for probabilistic shaped (PS) systems to optimize the joint decoding of low-density parity-check (LDPC) codes and constant composition distribution matchers (CCDMs). A major challenge in analyzing PS systems is the non-uniform channel [...] Read more.

This paper proposes a symmetrized extrinsic information transfer (S-EXIT) chart analysis for probabilistic shaped (PS) systems to optimize the joint decoding of low-density parity-check (LDPC) codes and constant composition distribution matchers (CCDMs). A major challenge in analyzing PS systems is the non-uniform channel input caused by shaping, which invalidates the all-zero assumption of traditional EXIT charts, coupled with the three-node structure of the joint decoder (variable nodes, check nodes, and shaping nodes) that exceeds the two-decoder framework of conventional EXIT analysis. To resolve these issues, we first prove the symmetry of the joint decoder and introduce a “symmetrized density” transformation to render the channel output symmetric, thereby enabling the extension of EXIT chart analysis to PS systems. We then approximate the EXIT function of the shaping node decoder via polynomial fitting and integrate it with the variable node decoder into a unified model (VSND) for threshold analysis. On one hand, the proposed S-EXIT chart provides a theoretical threshold for the joint decoder, which is crucial for guiding system design. On the other hand, it enables the joint optimization of LDPC code rates and CCDM rates, unlocking additional performance gains. Simulations over additive white Gaussian noise (AWGN) channels demonstrate that short-blocklength CCDMs (e.g., blocklength 20) achieve up to 1.2 dB gain over uniform systems via S-EXIT-based rate optimization. This work addresses the performance limitations of short-blocklength CCDMs in high-speed optical transmissions, offering a practical and efficient analytical tool for PS system design. Full article

(This article belongs to the Special Issue Advances in Optical Communications and Optical Networks)

► Show Figures

Figure 1

16 pages, 1546 KB

Open AccessArticle

A Deep Reinforcement Learning-Based Approach for Bandwidth-Aware Service Function Chaining

by Yan-Jing Wu, Shi-Hao Hwang, Wen-Shyang Hwang and Ming-Hua Cheng

Electronics 2026, 15(1), 227; https://doi.org/10.3390/electronics15010227 - 4 Jan 2026

Cited by 1 | Viewed by 1032

Abstract

Network function virtualization (NFV) is an emerging technology that is gaining popularity for network function migration. NFV converts a network function from a dedicated hardware device into a virtual network function (VNF), thereby improving the agility of network services and reducing management costs. [...] Read more.

Network function virtualization (NFV) is an emerging technology that is gaining popularity for network function migration. NFV converts a network function from a dedicated hardware device into a virtual network function (VNF), thereby improving the agility of network services and reducing management costs. A complex network service can be expressed as a service function chain (SFC) request, which consists of an ordered sequence of VNFs. Given the inherent heterogeneity and dynamic nature of network services, effective SFC deployment encounters significant unpredictable challenges. Machine learning-based methods offer the flexibility to predict and select the optimal next action based on existing data models. In this paper, we propose a deep reinforcement learning-based approach for bandwidth-aware service function chaining (DRL-BSFC). Aiming to simultaneously improve the acceptance ratio of SFC requests and maximize the total revenue for Internet service providers, DRL-BSFC integrates a graph convolutional network (GCN) for feature extraction of the underlying physical network, a sequence-to-sequence (Seq2Seq) model for capturing the order information of an SFC request, and a modified A3C (Asynchronous Advantage Actor–Critic) algorithm of deep reinforcement learning. To ensure efficient resource utilization and a higher acceptance ratio of SFC requests, the bandwidth cost for deploying an SFC is explicitly incorporated into the A3C’s reward function. The effectiveness and superiority of DRL-BSFC compared to the existing DRL-SFCP scheme are demonstrated via simulations. The performance measures include the acceptance ratio of SFC requests, the average bandwidth cost, the average remaining link bandwidth, and the average revenue-to-cost ratio under different SFC request arrival rates. Full article

(This article belongs to the Special Issue New Trends in Machine Learning, System and Digital Twins)

► Show Figures

Figure 1

14 pages, 1590 KB

Open AccessArticle

A Novel Switching Sequence Control Strategy for Reference Tracking in Power Converters

by Yujia Tang, Yihua Zhu, Guoqing Wang, Wenzhe Hao, Zijian Zhang, Zhiyong Dai and Guangqi Li

Electronics 2026, 15(1), 226; https://doi.org/10.3390/electronics15010226 - 3 Jan 2026

Viewed by 568

Abstract

With the growing penetration of wind energy into modern power grids, the demand for high-performance converter control has increased significantly. In particular, precise current reference tracking is essential to guarantee efficient energy conversion and robust system operation under dynamic wind and grid variations. [...] Read more.

With the growing penetration of wind energy into modern power grids, the demand for high-performance converter control has increased significantly. In particular, precise current reference tracking is essential to guarantee efficient energy conversion and robust system operation under dynamic wind and grid variations. This paper addresses the challenge of precise reference tracking in power converters by introducing a novel switching sequence control (SSC) strategy. The proposed method is systematically developed and demonstrated through a step-by-step application to a power converter. More importantly, the SSC framework enables a systematic and accurate analysis of converter performance in both dynamic and steady-state regimes. The effectiveness and practicality of the proposed control strategy are validated through comprehensive simulation and experimental results. Full article

(This article belongs to the Special Issue New Trends in Power Electronics for Renewable Energy and Power Systems)

► Show Figures

Graphical abstract

30 pages, 5831 KB

Open AccessSystematic Review

A Systematic Literature Review of Augmented Reality’s Development in Construction

by José Marinho, Filipe Sá, João Durães, Inácio Fonseca and Nuno Cid Martins

Electronics 2026, 15(1), 225; https://doi.org/10.3390/electronics15010225 - 3 Jan 2026

Cited by 1 | Viewed by 3057

Abstract

Augmented reality (AR) has emerged as a transformative technology, allowing users to engage with digital content overlaid on the physical world. In the construction industry, AR shows significant potential to enhance visualization, collaboration, training, and safety across the project lifecycle. This paper presents [...] Read more.

Augmented reality (AR) has emerged as a transformative technology, allowing users to engage with digital content overlaid on the physical world. In the construction industry, AR shows significant potential to enhance visualization, collaboration, training, and safety across the project lifecycle. This paper presents a systematic literature review (SLR) of 136 publications on the use of AR in construction published between 2019 and 2025, focusing on architectures, technologies, trends, and challenges. The review identifies the main architectures (cloud, hybrid, and local) and examines how AR is combined with Building Information Modeling (BIM) systems, digital twins, the Internet of Things (IoT), and Unmanned Aerial Vehicles (UAVs). Key application trends are identified and discussed, including on-site visualization, inspection and monitoring, immersive training, hazard detection, and remote collaboration. Challenges and constraints to the adoption of AR in construction are highlighted and examined such as hardware limitations, usability and ergonomics issues, interoperability with existing systems, high costs, and resistance to organizational change. By systematizing existing approaches and mapping both opportunities and barriers, this review provides a comprehensive reference for researchers, practitioners, and policy makers aiming to accelerate AR adoption in the construction sector. Full article

► Show Figures

Figure 1

39 pages, 3907 KB

Open AccessArticle

RoadMark-cGAN: Generative Conditional Learning to Directly Map Road Marking Lines from Aerial Orthophotos via Image-to-Image Translation

by Calimanut-Ionut Cira, Naoto Yokoya, Miguel-Ángel Manso-Callejo, Ramon Alcarria, Clifford Broni-Bediako, Junshi Xia and Borja Bordel

Electronics 2026, 15(1), 224; https://doi.org/10.3390/electronics15010224 - 3 Jan 2026

Viewed by 1305

Abstract

Road marking lines can be extracted from aerial images using semantic segmentation (SS) models; however, in this work, a conditional generative adversarial network, RoadMark-cGAN, is proposed for direct extraction of these representations with image-to-image translation techniques. The generator features residual and attention blocks [...] Read more.

Road marking lines can be extracted from aerial images using semantic segmentation (SS) models; however, in this work, a conditional generative adversarial network, RoadMark-cGAN, is proposed for direct extraction of these representations with image-to-image translation techniques. The generator features residual and attention blocks added in a functional bottleneck, while the discriminator features a modified PatchGAN, with an optimized encoder and an attention block added. The proposed model is improved in three versions (v2 to v4), in which dynamic dropout techniques and a novel “Morphological Boundary-Sensitive Class-Balanced” (MBSCB) loss are progressively added to better handle the high class imbalance present in the data. All models were trained on a novel “RoadMarking-binary” dataset (29,405 RGB orthoimage tiles of 256 × 256 pixels and their corresponding ground truth masks) to learn the distribution of road marking lines found on pavement. The metrical evaluation on the test set containing 2045 unseen images showed that the best proposed model achieved average improvements of 45.2% and 1.7% in the Intersection-over-Union (IoU) score for the positive, underrepresented class when compared to the best Pix2Pix and SS models, respectively, trained for the same task. Finally, a qualitative, visual comparison was conducted to assess the quality of the road marking predictions of the best models and their mapping performance. Full article

(This article belongs to the Special Issue Signal and Image Processing Applications in Artificial Intelligence, 2nd Edition)

► Show Figures

Figure 1

19 pages, 38545 KB

Open AccessArticle

Improving Dynamic Visual SLAM in Robotic Environments via Angle-Based Optical Flow Analysis

by Sedat Dikici and Fikret Arı

Electronics 2026, 15(1), 223; https://doi.org/10.3390/electronics15010223 - 3 Jan 2026

Viewed by 1113

Abstract

Dynamic objects present a major challenge for visual simultaneous localization and mapping (Visual SLAM), as feature measurements originating from moving regions can corrupt camera pose estimation and lead to inaccurate maps. In this paper, we propose a lightweight, semantic-free front-end enhancement for ORB-SLAM [...] Read more.

Dynamic objects present a major challenge for visual simultaneous localization and mapping (Visual SLAM), as feature measurements originating from moving regions can corrupt camera pose estimation and lead to inaccurate maps. In this paper, we propose a lightweight, semantic-free front-end enhancement for ORB-SLAM that detects and suppresses dynamic features using optical flow geometry. The key idea is to estimate a global motion direction point (MDP) from optical flow vectors and to classify feature points based on their angular consistency with the camera-induced motion field. Unlike magnitude-based flow filtering, the proposed strategy exploits the geometric consistency of optical flow with respect to a motion direction point, providing robustness not only to depth variation and camera speed changes but also to different camera motion patterns, including pure translation and pure rotation. The method is integrated into the ORB-SLAM front-end without modifying the back-end optimization or cost function. Experiments on public dynamic-scene datasets demonstrate that the proposed approach reduces absolute trajectory error by up to approximately 45% compared to baseline ORB-SLAM, while maintaining real-time performance on a CPU-only platform. These results indicate that reliable dynamic feature suppression can be achieved without semantic priors or deep learning models. Full article

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

► Show Figures

Figure 1

18 pages, 729 KB

Open AccessArticle

HetRelMTL-Net: A Unified Framework for Knowledge Graph Completion via Graph–Text Fusion and Multi-Task Dynamic Optimization

by Yujie Wu, Xuefeng Xi, Fei Wang, Shengli Sheng, Zhiming Cui and Run Zhu

Electronics 2026, 15(1), 222; https://doi.org/10.3390/electronics15010222 - 3 Jan 2026

Viewed by 879

Abstract

Knowledge graph completion (KGC) necessitates comprehensive modeling of heterogeneous relations by effectively integrating both graph structural information and textual semantics. Current approaches often exhibit fragmented feature utilization or suboptimal multi-tasking coordination, which limits their capability to handle complex relational patterns such as symmetry, [...] Read more.

Knowledge graph completion (KGC) necessitates comprehensive modeling of heterogeneous relations by effectively integrating both graph structural information and textual semantics. Current approaches often exhibit fragmented feature utilization or suboptimal multi-tasking coordination, which limits their capability to handle complex relational patterns such as symmetry, hierarchy, and asymmetry. This paper proposes HetRelMTL-Net, a unified framework that introduces two key innovations: (1) GraphBert-KGC, a graph–text fusion module that dynamically aligns structural and semantic features through relation-aware attention and adaptive gating mechanisms, achieving a 97% reduction in parameter redundancy compared to fixed-projection baselines; and (2) a multi-task learning architecture that jointly optimizes link prediction, relation classification, and path reasoning via a KL-divergence-based dynamic weighting strategy, effectively mitigating task conflicts while enhancing semantic discriminability. Extensive experiments on two publicly available benchmarks, WN18RR and FB15k-237, demonstrate state-of-the-art performance: achieving 28.7% Hits@1 on asymmetric relations (a 19.1% improvement over RotatE), an 85.8% higher MRR than TransE, and 12% faster convergence. The robustness and efficacy of the framework are further validated through detailed ablation studies, attention visualizations, and real-world case analyses. Full article

(This article belongs to the Special Issue Advanced Research in Technology and Information Systems, 2nd Edition)

► Show Figures

Figure 1

17 pages, 3250 KB

Open AccessArticle

Evaluating Middleware Performance in the Transition from Monolithic to Microservices Architecture for Banking Applications

by Rizza Fauziah and Nico Surantha

Electronics 2026, 15(1), 221; https://doi.org/10.3390/electronics15010221 - 2 Jan 2026

Viewed by 2429

Abstract

The swift development of digital financial services has increased transaction volumes and heightened system performance requirements. Cardless cash deposit transactions at PT Bank XYZ have significantly increased since 2022. This growth necessitates an evaluation and improvement of the existing system architecture. This study [...] Read more.

The swift development of digital financial services has increased transaction volumes and heightened system performance requirements. Cardless cash deposit transactions at PT Bank XYZ have significantly increased since 2022. This growth necessitates an evaluation and improvement of the existing system architecture. This study proposes a microservices-based architecture deployed in a middleware environment to enhance performance, scalability, and availability. Key enhancements include asynchronous service processing, dual-layer authentication, and data caching using the Terracotta Server Array. The evaluation uses metrics such as CPU usage, RAM usage, latency, throughput, error rate, success rate, and recovery time. Both the monolithic and microservice architectures were assessed through stress testing. Tools used include Red Hat OpenShift Dashboard, NMon Visualizer, and Apache JMeter. Results indicate that the microservices architecture outperforms the monolithic architecture by delivering better resource efficiency, lower latency, higher throughput, and faster recovery times. Moreover, implementing dual-layer authentication enhances security without significantly increasing system complexity. The findings confirm the long-term viability of the microservices architecture for high-demand financial applications. Full article

(This article belongs to the Special Issue Advanced System Architectures and AI-Driven Innovations for Next-Generation Computing)

► Show Figures

Figure 1

23 pages, 4423 KB

Open AccessArticle

Softmax-Derived Brain Age Mapping: An Interpretable Visualization Framework for MRI-Based Brain Age Prediction

by Ting-An Chang, Shao-Yu Yan, Kuan-Chih Wang and Chung-Wen Hung

Electronics 2026, 15(1), 220; https://doi.org/10.3390/electronics15010220 - 2 Jan 2026

Viewed by 1381

Abstract

Brain age has been widely recognized as an important biomarker for monitoring adolescent brain development and assessing dementia risk. However, existing model visualization methods primarily highlight brain regions associated with aging, making it difficult to comprehensively reveal broader brain changes. In this study, [...] Read more.

Brain age has been widely recognized as an important biomarker for monitoring adolescent brain development and assessing dementia risk. However, existing model visualization methods primarily highlight brain regions associated with aging, making it difficult to comprehensively reveal broader brain changes. In this study, we developed a VGGNet-based brain age prediction model and proposed the Softmax-Derived Brain Age Mapping algorithm to simultaneously identify brain regions associated with both youthful and aging features. The resulting saliency maps provide explicit representations of developmental and degenerative processes across different brain regions. Brain Age Map analysis revealed that aging features in the healthy group were primarily confined to the frontal cortex, aligning with findings that the frontal lobe is the earliest region to undergo natural senescence. In contrast, the dementia group exhibited widespread aging across the frontal, temporal, parietal, and occipital lobes, as well as the ventricular regions. These results suggest that the spatial distribution of brain aging can serve as a critical biomarker for distinguishing normal aging trajectories from pathological degeneration. From an application perspective, we further explored the potential of the proposed framework in neurodegenerative diseases. The analysis reveals that dementia patients generally exhibit an advanced brain age, with cortical aging being markedly more pronounced than in age-matched healthy samples. Notably, although dementia cases were not included in the training set, the model was still able to localize abnormalities in relevant brain regions, underscoring its potential value as an assistive tool for early dementia diagnosis. Full article

(This article belongs to the Special Issue Image and Signal Processing Techniques and Applications)

► Show Figures

Figure 1

34 pages, 3066 KB

Open AccessEditor’s ChoiceArticle

Underwater Antenna Technologies with Emphasis on Submarine and Autonomous Underwater Vehicles (AUVs)

by Dimitrios G. Arnaoutoglou, Tzichat M. Empliouk, Dimitrios-Naoum Papamoschou, Yiannis Kyriacou, Andreas Papanastasiou, Theodoros N. F. Kaifas and George A. Kyriacou

Electronics 2026, 15(1), 219; https://doi.org/10.3390/electronics15010219 - 2 Jan 2026

Cited by 3 | Viewed by 2815

Abstract

Following the persistent evolution of terrestrial 5G wireless systems, a new field of underwater communication has emerged for various related applications like environmental monitoring, underwater mining, and marine research. However, establishing reliable high-speed underwater networks remains notoriously difficult due to the severe RF [...] Read more.

Following the persistent evolution of terrestrial 5G wireless systems, a new field of underwater communication has emerged for various related applications like environmental monitoring, underwater mining, and marine research. However, establishing reliable high-speed underwater networks remains notoriously difficult due to the severe RF attenuation in conductive seawater, which strictly limits range coverage. In this article, we focus on a comprehensive review of different antenna types for future underwater communication and sensing systems, evaluating their performance and suitability for Autonomous Underwater Vehicles (AUVs). We critically examine and compare distinct antenna technologies, including Magnetic Induction (MI) coils, electrically short dipoles, wideband traveling wave antennas, printed planar antennas, and novel magnetoelectric (ME) resonators. Specifically, these antennas are compared in terms of physical footprint, operating frequency, bandwidth, and realized gain, revealing the trade-offs between miniaturization and radiation efficiency. Our analysis aims to identify the benefits and weaknesses of the different antenna types while emphasizing the necessity of innovative antenna designs to overcome the fundamental propagation limits of the underwater channel. Full article

(This article belongs to the Special Issue Smart Antennas and Systems for 5G and Beyond: Latest Advances and Prospects, 2nd Edition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 15, Issue 1 (January-1 2026) – 248 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI