Electronics

19 pages, 1293 KB

Open AccessArticle

Validation of Soft Wearable Sensors for Wrist and Elbow Kinematics During Simulated Industrial Tasks

by Purva Talegaonkar, David Saucier, Laith Bani Khaled, Erin Tillery, Alana J. Turner, Russell Lowell, James Weinstein, John E. Ball, Harish Chander, Brian K. Smith and Reuben F. Burch V

Electronics 2026, 15(11), 2453; https://doi.org/10.3390/electronics15112453 - 3 Jun 2026

Abstract

Accurate and unobtrusive measurement of upper-limb kinematics is critical for advancing wearable sensing technologies used in industrial ergonomics, human–machine interaction, and real-time biomechanics monitoring. This study evaluates the performance of two soft, flexible wearable sensors—BendLabs biaxial angular displacement sensors and StretchSense capacitive stretch [...] Read more.

Accurate and unobtrusive measurement of upper-limb kinematics is critical for advancing wearable sensing technologies used in industrial ergonomics, human–machine interaction, and real-time biomechanics monitoring. This study evaluates the performance of two soft, flexible wearable sensors—BendLabs biaxial angular displacement sensors and StretchSense capacitive stretch sensors—for quantifying wrist and elbow motions during simulated dynamic industrial tasks. Wrist flexion–extension and radial–ulnar deviation were measured using BendLabs sensors mounted on the dorsal hand, while elbow flexion–extension was captured using StretchSense sensors positioned along the elbow joint. A multi-camera optical motion capture system served as the reference standard. Sensor data were preprocessed using baseline correction, smoothing, denoising, and normalized cross-correlation techniques to support temporal alignment with motion-capture recordings. Across all activities, the BendLabs sensors demonstrated moderate agreement with motion capture for wrist kinematics, with generally better performance for radial–ulnar deviation than for flexion–extension. StretchSense sensors demonstrated stronger agreement with motion capture for elbow flexion–extension, with performance that was generally consistent across task types. These findings support the feasibility of soft wearable sensors for capturing upper-limb kinematics during simulated occupational tasks and highlight their potential for integration into ergonomic assessment, occupational monitoring systems, and future industrial wearable platforms. Full article

(This article belongs to the Special Issue New Insights Into Smart and Intelligent Sensors)

15 pages, 2001 KB

Open AccessArticle

Adaptable and Hybrid Automation for Human–AI Task Allocation: Application to Call Center Supervision

by Lallie Donat-Bouillud and Kahina Amokrane-Ferka

Electronics 2026, 15(11), 2452; https://doi.org/10.3390/electronics15112452 - 3 Jun 2026

Abstract

In complex environments, Operators need to manage continuous, real-time information flows while handling unexpected situations within a limited timeframe. This can lead to high cognitive load, stress, fatigue, etc. To prevent such situations, Artificial Intelligence (AI) systems are increasingly being considered. Their role [...] Read more.

In complex environments, Operators need to manage continuous, real-time information flows while handling unexpected situations within a limited timeframe. This can lead to high cognitive load, stress, fatigue, etc. To prevent such situations, Artificial Intelligence (AI) systems are increasingly being considered. Their role is no limited to assistance, but extends to performing some or all of the tasks initially carried out by the operator. However, inappropriate allocation of tasks between humans and machines can exclude the operator from the loop or reduce their vigilance. This paper proposes the design and implementation of three strategies for the dynamic reallocation of tasks between a human and an AI, considering factors related to the operator (cognitive load, stress) and their activity (activity modeling). An evaluation is conducted to compare three strategies. The first two are hybrid strategies, in which both the operator and the AI can modify task allocation. The first hybrid strategy is based on self-assessment, while the second is based on activity modeling. The third strategy is an adaptable strategy, in which only the operator can change task allocation. The use case is an emergency call center simulation implemented on InteractiveAI Preliminary findings from our user exploratory study suggest that participants tended to better accept adaptable automation, while also exhibiting a higher error distribution compared to hybrid automation strategies. No significant differences were observed in cognitive load or situational awareness in this limited sample. However, recurring instances of mode confusion were observed with hybrid strategies. Full article

(This article belongs to the Special Issue Emerging Trends in Multimodal Human-Computer Interaction)

► Show Figures

Figure 1

30 pages, 6276 KB

Open AccessArticle

Benchmarking Large Language Model Inference on Limited-Resource Edge Systems

by Henrikas Giedra, Dalius Matuzevičius, Tomyslav Sledevič, Giga Shubitidze and Artūras Serackis

Electronics 2026, 15(11), 2451; https://doi.org/10.3390/electronics15112451 - 3 Jun 2026

Abstract

Large language models (LLMs) are increasingly considered for deployment on edge and limited-resource systems, where local inference can reduce latency, improve privacy, and decrease dependence on cloud infrastructure. While prior studies have evaluated either task accuracy or hardware efficiency in isolation, few benchmarks [...] Read more.

Large language models (LLMs) are increasingly considered for deployment on edge and limited-resource systems, where local inference can reduce latency, improve privacy, and decrease dependence on cloud infrastructure. While prior studies have evaluated either task accuracy or hardware efficiency in isolation, few benchmarks combine generation-based response-quality evaluation with real-device power measurements on a representative limited-resource platform. This study addresses that gap by benchmarking twelve compact and mid-scale open-weight LLMs (sub-1B to 8B parameters), evaluating generation-based accuracy on a desktop platform and measuring deployment efficiency—throughput, power consumption, and energy use—on an NVIDIA Jetson Orin Nano Super; the accuracy–efficiency trade-off is thus established at the model-configuration level. Unlike prior Jetson-based evaluations relying solely on internal telemetry, this work pairs generation-compatible lm-eval accuracy tasks with a dual power-measurement setup that combines internal tegrastats rail readings with external board-level input power measured using a digital multimeter and explicitly compares GPU-accelerated and CPU-only inference modes. GPU-accelerated inference provided a clear advantage, increasing median throughput from 7.12 to 18.13 tok/s and improving external-meter energy efficiency from 0.453 to 0.823 tok/J, despite higher mean input power. Sub-1B models offered the best throughput and energy efficiency, whereas 7–8B models achieved stronger accuracy at a substantially higher energy cost per generated token. These results demonstrate that edge LLM deployment requires multi-objective evaluation balancing accuracy, throughput, power consumption, and energy efficiency. Full article

(This article belongs to the Special Issue Advances of Artificial Intelligence and Vision Applications: Third Edition)

28 pages, 26778 KB

Open AccessArticle

LIVAS-Net: A Parameter-Efficient 3D Architecture for Intracranial Artery Segmentation in TOF-MRA

by Mekhla Sarkar, Prasan Kumar Sahoo and Yen-Chu Huang

Electronics 2026, 15(11), 2450; https://doi.org/10.3390/electronics15112450 - 3 Jun 2026

Abstract

Cerebrovascular diseases, including stroke and intracranial aneurysm, affect millions worldwide and remain a leading cause of mortality and disability. Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) enables non-invasive visualization of intracranial arteries. However, the complex cerebrovascular anatomy, characterized by variable diameters, tortuous trajectories, and intricate [...] Read more.

Cerebrovascular diseases, including stroke and intracranial aneurysm, affect millions worldwide and remain a leading cause of mortality and disability. Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) enables non-invasive visualization of intracranial arteries. However, the complex cerebrovascular anatomy, characterized by variable diameters, tortuous trajectories, and intricate branching, renders manual segmentation time-consuming, subjective, and prone to inter-observer variability. While deep learning models achieve strong segmentation performance, existing 3D approaches typically require millions of parameters, limiting deployment in resource-constrained clinical settings. To address this challenge, this paper proposes a Lightweight Intracranial Vascular Segmentation Network (LIVAS-Net), a parameter-efficient 3D encoder–decoder architecture using 3D Ghost convolution modules. It incorporates a novel Vessel Continuity Refinement Branch (VCRB), which aims to correct discontinuities in logit space through per-voxel learnable gating. Two model variants are introduced, LIVAS-Net (129K parameters, 18.3 GFLOPs) and LIVAS-L Net (2.97M parameters, 87.8 GFLOPs), achieving 7.9× and 1.6× fewer FLOPs than the standard 3D U-Net (144.5 GFLOPs), respectively. Evaluation on the multi-center COSTA benchmark shows a DSC of 0.8943 (HD95: 1.97 mm) and 0.9235 (HD95: 0.77 mm) on the ADAM test set, outperforming 3D U-Net (DSC: 0.8762). Cross-center evaluation on three external COSTA datasets yields overall DSCs of 0.7834 and 0.7967 versus 0.6998 for 3D UNet. Further evaluation on the CereVessMRA dataset (N = 271) reveals that LIVAS-Net achieves the highest DSC (0.669), demonstrating promising experimental results warranting future clinical validation in resource-constrained settings. Full article

(This article belongs to the Special Issue Feature Papers in "Computer Science & Engineering", 3rd Edition)

49 pages, 4808 KB

Open AccessArticle

A Purpose-Aware Semantic Reasoning Model for Patent Infringement Detection in the DIKWP Network

by Zhendong Guo and Yucong Duan

Electronics 2026, 15(11), 2449; https://doi.org/10.3390/electronics15112449 - 3 Jun 2026

Abstract

Patent infringement detection requires coordinated interpretation of technical claims, legal standards, and contextual evidence. This study proposes a semantic AI framework for patent infringement detection grounded in the DIKWP network and artificial consciousness theory. The DIKWP network organizes the analytical modules as interacting [...] Read more.

Patent infringement detection requires coordinated interpretation of technical claims, legal standards, and contextual evidence. This study proposes a semantic AI framework for patent infringement detection grounded in the DIKWP network and artificial consciousness theory. The DIKWP network organizes the analytical modules as interacting semantic spaces rather than as a strictly layered pipeline. This design supports iterative semantic interpretation, knowledge integration, and purpose-oriented reasoning. The framework integrates document ingestion, semantic information extraction, ontology-based knowledge representation, rule-guided inference, and decision support. The system processes patent claims, product descriptions, and prior-art documents with patent-oriented NLP. Named entity recognition and subject–action–object parsing convert unstructured text into structured semantic representations. Legal and technical ontologies support claim-element interpretation. Knowledge graphs, semantic pattern matching, and inference rules then align claim elements with product features and identify potential infringement risks. A prototype implementation demonstrates end-to-end processing from raw text to infringement-oriented assessment. The evaluation was conducted in two layers. First, a controlled synthetic patent–product corpus was used to isolate claim-element reasoning, rule-guided inference, and purpose-conditioned operating modes. Second, a real-world pilot corpus was constructed from publicly available patent claims and real product technical descriptions, including manufacturer manuals, technical datasheets, official product webpages, installation guides, and technical brochures. The controlled-corpus results show that the DIKWP network improves over keyword-matching and ontology-only baselines by integrating semantic coverage, claim-level legal reasoning, and explainable output. The real-world pilot provides a preliminary external-validity check of whether the framework can preserve element-level reasoning under realistic drafting styles, domain terminology, incomplete product evidence, and borderline claim-to-product correspondences. These findings provide preliminary evidence of feasibility and analytical value, rather than a final benchmark of litigation-level performance. Full article

(This article belongs to the Special Issue AI for Industry)

20 pages, 2016 KB

Open AccessFeature PaperArticle

Fixed-Frequency Dual-Active-Bridge Resonant Converter with Four Degrees of Freedom Using Triple Phase Shift and Current-Controlled Variable-Inductor

by Juan L. Bellido, Vicente Esteve, Mattia Vogni and José Jordán

Electronics 2026, 15(11), 2448; https://doi.org/10.3390/electronics15112448 - 3 Jun 2026

Abstract

The increasing adoption of electric vehicles (EVs) demands highly efficient bidirectional DC–DC converters capable of seamless energy transfer between the grid and vehicle batteries. This paper introduces a Fixed-Frequency Dual-Active-Bridge (DAB) resonant converter featuring four degrees of freedom, achieved through a combination of [...] Read more.

The increasing adoption of electric vehicles (EVs) demands highly efficient bidirectional DC–DC converters capable of seamless energy transfer between the grid and vehicle batteries. This paper introduces a Fixed-Frequency Dual-Active-Bridge (DAB) resonant converter featuring four degrees of freedom, achieved through a combination of triple phase-shift (TPS) modulation and a current-controlled variable inductor (VI). The proposed control strategy aims to minimize conduction and switching losses by simultaneously managing reactive power, RMS current, and soft-switching conditions across wide variations in voltage and power. Unlike conventional phase-shift or variable-frequency modulations, the fixed-frequency operation maintains full zero-voltage switching (ZVS) for the two bridges, and zero-current switching (ZCS) in the bridge that is receiving energy, enhancing overall system reliability and control simplicity. The proposed converter is validated through simulations and experimental results from a SiC MOSFET-based 14 kW prototype operating at 122 kHz, demonstrating peak efficiencies above 97% under both charging and discharging modes. The experimental results confirm that the proposed DAB topology and modulation scheme significantly improve efficiency and controllability, making it a promising solution for next-generation on-board chargers and vehicle-to-grid (V2G) applications. Full article

(This article belongs to the Special Issue Advances in Power Converter Design, Control and Applications, 2nd Edition)

21 pages, 23743 KB

Open AccessArticle

Dynamic Extension IDA-PBC for an Active Switched-Inductor High-Gain Power Converter

by Diego Langarica-Cordoba, Panfilo R. Martinez-Rodriguez, David Reyes-Cruz, Rafael Cisneros, Angel Hernandez-Gomez and Juan A. Villanueva-Loredo

Electronics 2026, 15(11), 2447; https://doi.org/10.3390/electronics15112447 - 3 Jun 2026

Abstract

This paper presents a nonlinear control scheme for regulating the output voltage of a high-gain active switched-inductor boost converter. The proposed converter topology extends the conventional boost converter by incorporating an additional inductor and a power semiconductor device, thereby enhancing the voltage conversion [...] Read more.

This paper presents a nonlinear control scheme for regulating the output voltage of a high-gain active switched-inductor boost converter. The proposed converter topology extends the conventional boost converter by incorporating an additional inductor and a power semiconductor device, thereby enhancing the voltage conversion ratio. The control objectives are twofold: precise regulation of the output voltage and stabilization of the inductor current. To achieve these goals, an interconnection and damping assignment passivity-based control strategy is developed. A dynamic extension is further introduced to compensate for steady-state errors caused by unmodeled parasitic resistances in the system components. In addition, a reference current generator with proportional–integral action is implemented to provide an appropriate current reference. The effectiveness of the proposed controller is validated both numerically and experimentally under three operating scenarios: load step changes, input voltage variations, and output voltage reference transitions. Full article

(This article belongs to the Special Issue Section Collection Series: New Horizons and Recent Advances in Power Electronics, 2nd Edition)

29 pages, 931 KB

Open AccessArticle

Threat Analysis and Risk Assessment of the Takeover Request Component in Advanced Driver Assistance Systems for SAE Level 2–3

by Adnan Kujovic, João André Gomes Marques, Mark Paul Tamaş and Rahamatullah Khondoker

Electronics 2026, 15(11), 2446; https://doi.org/10.3390/electronics15112446 - 3 Jun 2026

Abstract

This paper presents a Threat Analysis and Risk Assessment (TARA) of the takeover request (TOR) component in Advanced Driver Assistance Systems (ADAS) for SAE Level 2–3 automation. A TOR prompts the human driver to retake control when the system approaches its Operational Design [...] Read more.

This paper presents a Threat Analysis and Risk Assessment (TARA) of the takeover request (TOR) component in Advanced Driver Assistance Systems (ADAS) for SAE Level 2–3 automation. A TOR prompts the human driver to retake control when the system approaches its Operational Design Domain limits or when risk increases; late, false, or muted requests directly impact safety. The study models the TOR pipeline (perception, driver monitoring, decision logic, in-vehicle networks, and Human–Machine Interface) as assets and data flows, applies STRIDE-based threat identification using Microsoft Threat Modeling Tool and Ansys Medini Analyze, and rates risks under ISO/SAE 21434 with traceability to ISO 26262, ISO 21448, and UNECE R155/R157. The assessment produces 165 threat rows, with an initial risk distribution of 1 Critical, 113 High, 34 Medium, and 17 Low. Results show that tampering, denial of service, and spoofing dominate the TOR threat landscape, with the central processing unit, sensor-to-CPU links, and HMI channels as primary trust anchors. After applying mitigation measures including secure boot, message authentication, intrusion detection, redundancy checks, and encrypted communication, the residual post-mitigation security levels were reduced to 0 Critical, 0 High, 13 Medium, 101 Low, and 51 Negligible. Unlike other ADAS TARA studies, this TOR-focused analysis shows that cybersecurity risk is shaped by the interaction between cyber compromise, driver-readiness estimation, HMI delivery, fallback execution, and the limited handover time budget. The results support a defence-in-depth mitigation strategy for secure TOR operation in SAE Level 2–3 vehicles. Full article

(This article belongs to the Special Issue Innovations and Challenges in Automotive Mobility and Automation Systems)

44 pages, 2901 KB

Open AccessReview

Nanofluid-Based Cooling Strategies for Intelligent BTMSs in Electric Vehicles: Recent Advances, Thermal Safety, and Control-Oriented Architectures

by Tai Duc Le, Loc-Xuan Tong and Moo-Yeon Lee

Electronics 2026, 15(11), 2445; https://doi.org/10.3390/electronics15112445 - 3 Jun 2026

Abstract

Effective thermal management is crucial for the performance, thermal safety, and lifespan of lithium-ion batteries in electric vehicles (EVs). Thermal management strategies are essential for preventing overheating, thermal imbalance, and the associated risk of thermal runaway. Nanofluids are emerging and attracting considerable attention [...] Read more.

Effective thermal management is crucial for the performance, thermal safety, and lifespan of lithium-ion batteries in electric vehicles (EVs). Thermal management strategies are essential for preventing overheating, thermal imbalance, and the associated risk of thermal runaway. Nanofluids are emerging and attracting considerable attention as potential coolants for high-power energy storage and electronics systems. This review updates and summarizes the most recent advances in nanofluid-based cooling strategies for battery thermal management systems (BTMSs) over the past five years, emphasizing their implications for battery thermal safety. Three main nanofluid-based cooling strategies have been evaluated in depth, including nanofluid-based indirect liquid cooling, nanoparticle-enhanced PCM cooling, and nanofluid-based heat pipe cooling. Various nanofluid formulations, including mono, hybrid, and ternary nanofluids, have been considered and evaluated for their heat dissipation under high charge/discharge and abuse-relevant conditions. Thermal and hydraulic performance characteristics, including maximum temperature, maximum temperature difference, and pressure drop, have been comprehensively evaluated for different nanofluid-based cooling strategies. The findings demonstrated that nanofluids significantly improved heat transfer rates and enhanced temperature control efficiency. In particular, hybrid and ternary nanofluids exhibit superior thermal performance and effectively suppress the escalation of safety-critical temperatures. Beyond summarizing cooling performance, this review further discusses the role of nanofluid-based cooling strategies as functional thermal-control layers within intelligent BTMS architectures. Particular attention is given to their compatibility with sensing networks, BMS-/VCU-level supervisory control, predictive thermal models, actuator responsiveness, fault-warning algorithms, and long-term reliability under realistic driving and fast charging conditions. Therefore, this review provides architecture-oriented insights for developing safe, energy-efficient, and control-ready BTMSs for next-generation high-power and connected EVs. Full article

(This article belongs to the Special Issue Battery Health Management for Cyber-Physical Energy Storage Systems)

21 pages, 2630 KB

Open AccessArticle

Aggregation Control Strategy for Battery Swapping Station Clusters in Response to Battery Swapping and Grid Regulation Needs

by Jiawei Chen, Wenzuo Tang, Wenke Xu, Xi Chen, Yuan Jin, Xianglu Liu and Jingruo Hu

Electronics 2026, 15(11), 2444; https://doi.org/10.3390/electronics15112444 - 3 Jun 2026

Abstract

The participation of battery swapping station (BSS) clusters in grid regulation is significantly constrained by the spatio-temporal uncertainty and climate sensitivity of electric vehicle (EV) demand. To address these issues, this paper proposes an aggregated scheduling method that integrates demand forecasting and rolling [...] Read more.

The participation of battery swapping station (BSS) clusters in grid regulation is significantly constrained by the spatio-temporal uncertainty and climate sensitivity of electric vehicle (EV) demand. To address these issues, this paper proposes an aggregated scheduling method that integrates demand forecasting and rolling optimization. First, a demand forecasting model is established by considering seasonal climate and users’ range anxiety. On this basis, a “day-ahead bidding and intra-day tracking” two-stage scheduling framework is constructed. In the day-ahead stage, the optimal bidding power of the cluster is determined for minimizing the overall cluster cost. In the intra-day stage, taking the bidding power as the tracking index, the demand distribution scheme and station charging/discharging strategies are synergistically optimized to minimize the operational costs. Furthermore, for real-time EV swapping requests, suitable BSS nodes are recommended based on the distribution scheme. To address the stochasticity of user rejection, rolling optimization is applied for real-time adjustments, ensuring reliable grid response and service quality. Finally, a case study using real operational data verifies the effectiveness of the proposed model. Full article

► Show Figures

Figure 1

23 pages, 8606 KB

Open AccessArticle

FPGA-Based AI-Driven Hardware-in-the-Loop Platform for Low-Latency Real-Time ABS ECU Testing

by Farshideh Kordi, Paul Fortier and Amine Miled

Electronics 2026, 15(11), 2443; https://doi.org/10.3390/electronics15112443 - 3 Jun 2026

Abstract

This paper presents an FPGA-based hardware-in-the-loop (HIL) platform for real-time simulation testing of anti-lock braking system (ABS) electronic control units (ECUs). The proposed system integrates a Temporal Convolutional Network (TCN) model implemented on FPGA hardware to provide real-time predictions of wheel speed sensors [...] Read more.

This paper presents an FPGA-based hardware-in-the-loop (HIL) platform for real-time simulation testing of anti-lock braking system (ABS) electronic control units (ECUs). The proposed system integrates a Temporal Convolutional Network (TCN) model implemented on FPGA hardware to provide real-time predictions of wheel speed sensors under complex braking scenarios. The FPGA acceleration achieves low-latency processing with a total end-to-end latency of 10.61 µs per prediction cycle, corresponding to approximately 94.3 Ksamples/s, which is suitable for closed-loop automotive testing. Experimental results show that the TCN model provides accurate prediction based on mean squared errors below 0.001043 for key parameters such as wheel speed sensors and lateral acceleration. The modular architecture of the simulator allows extensibility to other automotive ECUs and provides a scalable solution for real-time system validation in safety-critical applications. Full article

(This article belongs to the Special Issue FPGA-Based Accelerators for Deep Neural Networks)

► Show Figures

Figure 1

25 pages, 15692 KB

Open AccessArticle

An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection

by Wenrui Wang, Dong Zhou, Wenjie Xie and Wenshuai Zhang

Electronics 2026, 15(11), 2442; https://doi.org/10.3390/electronics15112442 - 3 Jun 2026

Abstract

Real-time deployment of modern object-detection networks on edge devices is challenging because of limited compute resources, external-memory bandwidth, and strict power constraints. To address these issues, this paper presents a host–FPGA collaborative accelerator for quantized YOLOv5n on a Xilinx Zynq-7100 platform. The proposed [...] Read more.

Real-time deployment of modern object-detection networks on edge devices is challenging because of limited compute resources, external-memory bandwidth, and strict power constraints. To address these issues, this paper presents a host–FPGA collaborative accelerator for quantized YOLOv5n on a Xilinx Zynq-7100 platform. The proposed design includes a modular multi-operator neural processing unit supporting seven atomic operators, a Dual-Multiply Packing (DMP) scheme to improve DSP48E1-based INT8 convolution density, a cache–compute–cache dataflow with global ping-pong buffering to overlap DMA transfers and computation, and a Multi-Quantization Domain Alignment (MQDA) pipeline to preserve accuracy at Add and Cat fusion nodes. Implemented at 200 MHz, the prototype achieves 24.617 ms FPGA-side forward-inference latency, 36.686 ms end-to-end single-frame latency, 27.2 FPS system-level performance, 182.8 GOPS equivalent throughput, and 8.536 W on-chip power consumption, corresponding to 21.42 GOPS/W. Experimental results also show that INT8 quantization causes only limited accuracy degradation, while MQDA improves quantized detection accuracy by reducing cross-domain fusion error. These results demonstrate that the proposed architecture provides an effective balance among throughput, energy efficiency, hardware cost, and quantized accuracy for real-time edge object detection. Full article

► Show Figures

Figure 1

26 pages, 31069 KB

Open AccessArticle

Eight-Wheel Mecanum Omnidirectional Autonomous Mobile Robot: Kinematics, Architecture, and Validation

by Leonardo D. Ortega-Lomeli, Luis C. Básaca-Preciado, Ulises Orozco-Rosas, J. D. Castro-Toscano and M. A. Ponce-Camacho

Electronics 2026, 15(11), 2441; https://doi.org/10.3390/electronics15112441 - 3 Jun 2026

Abstract

Autonomous omnidirectional vehicles that combine redundant holonomic kinematics, ROS 2/micro-ROS implementation, and simulation-to-real validation remain limited in the literature. This paper presents an eight-wheel Mecanum autonomous mobile robot for campus navigation in environments shared with pedestrians. The work formulates forward and inverse kinematics [...] Read more.

Autonomous omnidirectional vehicles that combine redundant holonomic kinematics, ROS 2/micro-ROS implementation, and simulation-to-real validation remain limited in the literature. This paper presents an eight-wheel Mecanum autonomous mobile robot for campus navigation in environments shared with pedestrians. The work formulates forward and inverse kinematics for the redundant eight-wheel topology and implements a distributed architecture in which ROS 2 handles high-level navigation and micro-ROS connects ESP32-based wheel interfaces. The platform integrates LiDAR, stereo vision, inertial, encoder, and ultrasonic sensing within a closed-loop navigation stack. Validation was conducted through Gazebo simulation and physical experiments using an out-and-back navigation protocol. In the physical platform, 91 of 100 missions were completed without safety interruptions, with pose-accuracy success rates of 96% for outbound legs and 81% for return legs under

e_{p} < 1.5 m

and

| e_{θ} | < 15^{\circ}

. Median errors at the intermediate waypoint were

0.64 m

,

0.191 m

, and

17^{\circ}

, while final-pose medians after return were

1.016 m

,

0.573 m

, and

{28.5}^{\circ}

. These results provide a quantitative baseline for campus-scale redundant Mecanum navigation and identify heading recovery as the main limitation. Full article

(This article belongs to the Special Issue Robotics: From Technologies to Applications)

► Show Figures

Figure 1

23 pages, 2468 KB

Open AccessArticle

Research on Robot Terrain Perception Based on Attention Mechanism and Confusion Enhancement

by Xingyu Liu, Nian Wang, Meng Hong, Chao Huang, Yushuang Xiao, Sijia Liu, Zheng Xiao, Zhongren Wang, Sijia Guan and Min Guo

Electronics 2026, 15(11), 2440; https://doi.org/10.3390/electronics15112440 - 3 Jun 2026

Abstract

Robotic visual perception and terrain recognition are critical for autonomous locomotion and adaptive control in complex environments. However, existing models often extract weak features, confuse classes, and deliver unstable recognition. Most prior studies use end-to-end convolutional networks or single-stream feature extraction, which limits [...] Read more.

Robotic visual perception and terrain recognition are critical for autonomous locomotion and adaptive control in complex environments. However, existing models often extract weak features, confuse classes, and deliver unstable recognition. Most prior studies use end-to-end convolutional networks or single-stream feature extraction, which limits the balance between fine-grained visual representation and adaptive discrimination of confusing samples. To solve this problem, this paper proposes a vision model that blends attention mechanisms with a confusion augmentation strategy. Using an improved ResNet50 backbone, we add a local feature sharpening module and a channel–spatial attention module to strengthen edge texture and global context representation. We also design a confusion augmentation strategy based on the similarity of hard samples. It generates mixed samples through cross-perturbation in feature space, thereby improving the discrimination of highly similar terrains. Experiments show that our model achieves an accuracy of over 98.19% on various terrains, including cement, asphalt, sand, and snow. t-SNE visualization and Grad-CAM analysis demonstrate clear class separability and good interpretability, confirming the effectiveness and robustness of the approach for robotic terrain recognition. Full article

► Show Figures

Figure 1

21 pages, 6485 KB

Open AccessReview

A Review on Electromagnetic Spectrum Map Construction: Methods, Challenges, and System Integration for 6G

by Chenxiao Yu, Min Guo, Qing Guo, Dongwei Zhao, Lechi Zhang, Zhenyu Xu, Anjie Cao, Junteng Yang, Wensheng Lin, Wenchi Cheng, Qinghe Du and Lixin Li

Electronics 2026, 15(11), 2439; https://doi.org/10.3390/electronics15112439 - 3 Jun 2026

Abstract

As wireless networks evolve from 5G toward 6G, the complexity of the electromagnetic environment increases sharply. Spectrum usage expands significantly into millimetre-wave (mmWave) and terahertz (THz) high-frequency bands. Network node density and mobility increase markedly. Moreover, communication-sensing-computation functions are deeply integrated. Accurate, real-time, [...] Read more.

As wireless networks evolve from 5G toward 6G, the complexity of the electromagnetic environment increases sharply. Spectrum usage expands significantly into millimetre-wave (mmWave) and terahertz (THz) high-frequency bands. Network node density and mobility increase markedly. Moreover, communication-sensing-computation functions are deeply integrated. Accurate, real-time, full-band Electromagnetic Spectrum Maps (ESMs) have become a core infrastructure for 6G spectrum situational awareness, Dynamic Spectrum Access (DSA), interference coordination, and Integrated Sensing and Communication (ISAC). However, while a growing body of recent work extends radio mapping to multi-band and temporal domains, the predominant focus of existing Radio Map research remains the two-dimensional spatial power distribution at a single fixed frequency—essentially a degenerate special case of ESM after the frequency and time dimensions are collapsed—and no existing survey unifies 3D spatial construction, time-varying prediction, and full 6G system integration under a shared 4D formalism. This paper focuses on the three core research dimensions of ESMs, i.e., 3D spatial ESM construction, dynamic time-varying ESM modelling and prediction, and ESM integration with 6G systems. Under a unified four-dimensional ESM framework (space × frequency × time × power), we clarify the hierarchical relationships among ESM/SEM/REM/Radio Map/Channel Knowledge Maps (CKMs). Then, we systematically review 3D ESM construction, dynamic ESM modelling and prediction, and the integration of ESM with CKM/Digital Twin Networks (DTNs)/ISAC. Finally, we identify five, core open problems that constrain the development of the field to provide a systematic reference for 6G intelligent spectrum management research. Full article

(This article belongs to the Special Issue Multimodal Sensing and Communications for B5G/6G Systems)

► Show Figures

Figure 1

18 pages, 2104 KB

Open AccessArticle

An Application-Oriented Comparative Study of Segmentation Paradigms for Key Geospatial Element Extraction Under Extreme Class Imbalance

by Jiali Jin, Xi Yong, Honglin Sun, Sai Wang, Peiyu Zhang, Zelong Zheng, Zhaofeng He, Qi Li, Zhenan Sun and Jing Fu

Electronics 2026, 15(11), 2438; https://doi.org/10.3390/electronics15112438 - 3 Jun 2026

Abstract

Remote sensing applications often require the extraction of a small number of task-critical geospatial elements under severe class imbalance. This setting is challenging because dominant categories occupy most pixels, while targets of interest may be sparse, fragmented, or semantically ambiguous. In this study, [...] Read more.

Remote sensing applications often require the extraction of a small number of task-critical geospatial elements under severe class imbalance. This setting is challenging because dominant categories occupy most pixels, while targets of interest may be sparse, fragmented, or semantically ambiguous. In this study, we build our analysis on a remote sensing dataset consisting of 10,482 pixel-wise annotated RGB image tiles covering 14 semantic categories with pronounced long-tailed characteristics. Based on this dataset, we conduct an application-oriented comparative study of eight representative segmentation models on four key geospatial element categories with different sparsity levels and visual properties. Quantitative evaluation is performed using Intersection over Union, Precision, Recall, and F1-score, and representative qualitative cases are examined to analyze model behavior. An additional comparison with conventional multi-class segmentation shows that the target-oriented setting should be understood not as a universally superior alternative, but as a complementary application-oriented setting for analyzing target-specific delineation behavior under severe imbalance. The results further indicate that segmentation difficulty cannot be explained by target proportion alone, but is jointly associated with target morphology, spatial fragmentation, and semantic similarity to surrounding categories. These findings provide practical guidance for segmentation model selection in highly imbalanced remote sensing applications. Full article

(This article belongs to the Special Issue Data-Related Challenges in Machine Learning: Theory and Application)

► Show Figures

Figure 1

22 pages, 5447 KB

Open AccessArticle

Resilient Cooperative Localisation for EVs Using V2X Sidelink Measurements Under Hybrid Cyber-Attacks: A Deep Learning-Based Physical-Layer Security Framework

by Ahmed M. A. A. Elngar, Mohammed J. Abdulaal and Mohammed Ahmed Salem

Electronics 2026, 15(11), 2437; https://doi.org/10.3390/electronics15112437 - 3 Jun 2026

Abstract

In this work, we explore resilient cooperative localisation for electric vehicles subject to the hybrid attack of gradual global navigation satellite system (GNSS) drag-off spoofing along with received signal strength indicator (RSSI) jamming. In order to mitigate such attacks, a deep learning-based physical-layer [...] Read more.

In this work, we explore resilient cooperative localisation for electric vehicles subject to the hybrid attack of gradual global navigation satellite system (GNSS) drag-off spoofing along with received signal strength indicator (RSSI) jamming. In order to mitigate such attacks, a deep learning-based physical-layer security approach is presented. The presented approach includes a long short-term memory (LSTM) detector for attack detection, a regression-based RSSI signal purifier, and a cooperative fusion scheme, which decreases the dependence on the GNSS branch in case of attack detection. The proposed approach is validated via the Berlin Vehicle-to-Everything (V2X) dataset with respect to six scenarios, including benign GNSS-only and cooperative localisation, attacked localisation without defence, and attacked localisation with physical-layer security support. According to the experimental evaluation results, the considered hybrid attack significantly impacts the localisation accuracy, leading to an increase in the GNSS-only localisation error to root mean square error (RMSE) = 149.93 m, mean absolute error (MAE) = 129.81 m, and maximum error = 259.62 m. At the same time, the proposed cooperative localisation with physical-layer security decreases the attacked cooperative localisation error to RMSE = 4.00 m, MAE = 3.51 m, and maximum error = 12.01 m. Full article

(This article belongs to the Special Issue Physical Layer Technologies for Low-Altitude Intelligent Networks)

► Show Figures

Figure 1

14 pages, 2138 KB

Open AccessArticle

On-Chip Diplexer at E-Band 83/95 GHz

by Mohammed Wehbi, Loïc Vincent, Cédric Durand, Philippe Ferrari and Hamza Issa

Electronics 2026, 15(11), 2436; https://doi.org/10.3390/electronics15112436 - 3 Jun 2026

Abstract

This paper presents a fully integrated E-band (83/95 GHz) diplexer realized in STMicroelectronics’ BiCMOS 55 nm technology. The design directly addresses the critical trade-off between miniaturization and the performance required for high-frequency on-chip systems. The key innovation is a novel patch resonator optimally [...] Read more.

This paper presents a fully integrated E-band (83/95 GHz) diplexer realized in STMicroelectronics’ BiCMOS 55 nm technology. The design directly addresses the critical trade-off between miniaturization and the performance required for high-frequency on-chip systems. The key innovation is a novel patch resonator optimally exploiting the multi-layer structure of the technology’s Back-End-Of-Line. It achieves significant compactness by jointly combining two distinct miniaturization techniques: slotted structures and mushroom-type capacitive loading. This method results in an impressive 77% size reduction compared to conventional designs. Furthermore, we introduce precisely controlled transmission zeros (TZs) to maximize inter-band isolation. The fabricated diplexer achieves a remarkably narrow fractional bandwidth (FBW) of 8.2%—the lowest reported to date for integrated BiCMOS/CMOS E-band implementations—and a robust inter-band isolation exceeding 25 dB, while demonstrating excellent return loss (better than 25 dB). Hence, this work validates a highly compact and scalable approach for integrated E-band transceivers, paving the way for future 6G front-end applications. Full article

► Show Figures

Figure 1

26 pages, 6760 KB

Open AccessArticle

A Proposal-Aware Proactive Encoding Framework for Trajectory Prediction in Autonomous Driving

by Hongkun Liu, Xuetao Liu and Ziyi Liu

Electronics 2026, 15(11), 2435; https://doi.org/10.3390/electronics15112435 - 2 Jun 2026

Abstract

Trajectory prediction plays a crucial role in autonomous driving by forecasting the future trajectories of agents to support safe and efficient decision-making. Most existing methods that adopt an encoder–decoder architecture have achieved remarkable success, where the scene encoder extracts contextual representations from agents’ [...] Read more.

Trajectory prediction plays a crucial role in autonomous driving by forecasting the future trajectories of agents to support safe and efficient decision-making. Most existing methods that adopt an encoder–decoder architecture have achieved remarkable success, where the scene encoder extracts contextual representations from agents’ history trajectories and lane segments. However, this architecture remains fundamentally constrained by the blind encoder. Specifically, the scene encoder of models extracts contextual information without foresight, leading to significant semantic pollution from proposal-irrelevant context, thereby degrading the prediction performance. To rectify this model deficiency, we propose ProFocus, a proactive encoding framework that reformulates the trajectory prediction model architecture via an anticipatory feedback loop. ProFocus generates the potential proposals in the nascent stage layers, utilizing them as attentional priors to dynamically modulate the scene encoding process. In addition, to optimize the information flow within the attention mechanism and reduce irrelevant context interference in attention distributions, we introduce spatio-temporal focal attention (STFA). By implementing a relation-conditioned sharpening operator through a spatio-temporal relation-controlled softmax, STFA adaptively recalibrates the attention distribution according to related dependencies. Comprehensive evaluations on the Argoverse 1 dataset and INTERACTION dataset validate that ProFocus attains competitive performance across miss rate (MR), minimum average displacement error (minADE) and minimum final displacement error (minFDE), while maintaining a real-time inference speed of 16 ms on an RTX 3090. The results from our ablation studies demonstrate that ProFocus reduces MR, minFDE, and minADE by 2.80%, 2.52%, and 1.41% relative to the baseline, respectively. Furthermore, qualitative visualizations also corroborate that ProFocus exhibits robust performance in diverse traffic scenarios. Full article

► Show Figures

Figure 1

20 pages, 741 KB

Open AccessArticle

An Energy-Sustainable Approach Combining Time Slot Allocation and Power Splitting Ratio Determination in SWIPT-Enabled WSNs

by Zhizhong He, Xuan Liu and Deyu Lin

Electronics 2026, 15(11), 2434; https://doi.org/10.3390/electronics15112434 - 2 Jun 2026

Abstract

Little existing work addresses the joint design of time slot allocation and power splitting ratio optimization in simultaneous wireless information and power transfer (SWIPT)-enabled wireless sensor networks (WSNs). To fill this gap, this paper proposes a novel energy-sustainable framework termed ETAPS that co-optimizes [...] Read more.

Little existing work addresses the joint design of time slot allocation and power splitting ratio optimization in simultaneous wireless information and power transfer (SWIPT)-enabled wireless sensor networks (WSNs). To fill this gap, this paper proposes a novel energy-sustainable framework termed ETAPS that co-optimizes time slot allocation and power splitting ratio for SWIPT-enabled WSNs. A dedicated frame structure is designed that partitions each cluster member (CM) into four operational modes for slot scheduling, toward conflict-free and coordinated resource allocation among CMs. A dynamic power splitting strategy is further developed to adaptively refine slot allocation for CMs and derive the optimal power splitting ratio for the cluster head (CH). Comprehensive numerical simulations are performed to validate the proposed scheme. The results demonstrate that ETAPS maintains effective energy sustainability even under limited energy input from the energy access point (EAP). When the EAP provides a sufficient energy supply, the optimal power splitting ratio converges to 0.9. Moreover, under sufficient transmit power at CMs, ETAPS adaptively allocates transmission time from CMs to the CH by setting the optimal power splitting ratio to 0.6. Full article

(This article belongs to the Special Issue Next-Generation MIMO Systems with Enhanced Communication and Sensing)

36 pages, 14036 KB

Open AccessArticle

A Suppression Method for Filter-Order Burden Based on Asynchronous SAR Quantizer Residue

by Zongyan Hou, Haitao Xie, Linhan Zhang, Jie Wu and Wenzao Shi

Electronics 2026, 15(11), 2433; https://doi.org/10.3390/electronics15112433 - 2 Jun 2026

Abstract

This paper presents a passive residue-coupled discrete-time delta–sigma (

Δ Σ

) modulator for low-power narrowband sensing applications. Instead of adding a fourth active integrator, the proposed architecture keeps a third-order switched-capacitor main loop and reuses the intrinsic top-plate residue of an 8-bit [...] Read more.

This paper presents a passive residue-coupled discrete-time delta–sigma (

Δ Σ

) modulator for low-power narrowband sensing applications. Instead of adding a fourth active integrator, the proposed architecture keeps a third-order switched-capacitor main loop and reuses the intrinsic top-plate residue of an 8-bit asynchronous successive-approximation-register (SAR) quantizer. The retained capacitive digital-to-analog converter (CDAC) residue is passively reinjected through a charge-redistribution path, introducing an additional high-pass error-propagation factor in the effective noise transfer function (NTF). Under a bounded effective coupling coefficient, the proposed loop approaches fourth-order-like in-band noise suppression while retaining third-order active-loop complexity. Behavioral simulations show that the Enhanced mode improves the peak signal-to-noise-and-distortion ratio (SNDR) by 16.9 dB over the Baseline third-order mode at an oversampling ratio (OSR) of 128. Circuit-level corner verification of the standalone SAR confirms correct bit cycling and a settled residue-retention window under typical–typical (TT), slow–slow (SS), and fast–fast (FF) conditions: with the slowest conversion window of about 21.4 ns at the SS corner and a sampling period of 39.06 ns at

f_{s} = 25.6

MHz, roughly 17.66 ns of timing margin remains for residue holding, passive reinjection, and clock non-overlap. The proposed method provides an architecture-level route for improving in-band noise shaping without increasing the number of active integrator stages, and is particularly attractive for low-power, narrowband, and sensor-oriented analog-to-digital converter (ADC) applications. Full article

(This article belongs to the Special Issue Design and Application of Digital Circuit and Systems)

24 pages, 880 KB

Open AccessArticle

Decision-Making Method for Load Connection in Business Expansion Considering the Bearing Capacity of Active Distribution Network and Load Growth

by Xixi Li, Junxian Luo, Zhicong Kuang and Yuling He

Electronics 2026, 15(11), 2432; https://doi.org/10.3390/electronics15112432 - 2 Jun 2026

Abstract

To address the insufficient consideration of load temporal characteristics, load growth, distributed generation (DG) integration, and business-expansion load connection in existing available-capacity assessment methods, this paper proposes a load-connection decision-making method for active distribution network. Firstly, considering the load temporal characteristics, load growth, [...] Read more.

To address the insufficient consideration of load temporal characteristics, load growth, distributed generation (DG) integration, and business-expansion load connection in existing available-capacity assessment methods, this paper proposes a load-connection decision-making method for active distribution network. Firstly, considering the load temporal characteristics, load growth, DG, and the bearing capacity of transformer distribution districts, a time-series bearing capacity analysis model of transformer distribution districts is proposed. In addition, a heuristic topology search strategy considering dynamic capacity constraints is developed to identify feasible power-supply paths and evaluate the dynamically validated available capacity. Secondly, considering the integration of DG and energy storage systems (ESSs), as well as key indicators such as load balance, temporal characteristic matching and comprehensive economic performance, a business-expansion load-connection decision-making method for active distribution network is proposed. Finally, the effectiveness of the proposed model and method is validated through a case study. The results show that after DG and ESS integration, the load balancing degree and temporal characteristic matching index are improved by approximately 31.42% and 18.21%, respectively. Compared with the peak-capacity method, single-capacity-index method, and loss-priority method, the proposed method achieves the highest or jointly highest comprehensive decision value under different operating scenarios. The improved branch-and-bound method reduces the number of actual evaluations while obtaining the same optimal decision result. The proposed method can optimize load-connection schemes and provide theoretical foundation and practical decision support for active distribution network planning and business expansion. Full article

29 pages, 8886 KB

Open AccessArticle

Privacy-Preserving Cascaded Federated Deep Learning for Nomophobia Risk Prediction with Encrypted Masked Updates

by Md Wahidur Rahman, Rahat Khan, Mais Nijim, Waseem Al Aqqad, Yoichi Tomioka, Jungpil Shin and Mehdi Hasan

Electronics 2026, 15(11), 2431; https://doi.org/10.3390/electronics15112431 - 2 Jun 2026

Abstract

Smartphones are now deeply embedded in daily life, but excessive dependence may increase the risk of nomophobia, which is associated with anxiety, sleep disruption, and reduced productivity. Existing screening methods mainly rely on self-reported questionnaires, which are subjective and difficult to scale for [...] Read more.

Smartphones are now deeply embedded in daily life, but excessive dependence may increase the risk of nomophobia, which is associated with anxiety, sleep disruption, and reduced productivity. Existing screening methods mainly rely on self-reported questionnaires, which are subjective and difficult to scale for continuous monitoring. This study proposes a privacy-preserving federated deep learning framework for three-level nomophobia risk prediction (Normal, Mild, and Severe) using smartphone usage logs while keeping raw user data on local devices. The proposed pipeline uses a publicly available secondary dataset with 1000 original records and expands it to 100,000 records through constraint-aware synthetic augmentation. A continuous risk score is computed from standardized smartphone usage indicators and then converted into three classes using tertile-based thresholds. Several local architectures, including CNN, MLP, ResMLP, Wide & Deep, and a lightweight TabNet-style gated model, are evaluated under FedAvg. In the reported experiments, differential privacy is enabled through DP-SGD with gradient clipping and Gaussian noise. To protect update transmission, the framework applies protected update sharing through encrypted transport of masked updates. Each client masks its local update and encrypts the masked payload before transmission. This mechanism improves communication confidentiality and reduces the direct exposure of client updates. Under a fixed federated setup with five clients and 25 communication rounds, tabular models achieved near-ceiling performance on the constructed test set. The MLP achieved 99.12% accuracy, 99.12% F1-score, 0.9868 MCC, and 0.9997 AUC, while Wide & Deep achieved 98.95% accuracy, 98.95% F1-score, 0.9843 MCC, and 0.9997 AUC. In contrast, sequential models such as RNN and LSTM showed near-random performance, suggesting that the current aggregated feature representation is better suited to tabular learning than temporal modeling. These results indicate that the proposed federated pipeline can effectively learn the constructed nomophobia risk labels while preserving local data ownership. However, because the labels are derived from usage features rather than clinical or psychometric assessment, the findings should be interpreted as proof-of-concept results for constructed risk labels rather than evidence of clinical diagnostic validity. Full article

(This article belongs to the Special Issue Security and Privacy Challenges in Integrated IoT and Edge Systems)

► Show Figures

Figure 1

50 pages, 3882 KB

Open AccessArticle

Adaptive Neuro-Fuzzy Inference System for High-Accuracy Flexible Power Point Prediction in Utility-Scale Grid-Connected Photovoltaic Plants

by Yassine Boudouaoui, Abdellatif Seghiour, Ali Abderrazak Tadjeddine, Abdelkader Mekri, Fouad Kaddour, Imene Meriem Mostefaoui, Aissa Chouder and Abdelhamid Rabhi

Electronics 2026, 15(11), 2430; https://doi.org/10.3390/electronics15112430 - 2 Jun 2026

Abstract

Grid-connected photovoltaic (PV) systems integrated into industrial and institutional buildings are critical components of sustainable built environments, where accurate real-time power estimation underpins smart energy management, demand–supply balancing, and reduced dependence on the utility grid. This study develops and validates an Adaptive Neuro-Fuzzy [...] Read more.

Grid-connected photovoltaic (PV) systems integrated into industrial and institutional buildings are critical components of sustainable built environments, where accurate real-time power estimation underpins smart energy management, demand–supply balancing, and reduced dependence on the utility grid. This study develops and validates an Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting of the flexible power point (FPP) in a 117.76 kWp rooftop PV plant serving a technical workshop facility in northwestern Algeria. The proposed model uses environmental inputs (solar irradiance, ambient temperature, module temperature) and electrical inputs (load power, grid power) acquired from a supervisory monitoring infrastructure to predict the PV system’s FPP under real operating conditions in the built environment. A dataset of 24,479 valid samples spanning 85 distinct calendar days (1 May to 24 July 2025) was collected and preprocessed through cleaning, filtering, and feature-specific normalization. To ensure rigorous out-of-sample evaluation, three complementary validation strategies were implemented: (S1) a random day-based split (60 train/11 test days), (S2) a strictly chronological 70/15/15% split (50/11/10 days), and (S3) an external 14-day hold-out (11–24 July 2025) excised before any training, tuning or model selection step. Statistical analysis reveals strong nonlinear dependence of PV power on solar irradiance and module temperature, with correlations

r \approx 0.93

between irradiance and module temperature,

r \approx 0.82

between irradiance and PV power, and

r \approx 0.95

between load and grid power, highlighting the importance of accurate predicting for facility-level energy management. The ANFIS model achieves

R^{2} = 0.9992

, RMSE

= 653.62

W and MAE

= 276.90

W on the random-split test set;

R^{2} = 0.9998

, RMSE

= 325.40

W and MAE

= 119.17

W on the chronological test set and

R^{2} = 0.9997

–

0.9998

, RMSE

= 363.45

–

408.50

W on the external 14-day hold-out that was never seen during training. Comparative experiments with k-Nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine, and a Deep Neural Network show that ANFIS is the only model maintaining sub-700 W RMSE on every split, whereas all five benchmarks degrade sharply under chronological and external evaluation (e.g., SVM 2225 → 5198 W; Decision Tree 7440 → 8058 W; DNN 1576 → 2576 W). The persistence of test/external RMSE below the training RMSE on data never used during model construction empirically rules out data leakage as a cause of the high accuracy. These results demonstrate that the proposed, interpretable neuro-fuzzy framework offers a robust and accurate tool for PV power estimation in building-integrated systems, supporting smart energy management and improved performance of energy-intensive built environments. Full article

(This article belongs to the Special Issue Renewable Energy Power and Artificial Intelligence)

► Show Figures

Figure 1

19 pages, 776 KB

Open AccessArticle

A Polynomial-Structured Encoding Method for High-Density QC-LDPC Codes

by Zhe Liu, Wu Guan, Xiujun Zhang, Peihao Fan and Liping Liang

Electronics 2026, 15(11), 2429; https://doi.org/10.3390/electronics15112429 - 2 Jun 2026

Abstract

High-density (HD) quasi-cyclic low-density parity-check (QC-LDPC) codes are widely adopted in high-speed, high-reliability optical communication systems. However, the high density of the quasi-cyclic parity-check matrix prevents the direct derivation of a corresponding quasi-cyclic generator matrix, leading to computationally prohibitive encoding complexity. To address [...] Read more.

High-density (HD) quasi-cyclic low-density parity-check (QC-LDPC) codes are widely adopted in high-speed, high-reliability optical communication systems. However, the high density of the quasi-cyclic parity-check matrix prevents the direct derivation of a corresponding quasi-cyclic generator matrix, leading to computationally prohibitive encoding complexity. To address this limitation, based on the established polynomial-ring representation of QC-LDPC codes, this paper develops a structure-preserving polynomial-domain transformation for the high-density 50G-PON QC-LDPC parity-check matrix. The proposed method transforms the dense quasi-cyclic parity-check matrix into a compact systematic encoding form over

R = F_{2} [x] / (x^{256} - 1)

. As a result, parity generation is reduced to the inversion of a small

3 \times 3

polynomial submatrix and a sequence of cyclic-shift-and-XOR operations. Based on this construction, an optimized HD-QC-LDPC encoding algorithm and its corresponding FPGA architecture are developed. The resulting hardware encoder achieves a throughput of 58.9 Gbps at a 200 MHz clock frequency on a Xilinx Kintex-7 FPGA, satisfying the throughput and latency requirements of 50G-PON systems. Full article

21 pages, 444 KB

Open AccessArticle

Cognitive Biases in Large Language Models: A Systematic Quantitative Assessment and Debiasing Analysis

by Antonio Pagliaro

Electronics 2026, 15(11), 2428; https://doi.org/10.3390/electronics15112428 - 2 Jun 2026

Abstract

Large Language Models (LLMs) are increasingly deployed in decision-support systems across high-stakes domains, yet their susceptibility to cognitive biases—systematic deviations from rational judgment well-documented in human psychology—remains poorly understood in quantitative terms. Existing studies typically examine a narrow set of biases, test a [...] Read more.

Large Language Models (LLMs) are increasingly deployed in decision-support systems across high-stakes domains, yet their susceptibility to cognitive biases—systematic deviations from rational judgment well-documented in human psychology—remains poorly understood in quantitative terms. Existing studies typically examine a narrow set of biases, test a single model family, and rely on qualitative assessments of bias presence. In this work, we present a rigorous experimental framework, inspired by the methodology of experimental physics, for the systematic quantitative measurement of cognitive biases in LLMs. We introduce the Bias Strength Index (BSI), a normalized metric with associated confidence intervals that quantifies the magnitude of bias on a continuous scale, and we decompose the total uncertainty into statistical and systematic components—the latter arising from prompt reformulation. We evaluate a comprehensive taxonomy of eleven cognitive biases (including anchoring, framing effect, confirmation bias, availability heuristic, sunk cost fallacy, bandwagon effect, status quo bias, and others) across eight state-of-the-art LLMs from seven families: GPT-4.1 Mini, Claude 3.5 Sonnet, Gemini 2.5 Flash, Llama 3.3 70B, Llama 3.1 8B, Mistral Large (mistral-large-2411), DeepSeek V3, and MiniMax M2.5. Each bias is probed through multiple semantically equivalent prompt variants, with N = 100 independent trials per configuration, yielding a dataset of over 70,000 model responses. Our results reveal that all tested models exhibit non-zero bias effects for multiple bias categories, though with markedly different profiles. A trial-level Generalized Linear Mixed-Effects Model (GLMM) analysis finds statistically significant bias effects in 27 of 43 testable bias–model combinations (62.8%) after multiple-comparison correction, while a more conservative variant-level test—which requires effects to generalize across prompt formulations—yields only one significant result, highlighting the dominant role of prompt-induced systematic uncertainty. Framing and primacy/recency effects are near-universal, while susceptibility to other biases varies substantially across model families. We further evaluate three debiasing strategies—zero-shot chain-of-thought, adversarial counter-prompting, and role-based prompting—applied at inference time without modifying model weights. Our findings provide a quantitative foundation for auditing cognitive biases in LLMs and highlight the bias-dependent effectiveness of prompt-based debiasing techniques. Full article

(This article belongs to the Special Issue Future Technologies for Data Management, Processing and Application, 2nd Edition)

29 pages, 8188 KB

Open AccessArticle

Efficient Fault Rupture Simulation with a Dual-Stage Fourier Neural Operator and Physics-Based Sampling

by Ming Yuan, Zhaohui Guo and Qiang Liu

Electronics 2026, 15(11), 2427; https://doi.org/10.3390/electronics15112427 - 2 Jun 2026

Abstract

Accurately simulating fault rupture dynamics is critical for aftershock prediction but remains computationally prohibitive due to the multiscale nature of earthquake processes. While Fourier Neural Operators (FNOs) offer a promising framework for seismic simulation, their direct application to rupture dynamics is hindered by [...] Read more.

Accurately simulating fault rupture dynamics is critical for aftershock prediction but remains computationally prohibitive due to the multiscale nature of earthquake processes. While Fourier Neural Operators (FNOs) offer a promising framework for seismic simulation, their direct application to rupture dynamics is hindered by spectral bias from global processing and resolution loss from uniform downsampling. To overcome these limitations, this paper introduces a novel dual-stage FNO architecture explicitly designed for multiscale rupture simulation. The architecture decouples the problem into a first stage for efficient low-frequency wave propagation in the non-fault zone and a second stage for resolving meter-scale nonlinear rupture dynamics within the fault zone. Then, we propose a physics-based sampling strategy that maintains high resolution in the critical fault zone while coarsening the non-fault zone based on wave-propagation criteria, coupled with an interpolation scheme that enforces conservation of mass, momentum, and energy. Evaluated on the SCEC TPV101 benchmark, our integrated framework achieves a 92.4% reduction in model parameters and a 2.34× speedup in training time compared to a baseline FNO approach, while also reducing the NRMSE in fault zones by 80.1%. Furthermore, the model demonstrates robust generalization to unseen geological parameters. Full article

(This article belongs to the Topic Advanced Artificial Intelligence Solutions for Modern Engineering Applications)

18 pages, 782 KB

Open AccessArticle

From Single-Stage Penalty to Sustained Deterrence: A Threshold-Based Analysis of 51% Attack Governance in IoT-Enabled Blockchain Systems

by Xuehuan Jiang, Xiao Liu, Guangxu Xie, Haibo Huang, Qingqi Pei, Chenhong Xiangli and Zhixue Wang

Electronics 2026, 15(11), 2426; https://doi.org/10.3390/electronics15112426 - 2 Jun 2026

Abstract

The integration of blockchain technology into the Internet of Things (IoT) offers a decentralized paradigm for data integrity. However, the emergence of 51% attacks—driven by hashrate concentration—threatens the foundational trust of these resource-constrained networks. In resource-constrained IoT-enabled blockchain environments, mining-power asymmetry and limited [...] Read more.

The integration of blockchain technology into the Internet of Things (IoT) offers a decentralized paradigm for data integrity. However, the emergence of 51% attacks—driven by hashrate concentration—threatens the foundational trust of these resource-constrained networks. In resource-constrained IoT-enabled blockchain environments, mining-power asymmetry and limited governance capability may amplify the impact of strategic attacks. These characteristics motivate the need to analyze long-term adversarial behavior and governance effectiveness under repeated interactions. This paper develops a threshold-based analytical framework that integrates a single-stage decision model and a multi-stage discounted decision model to analyze 51% attack decisions and governance effects in asymmetric blockchain mining environments. We characterize the interaction between competing mining pools as a multi-stage game, integrating key parameters such as the discount factor of future utility and recovery penalty cycles. Our analysis demonstrates that a multi-stage framework creates a “long-term deterrent effect” where the net present value of potential future losses outweighs the immediate gains of hashrate abuse. analytical results indicate that the strategic threshold for launching an attack is highly sensitive to the duration of punitive measures and the accuracy of IoT-based anomaly detection. The results provide useful insights into the design of governance and incentive mechanisms for blockchain systems deployed in resource-constrained and heterogeneous environments. Full article

(This article belongs to the Special Issue New Trends in Cybersecurity and Hardware Design for IoT)

34 pages, 31487 KB

Open AccessArticle

A Field-Deployable Visual Monitoring Device for Measuring Nocturnal Phototactic Rhythm of Rice Pests

by Youhao Fu, Lei Shu, Kailiang Li, Fang Dai, Ru Han, Wei Lin, Jiarui Fang and Chang Meng

Electronics 2026, 15(11), 2425; https://doi.org/10.3390/electronics15112425 - 2 Jun 2026

Abstract

Currently, devices such as solar insecticidal lamps are widely used in agricultural pest control, but routine trapping is insufficient to meet the demands of precision agriculture. Therefore, determining the nocturnal phototactic rhythm of pests to optimize the control strategies of insecticidal lamps has [...] Read more.

Currently, devices such as solar insecticidal lamps are widely used in agricultural pest control, but routine trapping is insufficient to meet the demands of precision agriculture. Therefore, determining the nocturnal phototactic rhythm of pests to optimize the control strategies of insecticidal lamps has become key to achieving precise pest control. However, existing automated monitoring and forecasting devices struggle to effectively monitor the nocturnal phototactic rhythm of small pests. To address this issue, this study developed an automated monitoring system for phototactic rhythm based on sticky traps and machine vision. For the hardware, an image acquisition device integrating a darkroom and scheduled supplementary lighting was designed to obtain stable time-series images of nocturnal pests. For the algorithm, the YOLO-STP detection model was proposed by improving upon the baseline YOLOv11 model. This model introduces a P2 detection layer, a Coordinate Attention (CA) mechanism, and a hybrid bounding box regression loss function integrating WIoU and NWD. Combined with a sliding window cropping method, it further enhances the detection capability for small objects. Additionally, an incremental counting method based on spatial cascade matching was proposed to mitigate counting errors caused by target occlusion or detachment in the time-series images. Experimental results indicate that the mean average precision (mAP) of the detection model was 93.2%. For the counting method, the coefficient of determination (

R^{2}

) was 0.98, with an RMSE of 1.97 and an MAE of 1.60. Field validation in real-world paddy fields demonstrated that the system can accurately record the abundance changes of 12 pest species, intuitively visualizing the differences in phototactic rhythms among various species. This study provides a viable automated monitoring tool for acquiring the nocturnal activity rhythm data of agricultural pests in the field. Full article

(This article belongs to the Collection Electronics for Agriculture)

► Show Figures

Figure 1

39 pages, 4725 KB

Open AccessSystematic Review

Advancements in Physics-Informed Neural Networks for Solving Maxwell’s Equations: A Systematic Literature Review

by Lucas Schmeing and Fabian Pioch

Electronics 2026, 15(11), 2424; https://doi.org/10.3390/electronics15112424 - 2 Jun 2026

Abstract

This systematic literature review investigates the use of physics-informed neural networks (PINNs) in electromagnetics by examining peer-reviewed articles and conference papers. By integrating governing physical laws into the loss function of a neural network, PINNs offer a mesh-free method in scientific computing. Records [...] Read more.

This systematic literature review investigates the use of physics-informed neural networks (PINNs) in electromagnetics by examining peer-reviewed articles and conference papers. By integrating governing physical laws into the loss function of a neural network, PINNs offer a mesh-free method in scientific computing. Records published between 2020 and 2025 were retrieved from the databases Scopus, Web of Science, and IEEE Xplore. The initial dataset comprised 500 records, from which 292 unique publications were identified. These were screened, yielding a final set of 139 publications that met predefined eligibility criteria. The analysis reveals growth in research activity, with a pronounced increase from 2022 onward. The literature predominantly addresses electrodynamic problems, employs feedforward neural network architectures, and adopts physics-only training. Two-dimensional problem formulations dominate, with three-dimensional formulations concentrated almost exclusively in electrodynamics, and no publications addressing electroquasistatics were identified. Contingency tables show that methodological choices are not independent of problem characteristics: medium selection correlates with physics regime, and architectural diversity increases with spatial dimensionality. Based on these findings, priorities for future work include: addressing the gap in electroquasistatics, extending three-dimensional formulations to static and quasistatic regimes, broader architectural experimentation in lower-dimensional settings, and increased integration of labeled data in static electromagnetics. To support methodological consistency and reproducibility, a reporting checklist for future PINN-based electromagnetics publications is proposed. Full article

Journal Menu

Journal Browser

Electronics, Volume 15, Issue 11 (June-1 2026) – 223 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI