IEEE Access最新文献

{"title":"Improving Upper Limb Movement Classification from EEG Signals Using Enhanced Regularized Correlation-Based Common Spatio-Spectral Patterns","authors":"Amin Besharat;Nasser Samadzadehaghdam","doi":"10.1109/ACCESS.2025.3563417","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563417","url":null,"abstract":"Detection of movement from electroencephalogram (EEG) signals is crucial for advancing brain-computer interface (BCI) systems, particularly in rehabilitating individuals with disabilities. This study focuses on decoding two types of ipsilateral movements (right arm and thumb) and the resting state from EEG signals—a challenging task due to the reduced signal discrimination between ipsilateral movements. To address this challenge, we propose a novel framework that combines precise segmentation of EEG signals during movement with an improved feature extraction method. First, we detect accurate segmentation of EEG signals by using the teager-kaiser energy operator for electromyographic (EMG) signals, which allows for precise detection of the onset and end of movements. Next, for feature extraction, we developed the regularized correlation-based common spatio-spectral patterns (RCCSSP) algorithm, which improves the traditional common spatial patterns (CSP) by incorporating regularization based on correlation. RCCSSP employs spatio-spectral canonical correlation analysis (SS-CCA) with an advanced regularization approach. Specifically, this method calculates the correlation between two classes for each channel, assigning higher weights to channels with lower correlation to increase their impact while minimizing the effect of noisy channels with higher correlation. Classification is then performed using distance-weighted k-nearest neighbor and support vector machine algorithms. Experimental results from 15 healthy subjects demonstrate that the proposed approach achieves an average classification accuracy of 88.94%, representing a significant 11.66% improvement over the best-reported method. This work highlights the potential of precise movement segmentation and robust feature extraction in decoding ipsilateral movements for BCI applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71432-71446"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10972360","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BorB: A Novel Image Segmentation Technique for Improving Plant Disease Classification With Deep Learning Models","authors":"T. Ozcan;E. Polat","doi":"10.1109/ACCESS.2025.3563160","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563160","url":null,"abstract":"Disease detection from leaf images has been among the popular studies in recent years. Classifying leaf diseases using computational methods provides great convenience for farming. In the studies carried out in this field, systems that work with high accuracy and are least affected by environmental factors that can be used in agricultural lands come to the fore. This study investigates the application of deep learning architectures for accurate and efficient plant disease detection within the context of the ongoing digital transformation of the agricultural sector. Recognizing the critical role of AI in modernizing agriculture, this research focuses on enhancing the accuracy of the classification of plant diseases. To facilitate this research, a novel dataset, “EruCauliflowerDB”, was meticulously curated, comprising high-resolution images of cauliflower plants infected with Alternaria Leaf Spot and Black Rot. The obtained EruCauliflower dataset contains 114 images from the Alternaria Leaf Spot disease class and 99 images from the Black Rot disease class. A novel integrated classification system was developed, encompassing three key stages. First, a novel segmentation method, “BorB,” was introduced to effectively isolate diseased leaf regions. This segmentation method enables us to extract features of leaf images in Lab and RGB formats. Combining the features obtained from the two image formats with the OR logical operation separates the leaf region from the background. Second, data augmentation techniques, including geometric transformations, were applied to the segmented images to enhance data diversity and improve model robustness. Finally, four state-of-the-art deep learning models—VGG16, ResNet50, EfficientNetB3, and MobileNetV3 Large—were employed for disease classification. The proposed integrated system demonstrated exceptional performance, achieving 100% classification accuracy on the EruCauliflowerDB dataset across all four models. To assess the system’s robustness, further evaluations were conducted on the independent MangoLeafBD dataset, yielding consistent results with 100% classification accuracy. The proposed Integrated Classifier method was applied by selecting 15 classes from the PlantVillage, another multi-class dataset. As a result of the experiments, PlantVillage plant leaf images were classified with 99.78% accuracy. Experimental results show that the proposed method can be effectively utilized in real-world agricultural settings to assist farmers in early disease detection, thereby reducing crop losses and improving yield quality.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71822-71839"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973129","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging BERT, DistilBERT, and TinyBERT for Rumor Detection","authors":"Aijazahamed Qazi;R. H. Goudar;Rudragoud Patil;Geetabai S. Hukkeri;Dhanashree Kulkarni","doi":"10.1109/ACCESS.2025.3563301","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563301","url":null,"abstract":"The rapid spread of false information on social media has become a major challenge in today’s digital world. This has created a need for an effective rumor detection system that can identify and control the spread of false information in real-time. The proposed work introduces a rumor detection system by integrating transformer-based models such as BERT, DistilBERT, and TinyBERT with traditional Machine Learning (ML) techniques. The classifiers include Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF) and Naïve Bayes (NB) help in categorizing content as either rumor or non-rumor based on the patterns. The proposed work evaluated BERT, DistilBERT, TinyBERT combined with ML models (SVM, DT, RF, NB) across PHEME dataset using 70:30, 60:40, and 80:20 splits. Overall, BERT + DT and TinyBERT + SVM provided significant results, with BERT + RF and DistilBERT + NB demonstrating better classification capabilities across various events and split ratios on the dataset.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72918-72929"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design-LIME: An Interpretable Visualization Method for Electric Motor Design Based on Deep Learning","authors":"Kazuhisa Iwata;Hidenori Sasaki","doi":"10.1109/ACCESS.2025.3563351","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563351","url":null,"abstract":"A novel visualization method for interpreting the resultant design from topology optimization (TO) is proposed. We employ a pre-trained deep learning (DL) model to predict the degree of influence of transitions from air to magnetic materials, and build an interpretable linear model to display the visualization result. The proposed method, Design-LIME, is applied for visualizing the impact of effective regions on the torque characteristics of interior permanent magnet synchronous motors (IPMSMs). Compared to conventional visualization methods based on explainable artificial intelligence (XAI), Design-LIME presents accurate and simple visualization results. Furthermore, a novel multistep TO method is proposed. The proposed TO utilizes Design-LIME to efficiently address the electromagnetic and mechanical characteristics of IPMSMs by extracting the effective region of the IPMSM characteristics. The proposed TO method improves search performance by 18.7% when compared with the conventional single-step optimization method. The proposed method enables more efficient motor designs with improved electromagnetic and mechanical performance. The proposed method contributes to the streamlining of the design process not only for motors but also for various electrical devices.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73697-73708"},"PeriodicalIF":3.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DiffTST: Diff Transformer for Multivariate Time Series Forecast","authors":"Song Yang;Wenyong Han;Yaping Wan;Tao Zhu;Zhiming Liu;Shuangjian Li","doi":"10.1109/ACCESS.2025.3563070","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563070","url":null,"abstract":"Deep learning models employing the Transformer architecture have demonstrated exceptional performance in the field of multivariate time series forecasting research. However, these models often incorporate irrelevant or weakly relevant information during the processing of time series, leading to noise. This phenomenon diverts the attention mechanism from crucial features within the time series, thereby impacting the overall forecasting performance. To mitigate this issue, our study introduces DiffTST, which employs a Differential Transformer to enhance the model’s focus on relevant context within the time series, thereby mitigating the influence of noise on forecasting accuracy. The model utilizes independent channels to process time series data, ensuring that each input token contains information from a single channel exclusively. Furthermore, each channel is segmented into multiple patches to facilitate the extraction of local information. Subsequently, the Differential Transformer module is employed to process the sequence features of these patches, alleviating the tendency of Transformer-based models to allocate excessive attention to irrelevant sequence information. Ultimately, the forecast outcomes are derived through a Multi-Layer Perceptron. Our findings indicate that DiffTST achieves higher or comparable long-term forecasting accuracy compared to the current state-of-the-art Transformer-based models. On the main datasets (Weather, Traffic, Electricity), our method reduces MSE by 0.008, 0.087, and 0.023 and MAE by 0.004, 0.069, and 0.025 compared to PatchTST.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73671-73679"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10972038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SCM-DL: Split-Combine-Merge Deep Learning Model Integrated With Feature Selection in Sports for Talent Identification","authors":"Didem Abidin;Muhammed G. Erdem","doi":"10.1109/ACCESS.2025.3562551","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3562551","url":null,"abstract":"In sports, identifying athletes with high potential to excel in sports schools is pivotal. In the literature, this process is called Talent Identification (TID) and is defined as “to know the players participating in the sport with the potential to be perfect.” The problem discussed in this paper focuses on the early identification of an athlete’s talented sports branch before they are assigned to a specific branch. This determination process is based on the evaluation of general performance tests and assessments. TID solutions in the literature use AI-driven methods (i.e., Machine Learning, Neural Nets, etc.). However, they could not beat the following deficiencies: they cannot be used with the dataset features having complex and non-linear relationships, are not scalable in the number of features, are not adaptable to hierarchical data, cannot generalize the solution, depend on any predefined thresholds or prior assumptions, are not adaptable to the other datasets, are not tolerable to the incomplete inputs. A two-stage TID solution has been introduced to address the deficiencies above and resolve the TID challenge. In the first stage (TID1), the admitted athletes are determined. In the second stage (TID2), athletes are classified into their talented branches (Football, basketball, volleyball, or athletics). TID1 uses our Shallow Deep learning (SDL) model to classify the admitted. In this stage, a remarkable performance was obtained with 98.85%. In TID2, nine different feature selection methods (four RFE-related methods, three SelectKBest-related methods, and Lasso and Boruta) are applied to reduce the number of features. After feature selection, our novel SCM-DL deep learning classifier model (apart from the architectures in literature, this model is constructed internally with parallel layers and carries a combinatorial layer that is beyond the combination of existing techniques) is applied and compared with Random Forest, Decision Tree, Extra Tree, and Support Vector Classifiers. The SCM-DL integrated with the RFE_DTC feature selection method achieved the highest performance for six features, yielding an accuracy rate of 97.40% and a Matthews Correlation Coefficient performance rate of 96.6%. By this result, our model guided the coaches by indicating which features to focus on in talent identification.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"71148-71172"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10971350","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Balancing Illumination and Communication in Indoor VLC: Impact of Multiple LED Configurations on System Performance","authors":"David Esteban Farfán-Guillén;Paulo Pereira Monteiro;Juan Camilo Castellanos Rodriguez;Alexandre De Almeida Prado Pohl","doi":"10.1109/ACCESS.2025.3562801","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3562801","url":null,"abstract":"This study explores the influence of multiple luminaire arrangements on the dual functionality of visible light communication systems (VLC), focusing on their impact on illumination uniformity and communication performance. A comprehensive analysis of various luminaire distributions, ranging from single to multiple luminaires, is performed to identify configurations that optimize lighting quality and data transmission efficiency. In particular, the study examines three luminaire arrangements—circular, square, and circular-square—implemented in configurations of 1 to 12 luminaires, and includes theoretical modeling and experimental validation in indoor environments, covering single-input single-output (SISO), multiple-input single-output (MISO), and multiple-input multiple-output (MIMO) configurations up to <inline-formula> <tex-math>$3 times 2$ </tex-math></inline-formula> systems. Orthogonal frequency division multiplexing (OFDM) with repetition coding (RC) is employed, which distributes data across subcarriers while replicating signals across transmitters to enhance spatial diversity. Key performance metrics, such as illumination, uniformity, quality factor (<inline-formula> <tex-math>$F_{a}$ </tex-math></inline-formula>), and coefficient of variation (CV(RMSE)), are evaluated for illumination, while communication performance is assessed using bit error rate (BER) metrics. The results demonstrate that the overall performance is improved as the number of luminaries increases, however a saturation point exists beyond which additional luminaires yield diminishing returns. Our findings highlight the complex interplay between illumination uniformity and communication performance in VLC systems, providing valuable insights for designing high-performance MIMO systems in smart indoor environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"70195-70210"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10971352","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Parkinson’s Disease Diagnosis Using Decomposition Techniques and Deep Learning for Accurate Gait Analysis","authors":"S. Jeba Priya;C. Anand Deva Durai;M. S. P. Subathra;S. Thomas George;Andrew Jeyabose","doi":"10.1109/ACCESS.2025.3562566","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3562566","url":null,"abstract":"Parkinson’s disease (PD) is a prevalent neurological disorder that significantly impacts posture and gait, leading to movement abnormalities due to malfunctions in the brain and nervous system. Gait signals are essential for identifying PD, and various techniques have been employed for classification, with a focus on spatiotemporal factors. Additionally, cognitive monitoring systems for PD symptoms have been developed. Recent advancements involve decomposing gait signals using techniques such as empirical mode decomposition (EMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD) to streamline data for improved computational efficiency. Machine learning (ML) and deep learning (DL) algorithms are widely used to enhance classification accuracy. This study integrates decomposition techniques with ML algorithms such as support vector machines (SVMs), artificial neural networks (ANNs), decision trees (DTs), and k-nearest neighbors (k-NNs), as well as DL algorithms such as long short-term memory (LSTM), bidirectional long short-term memory (LSTM), and convolutional neural networks (CNNs), for PD classification. The combination of VMD with the 1D-CNN achieved the highest accuracy, sensitivity, and specificity, with values of 99.1 %, 100 %, and 100 %, respectively. This finding suggests a promising approach for further research in this field. The optimized VMD-1D-CNN combination demonstrated significant potential for accurately diagnosing PD based on gait dynamics. The successful application of these methods highlights the importance of advanced signal processing techniques in improving the detection and management of neurological disorders.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"74078-74091"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10971181","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Green Cloud-Based Framework for Energy-Efficient Task Scheduling Using Carbon Intensity Data for Heterogeneous Cloud Servers","authors":"B. M. Beena;Prashanth Cheluvasai Ranga;Thotapalli Sri Surya Manideep;Sneha Saragadam;Garikipati Karthik","doi":"10.1109/ACCESS.2025.3562882","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3562882","url":null,"abstract":"Managing modern data centre operations is increasingly complex due to rising workloads and numerous interdependent components. Organizations that still rely on outdated, manual data management methods face a heightened risk of human error and struggle to adapt quickly to shifting demands. This inefficiency leads to excessive energy consumption and higher CO2 emissions in cloud data centres. To address these challenges, integrating advanced automation within Infrastructure as a Service (IaaS) has become essential for IT industries, representing a significant step in the ongoing transformation of cloud computing. For data centres aiming to enhance efficiency and reduce their carbon footprint, intelligent automation provides tangible benefits, including optimized resource allocation, dynamic workload balancing, and lower operational costs. As computing resources remain energy-intensive, the growing demand for AI and ML workloads is expected to surge by 160% by 2030 (Goldman Sachs). This heightened focus on energy efficiency has driven the need for advanced scheduling systems that reduce carbon emissions and operational expenses. This study introduces a deployable cloud-based framework that incorporates real-time carbon intensity data into energy-intensive task scheduling. By utilizing AWS services, the proposed algorithm dynamically adjusts high-energy workloads based on regional carbon intensity fluctuations, using both historical and real-time analytics. This approach enables cloud service providers and enterprises to minimize environmental impact without sacrificing performance. Designed for seamless integration with existing cloud infrastructures—including AWS, Google Cloud, and Azure—this scalable solution utilizes Kubernetes-based scheduling and containerized workloads for intelligent resource management. By combining automation, real-time analytics, and cloud-native technologies, the framework significantly enhances energy efficiency compared to traditional scheduling methods. Moreover, the proposed system aligns with key United Nations Sustainable Development Goals (SDGs), including climate action (SDG 13), clean energy (SDG 7), sustainable urban development (SDG 11), and infrastructure innovation (SDG 9). By promoting energy-efficient cloud computing, this research supports a more sustainable, cost-effective digital ecosystem that meets the growing demands of high-performance computing and AI-driven workloads.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73916-73938"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10971939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Distributed Photovoltaic Operation and Maintenance Cloud Platform for PV Aerial Inspections With Sparse Industrial Data","authors":"Chengwu Liang;Songqi Jiang;Jie Yang;Wei Hu;Yalong Liu;Peiwang Zhu;Guofeng He;Chunlei Shi","doi":"10.1109/ACCESS.2025.3561234","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3561234","url":null,"abstract":"Distributed photovoltaic (DPV) power sites in industrial parks are characterized by dispersed layouts, practical fault detection environments, and high safety requirements. Conventional manual DPV O&M systems using handheld sensors are inefficient, expensive, and struggle with fault detection due to sparse industrial data and uni-modal information limitations. To this, this paper proposes an innovative advanced algorithm for DPV fault detection in industrial parks, utilizing a new sparse industrial dataset, “SolarPark,” collected via multi-modal UAVs and annotated through a multi-expert process with uncertainty scoring. By fusing the Convolutional Block Attention Module (CBAM), Bidirectional Feature Pyramid Network (BiFPN), Ghost modules, the algorithm enhances attention to critical photovoltaic fault-related channel information, strengthens multi-scale photovoltaic fault feature fusion, and achieves lightweight efficiency. Combined with multi-modal UAV videos, the proposed industrial DPV fault detection algorithm achieves a precision of 95.4%, effectively ensuring the efficiency of DPV power sites in data-scarce industrial scenarios. Extensive experiments on the developed cloud platform confirm the proposed algorithm’s efficient, cost-effective, and easy to deploy for aerial inspections of DPV O&M systems.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"69677-69689"},"PeriodicalIF":3.4,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10972109","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}