IEEE Access最新文献

{"title":"Fault-Tolerant Methods for Three-Level T-Type Inverter to Balance Neutral-Point Voltage","authors":"Duc-Tri do;Anh-Tuan Nguyen-Phan;Khai M. Nguyen;Vinh-Thanh Tran","doi":"10.1109/ACCESS.2025.3565856","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565856","url":null,"abstract":"This paper proposes new fault-tolerant (FT) space-vector modulation (SVM) techniques for three-level T-type inverter (3L-T2I) to balance neutral-point voltage (NPV) under faulty conditions. Unlike conventional FT-SVM methods, which use three-nearest vectors to synthesize output voltages, the proposed SVM methods add one small vector to conventional switching sequences to obtain NPV balance. Dwell-time of extra vectors are maximized to decrease NPV balanced time. Comparing to conventional FT-SVM methods, the proposed approaches can significantly reduce the difference in capacitor voltages. As a result, the amplitudes of DC component and high-order harmonics of output currents are also reduced. Consequently, the quality of output current is improved. Experimental results, which are conducted by a 1.1-kVA laboratory prototype, are presented to verify the effectiveness of the proposed FT methods. Comparison studies based on experimental results are also presented to demonstrate the advantages of NPV balance of the proposed method compared to conventional FT methods.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"78084-78096"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980350","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925007","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 Diversity in Session-Based Recommendation Between Relevance and Unexpectedness","authors":"Sangyeon Kim;Sanghyeok Boo;Gyewon Jeon;Dongmin Shin;Sangwon Lee","doi":"10.1109/ACCESS.2025.3565767","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565767","url":null,"abstract":"Recommender systems encounter the potential problem of filter bubble, neglecting the diversity of recommendations. These systems are inevitable to lower user experience because they cannot but provide tedious recommendations. Although several solutions have been introduced to increase diversity, it is still challenging to prevent accuracy loss with diversity enhancement. This study presents a new user-oriented algorithm for session-based recommendations that aims to improve diversity in consideration of two serendipity components—relevance and unexpectedness. Specifically, our approach first adopts serendipitous preference embedding into the recommender system based on session and graph neural networks. Next, we leverage a greedy algorithm of the maximum a posteriori (MAP) inference for the determinantal point process to re-rank items. Lastly, it additionally incorporates personalized trade-off balancing through a parameter that can be controlled by the user. To validate our approach, we conducted an experiment with two real-world datasets to demonstrate its ability to balance accuracy and diversity. The results showed that our approach generated not only relevant but unexpected recommendations, successfully improving diversity without accuracy loss. This study contributes to recommendation diversification methods, especially for session-based recommender systems under the user-centric perspective.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77833-77846"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980295","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925008","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":"Self-Supervised Drift-Resilient Classification for Time Series Industrial Anomaly Detection","authors":"Myung-Kyo Seo;Byeong Hoon Yoon;Junseung Ryu;Hyung Ju Hwang","doi":"10.1109/ACCESS.2025.3565886","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565886","url":null,"abstract":"In modern industrial environments, early detection of anomalies is essential to prevent unplanned downtime and maintain operational efficiency. Traditional rule-based and supervised methods often struggle with data drift, limited labeled data, and the inability to capture the complex interdependencies inherent in interconnected industrial systems. To address these challenges, we propose a drift-resistant self-supervised anomaly detection framework specifically designed for industrial applications. Unlike conventional fault classification approaches that identify predefined defect types, our model focuses on detecting subtle, evolving anomalies in time-series vibration data. The framework integrates advanced statistical and spectral feature extraction with a dynamic, rolling-window-based data grouping strategy, enabling the model to adapt robustly to temporal variations. Evaluation is based solely on accuracy and the experimental results demonstrate that our approach achieves up to 75% faster anomaly alerts compared to conventional ISO 10816 standards. Validation in NASA bearing datasets, as well as real-world vibration data from industrial fans, motors, and gearboxes confirms the model scalability and practical applicability. This work provides a cost-effective and reliable solution for continuous condition monitoring, thereby laying a strong foundation for enhanced predictive maintenance in complex industrial settings.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"78021-78043"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980278","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925072","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":"Segmenting Online Shoppers: A Combined Cluster and Logistic Regression Approach for Forecasting Purchase Behavior","authors":"Wong Ming Wong;Wunhong Su","doi":"10.1109/ACCESS.2025.3565897","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565897","url":null,"abstract":"This paper examines customers’ online shopping behavior and its relationship to purchase decisions. There are two research questions for the paper: 1) How can marketers segment prior customers’ online shopping behavior to develop a more accurate consumer segmentation for forecasting purchase behavior? 2) Which factors influence customers’ online shopping behavior? The analysis used a dataset of 12,330 samples with ten continuous and eight categorical variables. Cluster and logistic regression analyses were conducted on the dataset. Cluster analysis grouped customers by operating system, browser, location, and traffic type, while logistic regression estimated online customers’ purchase intentions. The results show that different factors influence various customer segments. In Group 1, administrative factors, product-related duration, exit rate, and page value significantly affect purchase behavior. In Group 2, product-related factors, exit rate, page value, and special days play an important role. In Group 3, product-related factors, bounce rate, page value, and visitor type are key factors. This paper contributes by using cluster analysis and logistic regression to segment online customer usage behavior and forecast purchase behavior. It evaluates key predictors of online shopping behavior that differ across customer groups, supporting targeted marketing strategies and decision-making.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"79467-79478"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980324","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925140","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":"Low SAR Multi-Coupling Feed Antenna and Multi-Device MIMO System Design: Suitable for Multi-Band Wireless Communications","authors":"Ming-An Chung;Zhi-Xuan Zhang;Chia-Chun Hsu;Chia-Wei Lin","doi":"10.1109/ACCESS.2025.3565750","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565750","url":null,"abstract":"This article introduces the design of a multi-coupling feed antenna (MCFA) appropriate for 4G LTE, 5G NR (sub-6 GHz), and WLAN frequency bands. Most antenna designs used in different consumer electronic products only include specific 5G NR frequency bands, while the MCFA antenna proposed in this article covers applications in multiple frequency bands and will meet the needs of more communication devices. MCFA is designed on an FR-4 substrate and uses the coupled-feed structure to achieve diverse operating frequencies. This article also uses the antenna to construct a multi-coupling feed antenna MIMO system (MCFA-MIMO system), which is suitable for electronic devices such as laptops, smartphones, and Wi-Fi base stations. The antenna uses a simple structural design and does not require any RLC components to achieve multiple operating frequency bands, isolation below -11dB, a maximum gain of 4.7, and a maximum efficiency of 78%. The measurement and simulation results of the proposed antennas prove that each multi-band antenna performs consistently in MIMO systems and has high gain and high isolation performance. The simulation values of the specific absorption rate (SAR) of MCFA-MIMO system comply with international specifications and will not harm human health. This makes this antenna design a candidate for modern portable electronic devices.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"76715-76731"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980251","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913301","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":"On-Chip Age Estimation Using Machine Learning","authors":"Turki Alnuayri;Saqib Khursheed;Daniele Rossi","doi":"10.1109/ACCESS.2025.3565913","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565913","url":null,"abstract":"The semiconductor supply chain industry is spread worldwide to reduce costs and meet the high demand for integrated circuits (ICs) in electronic systems. The high utilisation of electronic devices in the next decade is forecasted to reach trillions, increasing the already high volume of e-waste. It will lead to concerns about the security and reliability of ICs, particularly those exposed to counterfeiting, i.e., recycled and remarked ICs. This paper harvests aging degradation induced by bias temperature instability (BTI) and hot carrier injection (HCI), observing frequency (f) and discharge time (<inline-formula> <tex-math>$tau _{dv}$ </tex-math></inline-formula>) affected by changes in drain current and sub-threshold leakage current over the lifetime of an IC to estimate the IC age. This is carried out using Cadence simulations, implementing 13- and 51-stage ring oscillators (ROs) using a 22-nm CMOS technology and aging model provided by GlobalFoundries (GF). The machine learning (ML) algorithm of support vector regression (SVR) is adapted for this application, using a training process that involves operating temperature, <inline-formula> <tex-math>$tau _{dv}$ </tex-math></inline-formula>, f, aging time and inter-die and intra-die process variation (PV). The data sampling is performed over a simulated 12-year period with representative temperatures between 20°C up to 100°C and with additional testing data from 25°C up to 75°C. Incorporating the PV effect with the SVR model allows the proposed SVR model to be adopted in practical IC implementation. The results demonstrate high accuracy in aging estimation by SVR with/without PV effects. The proposed SVR model detects the age of an IC with an error accuracy between 0.206 and 0.667 (deviation of 74.16 and 240.12 days), and 0.091 and 0.237 (deviation of 32.76 and 85.32 days) based on the Root Mean Square Error (RMSE) for 13- and 51-satge RO, respectively. It outperforms the state-of-the-art IC age prediction models even when learning and validating the model with aging and PV.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77334-77352"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980245","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943955","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":"MECFormer: Multiple Exposure Correction Transformer Based on Autoencoder","authors":"Jong-Hyeon Baek;Hyo-Jun Lee;Hanul Kim;Yeong Jun Koh","doi":"10.1109/ACCESS.2025.3565727","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565727","url":null,"abstract":"Images captured with wrong exposure conditions inevitably produce unsatisfactory visual effects. Thus, multiple exposure correction has drawn much attention, which should correct for degraded images due to various wrong exposure conditions. However, the problem of handling the different nature of underexposed and overexposed images makes this task challenging. In this work, we introduce the novel multiple exposure correction transformer, named MECFormer, to tackle this problem. MECFormer consists of autoencoder, encoder, and dual-path aggregation decoder. First, the autoencoder extracts multi-scale exposure features representing the level of input exposure. Second, the encoder embeds input images into multi-scale image features. Third, the dual-path aggregation decoder sequentially restores exposures by effectively aggregating multi-scale exposure features and image features. MECFormer achieves the state-of-the art performance on two multi-exposure correction datasets. Also, we provide extensive ablation studies to show the effectiveness of the proposed components.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"83123-83135"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980299","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072864","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":"Estimation of Required Characteristic Modes for Stirrers in a Reverberation Chamber","authors":"Kodai Yaguchi;Takahiro Aoyagi","doi":"10.1109/ACCESS.2025.3565699","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565699","url":null,"abstract":"This paper investigates an approach for assessing stirrer performance in a reverberation chamber (RC) using characteristic mode analysis (CMA). In the design of a reverberation chamber, evaluating stirrer performance is crucial; however, it is considered challenging to assess it independently. In this study, we focus on evaluation based on the number of characteristic modes and clarify the quantitative relationship between electric field uniformity and the number of characteristic modes through RC analysis of 117 configurations. For the 117 cases obtained, non-parametric estimation was performed to model the data without assuming any physical relationships. The findings suggest that the stirrer’s influence on field uniformity stabilizes when its characteristic mode count reaches 40 to 60, aligning with the cavity mode density at the lowest usable frequency (LUF). The derived criterion also meets the IEC’s “medium” field anisotropy requirement. Additionally, comparison with geometric parameters in the IEC standard indicates that conventional metrics, such as stirrer length, can distinguish performance variations by up to 33.3%, whereas the characteristic mode-based evaluation improves this distinction to 66.7%. In addition, CMA-based evaluation can reduce design time by 27%.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77847-77861"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980308","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924965","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":"SPARCQ: Enhancing Scalability and Adaptability of Proactive Edge Caching Through Q-Learning","authors":"Shruti Lall;Johan de Clercq;Nelishia Pillay;Bodhaswar T. Maharaj","doi":"10.1109/ACCESS.2025.3566002","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3566002","url":null,"abstract":"The exponential growth of network traffic and data-intensive applications demands innovative solutions to manage data efficiently and ensure high-quality user experiences. Proactive edge caching has become a crucial technique for enhancing network performance by predicting and pre-storing content closer to users before access. Accurate prediction models, such as Long Short-Term Memory (LSTM) networks, are crucial for effective proactive caching. However, these models rely on carefully tuned hyperparameters to maintain predictive accuracy, and manual tuning is impractical in dynamic and diverse network environments, limiting scalability and adaptability. To overcome these challenges, we propose a novel framework, SPARCQ, that leverages Q-learning, a reinforcement learning algorithm, to automate hyperparameter tuning for LSTM-based prediction models. By dynamically adjusting hyperparameters, our approach ensures accurate predictions, improving caching efficiency and adaptability. Using the MovieLens dataset, we achieve an average improvement of 8% in cache hit ratios compared to baseline models, including popularity-based and untuned models. Additionally, our framework demonstrates scalability and robustness across geographically distributed regions, consistently adapting to diverse and evolving data patterns.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"79410-79429"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980285","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925010","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 Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions","authors":"Ife Olalekan Ebo;Idowu Ajayi;Lina Mroueh;Youmni Ziade;Sylvain Azarian","doi":"10.1109/ACCESS.2025.3565853","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3565853","url":null,"abstract":"The use of Low-Power Wide Area Network (LPWAN) technologies, such as Long Range (LoRa), Sigfox, and IEEE 802.15.4g (ZigBee), has grown significantly, addressing a wide range of applications including smart metering, agriculture, smart homes, and healthcare. These technologies are valued for their simplicity, flexible connectivity, low power consumption, efficient modulation techniques, and moderate data rates. As a result, they can coexist within the same environment, serving either similar or distinct applications. However, the increasing deployment of devices and technologies has amplified the likelihood of interference between them, leading to performance degradation, particularly in real-world scenarios under challenging conditions where noise power surpasses signal power. The rapid proliferation of these technologies, especially within unlicensed Industrial, Scientific, and Medical (ISM) frequency bands, underscores the need for effective techniques to ensure seamless coexistence without disrupting communication. To address this challenge, we investigate the role of data representation and propose a Channel Attention-based Denoising Autoencoder U-Net and Classifier (UNA-DAEC). This model is designed to denoise multi-label LPWAN signals affected by white Gaussian noise and accurately classify overlapping transmissions, specifically IEEE 802.15.4g, Sigfox, and LoRa signals, within the same environment. The primary objective of UNA-DAEC is to achieve reliable signal classification in low Signal-to-Noise Ratio (SNR) conditions. This is achieved by first denoising the noisy signals to obtain optimal representations, enabling high classification accuracy with a single forward and backward propagation. Our results further demonstrate that data representation plays a critical role in identifying and classifying LPWAN signals, particularly in challenging low-SNR environments, with a significant performance of 44%, 7%, and 26% over CNN-based IQ, CNN-based FFT and DAE+Classifier methods, respectively, at -10 dB SNR.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"77317-77333"},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980283","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925059","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}