Electronics

2 pages, 133 KB

Open AccessCorrection

Correction: Jeong et al. A 2.4 GHz CMOS Pulse-Mode Transmitter for RF Body-Contouring Device Applications. Electronics 2025, 14, 4826

by Geonwoo Jeong, Hwayoung Jung, Sijin Jang, Kyu-Jin Cho, Jae-Woo Shin, Yun-Seong Eo, Eun-Seong Kim, Nam-Young Kim, Jaeeun Jang and Hyunchol Shin

Electronics 2026, 15(10), 2090; https://doi.org/10.3390/electronics15102090 (registering DOI) - 14 May 2026

Abstract

The authors Kyu-Jin Cho, Jae-Woo Shin, Yun-Seong Eo, Eun-Seong Kim, and Nam-Young Kim were not included as authors in the original publication [...] Full article

15 pages, 2962 KB

Open AccessArticle

Design and Experimental Evaluation of a Low-Cost Dual-Frequency Sensor for Soil Electrical Conductivity and Moisture Estimation

by Vasileios D. Koufogeorgos, Kyriakos Tsiakmakis, Vasileios Vassios, Maria S. Papadopoulou, George Kokkonis, Stefanos Stefanou and Argyrios T. Hatzopoulos

Electronics 2026, 15(10), 2089; https://doi.org/10.3390/electronics15102089 - 13 May 2026

Abstract

Soil apparent electrical conductivity (EC_a), volumetric water content (VWC), and temperature are important parameters for evaluating soil condition and supporting irrigation and crop management practices. This study presents the design and experimental evaluation of a ultra-low-hardware-cost soil sensing [...] Read more.

Soil apparent electrical conductivity (EC_a), volumetric water content (VWC), and temperature are important parameters for evaluating soil condition and supporting irrigation and crop management practices. This study presents the design and experimental evaluation of a ultra-low-hardware-cost soil sensing system capable of estimating these three parameters through impedance-based measurements at different frequency ranges. The proposed system uses sinusoidal excitation in the kHz range for EC_α estimation and in the MHz range for VWC estimation, while temperature is also considered as a relevant factor affecting the electrical behavior of soil. The sensor was experimentally tested on three soil types under two moisture conditions, namely water addition with and without mixing, and the results were compared with those obtained from a commercial instrument (5TE Meter Group). The overall mean error of the developed system, without calibration, was 20.2%, with mean errors of 16.3% for EC_a and 24.2% for VWC. Although the accuracy achieved is lower than that of commercial instruments, the results demonstrate that the proposed system can provide a satisfactory preliminary assessment of soil conditions in applications where low cost, simplicity and ease of implementation are important. The results can be significantly improved if calibration is made initially for the soil type of the field to be measured. Electrode geometry, lack of calibration with a larger set of soil samples and PCB implementation issues are the main limitations affecting performance. Overall, the proposed approach shows potential as a supportive tool for low-cost agricultural monitoring and decision-making applications. The implementation of a system that measures soil conductivity and moisture in two frequency ranges measurement (kHz for EC_α/MHz for VWC), with synchronous soil temperature measurement, at a particularly low cost, is the innovation of the sensor system. Full article

24 pages, 579 KB

Open AccessArticle

Evaluating LLMs for the Automated Generation of Operational Detection Rules in Enterprise EDR Environments

by Ioannis Konstantaras, Efstratios Chatzoglou, Konstantinos E. Kampourakis and Georgios Kambourakis

Electronics 2026, 15(10), 2088; https://doi.org/10.3390/electronics15102088 - 13 May 2026

Abstract

Modern Endpoint Detection and Response (EDR) platforms, such as Microsoft Defender for Endpoint (MDE), provide sophisticated telemetry but often leave Security Operations Centers (SOCs) struggling with a significant detection lag, namely the time required to manually translate emerging threat intelligence into operational logic. [...] Read more.

Modern Endpoint Detection and Response (EDR) platforms, such as Microsoft Defender for Endpoint (MDE), provide sophisticated telemetry but often leave Security Operations Centers (SOCs) struggling with a significant detection lag, namely the time required to manually translate emerging threat intelligence into operational logic. This paper presents a systematic empirical study of an LLM-integrated pipeline designed to automate the transformation of structured threat intelligence from OpenCTI into functional Kusto Query Language (KQL) detection rules. By utilizing Large Language Models (LLMs) as a contextual translation layer, we evaluate a framework that maps graph-based STIX metadata directly to proprietary EDR schemas. Our experiments, conducted within a high-fidelity Windows Server 2025 environment, reveal that LLM-augmented rules successfully addressed critical visibility gaps in reconnaissance and early-stage lateral movement where native MDE heuristics remained silent. Importantly, the implementation reduced the intelligence-to-logic latency from an average of 45 min of manual engineering to sub-5-min automated cycles. While the findings identify persistent challenges regarding schema hallucinations, the study concludes that LLM-assisted detection engineering serves as a significant operational force multiplier, enabling defensive postures to evolve at the velocity of the modern threat landscape. Full article

28 pages, 12194 KB

Open AccessArticle

CDMed: Medication Recommendation via Causal Inference and Dual-Granularity Information Enhancement

by Jialei Liu, Haitao Wang and Jianfeng He

Electronics 2026, 15(10), 2087; https://doi.org/10.3390/electronics15102087 - 13 May 2026

Abstract

Medication recommendation, a crucial application of artificial intelligence in healthcare, has garnered widespread attention due to its research and practical value. However, existing methods often struggle to address three key challenges: misleading co-occurrence correlations, insufficient medication representation, and the balance between recommendation accuracy [...] Read more.

Medication recommendation, a crucial application of artificial intelligence in healthcare, has garnered widespread attention due to its research and practical value. However, existing methods often struggle to address three key challenges: misleading co-occurrence correlations, insufficient medication representation, and the balance between recommendation accuracy and drug–drug interaction (DDI). To overcome these challenges, we propose CDMed, a medication recommendation framework based on causal inference and dual-granularity information enhancement. First, the framework applies causal inference to identify and quantify the real therapeutic pathways among diseases, procedures, and medications in electronic health record (EHR), effectively filtering out spurious correlations commonly found in co-occurrence statistics. Second, by integrating coarse-grained medical entity relationships with fine-grained molecular structural information, it achieves effective multi-scale information fusion and enhances medication representation. Additionally, CDMed jointly models the 2D and 3D molecular structures of medications, serving as the foundation for subsequent molecular feature extraction. Finally, to achieve a balance between recommendation accuracy and safety, we applied a DDI-Constrained Bias Correction at the output stage, which enhances recommendation accuracy while controlling clinical risks. Extensive experiments on two public datasets demonstrate that CDMed improves recommendation accuracy by 2.2%, while maintaining a low DDI rate of 0.0661 alongside high inference efficiency. This result proves that CDMed achieves an optimal balance among recommendation accuracy, safety, and computational efficiency. Full article

(This article belongs to the Special Issue AI-Driven Intelligent Systems in Energy, Healthcare, and Beyond)

15 pages, 2216 KB

Open AccessArticle

Time-Series Modeling Based on a Modified Volterra Neural Network

by Wei-Der Chang

Electronics 2026, 15(10), 2086; https://doi.org/10.3390/electronics15102086 - 13 May 2026

Abstract

This paper proposes a novel neural network model that integrates a modified Volterra digital filter with a feedforward neural network for time-series modeling. In the proposed architecture, all input signals in the conventional Volterra filter are replaced by corresponding output signals, since time-series [...] Read more.

This paper proposes a novel neural network model that integrates a modified Volterra digital filter with a feedforward neural network for time-series modeling. In the proposed architecture, all input signals in the conventional Volterra filter are replaced by corresponding output signals, since time-series problems typically consist of observable output sequences over time without explicit external inputs. These output signals, together with their cross-product terms, are constructed as input vectors for the feedforward neural network. To optimize the network parameters, including weights and thresholds, the well-known particle swarm optimization (PSO) algorithm is employed. Based on the proposed PSO-trained neural network model, two types of time series are investigated: chaotic time series and financial time series involving exchange rates. For each case, multiple independent runs with different initial conditions are conducted to ensure the robustness of the proposed method. Furthermore, the effects of varying filter orders and population sizes on modeling performance are also examined. Full article

(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications, 4th Edition)

► Show Figures

Figure 1

27 pages, 3043 KB

Open AccessArticle

Quaternion DMP with Controllable Final Angular Velocity for Robot Skill Generalization

by Xinhai Yao, Enzheng Zhang, Weijie Liao and Yihui Shen

Electronics 2026, 15(10), 2085; https://doi.org/10.3390/electronics15102085 - 13 May 2026

Abstract

Dynamic Movement Primitives (DMPs) are widely used for learning and generalizing robot skills. However, standard quaternion DMPs, when modeling orientation trajectories, constrain only the final orientation and cannot freely specify the final angular velocity. This limitation restricts its application to dynamic tasks requiring [...] Read more.

Dynamic Movement Primitives (DMPs) are widely used for learning and generalizing robot skills. However, standard quaternion DMPs, when modeling orientation trajectories, constrain only the final orientation and cannot freely specify the final angular velocity. This limitation restricts its application to dynamic tasks requiring precise boundary conditions, such as hitting or throwing. Although existing improved methods achieve velocity generalization to some extent, they often struggle to balance trajectory shape preservation with dynamic smoothness, frequently causing significant deviation from demonstrations or abrupt acceleration discontinuities. In this paper, we propose a novel robot skill generalization method that enables controllable final angular velocity for quaternion DMPs. Specifically, we construct a dynamic goal system driven by a quintic polynomial in Lie algebra space, analytically planning the target orientation’s evolution based on given multi-order boundary constraints. This mechanism not only achieves precise control over the final angular velocity but also inherently guarantees global C² continuous dynamics across primitive segments. Comparative simulations and real-world robot hitting experiments demonstrate that, compared to existing approaches, our proposed method effectively satisfies dynamic boundary constraints while exhibiting superior shape preservation, minimal trajectory deviation, and higher smoothness, thereby significantly improving skill generalization performance in complex dynamic tasks. Full article

(This article belongs to the Topic Robot Manipulation Learning and Interaction Control)

17 pages, 1321 KB

Open AccessArticle

TinySLFL: A Flash-Endurance-Aware Federated Edge Learning Framework with Layer-Wise Delayed Aggregation for Resource-Constrained Microcontrollers

by Yiru Tao, Juncheng Jia and Tao Deng

Electronics 2026, 15(10), 2084; https://doi.org/10.3390/electronics15102084 - 13 May 2026

Abstract

Federated edge learning on microcontrollers (MCUs) enables privacy-preserving adaptation, but on-device training faces a hardware tradeoff: fitting backpropagation into a limited static random-access memory (SRAM) often relies on on-chip flash as auxiliary storage, while repeated parameter persistence rapidly consumes finite program/erase (P/E) endurance. [...] Read more.

Federated edge learning on microcontrollers (MCUs) enables privacy-preserving adaptation, but on-device training faces a hardware tradeoff: fitting backpropagation into a limited static random-access memory (SRAM) often relies on on-chip flash as auxiliary storage, while repeated parameter persistence rapidly consumes finite program/erase (P/E) endurance. This paper proposes TinySLFL, a flash-endurance-aware federated learning framework for resource-constrained MCUs. On the client, layer-wise training bounds the peak SRAM usage to one layer, and delayed aggregation keeps intermediate updates in SRAM so that each communication round incurs only one flash persistence. On the server, dynamic aggregation combines loss-aware freezing with proxy-accuracy-guided filtering to improve the robustness under non-independently and identically distributed (Non-IID) data while suppressing unnecessary rounds. Experiments on CIFAR-10 and SVHN under a severe Dirichlet label skew and on a naturally heterogeneous FEMNIST showed, in a server-side simulation, that TinySLFL reduces the cumulative protocol-level erase-block operations (EOs) required to reach a common target accuracy by 97.8–98.6% relative to sequential layer training (SLT) and improves the mean Top-1 accuracy by up to 5.24 percentage points over the same ResNet-8 backbone in a five-seed evaluation. The power, latency, SRAM, and deployment feasibility were reported from actual ESP32-S3 measurements. These results demonstrate durable federated learning for extreme-edge MCUs. Full article

(This article belongs to the Special Issue Federated Edge Learning: Models, Mechanisms, Algorithms, and Applications)

34 pages, 16779 KB

Open AccessArticle

MELT: A Style-Adaptive Multimodal Folktale Generation Framework for Underrepresented Cultures

by Hanbi Choi, Yuri Kim, Dohee Kim, Heejae Shin and Minsu Lee

Electronics 2026, 15(10), 2083; https://doi.org/10.3390/electronics15102083 - 13 May 2026

Abstract

Generating culturally coherent multimodal folktales presents unique challenges, particularly for underrepresented cultures facing data scarcity and cultural bias. Existing approaches predominantly rely on Western-centric corpora, limit outputs to text–image modalities, and reduce culture to a superficial stylistic layer rather than a core narrative [...] Read more.

Generating culturally coherent multimodal folktales presents unique challenges, particularly for underrepresented cultures facing data scarcity and cultural bias. Existing approaches predominantly rely on Western-centric corpora, limit outputs to text–image modalities, and reduce culture to a superficial stylistic layer rather than a core narrative structure. In this paper, we propose MELT (Multimodal Engine for Localized Tales) a unified framework for culturally adaptive story generation across text, illustration, and audio. To achieve this, MELT embeds cultural context as a foundational generative constraint and integrates three modules: (1) a localized folktale generation module leveraging structured prompting and contextual reasoning to preserve the narrative flow and cultural identity of traditional folktales; (2) an illustration generation module that ensures cultural style and character consistency using a Tri-Stage LoRA (Low-Rank Adaptation) pipeline; (3) a storytelling audio component tailored to cultural prosody and oral storytelling conventions. Case studies on Korean and Bengali folktales demonstrate MELT’s ability to generate culturally coherent outputs using lightweight, data-efficient adaptation techniques. Human evaluation results demonstrated that MELT consistently outperformed the baseline across both case studies, showing a substantial improvement in cultural adaptation, nearly doubling the score in the Korean folktale evaluation. By positioning culture as a core generative principle, MELT provides a pathway for culturally coherent AI storytelling, particularly for underrepresented traditions. Full article

(This article belongs to the Special Issue Multimodal Learning for Multimedia Content Analysis and Understanding)

► Show Figures

Graphical abstract

15 pages, 1288 KB

Open AccessArticle

Feasibility Study of Noninvasive Subcutaneous Imaging for Vein Localization

by Sen Bing, Mao-Hsiang Huang, Hung Cao and J.-C. Chiao

Electronics 2026, 15(10), 2082; https://doi.org/10.3390/electronics15102082 - 13 May 2026

Abstract

This work presents a noninvasive imaging method to locate veins using a tuned microwave loop resonator. It offers a low-cost, fast, and effective solution to the challenges in venipuncture. The sensor features a loop resonator with a 5.2 mm radius, incorporating a self-tuning [...] Read more.

This work presents a noninvasive imaging method to locate veins using a tuned microwave loop resonator. It offers a low-cost, fast, and effective solution to the challenges in venipuncture. The sensor features a loop resonator with a 5.2 mm radius, incorporating a self-tuning mechanism, and operates at 2.408 GHz with a reflection coefficient of −48.77 dB. It generates localized high-intensity electric fields that penetrate tissues to sufficient depths, enabling the detection of veins based on shifts in resonant frequencies that are induced by the varied dielectric properties of blood vessels. Two-dimensional raster scan simulations of the cephalic and median cubital veins yielded a ∼25 MHz downward resonant-frequency shift between vein and non-vein positions, with the median cubital vein still detectable at depths up to 6 mm. To quantify generalization to real tissues, a decision tree classifier trained on 63 simulation samples and evaluated on 335 in vivo measurements achieved 82.09% classification accuracy (sensitivity 81.25%, specificity 83.02%), demonstrating that the simulation-derived frequency contrast transfers reliably to experimental data despite inter-subject tissue variability. Extensive tests conducted demonstrate the sensor’s effectiveness, producing consistent and distinguishable frequency shifts when the sensor moves on the skin across veins. This technology holds significant promise for improving venipuncture accuracy, minimizing complications, and enhancing patient comfort. Full article

(This article belongs to the Special Issue Advanced MEMS and Resonator Technologies: Design, Control, and Real-World Validation)

18 pages, 2172 KB

Open AccessArticle

Physics-Informed Neural Network-Based Solution Strategy for Voltage-Reactive Power Online Feedback Optimization Control

by Yue Shui, Zhimin Li and Gao Qiu

Electronics 2026, 15(10), 2081; https://doi.org/10.3390/electronics15102081 - 13 May 2026

Abstract

With the continuous increase in renewable energy penetration and the expansion of power grid scale, the computational complexity and solution time of traditional voltage-reactive power (V-Q) control solution methods have grown significantly, making it difficult to achieve fast responses in real-time voltage control. [...] Read more.

With the continuous increase in renewable energy penetration and the expansion of power grid scale, the computational complexity and solution time of traditional voltage-reactive power (V-Q) control solution methods have grown significantly, making it difficult to achieve fast responses in real-time voltage control. To address this issue, this paper proposes a physics-informed neural network (PINN)-based solution strategy for V-Q online feedback optimization (OFO) control. First, an optimal reactive power flow (ORPF) model is established with the objective of minimizing the control cost of reactive power resources. By integrating PMU measurement data, the ORPF problem is transformed into an OFO control problem. Then, a PINN-driven V-Q control solution framework is developed, and an improved grey wolf optimizer is employed to optimize the initial parameters of the PINN, enabling the fast online computation of a V-Q control strategy. Test results demonstrate that under both single-fault disturbance and multiple-fault disturbance scenarios, the proposed method can accurately identify different disturbance conditions and achieve rapid voltage regulation. Compared with traditional control solution methods, the proposed method reduces the average computation time by 87.2% and 89.4%, respectively, significantly improving control solution efficiency. Full article

(This article belongs to the Special Issue Advances in Power System Dynamics, Stability, Control and Dispatch with Large-Scale Renewable Energy Penetrated, 3rd Edition)

► Show Figures

Figure 1

20 pages, 1071 KB

Open AccessArticle

A Probabilistic Linguistic Multi-Criteria Optimization Approach: An Application on Cold Chain Supplier Selection for Perishable Goods

by Jingming Hu, Yong Qin and Chong Wang

Electronics 2026, 15(10), 2080; https://doi.org/10.3390/electronics15102080 - 13 May 2026

Abstract

In complex multi-criteria decision-making scenarios, the inherent ambiguity of evaluation data and the frequent unavailability of complete attribute weight information pose significant challenges for domain experts. To address these methodological limitations, this study proposes a novel TOPSIS-based decision-making framework that integrates optimization algorithms [...] Read more.

In complex multi-criteria decision-making scenarios, the inherent ambiguity of evaluation data and the frequent unavailability of complete attribute weight information pose significant challenges for domain experts. To address these methodological limitations, this study proposes a novel TOPSIS-based decision-making framework that integrates optimization algorithms with probabilistic linguistic term sets (PLTSs). Specifically, a distance measurement optimization model is constructed to objectively resolve the issue of incomplete attribute weight information. This mathematical approach enables the seamless fusion of qualitative expert judgments with quantitative metrics, effectively managing uncertainty and information deficiency in the decision-making process. To validate the practical viability and superiority of the proposed methodology, it is applied to an empirical case study of supplier selection in the cold chain logistics sector for fresh and perishable commodities. The evaluation encompasses three core dimensions: (i) environmental sustainability and energy efficiency, (ii) quality assurance and operational control, and (iii) supply chain collaboration and resilience. Empirical findings demonstrate that the proposed methodological framework substantially strengthens the robustness and reliability of selection outcomes under information-deficient conditions. Relative to conventional approaches, the developed framework demonstrates superior mathematical adaptability and effectively captures decision distortions, thereby offering rigorous theoretical contributions to decision-making under uncertainty and providing actionable practical guidance for complex supply chain evaluations. Full article

(This article belongs to the Topic Artificial Intelligence Models, Tools and Applications: 2nd Edition)

31 pages, 712 KB

Open AccessArticle

TDSR: Distributed Data Asset Registration and Cross-Jurisdictional Verification in Trusted Data Spaces

by Xingxing Yang, Jieling Xie, Weiping Deng, Chi Zhang, Junqi Ren, Shuang Liu, Wai Ip Lei, Wei Wang and Wenyong Wang

Electronics 2026, 15(10), 2079; https://doi.org/10.3390/electronics15102079 - 13 May 2026

Abstract

Trans-border data circulation across multi-jurisdictional boundaries faces an operational conflict between ownership provenance prerequisites and data minimisation mandates, compounded by the tight coupling of large data payloads with synchronous state consensus ledgers, which forces replication of feature matrices across all consensus nodes and [...] Read more.

Trans-border data circulation across multi-jurisdictional boundaries faces an operational conflict between ownership provenance prerequisites and data minimisation mandates, compounded by the tight coupling of large data payloads with synchronous state consensus ledgers, which forces replication of feature matrices across all consensus nodes and leads to network saturation. Existing frameworks remain unequipped to resolve this, as coupling in-band payload routing with synchronous state ledgers generates communication overheads scaling with data volume. The proposed Trusted Data Space with Registration (TDSR) implements a four-layer protocol stack. A dual-plane topology establishes a decoupled storage–ledger mechanism, partitioning asynchronous payload datastores and synchronous consensus ledgers to sustain throughput independent of data dimensionality. Navigating this infrastructure, the Unified Data Resource Identifier (UDRI) executes out-of-band cross-domain routing without exposing verifier intents. Driven by the Oblivious Data Asset Registration (ODAR) mechanism, a two-phase, four-algorithm lifecycle dictates end-to-end ownership provenance. This execution shifts hypothesis testing to isolated sandboxes via an algorithm-agnostic mathematical contract, capping external data transit at a constant leakage bound. A deployed testbed across the Guangdong-Hong Kong-Macao Greater Bay Area validates the proposed architecture, supporting data circulation across divergent legal jurisdictions. Full article

(This article belongs to the Special Issue Emerging Technologies Integration in IoT and Wireless Networks: Advancing Security and Performance in Cross-Domain Applications)

30 pages, 4673 KB

Open AccessArticle

MOSAIC: A Cognitively Motivated Multi-Agent Framework for Interpretable and Training-Free Empathetic Dialogue

by Kai Liu, Hangyu Xiong, Jinyi Zhang and Min Peng

Electronics 2026, 15(10), 2078; https://doi.org/10.3390/electronics15102078 - 13 May 2026

Abstract

Empathetic dialogue systems built upon large language models overwhelmingly adopt a monolithic inference paradigm that processes emotion perception, causal reasoning, memory retrieval, and response planning within a single forward pass without architecturally enforced intermediate representations, forfeiting intermediate-state transparency and long-horizon personalization. Drawing on [...] Read more.

Empathetic dialogue systems built upon large language models overwhelmingly adopt a monolithic inference paradigm that processes emotion perception, causal reasoning, memory retrieval, and response planning within a single forward pass without architecturally enforced intermediate representations, forfeiting intermediate-state transparency and long-horizon personalization. Drawing on neuroscientific and cognitive–psychological evidence that human empathy is functionally dissociable, we present MOSAIC (Multi-agent Orchestration with Structured Affective memory for Interpretable empathiC dialogue), a training-free framework that operationalizes empathetic dialogue as a four-stage cognitive pipeline: affective perception, causal appraisal, episodic memory retrieval, and response synthesis. Three innovations distinguish MOSAIC from prior work: (1) a cognitively motivated modular architecture whose functionally dissociable stages enable post hoc failure attribution through logged intermediate states; (2) a hierarchical three-tier emotional memory—perceptual, semantic, and episodic—coupled with adaptive three-dimensional retrieval over emotion, situation, and coping-strategy cues; and (3) a heterogeneous model orchestration strategy coordinating open-source and API-accessible models through role-specific chain-of-thought prompts, requiring no task-specific fine-tuning. We note that the EmpatheticDialogues evaluation pre-populates the memory store with 200 training-split episodes prior to test-set interaction, a data-access asymmetry relative to single-model baselines that must be borne in mind when interpreting comparative results. Experiments on EmpatheticDialogues and ESConv show that MOSAIC achieves a 76.4% weighted F1 and an empathy score of 3.87 (on a 1–5 Likert scale) and that it improves over single-model, training-free baselines on aggregate empathy and—most prominently—on human-rated personalization (3.67 vs. 3.24 against Claude-3.5 five-shot,

d = 0.48

). We caution that the comparison against training-free baselines is not data access-controlled (see the cold-start discussion in Methods); the personalization advantage, supported by the ablation without the Event Agent, is the result we treat as the primary practical contribution of this work. Full article

(This article belongs to the Special Issue Affective Computing in Human–Robot Interaction)

22 pages, 19168 KB

Open AccessFeature PaperArticle

RGB Ensemble Strategies for Unsupervised Industrial Anomaly Detection on the AutoVI Dataset

by Sergio Villanueva López, Emilio Soria-Olivas and Manuel Sánchez-Montañés

Electronics 2026, 15(10), 2077; https://doi.org/10.3390/electronics15102077 - 13 May 2026

Abstract

Real automotive inspection lines need robust defect detection under cluttered backgrounds, fluctuating illumination, and operator-introduced clutter, conditions under which fully supervised pipelines are rarely feasible because defective samples are scarce and heterogeneous. We address this gap with a deployment-oriented study of unsupervised anomaly [...] Read more.

Real automotive inspection lines need robust defect detection under cluttered backgrounds, fluctuating illumination, and operator-introduced clutter, conditions under which fully supervised pipelines are rarely feasible because defective samples are scarce and heterogeneous. We address this gap with a deployment-oriented study of unsupervised anomaly detection (UAD) on AutoVI, a public automotive benchmark, and we go beyond running existing detectors in three ways. First, we establish unified RGB and pseudo-depth baselines for seven UAD models under a single calibration and evaluation policy that combines threshold-agnostic metrics (AUROC, AP), operational metrics (TPR at fixed TNR), and pixel-level sPRO/AUsPRO under a 5% false-positive budget. Second, we show that a plug-and-play late fusion of independently calibrated RGB detectors consistently recovers pixel-level localization that no single model achieves, with no extra training and no architectural change; effects are large (Cohen’s

d > 2

on every flagged improvement) and statistically significant across three seeds. Third, we report an actionable negative result: combining RGB with monocular pseudo-depth through the same fusion scheme degrades rather than improves localization, and we trace the failure to the relative nature of estimated depth interacting with a parameter-free aggregator. Ablations on the fusion operator, ensemble size, and calibration support these findings, and the released calibrated artifacts make the comparison reproducible on other MVTec-style benchmarks. Full article

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

31 pages, 13501 KB

Open AccessArticle

Adaptive 3D Human Pose Estimation Based on Spatial–Temporal Complexity Awareness

by Wensi Zhang, Ziyan Yang, Chengfeng Hu, Jing Sun and Jie Li

Electronics 2026, 15(10), 2076; https://doi.org/10.3390/electronics15102076 - 13 May 2026

Abstract

Existing 3D human pose estimation methods use fixed computation strategies processing diverse action sequences, leading to computational redundancy for simple actions, insufficient high-frequency information capture for complex actions, and low long-sequence processing efficiency. To address these issues, this paper proposes a Spatial–Temporal Complexity-Aware [...] Read more.

Existing 3D human pose estimation methods use fixed computation strategies processing diverse action sequences, leading to computational redundancy for simple actions, insufficient high-frequency information capture for complex actions, and low long-sequence processing efficiency. To address these issues, this paper proposes a Spatial–Temporal Complexity-Aware Adaptive Computation Framework (CAAPoseFormer). First, a spatial–temporal coupled complexity quantification module is built to integrate spatial dispersion and temporal motion variance for graded action complexity quantification. On this basis, a time–frequency dual-domain adaptive pruning strategy is proposed to dynamically allocate temporal window length and frequency-domain DCT coefficients on demand. Furthermore, a mask-guided sparse interaction encoding mechanism is designed to enable efficient parallel computation of variable-length features by shielding invalid padding regions. Experiments on the Human3.6M dataset show that, versus the baseline PoseFormerV2, the proposed method cuts parameters by 85.3% and computational cost by 64.8% while retaining comparable accuracy (MPJPE 44.2 mm), boosting unit computational efficiency 2.8×. Moreover, compared with state-of-the-art (SOTA) methods like MHFormer and MotionBERT, our method reduces computational costs (MACs) by 97.4% and nearly three orders of magnitude, respectively. This framework effectively breaks the inference bottleneck of high-precision models on low-power hardware, suiting latency-sensitive real-time applications well. Full article

(This article belongs to the Special Issue Advances in Real-Time Object Detection and Tracking)

► Show Figures

Figure 1

18 pages, 2017 KB

Open AccessArticle

Optical Remote Sensing Image Classification Based on Quantum Statistics

by Xiaoli Li, Longlong Zhao, Hongzhong Li, Pan Chen, Luyi Sun, Shanxin Guo, Xuemei Zhao and Jinsong Chen

Electronics 2026, 15(10), 2075; https://doi.org/10.3390/electronics15102075 - 13 May 2026

Abstract

To address the difficulty of finely classifying complex optical remote sensing images, this paper innovatively proposes a new image classification method based on quantum statistics (QS) inspired by quantum physics. Each pixel in the image is regarded as a fermion, which is one [...] Read more.

To address the difficulty of finely classifying complex optical remote sensing images, this paper innovatively proposes a new image classification method based on quantum statistics (QS) inspired by quantum physics. Each pixel in the image is regarded as a fermion, which is one of the fundamental particles in quantum systems. The energy of the energy level where fermions are located is described using the negative logarithm of the distribution that the spectrum of the pixel follows. The Fermi-Dirac distribution, a quantum statistics model used to describe the complex occupation pattern of energy levels by fermions, is employed to characterize the membership relationship between pixels and classes, instead of traditional distance measures and probability measures. Then, the cost function guiding the convergence of classification is defined based on free energy, which is used to describe whether a system is in a state of thermal equilibrium according to energy, temperature, and entropy. To minimize the free energy, the derivative method and the simulated annealing algorithm are adopted to estimate the optimal solution for model parameters. The proposed method can describe complex features more effectively, obtain fine classification results, and overcome the curse of dimensionality in high-dimensional image classification. Finally, the feasibility and effectiveness are verified through qualitative and quantitative analysis of multispectral and hyperspectral image classification experiments. Full article

(This article belongs to the Special Issue Challenges and Prospects in Remote Sensing Data Intelligent Interpretation)

► Show Figures

Figure 1

21 pages, 1732 KB

Open AccessArticle

Resource-Aware Deep Reinforcement Learning for Joint Caching and Service Placement in Multi-Access Edge Computing

by Elias Dritsas and Maria Trigka

Electronics 2026, 15(10), 2074; https://doi.org/10.3390/electronics15102074 - 13 May 2026

Abstract

Multi-access edge computing (MEC) enables low-latency service provisioning by placing computation closer to mobile users. However, efficient service placement remains challenging due to dynamic user mobility, limited edge resources, and the need to manage service migration as system conditions evolve. This study proposes [...] Read more.

Multi-access edge computing (MEC) enables low-latency service provisioning by placing computation closer to mobile users. However, efficient service placement remains challenging due to dynamic user mobility, limited edge resources, and the need to manage service migration as system conditions evolve. This study proposes a resource-aware, cache-enabled service placement framework based on deep reinforcement learning (DRL) to dynamically select edge nodes for hosting services. The approach jointly considers user location, resource availability, and cache status within a unified decision framework, enabling efficient and adaptive service placement in dynamic MEC environments. The problem is formulated as a Markov decision process (MDP) and solved using deep Q-network (DQN)-based methods, with a reward function that balances latency, resource utilization, and cache efficiency. The proposed framework is evaluated in a simulated MEC environment with mobile users and multiple edge nodes. Experimental results demonstrate that the approach achieves lower latency, improved resource utilization, and enhanced cache efficiency compared to baseline strategies. Among the evaluated models, the dueling double deep Q-network (DDDQN) achieves the most balanced overall performance. The proposed framework provides an adaptive and scalable solution for service management in dynamic MEC environments. Full article

(This article belongs to the Special Issue Machine Learning Approach for Prediction: Cross-Domain Applications)

► Show Figures

Figure 1

41 pages, 12659 KB

Open AccessReview

A Survey of Machine Learning Algorithms for Autonomous Vehicles

by Agnieszka Lazarowska, Monika Rybczak, Mirosław Łącki, Krystian Kozakiewicz, Józef Lisowski and Andrzej Stateczny

Electronics 2026, 15(10), 2073; https://doi.org/10.3390/electronics15102073 - 13 May 2026

Abstract

This paper presents a comprehensive review of recent works (2020–2026) on machine learning (ML) algorithms applied to autonomous platforms such as unmanned underwater vehicles (UUVs), unmanned surface vehicles (USVs), unmanned aerial vehicles (UAVs), and ground-based mobile robots. The review focuses on the following [...] Read more.

This paper presents a comprehensive review of recent works (2020–2026) on machine learning (ML) algorithms applied to autonomous platforms such as unmanned underwater vehicles (UUVs), unmanned surface vehicles (USVs), unmanned aerial vehicles (UAVs), and ground-based mobile robots. The review focuses on the following functional areas: environment perception, simultaneous localization and mapping (SLAM), collision avoidance and path planning, and motion control. Different ML methods are covered, including supervised, semi-supervised, and unsupervised learning, as well as reinforcement learning and deep reinforcement learning. The reviewed methods are analyzed with respect to their performance, robustness, and suitability for different operational environments, including underwater, surface, air, and land domains. Finally, the authors identify key challenges and outline promising future directions aimed at improving the safety, autonomy, and reliability of autonomous vehicles. Full article

(This article belongs to the Special Issue Path Planning and Navigation for Autonomous Vehicles and Intelligent Robots)

► Show Figures

Figure 1

16 pages, 26838 KB

Open AccessFeature PaperArticle

Experimental Evaluation and Theoretical Analysis of I/Q Imbalance in Direct Millimeter-Wave Six-Port QPSK Demodulators

by Chaouki Hannachi, Matthieu Egels, Phillipe Pannier and Serioja Ovidiu Tatu

Electronics 2026, 15(10), 2072; https://doi.org/10.3390/electronics15102072 - 13 May 2026

Abstract

This paper presents a comprehensive investigation of the impact of I/Q (In-phase/Quadrature) imbalance on the performance of a six-port receiver operating in the millimeter-wave band, specifically in the 60–65 GHz frequency range. Unlike traditional heterodyne architectures, the six-port junction offers a low-cost and [...] Read more.

This paper presents a comprehensive investigation of the impact of I/Q (In-phase/Quadrature) imbalance on the performance of a six-port receiver operating in the millimeter-wave band, specifically in the 60–65 GHz frequency range. Unlike traditional heterodyne architectures, the six-port junction offers a low-cost and low-power alternative for direct conversion; however, it is highly sensitive to hardware imperfections. This study demonstrates that manufacturing tolerances in passive components, such as 90° hybrid couplers and power dividers, introduce significant amplitude and phase disparities. These imbalances geometrically distort the ideal QPSK constellation, transforming the circular decision boundaries into an elliptical profile. The research methodology employs a robust co-simulation approach in Advanced Design System (ADS), integrating measured S-parameters with mathematical analysis to quantify signal degradation. Performance is evaluated using the Error Vector Magnitude (EVM) metric. The experimental findings reveal that even at the higher end of the spectrum (65 GHz), where the amplitude imbalance reaches 0.7 dB and the phase error is approximately 5°, the six-port QPSK receiver maintains an EVM of 8.7%. This result is comfortably below the 17.5% limit mandated by modern wireless communication standards, such as LTE and 5G. These results confirm the architectural resilience of the six-port receiver, validating its effectiveness as a reliable solution for high-speed, short-range data transmission in future ultra-wideband telecommunication infrastructures. Full article

(This article belongs to the Special Issue Advances in 6G Wireless Communication Technologies)

► Show Figures

Figure 1

Journal Description

Electronics

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI