IEEE Access最新文献

{"title":"A Traffic Management System by Identifying Pollution Hotspots Among Sensitive Points in a Smart City","authors":"Pratik Dutta;Soumyadeep Sur;Sankhayan Choudhury;Sunirmal Khatua","doi":"10.1109/ACCESS.2025.3528987","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528987","url":null,"abstract":"Vehicular pollution becomes a crucial issue within the travel planning of a smart city. Especially, the pollution level at Sensitive Points (SP) like Schools and Hospitals should be kept within a threshold level while a routing solution is offered. In the existing works, the attempt to consider environmental pollution within traffic planning is minimal. In this attempt, we have proposed a framework for offering a routing strategy maintaining the desired pollution level at Sensitive Points. However, the most crucial challenge is to generate an estimation model for measuring pollution at Sensitive Points in an accurate way. In the proposed estimation model, we have attempted to accommodate the meteorological and other essential factors to make it more accurate. The pollution measures as computed by the model within SPs are analyzed for identifying the hot-spots, i.e., the alarming points where the pollution measure is supposed to be higher than the pre-defined threshold. Finally, the rerouting is executed on the affected road segments to maintain the desired level of pollution measured at the hot spots. Moreover, the re-routing has been done (if needed) so that the average remaining travel time of the vehicles will be minimal. Thus, the solution not only focuses on the environmental issues but also addresses the users’ satisfaction in terms of travel time. In the experiment phase, the traffic network is simulated by SUMO, and the entire proposal is implemented to compare with the notable existing comparable works. The proposed approach performs better in terms of the identified metrics, achieving a reduction in Average Vehicle Rerouting (AVR) to 17.26% compared to 20.10% in OPFTCaAP and maintaining a minimal Average Travel Time (ATT) increase for buses (-0.06%).","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10043-10061"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839414","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993866","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":"New SEPIC Derived Semi-Bridgeless PFC Converter for Battery Charging Application","authors":"Manish Kumar Dwivedi;R. Jayapragash","doi":"10.1109/ACCESS.2025.3529351","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3529351","url":null,"abstract":"This paper introduces an AC-DC semi-bridgeless dual-switch SEPIC converter, specifically designed for battery charging applications. It focuses on improving power factor (PF) by substantially reducing total harmonic distortion (THD) in the AC input current through a modified converter structure. Additionally, the converter achieves significant reductions in the sizes of its inductors as it operates in discontinuous conduction mode (DCM) to achieve the low current THD. This converter topology employs two power switches to realize the power factor correction (PFC). Primary novelty of the proposed converter lies in designing and selecting a circuit structure which ensures low THD and unity power factor by the energy balance principle of inductors and capacitors. Additionally, the incorporation blocking diodes in the proposed converter effectively eliminates circulating current through input inductor which in turn makes the converter more efficient. This novel circuit structure also eliminates the requirement of additional closed loop control algorithm for PFC. To validate the proposed concept, a prototype converter of 100W/53V is developed and tested. This converter yields a current THD of 2.1%, unity PF and efficiency of 92.4% at rated condition during hardware testing. The paper also conducts a comparative analysis with similar other converters to assess the performance of the proposed solution thoroughly. This comprehensive study underscores the effectiveness of the new converter for PFC and reducing input current THD for battery charging applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"12068-12080"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839504","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993118","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":"End-to-End Stroke Imaging Analysis Using Effective Connectivity and Interpretable Artificial Intelligence","authors":"Wojciech Ciezobka;Joan Falcó-Roget;Cemal Koba;Alessandro Crimi","doi":"10.1109/ACCESS.2025.3529179","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3529179","url":null,"abstract":"In this paper, we propose a reservoir computing-based and directed graph analysis pipeline. The goal of this pipeline is to define an efficient brain representation for connectivity in stroke data derived from magnetic resonance imaging. Ultimately, this representation is used within a directed graph convolutional architecture and investigated with explainable artificial intelligence (AI) tools, offering a more detailed understanding of how stroke alters communication within the brain. Stroke is one of the leading causes of mortality and morbidity worldwide, and it demands precise diagnostic tools for timely intervention and improved patient outcomes. Neuroimaging data, with their rich structural and functional information, provide a fertile ground for biomarker discovery. However, the complexity and variability of information flow in the brain require advanced analysis, especially if we consider the case of disrupted networks as those given by the brain connectome of stroke patients. To address the needs given by this complex scenario we proposed an end-to-end pipeline. This pipeline begins with defining the effective connectivity of the brain. This allows directed graph network representations that have not been fully investigated so far by graph convolutional network classifiers. To have a complete overview, the analysis with reservoir computing-based causality is compared to other two effective connectivity approaches: one linear (Granger causality) and one non-linear method (transfer entropy). Then, the pipeline subsequently incorporates a classification module to categorize the effective connectivity (directed graphs) of brain networks of patients versus matched healthy control. The graph convolutional architecture is also compared to legacy methods such as random forest and support vector machine providing a complete benchmark. While the pipeline includes a classification module for distinguishing between stroke patients and healthy controls, the focus is on the interpretation of these directed graphs, which reveal critical disruptions in connectivity. Indeed, the classification led to an area under the curve of 0.69 by using graph convolutional networks, 0.72 by using local topological profiling random forest, and 0.71 by using support vector machine with the given heterogeneous dataset. More importantly, thanks to explainable tools, an interpretation of disrupted networks across the brain networks was possible. This elucidates the effective connectivity biomarker’s contribution to stroke classification, fostering insights into disease mechanisms and treatment responses. This transparent analytical framework not only enhances clinical interpretability but also instills confidence in decision-making processes, crucial for translating research findings into clinical practice. Our proposed machine learning pipeline showcases the potential of reservoir computing to define causality and therefore directed graph networks, which can in turn be u","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10227-10239"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839398","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993549","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":"Emotion-Aware Ensemble Learning (EAEL): Revolutionizing Mental Health Diagnosis of Corporate Professionals via Intelligent Integration of Multi-Modal Data Sources and Ensemble Techniques","authors":"Gaurav Yadav;Mohammad Ubaidullah Bokhari;Saleh I. Alzahrani;Shadab Alam;Mohammed Shuaib","doi":"10.1109/ACCESS.2025.3529032","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3529032","url":null,"abstract":"In this contemporary landscape of corporate environments, the increasing prevalence of mental health challenges necessitates the development of innovative diagnostic methodologies. This research introduces the Emotion-Aware Ensemble Learning (EAEL) framework, a cutting-edge approach designed to revolutionize early mental health diagnosis among corporate professionals. EAEL integrates machine learning and deep learning paradigms to process multimodal data, including facial expression analysis and typing pattern recognition, offering a holistic evaluation of emotional well-being. Our investigation methodically trains base classifiers, such as Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forests (RF), on distinct and combined datasets derived from facial expressions and typing patterns. The EAEL framework demonstrates robust performance, achieving an accuracy of 0.95, precision of 0.96, recall of 0.94, and F1-Score of 0.95 when applied to the integrated dataset. These findings underscore EAEL’s transformative potential as a proactive tool for mental health interventions in corporate settings. Future iterations could enhance the framework by incorporating physiological signals, such as heart rate variability and EEG data, further improving diagnostic accuracy. EAEL’s ability to seamlessly integrate diverse data modalities not only sets a new standard for technology-driven mental health assessments but also promises substantial benefits for employee welfare and organizational effectiveness, with the potential for adaptation in clinical environments as well.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"11494-11516"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839368","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993805","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":"Pricing Strategy of Electric Vehicle Aggregators Based on Locational Marginal Price to Minimize Photovoltaic (PV) Curtailment","authors":"Hyunwoo Song;Gab-Su Seo;Dongjun Won","doi":"10.1109/ACCESS.2025.3528626","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528626","url":null,"abstract":"The global climate crisis demands urgent action to mitigate global warming. Using renewable energy sources, such as solar and wind power, for electricity generation is crucial. This shift from centralized to distributed power systems, however, brings challenges, including voltage fluctuations and renewable energy curtailment. The rapid growth of the electric vehicle (EV) industry adds complexity, increasing overall electricity demand and straining the power supply during peak charging times. This paper proposes a scheduling strategy for EV aggregators to reduce renewable energy curtailment and stabilize grid operation by strategically scheduling EV charging. Using Multi -Agent Transport Simulation (MATSim), a traffic simulation tool, EV driving data in Denver, Colorado, USA, were modeled. The EV aggregator adjusts charging fees based on locational marginal prices, encouraging EVs to charge at different stations according to pricing. Simulations on an IEEE 33-bus system with distributed energy resources and EV charging stations validate the proposed algorithm, demonstrating its effectiveness in reducing curtailment by 12.55% and stabilizing grid operation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"11232-11247"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838500","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993006","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":"Conformal and Flexible Antennas in Ultra-High Frequencies: Prospects and Challenges for Partial Discharge Diagnostics","authors":"M. A. Taher;Mohamadariff Othman;Hazlee Azil Illias;Tarik Abdul Latef;Tengku Faiz Tengku Mohmed Noor Izam;S. M. Kayser Azam;Muhammad Ubaid Ullah;Mohamed Alkhatib;Mousa I. Hussein","doi":"10.1109/ACCESS.2025.3529128","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3529128","url":null,"abstract":"With the exponential increase in smart device usage across various domains, flexible and conformal antenna technologies have emerged as transformative solutions, enabling wireless systems in numerous smart applications. However, selecting a suitable flexible and conformal substrate remains challenging because of the intricate characteristics and performance considerations of each material. Additionally, most applications of these substrates are confined to specific areas, such as body-worn devices, biomedical uses, and health services. In contrast, the use of ultra-high frequency (UHF, 0.3–3 GHz) antennas is largely concentrated in radio frequency identification (RFID) and telecommunications, with limited exploration in other areas. Recently, UHF antennas have gained attention for unconventional applications, including high-voltage (HV) defect detection, particularly partial discharge (PD) diagnosis. However, practical challenges arise due to the rigidity of commercial substrate materials. This paper provides a comprehensive survey on flexible and conformal UHF antennas’ applicability for PD diagnostics, a field that remains underexplored. We systematically assess the electrical, mechanical, and thermal properties of various flexible and conformal substrates relevant to UHF antenna development. In this investigation, we thoroughly analyse five substrate materials, namely polyimide (PI), polydimethylsiloxane (PDMS), Rogers laminates, polytetrafluoroethylene (PTFE), and polyethylene terephthalate (PET), and several types of UHF antennas including planar monopole, spiral antenna, Hilbert antenna, biconical antenna, and so on. The synthesis of this research delivers a complete roadmap, addressing existing limitations and proposing future directions for PD diagnosis by conformal and flexible antennas.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10139-10159"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839422","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993014","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":"Improved Identification Method for Equivalent Network Parameters of Transformer Windings Based on Driving Point Admittance","authors":"Yi Liu;Xiaobo Pei","doi":"10.1109/ACCESS.2025.3528886","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528886","url":null,"abstract":"To accurately and efficiently determine the operating state of transformers, based on the driving point admittance method, a trapezoidal equivalent network model for dual-windings transformers was established. Based on Kirchhoff’s law, the node voltages and branch currents of the equivalent network model are obtained, and then the state space equations describing the network model parameters and driving point admittance data are obtained. The state space equation of the equivalent network model was constructed. Then, an improved whale optimization algorithm was proposed for the identification of parameters in the transformer equivalent network model. Random populations were generated using chaotic mapping, and the performance of the algorithm was improved by changing nonlinear control and adding adaptive weight coefficients. An objective function that simultaneously includes amplitude and phase frequency information at resonance points was established. Based on the improved whale optimization algorithm, the parameters of the equivalent network model were inverted. Finally, a comparative simulation test was conducted between the proposed method and existing main methods such as GA and PSO. The results indicate that the minimum objective value for parameter identification using the IWOA is merely 0.71, indicating that the IWOA possesses excellent parameter identification capabilities.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"10062-10069"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838512","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993626","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":"Plant Leaf Identification Using Feature Fusion of Wavelet Scattering Network and CNN With PCA Classifier","authors":"S. Gowthaman;Abhishek Das","doi":"10.1109/ACCESS.2025.3528992","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528992","url":null,"abstract":"Deep learning models, particularly Convolutional Neural Networks (CNNs), are pivotal in enabling botanists to efficiently identify plant species, which is essential for applications in medicine, agriculture, and the food industry. Unlike traditional machine learning methods that often struggle to capture the intricate features of leaves, CNNs are well-suited for this task. However, their reliance on large datasets and substantial computational resources poses a significant challenge. To overcome these challenges, we present a new approach that combines features from Wavelet Scattering Networks (WSNs) and MobileNetV2. WSNs are particularly effective in capturing texture patterns using fixed filters that do not require a learning process, making them effective even with smaller datasets. Conversely, MobileNetV2 deep layer features complement this by capturing more complex, high-level features like shapes and edges, which are essential for distinguishing between different plant species. The extracted features are classified using a PCA-based classifier, which reduces redundancy and enhances accuracy. We tested our approach on the Flavia and Folio datasets, achieving impressive accuracies of 98.75% and 98.7%, respectively. Additionally, we used the Cope dataset to assess the scalability of our model across different classes and the UK Leaf dataset to evaluate its performance under varying background and noise conditions. This approach delivers good accuracy while minimizing computational demands, providing a practical and efficient solution for automated leaf classification, particularly in resource-constrained environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"11594-11608"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10839358","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993499","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":"Asymmetric Phase MPCC Interleaving Method for Boost PFC Converter With Enhanced Input Current Harmonic Characteristic","authors":"Hee-Jeong Seon;Hyun-Gyu Koh;Yeong-Jun Choi","doi":"10.1109/ACCESS.2025.3528639","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528639","url":null,"abstract":"This paper proposes an asymmetric phase model predictive current control (MPCC) interleaving method to improve power density, power factor (PF), and total harmonic distortion (THD) of power factor correction (PFC) converters. The MPCC method operates without a modulator, making it difficult to apply the conventional interleave method. Furthermore, the conventional interleaved method increases dead volume under light load conditions. To solve this problem, this paper proposes to implement the interleaving effect without a modulator by adjusting the timing of the discrete-time model prediction by setting the sampling time of the main phase and the auxiliary phase differently, and to reduce the dead volume by setting the inductance value of the auxiliary phase smaller than the main phase. The sampling period for the auxiliary phase is selected based on the inductance values of the main and auxiliary phases, as well as the main phase’s sampling period, to achieve similar ripple characteristics with a smaller inductor. The proposed method uses a smaller auxiliary inductance to maintain similar input current ripple as the conventional method, and moreover, improves PF and THD by increasing power density and reducing cusp distortion. The performance of the proposed method is verified through experiments on a boosted PFC converter using an Imperix module with 3.3 kW load. The verification results showed that the proposed method achieved improved PF under all load conditions, and improved THD at high load conditions, meeting the IEC-61000-3-2 CLASS A standard.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"9955-9964"},"PeriodicalIF":3.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10838556","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993515","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":"Strategy-Switch: From All-Reduce to Parameter Server for Faster Efficient Training","authors":"Nikodimos Provatas;Iasonas Chalas;Ioannis Konstantinou;Nectarios Koziris","doi":"10.1109/ACCESS.2025.3528248","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3528248","url":null,"abstract":"Deep learning plays a pivotal role in numerous big data applications by enhancing the accuracy of models. However, the abundance of available data presents a challenge when training neural networks on a single node. Consequently, various distributed training methods have emerged. Among these, two prevalent approaches are All-Reduce and Parameter Server. All-Reduce, operating synchronously, faces synchronization-related bottlenecks, while the Parameter Server, often used asynchronously, can potentially compromise the model’s performance. To harness the strengths of both setups, we introduce Strategy-Switch, a hybrid approach that offers the best of both worlds, combining speed with efficiency and high-quality results. This method initiates training under the All-Reduce system and, guided by an empirical rule, transitions to asynchronous Parameter Server training once the model stabilizes. Our experimental analysis demonstrates that we can achieve comparable accuracy to All-Reduce training but with significantly accelerated training.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"9510-9523"},"PeriodicalIF":3.4,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10836684","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993114","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}