Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (292)

Search Parameters:
Keywords = channel imbalance

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
27 pages, 1766 KiB  
Article
A Novel Optimized Hybrid Deep Learning Framework for Mental Stress Detection Using Electroencephalography
by Maithili Shailesh Andhare, T. Vijayan, B. Karthik and Shabana Urooj
Brain Sci. 2025, 15(8), 835; https://doi.org/10.3390/brainsci15080835 (registering DOI) - 4 Aug 2025
Abstract
Mental stress is a psychological or emotional strain that typically occurs because of threatening, challenging, and overwhelming conditions and affects human behavior. Various factors, such as professional, environmental, and personal pressures, often trigger it. In recent years, various deep learning (DL)-based schemes using [...] Read more.
Mental stress is a psychological or emotional strain that typically occurs because of threatening, challenging, and overwhelming conditions and affects human behavior. Various factors, such as professional, environmental, and personal pressures, often trigger it. In recent years, various deep learning (DL)-based schemes using electroencephalograms (EEGs) have been proposed. However, the effectiveness of DL-based schemes is challenging because of the intricate DL structure, class imbalance problems, poor feature representation, low-frequency resolution problems, and complexity of multi-channel signal processing. This paper presents a novel hybrid DL framework, BDDNet, which combines a deep convolutional neural network (DCNN), bidirectional long short-term memory (BiLSTM), and deep belief network (DBN). BDDNet provides superior spectral–temporal feature depiction and better long-term dependency on the local and global features of EEGs. BDDNet accepts multiple EEG features (MEFs) that provide the spectral and time-domain features of EEGs. A novel improved crow search algorithm (ICSA) was presented for channel selection to minimize the computational complexity of multichannel stress detection. Further, the novel employee optimization algorithm (EOA) is utilized for the hyper-parameter optimization of hybrid BDDNet to enhance the training performance. The outcomes of the novel BDDNet were assessed using a public DEAP dataset. The BDDNet-ICSA offers improved recall of 97.6%, precision of 97.6%, F1-score of 97.6%, selectivity of 96.9%, negative predictive value NPV of 96.9%, and accuracy of 97.3% to traditional techniques. Full article
Show Figures

Figure 1

31 pages, 2506 KiB  
Review
Muscarinic Receptor Antagonism and TRPM3 Activation as Stimulators of Mitochondrial Function and Axonal Repair in Diabetic Sensorimotor Polyneuropathy
by Sanjana Chauhan, Nigel A. Calcutt and Paul Fernyhough
Int. J. Mol. Sci. 2025, 26(15), 7393; https://doi.org/10.3390/ijms26157393 - 31 Jul 2025
Viewed by 430
Abstract
Diabetic sensorimotor polyneuropathy (DSPN) is the most prevalent complication of diabetes, affecting nearly half of all persons with diabetes. It is characterized by nerve degeneration, progressive sensory loss and pain, with increased risk of ulceration and amputation. Despite its high prevalence, disease-modifying treatments [...] Read more.
Diabetic sensorimotor polyneuropathy (DSPN) is the most prevalent complication of diabetes, affecting nearly half of all persons with diabetes. It is characterized by nerve degeneration, progressive sensory loss and pain, with increased risk of ulceration and amputation. Despite its high prevalence, disease-modifying treatments for DSPN do not exist. Mitochondrial dysfunction and Ca2+ dyshomeostasis are key contributors to the pathophysiology of DSPN, disrupting neuronal energy homeostasis and initiating axonal degeneration. Recent findings have demonstrated that antagonism of the muscarinic acetylcholine type 1 receptor (M1R) promotes restoration of mitochondrial function and axon repair in various neuropathies, including DSPN, chemotherapy-induced peripheral neuropathy (CIPN) and HIV-associated neuropathy. Pirenzepine, a selective M1R antagonist with a well-established safety profile, is currently under clinical investigation for its potential to reverse neuropathy. The transient receptor potential melastatin-3 (TRPM3) channel, a Ca2+-permeable ion channel, has recently emerged as a downstream effector of G protein-coupled receptor (GPCR) pathways, including M1R. TRPM3 activation enhanced mitochondrial Ca2+ uptake and bioenergetics, promoting axonal sprouting. This review highlights mitochondrial and Ca2+ signaling imbalances in DSPN and presents M1R antagonism and TRPM3 activation as promising neuro-regenerative strategies that shift treatment from symptom control to nerve restoration in diabetic and other peripheral neuropathies. Full article
Show Figures

Figure 1

19 pages, 3130 KiB  
Article
Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
by Xiaotong Yao, Huayu Yuan, Shanpeng Zhao, Wei Tian, Dongzhao Han, Xiaoping Li, Feng Wang and Sihua Wang
Sensors 2025, 25(15), 4714; https://doi.org/10.3390/s25154714 - 30 Jul 2025
Viewed by 224
Abstract
The conductors of high-speed railway OCSs (Overhead Contact Systems) are susceptible to conductor galloping due to the impact of natural elements such as strong winds, rain, and snow, resulting in conductor fatigue damage and significantly compromising train operational safety. Consequently, monitoring the galloping [...] Read more.
The conductors of high-speed railway OCSs (Overhead Contact Systems) are susceptible to conductor galloping due to the impact of natural elements such as strong winds, rain, and snow, resulting in conductor fatigue damage and significantly compromising train operational safety. Consequently, monitoring the galloping status of conductors is crucial, and instance segmentation techniques, by delineating the pixel-level contours of each conductor, can significantly aid in the identification and study of galloping phenomena. This work expands upon the YOLO11-seg model and introduces an instance segmentation approach for galloping video and image sensor data of OCS conductors. The algorithm, designed for the stripe-like distribution of OCS conductors in the data, employs four-direction Sobel filters to extract edge features in horizontal, vertical, and diagonal orientations. These features are subsequently integrated with the original convolutional branch to form the FDSE (Four Direction Sobel Enhancement) module. It integrates the ECA (Efficient Channel Attention) mechanism for the adaptive augmentation of conductor characteristics and utilizes the FL (Focal Loss) function to mitigate the class-imbalance issue between positive and negative samples, hence enhancing the model’s sensitivity to conductors. Consequently, segmentation outcomes from neighboring frames are utilized, and mask-difference analysis is performed to autonomously detect conductor galloping locations, emphasizing their contours for the clear depiction of galloping characteristics. Experimental results demonstrate that the enhanced YOLO11-seg model achieves 85.38% precision, 77.30% recall, 84.25% AP@0.5, 81.14% F1-score, and a real-time processing speed of 44.78 FPS. When combined with the galloping visualization module, it can issue real-time alerts of conductor galloping anomalies, providing robust technical support for railway OCS safety monitoring. Full article
(This article belongs to the Section Industrial Sensors)
Show Figures

Figure 1

34 pages, 1544 KiB  
Review
The Crucial Interplay Between the Lungs, Brain, and Heart to Understand Epilepsy-Linked SUDEP: A Literature Review
by Mohd Yaqub Mir, Bilal A. Seh, Shabab Zahra and Adam Legradi
Brain Sci. 2025, 15(8), 809; https://doi.org/10.3390/brainsci15080809 - 28 Jul 2025
Viewed by 403
Abstract
Sudden Unexpected Death in Epilepsy (SUDEP) is a leading cause of mortality among individuals with epilepsy, particularly those with drug-resistant forms. This review explores the complex multisystem mechanisms underpinning SUDEP, integrating recent findings on brain, cardiac, and pulmonary dysfunctions. Background/Objectives: The main objective [...] Read more.
Sudden Unexpected Death in Epilepsy (SUDEP) is a leading cause of mortality among individuals with epilepsy, particularly those with drug-resistant forms. This review explores the complex multisystem mechanisms underpinning SUDEP, integrating recent findings on brain, cardiac, and pulmonary dysfunctions. Background/Objectives: The main objective of this review is to elucidate how seizures disrupt critical physiological systems, especially the brainstem, heart, and lungs, contributing to SUDEP, with emphasis on respiratory control failure and autonomic instability. Methods: The literature from experimental models, clinical observations, neuroimaging studies, and genetic analyses was systematically examined. Results: SUDEP is frequently preceded by generalized tonic–clonic seizures, which trigger central and obstructive apnea, hypoventilation, and cardiac arrhythmias. Brainstem dysfunction, particularly in areas such as the pre-Bötzinger complex and nucleus tractus solitarius, plays a central role. Genetic mutations affecting ion channels (e.g., SCN1A, KCNQ1) and neurotransmitter imbalances (notably serotonin and GABA) exacerbate autonomic dysregulation. Risk is compounded by a prone sleeping position, reduced arousal capacity, and impaired ventilatory responses. Conclusions: SUDEP arises from a cascade of interrelated failures in respiratory and cardiac regulation initiated by seizure activity. The recognition of modifiable risk factors, implementation of monitoring technologies, and targeted therapies such as serotonergic agents may reduce mortality. Multidisciplinary approaches integrating neurology, cardiology, and respiratory medicine are essential for effective prevention strategies. Full article
Show Figures

Graphical abstract

15 pages, 4874 KiB  
Article
A Novel 3D Convolutional Neural Network-Based Deep Learning Model for Spatiotemporal Feature Mapping for Video Analysis: Feasibility Study for Gastrointestinal Endoscopic Video Classification
by Mrinal Kanti Dhar, Mou Deb, Poonguzhali Elangovan, Keerthy Gopalakrishnan, Divyanshi Sood, Avneet Kaur, Charmy Parikh, Swetha Rapolu, Gianeshwaree Alias Rachna Panjwani, Rabiah Aslam Ansari, Naghmeh Asadimanesh, Shiva Sankari Karuppiah, Scott A. Helgeson, Venkata S. Akshintala and Shivaram P. Arunachalam
J. Imaging 2025, 11(7), 243; https://doi.org/10.3390/jimaging11070243 - 18 Jul 2025
Viewed by 466
Abstract
Accurate analysis of medical videos remains a major challenge in deep learning (DL) due to the need for effective spatiotemporal feature mapping that captures both spatial detail and temporal dynamics. Despite advances in DL, most existing models in medical AI focus on static [...] Read more.
Accurate analysis of medical videos remains a major challenge in deep learning (DL) due to the need for effective spatiotemporal feature mapping that captures both spatial detail and temporal dynamics. Despite advances in DL, most existing models in medical AI focus on static images, overlooking critical temporal cues present in video data. To bridge this gap, a novel DL-based framework is proposed for spatiotemporal feature extraction from medical video sequences. As a feasibility use case, this study focuses on gastrointestinal (GI) endoscopic video classification. A 3D convolutional neural network (CNN) is developed to classify upper and lower GI endoscopic videos using the hyperKvasir dataset, which contains 314 lower and 60 upper GI videos. To address data imbalance, 60 matched pairs of videos are randomly selected across 20 experimental runs. Videos are resized to 224 × 224, and the 3D CNN captures spatiotemporal information. A 3D version of the parallel spatial and channel squeeze-and-excitation (P-scSE) is implemented, and a new block called the residual with parallel attention (RPA) block is proposed by combining P-scSE3D with a residual block. To reduce computational complexity, a (2 + 1)D convolution is used in place of full 3D convolution. The model achieves an average accuracy of 0.933, precision of 0.932, recall of 0.944, F1-score of 0.935, and AUC of 0.933. It is also observed that the integration of P-scSE3D increased the F1-score by 7%. This preliminary work opens avenues for exploring various GI endoscopic video-based prospective studies. Full article
Show Figures

Figure 1

34 pages, 1051 KiB  
Review
Atrial Fibrillation in Diabetes: Pathogenesis and Targeted Rhythm Control Strategies
by Konstantinos Grigoriou, Paschalis Karakasis, Konstantinos Pamporis, Panagiotis Theofilis, Dimitrios Patoulias, Efstratios Karagiannidis, Barbara Fyntanidou, Antonios P. Antoniadis and Nikolaos Fragakis
Curr. Issues Mol. Biol. 2025, 47(7), 559; https://doi.org/10.3390/cimb47070559 - 17 Jul 2025
Viewed by 486
Abstract
Diabetes mellitus and atrial fibrillation (AF) frequently coexist, creating a complex bidirectional relationship that exacerbates cardiovascular risk and challenges clinical management. Diabetes fosters a profibrotic, pro-inflammatory, and proarrhythmic atrial substrate through a constellation of pathophysiologic mechanisms, including metabolic remodeling, oxidative stress, mitochondrial dysfunction, [...] Read more.
Diabetes mellitus and atrial fibrillation (AF) frequently coexist, creating a complex bidirectional relationship that exacerbates cardiovascular risk and challenges clinical management. Diabetes fosters a profibrotic, pro-inflammatory, and proarrhythmic atrial substrate through a constellation of pathophysiologic mechanisms, including metabolic remodeling, oxidative stress, mitochondrial dysfunction, ion channel dysregulation, and autonomic imbalance, thereby promoting AF initiation and progression. Conventional rhythm control strategies remain less effective in diabetic individuals, underscoring the need for innovative, substrate-targeted interventions. In this context, sodium–glucose cotransporter 2 (SGLT2) inhibitors and glucagon-like peptide-1 (GLP-1) receptor agonists have emerged as promising agents with pleiotropic antiarrhythmic properties, modulating fibrosis, inflammation, and mitochondrial integrity. Moreover, advances in anti-inflammatory, antifibrotic, and ion channel-modulating therapeutics, coupled with novel mitochondrial-targeted strategies, are reshaping the therapeutic landscape. Multi-omics approaches are further refining our understanding of diabetes-associated AF, facilitating precision medicine and biomarker-guided interventions. This review delineates the molecular nexus linking diabetes and AF, critically appraises emerging rhythm control strategies, and outlines translational avenues poised to advance individualized management in this high-risk population. Full article
(This article belongs to the Special Issue Advances in Molecular Therapies and Disease Associations in Diabetes)
Show Figures

Figure 1

29 pages, 1685 KiB  
Review
Translating Basic Science to Clinical Applications: A Narrative Review of Repurposed Pharmacological Agents in Preclinical Models of Diabetic Neuropathy
by Corina Andrei, Oana Cristina Șeremet, Ciprian Pușcașu and Anca Zanfirescu
Biomedicines 2025, 13(7), 1709; https://doi.org/10.3390/biomedicines13071709 - 13 Jul 2025
Viewed by 488
Abstract
Diabetic neuropathy (DN) remains a major clinical burden, characterized by progressive sensory dysfunction, pain, and impaired quality of life. Despite the available symptomatic treatments, there is a pressing need for disease-modifying therapies. In recent years, preclinical research has highlighted the potential of repurposed [...] Read more.
Diabetic neuropathy (DN) remains a major clinical burden, characterized by progressive sensory dysfunction, pain, and impaired quality of life. Despite the available symptomatic treatments, there is a pressing need for disease-modifying therapies. In recent years, preclinical research has highlighted the potential of repurposed pharmacological agents, originally developed for other indications, to target key mechanisms of DN. This narrative review examines the main pathophysiological pathways involved in DN, including metabolic imbalance, oxidative stress, neuroinflammation, ion channel dysfunction, and mitochondrial impairment. A wide array of repurposed drugs—including antidiabetics (metformin, empagliflozin, gliclazide, semaglutide, and pioglitazone), antihypertensives (amlodipine, telmisartan, aliskiren, and rilmenidine), lipid-lowering agents (atorvastatin and alirocumab), anticonvulsants (topiramate and retigabine), antioxidant and neuroprotective agents (melatonin), and muscarinic receptor antagonists (pirenzepine, oxybutynin, and atropine)—have shown promising results in rodent models, reducing neuropathic pain behaviors and modulating underlying disease mechanisms. By bridging basic mechanistic insights with pharmacological interventions, this review aims to support translational progress toward mechanism-based therapies for DN. Full article
(This article belongs to the Special Issue Novel Biomarker and Treatments for Diabetic Neuropathy)
Show Figures

Figure 1

16 pages, 2059 KiB  
Article
A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
by Liqiang Wang, Shixian Dai, Zijian Kang, Shuang Han, Guozhen Zhang and Yongqian Liu
Energies 2025, 18(14), 3696; https://doi.org/10.3390/en18143696 - 13 Jul 2025
Viewed by 307
Abstract
Gearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect the impact [...] Read more.
Gearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect the impact of class imbalance, thereby limiting diagnostic accuracy. To address these challenges, this paper proposes a fault diagnosis model for wind turbine gearboxes based on CNN-SA-GRU and Focal Loss. Specifically, a CNN-SA-GRU network is constructed to extract both spatial and temporal features, in which CNN is employed to extract local spatial features from SCADA data, Shuffle Attention is integrated to efficiently fuse channel and spatial information and enhance spatial representation, and GRU is utilized to capture long-term spatiotemporal dependencies. To mitigate the adverse effects of class imbalance, the conventional cross-entropy loss is replaced with Focal Loss, which assigns higher weights to hard-to-classify fault samples. Finally, the model is validated using real wind farm data. The results show that, compared with the cross-entropy loss, using Focal Loss improves the accuracy and F1 score by an average of 0.24% and 1.03%, respectively. Furthermore, the proposed model outperforms other baseline models with average gains of 0.703% in accuracy and 4.65% in F1 score. Full article
Show Figures

Figure 1

15 pages, 1423 KiB  
Review
Sperm Membrane Stability: In-Depth Analysis from Structural Basis to Functional Regulation
by Shan-Hui Xue, Bing-Bing Xu, Xiao-Chun Yan, Jia-Xin Zhang and Rui Su
Vet. Sci. 2025, 12(7), 658; https://doi.org/10.3390/vetsci12070658 - 11 Jul 2025
Viewed by 339
Abstract
Sperm membrane stability is a key factor in determining sperm viability and fertilization capability, with broad implications ranging from basic reproductive biology to livestock breeding practices. This comprehensive review examines the structural and functional mechanisms underlying sperm membrane integrity, including defensive barrier functions, [...] Read more.
Sperm membrane stability is a key factor in determining sperm viability and fertilization capability, with broad implications ranging from basic reproductive biology to livestock breeding practices. This comprehensive review examines the structural and functional mechanisms underlying sperm membrane integrity, including defensive barrier functions, potentiometric ion channel regulation, and motility modulation that collectively optimize sperm survival, motility, and fertilization potential. Environmental factors such as temperature fluctuations, abnormal pH levels (outside the optimal 7.2–8.2 range), pathological conditions, and hormonal imbalances can compromise membrane stability by inducing oxidative stress and protein denaturation. Key regulatory proteins, notably NPC2 for cholesterol homeostasis, Flotillin proteins for lipid raft organization, and Annexin V for membrane repair mechanisms, demonstrate essential roles in maintaining structural integrity. In livestock reproduction, membrane stability research facilitates the optimization of cryoprotectant formulations and freezing protocols, resulting in 15–25% improvements in post-thaw sperm survival rates and enhanced artificial insemination success. These findings provide valuable insights for advancing assisted reproductive technologies and improving reproductive efficiency in animal husbandry. Full article
Show Figures

Figure 1

30 pages, 3796 KiB  
Article
Applying Deep Learning Methods for a Large-Scale Riparian Vegetation Classification from High-Resolution Multimodal Aerial Remote Sensing Data
by Marcel Reinhardt, Edvinas Rommel, Maike Heuner and Björn Baschek
Remote Sens. 2025, 17(14), 2373; https://doi.org/10.3390/rs17142373 - 10 Jul 2025
Viewed by 309
Abstract
The unique vegetation in riparian zones is fundamental for various ecological and socio-economic functions in these transitional areas. Sustainable management requires detailed spatial information about the occurring flora. Here, we present a Deep Learning (DL)-based approach for processing multimodal high-resolution remote sensing data [...] Read more.
The unique vegetation in riparian zones is fundamental for various ecological and socio-economic functions in these transitional areas. Sustainable management requires detailed spatial information about the occurring flora. Here, we present a Deep Learning (DL)-based approach for processing multimodal high-resolution remote sensing data (aerial RGB and near-infrared (NIR) images and elevation maps) to generate a classification map of the tidal Elbe and a section of the Rhine River (Germany). The ground truth was based on existing mappings of vegetation and biotope types. The results showed that (I) despite a large class imbalance, for the tidal Elbe, a high mean Intersection over Union (IoU) of about 78% was reached. (II) At the Rhine River, a lower mean IoU was reached due to the limited amount of training data and labelling errors. Applying transfer learning methods and labelling error correction increased the mean IoU to about 60%. (III) Early fusion of the modalities was beneficial. (IV) The performance benefits from using elevation maps and the NIR channel in addition to RGB images. (V) Model uncertainty was successfully calibrated by using temperature scaling. The generalization ability of the trained model can be improved by adding more data from future aerial surveys. Full article
Show Figures

Figure 1

22 pages, 3494 KiB  
Article
Parcel Segmentation Method Combined YOLOV5s and Segment Anything Model Using Remote Sensing Image
by Xiaoqin Wu, Dacheng Wang, Caihong Ma, Yi Zeng, Yongze Lv, Xianmiao Huang and Jiandong Wang
Land 2025, 14(7), 1429; https://doi.org/10.3390/land14071429 - 8 Jul 2025
Viewed by 418
Abstract
Accurate land parcel segmentation in remote sensing imagery is critical for applications such as land use analysis, agricultural monitoring, and urban planning. However, existing methods often underperform in complex scenes due to small-object segmentation challenges, blurred boundaries, and background interference, often influenced by [...] Read more.
Accurate land parcel segmentation in remote sensing imagery is critical for applications such as land use analysis, agricultural monitoring, and urban planning. However, existing methods often underperform in complex scenes due to small-object segmentation challenges, blurred boundaries, and background interference, often influenced by sensor resolution and atmospheric variation. To address these limitations, we propose a dual-stage framework that combines an enhanced YOLOv5s detector with the Segment Anything Model (SAM) to improve segmentation accuracy and robustness. The improved YOLOv5s module integrates Efficient Channel Attention (ECA) and BiFPN to boost feature extraction and small-object recognition, while Soft-NMS is used to reduce missed detections. The SAM module receives bounding-box prompts from YOLOv5s and incorporates morphological refinement and mask stability scoring for improved boundary continuity and mask quality. A composite Focal-Dice loss is applied to mitigate class imbalance. In addition to the publicly available CCF BDCI dataset, we constructed a new WuJiang dataset to evaluate cross-domain performance. Experimental results demonstrate that our method achieves an IoU of 89.8% and a precision of 90.2%, outperforming baseline models and showing strong generalizability across diverse remote sensing conditions. Full article
Show Figures

Figure 1

27 pages, 13245 KiB  
Article
LHRF-YOLO: A Lightweight Model with Hybrid Receptive Field for Forest Fire Detection
by Yifan Ma, Weifeng Shan, Yanwei Sui, Mengyu Wang and Maofa Wang
Forests 2025, 16(7), 1095; https://doi.org/10.3390/f16071095 - 2 Jul 2025
Viewed by 355
Abstract
Timely and accurate detection of forest fires is crucial for protecting forest ecosystems. However, traditional monitoring methods face significant challenges in effectively detecting forest fires, primarily due to the dynamic spread of flames and smoke, irregular morphologies, and the semi-transparent nature of smoke, [...] Read more.
Timely and accurate detection of forest fires is crucial for protecting forest ecosystems. However, traditional monitoring methods face significant challenges in effectively detecting forest fires, primarily due to the dynamic spread of flames and smoke, irregular morphologies, and the semi-transparent nature of smoke, which make it extremely difficult to extract key visual features. Additionally, deploying these detection systems to edge devices with limited computational resources remains challenging. To address these issues, this paper proposes a lightweight hybrid receptive field model (LHRF-YOLO), which leverages deep learning to overcome the shortcomings of traditional monitoring methods for fire detection on edge devices. Firstly, a hybrid receptive field extraction module is designed by integrating the 2D selective scan mechanism with a residual multi-branch structure. This significantly enhances the model’s contextual understanding of the entire image scene while maintaining low computational complexity. Second, a dynamic enhanced downsampling module is proposed, which employs feature reorganization and channel-wise dynamic weighting strategies to minimize the loss of critical details, such as fine smoke textures, while reducing image resolution. Furthermore, a scale weighted Fusion module is introduced to optimize multi-scale feature fusion through adaptive weight allocation, addressing the issues of information dilution and imbalance caused by traditional fusion methods. Finally, the Mish activation function replaces the SiLU activation function to improve the model’s ability to capture flame edges and faint smoke textures. Experimental results on the self-constructed Fire-SmokeDataset demonstrate that LHRF-YOLO achieves significant model compression while further improving accuracy compared to the baseline model YOLOv11. The parameter count is reduced to only 2.25M (a 12.8% reduction), computational complexity to 5.4 GFLOPs (a 14.3% decrease), and mAP50 is increased to 87.6%, surpassing the baseline model. Additionally, LHRF-YOLO exhibits leading generalization performance on the cross-scenario M4SFWD dataset. The proposed method balances performance and resource efficiency, providing a feasible solution for real-time and efficient fire detection on resource-constrained edge devices with significant research value. Full article
(This article belongs to the Special Issue Forest Fires Prediction and Detection—2nd Edition)
Show Figures

Figure 1

24 pages, 40762 KiB  
Article
Multiscale Task-Decoupled Oriented SAR Ship Detection Network Based on Size-Aware Balanced Strategy
by Shun He, Ruirui Yuan, Zhiwei Yang and Jiaxue Liu
Remote Sens. 2025, 17(13), 2257; https://doi.org/10.3390/rs17132257 - 30 Jun 2025
Viewed by 326
Abstract
Current synthetic aperture radar (SAR) ship datasets exhibit a notable disparity in the distribution of large, medium, and small ship targets. This imbalance makes it difficult for a relatively small number of large and medium-sized ships to be effectively trained, resulting in many [...] Read more.
Current synthetic aperture radar (SAR) ship datasets exhibit a notable disparity in the distribution of large, medium, and small ship targets. This imbalance makes it difficult for a relatively small number of large and medium-sized ships to be effectively trained, resulting in many false alarms. Therefore, to address the issues of scale diversity, intra-class imbalance in ship data, and the feature conflict problem associated with traditional coupled detection heads, we propose an SAR image multiscale task-decoupled oriented ship target detector based on a size-aware balanced strategy. First, the multiscale target features are extracted using the multikernel heterogeneous perception module (MKHP). Meanwhile, the triple-attention module is introduced to establish the remote channel dependence to alleviate the issue of small target feature annihilation, which can effectively enhance the feature characterization ability of the model. Second, given the differences in the demand for feature information between the detection and classification tasks, a channel attention-based task decoupling dual-head (CAT2D) detector head structure is introduced to address the inherent conflict between classification and localization tasks. Finally, a new size-aware balanced (SAB) loss strategy is proposed to guide the network in focusing on the scarce targets in training to alleviate the intra-class imbalance problem during the training process. The ablation experiments on SSDD+ reflect the contribution of each component, and the results of the comparison experiments on the RSDD-SAR and HRSID datasets show that the proposed method achieves state-of-the-art performance compared to other state-of-the-art detection models. Furthermore, our approach exhibits superior detection coverage for both offshore and inshore scenarios for ship detection tasks. Full article
(This article belongs to the Section Remote Sensing Image Processing)
Show Figures

Graphical abstract

31 pages, 2292 KiB  
Article
Symmetric Dual-Phase Framework for APT Attack Detection Based on Multi-Feature-Conditioned GAN and Graph Convolutional Network
by Qi Liu, Yao Dong, Chao Zheng, Hualin Dai, Jiaxing Wang, Liyuan Ning and Qiqi Liang
Symmetry 2025, 17(7), 1026; https://doi.org/10.3390/sym17071026 - 30 Jun 2025
Viewed by 360
Abstract
Advanced persistent threat (APT) attacks present significant challenges to cybersecurity due to their covert nature, high complexity, and ability to operate across multiple temporal and spatial scales. Existing detection techniques often struggle with issues like class imbalance, insufficient feature extraction, and the inability [...] Read more.
Advanced persistent threat (APT) attacks present significant challenges to cybersecurity due to their covert nature, high complexity, and ability to operate across multiple temporal and spatial scales. Existing detection techniques often struggle with issues like class imbalance, insufficient feature extraction, and the inability to capture complex attack dependencies. To address these limitations, we propose a dual-phase framework for APT detection, combining multi-feature-conditioned generative adversarial networks (MF-CGANs) for data reconstruction and a multi-scale convolution and channel attention-enhanced graph convolutional network (MC-GCN) for improved attack detection. The MF-CGAN model generates minority-class samples to resolve the class imbalance problem, while MC-GCN leverages advanced feature extraction and graph convolution to better model the intricate relationships within network traffic data. Experimental results show that the proposed framework achieves significant improvements over baseline models. Specifically, MC-GCN outperforms traditional CNN-based IDS models, with accuracy, precision, recall, and F1-score improvements ranging from 0.47% to 13.41%. The MC-GCN model achieves an accuracy of 99.87%, surpassing CNN (86.46%) and GCN (99.24%), while also exhibiting high precision (99.87%) and recall (99.88%). These results highlight the proposed model’s superior ability to handle class imbalance and capture complex attack behaviors, establishing it as a leading approach for APT detection. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

25 pages, 2711 KiB  
Article
Enhancing Multi-User Activity Recognition in an Indoor Environment with Augmented Wi-Fi Channel State Information and Transformer Architectures
by MD Irteeja Kobir, Pedro Machado, Ahmad Lotfi, Daniyal Haider and Isibor Kennedy Ihianle
Sensors 2025, 25(13), 3955; https://doi.org/10.3390/s25133955 - 25 Jun 2025
Viewed by 386
Abstract
Human Activity Recognition (HAR) is crucial for understanding human behaviour through sensor data, with applications in healthcare, smart environments, and surveillance. While traditional HAR often relies on ambient sensors, wearable devices or vision-based systems, these approaches can face limitations in dynamic settings and [...] Read more.
Human Activity Recognition (HAR) is crucial for understanding human behaviour through sensor data, with applications in healthcare, smart environments, and surveillance. While traditional HAR often relies on ambient sensors, wearable devices or vision-based systems, these approaches can face limitations in dynamic settings and raise privacy concerns. Device-free HAR systems, utilising Wi-Fi Channel State Information (CSI) to human movements, have emerged as a promising privacy-preserving alternative for next-generation health activity monitoring and smart environments, particularly for multi-user scenarios. However, current research faces challenges such as the need for substantial annotated training data, class imbalance, and poor generalisability in complex, multi-user environments where labelled data is often scarce. This paper addresses these gaps by proposing a hybrid deep learning approach which integrates signal preprocessing, targeted data augmentation, and a customised integration of CNN and Transformer models, designed to address the challenges of multi-user recognition and data scarcity. A random transformation technique to augment real CSI data, followed by hybrid feature extraction involving statistical, spectral, and entropy-based measures to derive suitable representations from temporal sensory input, is employed. Experimental results show that the proposed model outperforms several baselines in single-user and multi-user contexts. Our findings demonstrate that combining real and augmented data significantly improves model generalisation in scenarios with limited labelled data. Full article
(This article belongs to the Special Issue Sensors and Data Analysis for Biomechanics and Physical Activity)
Show Figures

Figure 1

Back to TopTop