IEEE Access最新文献

{"title":"Multimodal and Temporal Graph Fusion Framework for Advanced Phishing Website Detection","authors":"S. Kavya;D. Sumathi","doi":"10.1109/ACCESS.2025.3564530","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564530","url":null,"abstract":"Phishing attacks are among the persistent threats that are dynamically evolving and demand advanced detection mechanisms to counter more sophisticated techniques. Traditional detection approaches are usually based on single-modal features or static analysis, failing to capture the complex, multi-faceted nature of phishing websites and their dynamic behaviors. Thus, we present a robust Multi-Modal and Temporal Graph Fusion Framework integrating advanced learning paradigms that enhance accuracy and adaptability in phishing detection. Our work proposes four brand-new methods: Multi-Modal Hypergraph Fusion Network (MM-HFN), Temporal Graph Neural Network with Attention (TGNN-Att), Federated Graph Contrastive Learning Network (FGCL-Net), and Multi-Modal Temporal Hypergraph Fusion Network (MMTHF-Net). MM-HFN leverages hypergraphs to capture complex, high-order relationships at textual levels (BERT) and graph-based features versus visual ones (CNNs) for an accuracy in the 95-97% range. TGNN-Att addresses temporal variations in phishing behavior by using attention-enhanced temporal graph networks and LSTMs, providing dynamic detection with 94-96% accuracy. FGCL-Net ensures privacy-preserving learning across decentralized datasets through federated contrastive learning, achieving 93-95% accuracy while safeguarding data privacy. Finally, MMTHF-Net fuses multi-modal and temporal features into a dynamic hypergraph framework, achieving state-of-the-art accuracy of 96-98% with an F1-score of 0.97. These approaches together allow for exact, real-time phishing detection by capturing static and temporal behaviors, high-order relationships, and cross-modal features. The framework proposed demonstrates significant improvements compared to the state of the art, eliminating the shortcomings of single-modality and static analysis while offering scalability, privacy, and adaptability levels.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"74128-74146"},"PeriodicalIF":3.4,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10976643","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902731","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":"Recursive Shrinking Toward Effective Cluster Isolation for Robust Electronic Noses","authors":"Shiv Nath Chaudhri","doi":"10.1109/ACCESS.2025.3564211","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564211","url":null,"abstract":"In electronic noses (e-Noses), the employed sensors’ responses consist of overlapping clusters leading to inaccurate analysis. Larger intra-cluster distances and smaller inter-cluster distances within the dataset cause overlapping clusters. The lack of well-separated clusters hinders pattern recognition techniques from excelling and requires effective isolation for optimal performance. This work proposes recursive shrinking towards effective cluster isolation utilizing the synergy of principal component analysis and the bisection method. The clusters shrink towards their centers on each recursion by optimizing an objective function, effective inter-cluster distance (EICD). Overlapping characterizes negative EICD. The experimental findings demonstrate the effectiveness of the suggested approach on a dataset that includes responses from five different alcohol categories: 1-octanol, 1-propanol, 2-butanol, 2-propanol, and 1-isobutanol. The used dataset exhibits highly overlapped clusters with negative-valued EICD. Clusters of 1st, 2nd, 3rd, and 4th alcohol overlap with subsequent peers (i.e., 1-2, 3, 4, 5; 2-3, 4, 5; 3-4, 5; 4-5) and achieve negative EICD. Recursive shrinking produces completely isolated clusters with positive EICD values. The results depict the effectiveness of isolation numerically and graphically.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73939-73948"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975754","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902598","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 Novel LSTM Architecture for Automatic Modulation Recognition: Comparative Analysis With Conventional Machine Learning and RNN-Based Approaches","authors":"Sam Ansari;Soliman Mahmoud;Sohaib Majzoub;Eqab Almajali;Anwar Jarndal;Talal Bonny","doi":"10.1109/ACCESS.2025.3564032","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564032","url":null,"abstract":"The recognition of modulation types in received signals is essential for signal detection and demodulation, with broad applications in telecommunications, defense, and wireless communications. This paper introduces a pioneering approach to automatic modulation recognition (AMR) through the development of a highly optimized long short-term memory (LSTM) network. The proposed framework is engineered to capture intricate temporal dependencies within modulated signals, leveraging a gated architecture that effectively mitigates the vanishing gradient problem. This innovation markedly improves recognition accuracy, particularly in low-SNR conditions where traditional methods are often limited. A defining contribution of this work is the introduction of a novel, adaptive temporal-spectral feature learning mechanism, which seamlessly integrates both temporal and spectral characteristics of the signal. This paradigm eliminates the need for manual feature extraction, enhances interpretability, and significantly boosts classification efficiency. Furthermore, the proposed framework is designed for low-complexity deployment, ensuring its scalability and suitability for next-generation wireless networks and real-time communication systems. The proposed architecture is capable of distinguishing between seven modulation classes: BASK, 4-ASK, BFSK, 4-FSK, BPSK, 4-PSK, and 16-QAM. Performance is evaluated across a broad range of signal-to-noise ratios (SNR), from −10 dB to +30 dB, through extensive simulations. Experimental results demonstrate that the model achieves a recognition accuracy of 99.87% at an SNR of -5 dB, outperforming several conventional machine learning techniques, including multi-layer perceptron (MLP), radial basis function (RBF) networks, adaptive neuro-fuzzy inference systems (ANFIS), decision trees (DT), naïve Bayes (NB), support vector machines (SVM), probabilistic neural networks (PNN), k-nearest neighbors (KNN), and ensemble learning models, as well as recurrent neural networks (RNNs). Comparative analysis reveals that the proposed framework outperforms conventional machine learning techniques, with accuracy improvements ranging from 1.77% to 34.03% over the best- and worst-performing methods. Additionally, the proposed model achieves a performance gain of 2.02% over the deep learning (DL)-based RNN, further highlighting its superior capability in AMR.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72526-72543"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975788","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896150","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":"Monte Carlo Integration With Efficient Importance Sampling for Underwater Wireless Optical Communication Simulation","authors":"Ruqin Xiao;Pierre Combeau;Lilian Aveneau","doi":"10.1109/ACCESS.2025.3564070","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564070","url":null,"abstract":"Underwater optical communications have been proposed for various applications, ranging from coastal protection to short-range submarine communications. The development of dedicated communication systems requires intensive simulation of use cases with efficient methods, both in terms of accuracy and computational time. However, these simulations are challenging due to the complexity of the physical mechanisms of light propagation in water, which involves numerous scattering events on the various particles constituting the propagation medium. Previous tools have primarily relied on the Prahl algorithm, based on Monte Carlo simulation, and are therefore difficult to improve. Recently, a new framework, hereafter referred to as Xiao1, has been developed using an integral formalization of the propagation and Monte Carlo integration for its computation, achieving improved computational times compared to older Prahl techniques for the same level of accuracy. This paper builds upon this framework and proposes to incorporate further importance sampling into the Monte Carlo integration algorithm. It calculates a sub-domain around the receiver for each scattering point and selects a connecting sample with importance within this sub-domain. This paper presents the complete derivation of this new method. It then presents several case studies in which the simulations demonstrate that this new method performs significantly better. Depending on the configuration, these simulations exhibit a reduction in computational times by a factor ranging from 1.09 to 4048 compared with Prahl and from 1.07 to 2134 compared with Xiao1.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"73652-73670"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975749","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896257","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":"SERLogic: A Logic-Integrated Framework for Enhancing Sequential Recommendations","authors":"Lihang Fan","doi":"10.1109/ACCESS.2025.3563977","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563977","url":null,"abstract":"Sequential recommendation models are used to predict users’ next top-K preferred items based on their historical interactions. However, these models often struggle in “fuzzy areas” where recommendation scores are near decision thresholds, leading to false positives and false negatives. To overcome this limitation, we propose <inline-formula> <tex-math>$textsf {SERLogic}$ </tex-math></inline-formula>, an innovative framework that incorporates logic rules, termed <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula>, into existing sequential recommendation models to enhance their accuracy without the need for training a new machine learning model. <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula> represent a novel class of graph prediction rules characterized by a dual graph pattern <inline-formula> <tex-math>$mathcal {Q}$ </tex-math></inline-formula> and a dependency <inline-formula> <tex-math>$X rightarrow (x, likes, y)$ </tex-math></inline-formula>, where <inline-formula> <tex-math>$mathcal {Q}$ </tex-math></inline-formula> exhibits a dual star structure, and X extends ML sequential recommendation models and 1-WL test as predicates. With <inline-formula> <tex-math>$textsf {SERLogic}$ </tex-math></inline-formula>, we show 1) validation problem for <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula> is in polynomial time (<inline-formula> <tex-math>$textsf {PTIME}$ </tex-math></inline-formula>), enabling efficient verification of whether a graph satisfies a set of <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula>; 2) creator-critic algorithm that iteratively learns high-quality <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula>; 3) parallel algorithm that applies the discovered <inline-formula> <tex-math>$mathsf {TIE^{+}!s}$ </tex-math></inline-formula> to generate recommendations efficiently. Empirical evaluation on real-world datasets reveals that <inline-formula> <tex-math>$textsf {SERLogic}$ </tex-math></inline-formula> significantly enhances the performance of sequential recommendation models in terms of Recall@K and NDCG@K, while also achieving superior computational efficiency.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72221-72234"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975773","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902681","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":"Wake Homing Torpedo Guidance Using a Hierarchical Deep Reinforcement Learning Framework","authors":"Kunchul Hwang;Jinwhan Kim","doi":"10.1109/ACCESS.2025.3563906","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3563906","url":null,"abstract":"This paper proposes a novel Hierarchical Deep Reinforcement Learning (HRL) framework for wake homing torpedo guidance, applying the Discrete Event System Specification (DEVS) formalism to design high-level policies and reward shaping functions. Wake homing torpedo guidance generates course commands to enable the torpedo to follow the wake trajectory of a target ship. When the target ship evades the incoming torpedo, the wake trajectory becomes curved, often causing the torpedo to lose track due to the narrow detection range of the wake detection sensor. This necessitates a sophisticated algorithm to consistently track the target ship, particularly in scenarios where the torpedo exits and re-enters the wake trajectory in noisy environments. While heuristic algorithms can handle typical wake trajectories, developing a robust solution for unknown trajectories remains a significant challenge. To address this, we apply a novel reinforcement learning approach to develop the guidance logic and compare its performance with a conventional algorithm-based method. The performance and effectiveness of the proposed approach are demonstrated through numerical simulations.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72938-72952"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975769","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896237","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":"Boundary Control Behaviors of Multiple Low-Cost AUVs Using Acoustic Communication","authors":"Mohammed Tarnini;Saverio Iacoponi;Andrea Infanti;Cesare Stefanini;Giulia de Masi;Federico Renda","doi":"10.1109/ACCESS.2025.3564077","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564077","url":null,"abstract":"This study presents acoustic-based methods for the formation control of multiple autonomous underwater vehicles (AUVs). This study proposes two different models for implementing boundary and path control on low-cost AUVs using acoustic communication and a single central acoustic beacon. Both models are based on the history of relative range and do not rely on the full knowledge of the AUVs states based on a centralized beacon system. Two methods are presented: the Range Variation-Based (RVB) model completely relies on range data obtained by acoustic modems, whereas the Heading Estimation-Based (HEB) model uses ranges and range rates to estimate the position of the central boundary beacon and perform assigned behaviors. The models are tested on two formation control behaviors: Fencing and Milling. Fencing behavior ensures AUVs return within predefined boundaries, while Milling enables the AUVs to move cyclically on a predefined path around the beacon. Models are validated by successfully performing the boundary control behaviors in simulations, pool tests, including artificial underwater currents, and field tests conducted in the ocean. All tests were performed with fully autonomous platforms, and no external input or sensor was provided to the AUVs during validation. Quantitative and qualitative analyses are presented in the study, focusing on the effect and application of a multi-robot system.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72506-72525"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975816","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896553","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":"Efficient Computation of the K Nearest Neighbors Query Using Incremental Radius on a k²-tree","authors":"Rodrigo Torres-Avilés;Mónica Caniupán","doi":"10.1109/ACCESS.2025.3564185","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564185","url":null,"abstract":"Proximity searches within metric spaces are critical for numerous real world applications, including pattern recognition, multimedia information retrieval, and spatial data analysis, among others. With the exponential increase in data volume, the demand for memory efficient structures to store and process information has become increasingly important. In this paper, we present an alternative algorithm for efficient computation of the K-nearest neighbors (KNN) query using the <inline-formula> <tex-math>$k^{2}$ </tex-math></inline-formula>-tree compact data structure, using the incremental radius technique. This approach offers an alternative to the existing algorithm that utilizes a priority queue over <inline-formula> <tex-math>$k^{2}$ </tex-math></inline-formula>-trees. Through both theoretical and experimental analysis, we demonstrate that our proposed algorithm is up to 2 times faster compared to the priority queue based solution, while also providing substantial improvements in memory efficiency.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"72778-72789"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975746","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892491","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 Comprehensive Framework for Intelligent, Scalable, and Performance-Optimized Software Development","authors":"Noor Arshad;Talal Ashraf Butt;Muhammad Iqbal","doi":"10.1109/ACCESS.2025.3564139","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564139","url":null,"abstract":"Integrating Artificial Intelligence (AI) into the Software Development Life Cycle (SDLC) has become necessary to enhance efficiency, scalability, and performance in modern software systems. Instead of incorporating the AI functionality into their SDLC, traditional SDLC models typically add-on the AI software functionality after they have integrated AI functionality into their application or software process. Because of this, developers undergo inefficiencies in their development workflows, experience performance bottlenecks during testing, and experience challenges of incorporating AI to improve an application’s performance through optimization. This paper proposes a new AI-Optimized Software Development Life Cycle (AI-SDLC), which is a holistic and comprehensive framework that encases the embedded AI capabilities and optimization strategies throughout the SDLC process during every stage of the system development, so that requirements-gathering, development, testing, and maintenance are hybrid software processes and not dictated by AI vs. traditional software development processes. AI-SDLC presents new development roles, such as AI Integration Specialist, Code Optimizer, and UX Optimization Specialist, which helps developers work across disciplines and increases collaborative interaction between traditional developers and AI engineers. AI-SDLC also utilizes an AI-driven automated hybrid software process in areas such as requirement elicitation, design/architecture validation, testing, deployment monitoring, and scalability to produce robust high-performance systems in all areas of practicing software development life cycle work. The discourse includes a rich case study based on a Smart Logistics Management System to demonstrate practical implementation of the AI-SDLC and how it facilitates improvement in system efficiency and improved user experience. Additionally, the discussion also highlights the possibilities of AI-SDLC practical implementation in other industrial domain areas such as e-Commerce, finance, aviation and enterprise solution based projects with practical considerations for implementation. In conclusion, the discussion provides findings that support AI-SDLC as a structured and intelligence-driven approach to Software Development Life Cycle implementation that addresses the weaknesses of traditional software design and development frameworks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"74062-74077"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975747","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902722","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":"Multi-Objective Optimization of Off-Grid E-Bikes Charging Stations Powered by PhotoVoltaics","authors":"Fabio Corti;Gabriele Maria Lozito;Davide Astolfi;Salvatore Dello Iacono;Antony Vasile;Marco Pasetti;Alberto Reatti;Alessandra Flammini","doi":"10.1109/ACCESS.2025.3564117","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3564117","url":null,"abstract":"The integration of renewable energy in the power supply chain of Electric Vehicles (EVs) is fundamental in order to decarbonize the transportation sector. Yet, this poses additional threats to the smooth functioning of power systems. In the case of e-bikes, the load is modest and it becomes conceivable to exploit as much as possible distributed renewable power generation coupled with storage. For this reason, attention has recently been growing towards the development of off-grid charging stations for Light EVs (LEVs) powered by renewables. For this kind of charging stations, the power supply for the e-bikes can arrive solely from renewable power production or storage and it is not guaranteed that there is power available for the recharge whenever the demand occurs. Hence, the design of such systems needs to consider two conflicting objectives, which are the minimization of the costs and of the number of not served e-bikes. Based on such premise, this work contributes to the multi-objective optimization of off-grid charging stations for e-bikes. A Genetic Algorithm is employed to determine the most appropriate rated power of the installed PhotoVoltaic (PV) systems and of the energy storage, by incorporating statistical methods to estimate the daily number of e-bikes requiring charging, hence making the optimization process more reflective of actual usage patterns. Under the assumed conditions, the optimized solution guarantees a high quality of service, as the number of uncharged e-bikes is less than the 5%. The Capital Expenditure (CapEx) and Operational Expenditure (OpEx) are estimated for the identified optimized charging station and compared against the grid-connected case and it arises that the off-grid system is slightly more profitable after 3 years, due to the savings in the energy costs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"75412-75429"},"PeriodicalIF":3.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975755","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902633","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}