IEEE Access最新文献

{"title":"Time Delay Identification Method of Wind Turbine Drivetrain Test Bench Based on Instability Characteristics Observation","authors":"Lianjun Zhou;Zaiyu Chen;Minghui Yin;Senhua Luo","doi":"10.1109/ACCESS.2025.3565968","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565968","url":null,"abstract":"There is a huge difference in rotational inertia between the wind turbine drivetrain test bench (WTDTB) and the actual wind turbine, which needs to be accurately compensated. As a closed-loop control system with time delay, WTDTB working in the inertia simulation mode is prone to instability. The existing researches solve this problem by the time delay stability control algorithm based on high-order filter, which is on the premise that the filter order and the time delay order of the inertia compensation loop accurately match. However, the torque command response method currently used to measure time delay is not effective in practical applications. In order to accurately obtain the time delay, this paper draws on the idea of soft measurement based on operation parameters, finds and proves that there is a definite quantitative relationship between the compensation torque oscillation period and the time delay. On this basis, a time delay identification method based on instability characteristics observation is proposed. This method causes the controlled oscillation of the test bench by reasonably designing the oscillation experiment, extracts the oscillation period, and determines the time delay accordingly. The experiment results based on 15kW WTDTB verify the feasibility and effectiveness of the proposed method.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"76548-76560"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980275","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913550","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":"Research on Electromagnetic Safety of UAV Inspection in Substation","authors":"Wensheng Li;Mengyuan Chen;Haohao Jin;Ying Zhang;Hao Wu;Lin Yi;Li Cai","doi":"10.1109/ACCESS.2025.3565919","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565919","url":null,"abstract":"As power grids modernize, ensuring reliable substation operation grows increasingly critical. Uncrewed aerial vehicle (UAV) inspections provide significant advantages over traditional manual and robotic methods, such as cost-effectiveness, greater maneuverability, improved efficiency, and the ability to operate in closer proximity to equipment. However, the complex electromagnetic-field environment within substations poses challenges for UAV operations. Determining a safe distance between UAVs and high-voltage equipment is essential for deploying UAVs effectively in substation inspections. This study investigates electromagnetic field exposure during UAV-based substation inspections. A computational model was developed to evaluate the electromagnetic field and simulate the surface field distribution during UAV operation. The results indicate that the UAV is affected by strong electromagnetic fields near the four rotor blades and the central wing section. Laboratory high-voltage tests, combined with simulations, confirmed that the UAV can perform inspections while maintaining a 50 cm distance from high-voltage equipment. Furthermore, when the UAV approaches the equipment to the point of gap discharge, it can continue operating normally for a limited time, demonstrating its certain ability to withstand high-voltage electric fields. These findings provide critical insights for establishing safe operating distances for UAVs in substations.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"78097-78106"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980243","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925329","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 Hybrid Deep Learning Framework for Deepfake Detection Using Temporal and Spatial Features","authors":"Fazeel Zafar;Talha Ahmed Khan;Salas Akbar;Muhammad Talha Ubaid;Sameena Javaid;Kushsairy Abdul Kadir","doi":"10.1109/ACCESS.2025.3566008","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3566008","url":null,"abstract":"The rise of deep-fake technology has sparked concerns as it blurs the distinction between fake media by harnessing Generative Adversarial Networks (GANs). This has raised issues surrounding privacy and security in the realm. This has led to a decrease in trust during online interactions; thus, emphasizing the importance of creating reliable methods for detection purposes. Our research introduces a model for detecting deepfakes by utilizing an Enhanced EfficientNet B0 structure in conjunction with Temporal Convolutional Neural Networks (TempCNNs). This approach aims to tackle the challenges presented by the evolving sophistication of deep-fake techniques. The system dissects video inputs into frames to extract features comprehensively by using Multi Test Convolutional Networks (MTCNN). This method ensures face detection and alignment by focusing on facial regions. To enhance the model’s adaptability, to different scenarios and datasets we implement data augmentation techniques such as CutMix, MixUp and Random Erasing. These strategies help the model maintain its strength, against distortions found in deepfake content. The backbone of EfficientNet B0 utilizes Mobile Inverted Bottleneck Convolutions (MBConv) and Squeeze and Excitation (SE) blocks to enhance feature extraction by adjusting channels to highlight details effectively. A Feature Pyramid Network (FPN) facilitates the fusion of scale features capturing intricate details as well, as broader context. When tested on the FFIW 10 K dataset, which comprises 10,000 videos evenly split between manipulated content, the model attained a training accuracy of 91.5 % and a testing accuracy of 92.45 %, after 40 epochs. The findings showcase the model’s proficiency, in identifying videos with precision and tackling the issue of class imbalances found in datasets – a valuable contribution, to advancing dependable deepfake detection solutions. Furthermore, the model achieves an impressive balance between accuracy and computational efficiency, attaining 92.45% testing accuracy with a lightweight computational cost of 0.45 GFLOPs, making it a highly practical choice for real-world deployment.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"79560-79570"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10981422","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925074","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":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","authors":"Hang Zou;Qiyang Zhao;Samson Lasaulce;Lina Bariah;Mehdi Bennis;Mérouane Debbah","doi":"10.1109/ACCESS.2025.3565859","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565859","url":null,"abstract":"genai and communication networks are expected to have groundbreaking synergies for 6G. Connecting Generative Artificial Intelligence (GenAI) agents via a wireless network can potentially unleash the power of Collective Intelligence (CI) and pave the way for Artificial General Intelligence (AGI). However, current wireless networks are designed as a “data pipe” and are not suited to accommodate and leverage the power of GenAI. In this paper, we propose the GenAINet framework in which distributed GenAI agents communicate knowledge (facts, experiences, and methods) to accomplish arbitrary tasks. We first propose an architecture for a single GenAI agent and then provide a network architecture integrating GenAI capabilities to manage both network protocols and applications. Building on this, we investigate effective communication and reasoning problems by proposing a semantic-native GenAINet. Specifically, GenAI agents extract semantics from heterogeneous raw data, build and maintain a knowledge model representing the semantic relationships among pieces of knowledge, which is retrieved by GenAI models for planning and reasoning. Under this paradigm, different levels of collaboration can be achieved flexibly depending on the complexity of targeted tasks. Furthermore, we conduct two case studies in which, through wireless device queries, we demonstrate that extracting, compressing and transferring common knowledge can improve query accuracy while reducing communication costs; and in the wireless power control problem, we show that distributed agents can complete general tasks independently through collaborative reasoning without predefined communication protocols. Finally, we discuss challenges and future research directions in applying Large Language Models (LLMs) in 6G networks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77764-77777"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980288","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925152","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":"Study of the Effect of 3D Printing Parameters on the Dielectric Constant in Piezoelectric Polylactic Acid/Barium Titanate Composites via Fused Granular Fabrication","authors":"Rodrigo Ruz;Dreidy Vásquez;Rodrigo Ortiz;Francisco Pizarro","doi":"10.1109/ACCESS.2025.3565941","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565941","url":null,"abstract":"This research aims to study the fabrication of electronic devices using pellet extrusion 3D printing with composite material. The process employed a polymer-based composite material that incorporated a substantial amount of barium titanate powder, reaching 80 wt.%. A thorough examination was conducted to understand the various factors influencing the printed components, using a design of experiments (DOE) approach. This method identifies the optimal printing parameters for a Custom Fused Granular Fabrication printer, such as layer height (0.32), barrel temperature (240°C), flow rate (500), and printing speed (2 mm/s). The dielectric constant of the polylactic acid - barium titanate composite reached 8.47 and a loss tangent of 0.099 in the X-band, making it suitable for applications involving high frequencies with a lower cost process and using a more sustainable polymer.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"78959-78967"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10981427","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949299","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":"MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition","authors":"Pu Li;Guopeng Cheng;Guojun Deng;Shuanghong Qu;Min Huang;Guoxiang Li","doi":"10.1109/ACCESS.2025.3565908","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565908","url":null,"abstract":"Named Entity Recognition (NER) aims to automatically extract specific entities from unstructured text. Compared with English NER, Chinese NER faces challenges due to heterophony, where the same Chinese character may have different pronunciations and meanings. Additionally, the lack of clear separators between Chinese characters exacerbates these challenges, leading to difficulties in boundary detection and entity category determination. Inspired by the hieroglyphic and phonetic features of Chinese characters, this study proposes a multi-feature fusion embedding model (MP-NER). The model employs CNN for extracting radicals and phonetic features of Chinese characters, combines the encoded information from these features with pre-trained word vectors to generate fusion embedding vectors, and uses a fully-connected layer for feature transformation. Experiments were conducted on the Chinese benchmark datasets Resume, Weibo and MSRA. Compared to current mainstream models, the proposed model demonstrates superior performance in terms of F1 score, F1 score stability, and individual entity recognition accuracy. Ablation experiments further validate the effectiveness of the introduced radicals and phonetic features. The experimental results demonstrate that this model effectively captures the semantic information of Chinese characters, addresses the problem of Chinese character heterophony, and improves entity recognition performance. The code and datasets available at: <uri>https://github.com/FAKLITS/MP-NER</uri>","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"78427-78440"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980313","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918733","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":"Advancing Sentiment Analysis for Low-Resource Languages Using Fine-Tuned LLMs: A Case Study of Customer Reviews in Turkish Language","authors":"Rukiye Savran Kiziltepe;Ercan Ezin;Ömer Yentür;Arwa M. Basbrain;Murat Karakus","doi":"10.1109/ACCESS.2025.3566000","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3566000","url":null,"abstract":"This study investigates the application of advanced fine-tuned Large Language Models (LLMs) for Turkish Sentiment Analysis (SA), focusing on e-commerce product reviews. Our research utilizes four open-source Turkish SA datasets: Turkish Sentiment Analysis version 1 (TRSAv1), Vitamins and Supplements Customer Review (VSCR), Turkish Sentiment Analysis Dataset (TSAD), and TR Customer Review (TRCR). While these datasets were initially labeled based on star ratings, we implemented a comprehensive relabeling process using state-of-the-art LLMs to enhance data quality. To ensure reliable annotations, we first conducted a comparative analysis of different LLMs using the Cohen’s Kappa agreement metric, which led to the selection of ChatGPT-4o-mini as the best-performing model for dataset annotation. Our methodology then focuses on evaluating the SA capabilities of leading instruction-tuned LLMs through a comparative analysis of zero-shot models and Low-Rank Adaptation (LoRA) fine-tuned LlaMA-3.2-1B-IT and Gemma-2-2B-IT models. Evaluations were conducted on both in-domain and out-domain test sets derived from the original star-ratings-based labels and the newly generated GPT labels. The results demonstrate that our fine-tuned models outperformed leading commercial LLMs by 6% in both in-domain and out-domain evaluations. Notably, models fine-tuned on GPT-generated labels achieved superior performance, with in-domain and out-domain F1-scores reaching 0.912 and 0.9184, respectively. These findings underscore the transformative potential of combining LLM relabeling with LoRA fine-tuning for optimizing SA, demonstrating robust performance across diverse datasets and domains.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77382-77394"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980352","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943786","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":"An Artificial Neural Network for Short Time Air Temperature Prediction","authors":"Olívia S. Gomes;Manuel O. Binelo;Marcia de F. B. Binelo;João Paulo C. Oliveira;Emerson Galvani;Rogério Rozolen Alves","doi":"10.1109/ACCESS.2025.3565731","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565731","url":null,"abstract":"Air temperature is an extremely important factor in agriculture, from planting to post-harvest processes, and having the ability to predict air temperature can be a valuable tool for avoiding damage, maximizing production quality, and optimizing resources. In this work, we propose a simple air temperature prediction model based on a small neural network with a relatively small volume of training data. This work uses data from the Climatology and Biogeography Laboratory of the University of São Paulo (USP), from the Experimental Meteorological Station in São Paulo City, Brazil. The dataset corresponds to air temperature data collected during the years 2018 and 2020. For machine learning, two types of artificial neural networks were adopted: one of the long short-term memory recurrent network and one feed-forward network. Three past air temperatures were used to predict the next hour’s air temperature, and chain predictions were used to predict up to 24 hours. The feed-forward neural network presented the best results, with most errors below 2°C. The results show that it is possible to use a simple neural network, using only air temperature as the meteorological variable, to predict air temperature for the next hours. The simplicity of the model makes its application more feasible for various problems in agriculture.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77593-77598"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980271","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943888","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":"Highly-Efficient, Dual-Polarized Huygens’ Metasurfaces for Scan-Angle Enhancement Without Directivity Degradation","authors":"Jaemin Kim;Mohammad Soltani;Minseok Kim;George V. Eleftheriades","doi":"10.1109/ACCESS.2025.3565892","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565892","url":null,"abstract":"We hereby propose a dual-polarized beam-deflecting metasurface that can double the scan-angle range of a phased-array antenna without compromising the directivity across all scan angles, including broadside. In particular, our research focuses on expanding the scanning range of a dual-polarized phased-array antenna capable of independently steering TE and TM waves. This is achieved by placing a dual-polarized phase-gradient Huygens’ metasurface in front of the antenna. The Huygens’ metasurface employs crossed meander lines in four impedance layers that are suitably optimized to independently control the local electric and magnetic responses for maximizing the transmission for all incident beams. We validate our approach through theoretical analysis, full-wave simulations, and experimental verification. It is demonstrated that the beam-deflecting HMS achieves effective scan range expansion to <inline-formula> <tex-math>$-30^{circ } sim 0^{circ } $ </tex-math></inline-formula> and <inline-formula> <tex-math>$0^{circ } sim 30^{circ } $ </tex-math></inline-formula> for TE and TM beams, respectively, using a dual-polarized phased array antenna source that scans from −15° and 15°.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"83219-83228"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980303","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073155","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":"Collaborative Coverage Strategy Using Multiple UAVs-UGVs in CRN Mapping","authors":"Agung Nugroho Jati;Bambang Riyanto Trilaksono;Egi Muhammad Idris Hidayat;Widyawardana Adiprawita","doi":"10.1109/ACCESS.2025.3565779","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565779","url":null,"abstract":"Chemical, Radiological, and Nuclear (CRN) contamination poses a significant threat, potentially leading to mass casualties and long-term environmental repercussions. This paper presents a collaborative framework utilizing a heterogeneous coverage control approach to measure and generate an estimated density distribution map of a designated area. Multiple Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) are deployed strategically within partitioned regions, determined through weighted Voronoi tessellation. This method integrates both the robots’ internal parameters and environmental factors. The distinct operational domains of UAVs and UGVs facilitate region decomposition by accounting for variations in CRN dispersion, obstacle representation, and environmental conditions. The resulting cross-partitioned regions are systematically merged to enhance robot distribution efficiency. Each robot autonomously measures within its allocated region, updates contamination data, and generates a dispersion map. The proposed strategy enables an adaptive robot distribution, eliminating uncontaminated grids and improving mapping accuracy. Compared to existing methods, including homogeneous schemes, our approach reduces data variance in CRN-contaminated regions while maintaining mapping efficiency.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"85652-85668"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980321","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100025","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}