Expert Systems with Applications最新文献

{"title":"EA-OSPGB: Multiple robots dynamic online algorithm for solving full coverage path planning of multiple robots in unknown terrain environments","authors":"Yifei Cai ,&nbsp;Fangfang Zhang ,&nbsp;Jianbin Xin ,&nbsp;Jinzhu Peng ,&nbsp;Yaonan Wang","doi":"10.1016/j.eswa.2025.128569","DOIUrl":"10.1016/j.eswa.2025.128569","url":null,"abstract":"<div><div>To address the issue of high energy consumption resulting from poor synergy among multiple robots during full-coverage dynamic online planning in unknown terrain, this paper proposes a multi-robot coverage algorithm guided by the energy activity (EA) function. Additionally, a backtracking mechanism based on the terrain environment is incorporated. First, occupancy grid is employed to represent the area to be covered, with the local raster activity value function guiding the coverage of the working environment. Next, a terrain-based backtracking mechanism is incorporated into the algorithm to facilitate online collaboration among the robots and help them escape “dead zones,” thereby preventing conflicts in backtracking areas and reducing the likelihood of lengthy backtracking paths. Finally, by simulating various scenarios that a cleaning robot may encounter in an unknown terrain environment, we compared the results with those of other algorithms and with scenarios that did not consider terrain factors. The experimental results demonstrate that accounting for terrain is more effective in reducing the robot’s energy consumption. The experiments conducted in different situations highlight the benefits of considering terrain factors. Specifically, the average path length and the number of turns were reduced by 5.2 % and 30.5 % compared to the BOB algorithm, and by 3.1 % and 19.3 % compared to the <span><math><msup><mrow><mi>ε</mi></mrow><mi>★</mi></msup></math></span> algorithm. Thus, the feasibility and effectiveness of the proposed algorithm are confirmed.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"292 ","pages":"Article 128569"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight model for power grid cascading failures risk evaluation based on graph physics-informed attention network","authors":"Kehao Yang ,&nbsp;Fei Xue ,&nbsp;Tao Huang ,&nbsp;Shaofeng Lu ,&nbsp;Lin Jiang ,&nbsp;Xu Xu","doi":"10.1016/j.eswa.2025.128468","DOIUrl":"10.1016/j.eswa.2025.128468","url":null,"abstract":"<div><div>In modern power grids, cascading failures pose an escalating threat to grid reliability, leading to the importance of predicting the likelihood of such failures. While existing power flow-based models rely on detailed physical dynamics, their computational latency hinders online applications. This study introduces a lightweight Graph Physics-Informed Attention Network (GPIAN), uniquely integrating power grid physical laws with graph neural network attention to address this gap. GPIAN replaces conventional attention mechanism with a complex network-based framework, where the Electric Functional Strength (EFS), a metric quantifying node interaction guided by power grid principles, drives adaptive information aggregation. This design not only reduces model parameters by 90.7% compared to standard graph attention network but also embeds physical interpretability, enabling the model to prioritize critical node-edge dependencies in cascading failure scenarios. Experimental validation across IEEE-39, IEEE-118, IEEE-300, and Italian power grids demonstrates that GPIAN achieves higher prediction accuracy than mainstream methods, while maintaining fast inference speeds suitable for real-time deployment. These results highlight how merging physical principles with data-driven learning can transform cascading failure prediction, offering a practical, interpretable tool for proactive grid management and significantly advancing the field’s capacity to mitigate blackout risks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128468"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient image dehazing via temporal-aware diffusion","authors":"Haobo Liang,&nbsp;Yan Yang,&nbsp;Jiajie Jing","doi":"10.1016/j.eswa.2025.128565","DOIUrl":"10.1016/j.eswa.2025.128565","url":null,"abstract":"<div><div>Dense haze image dehazing constitutes an ill-posed inverse problem due to the severe degradation of original image information caused by complex atmospheric scattering effects. While existing approaches have demonstrated progress, they exhibit persistent limitations in preserving structural details and chromatic fidelity under dense haze conditions. Recent developments in latent diffusion models have opened new possibilities for image restoration through their strong generative capacities, yet current implementations face efficiency bottlenecks in the diffusion process. However, achieving efficient diffusion remains challenging.In this work, we propose Efficient Image Dehazing via Temporal-Aware Diffusion. Specifically, we establish a temporal information-guided residual encoding to generate more robust conditional guidance, enabling significant reduction of Markov chain length. Additionally, we design a Temporal-Aware Dynamic Convolution Block that serves two primary purposes: adapting to shorter diffusion steps through temporal information interference and parsing haze concentration distribution from information guidance. Finally, we propose an offline Backtracking Diffusion Sampling approach that refines the transfer pathway by iteratively backtracking the diffusion steps. This enables us to achieve effective diffusion-based dehazing within 15 steps.Extensive experiments demonstrate that our method achieves SOTA performance on both synthetic and real-world haze datasets. Our code links to <span><span>https://github.com/fatsotiger/E_Diff_dehaze</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128565"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectral kurtosis attention network (SKAN): Synergizing signal processing and deep learning for fault diagnosis of rolling element bearings","authors":"Jongmin Park ,&nbsp;Jinoh Yoo ,&nbsp;Taehyung Kim ,&nbsp;MinJung Kim ,&nbsp;Jong Moon Ha ,&nbsp;Byeng D. Youn.","doi":"10.1016/j.eswa.2025.128581","DOIUrl":"10.1016/j.eswa.2025.128581","url":null,"abstract":"<div><div>This paper proposes the Spectral Kurtosis Attention Network (SKAN), a novel approach that synergizes deep learning with signal processing for fault diagnosis of rolling element bearings. While deep-learning models have demonstrated remarkable performance in classifying the health states of mechanical systems under homogeneous conditions, their effectiveness often deteriorates because these models generalize poorly to operating conditions that differ from those seen during training, leading to a marked drop in classification accuracy. Moreover, the features extracted by conventional deep-learning models typically lack interpretability from a signal-processing perspective. To tackle these challenges, we propose a SKAN that employs a signal-processing-inspired network structure coupled with a physics-based feature-weighting strategy. Specifically, the proposed method leverages domain knowledge from spectral kurtosis to autonomously extract fault-related features with physical significance, while effectively transmitting these fault-related features through successive deep-learning layers. This novel approach not only improves fault-diagnosis capabilities but also significantly boosts the interpretability of the model, a critical aspect often overlooked in traditional methods. In this paper, we also introduce the SKAN-gram, which is an innovative feature representation technique that employs a binary tree format to further advance interpretability. SKAN’s effectiveness is validated in our research by applying it to three case studies under various operating conditions, with various loads &amp; speeds and time-varying speed conditions. In addition, this paper presents additional studies with noise interference and small training samples to demonstrate the superiority of the proposed method under the previous deep learning approaches suffer.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"292 ","pages":"Article 128581"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound report generation with fuzzy knowledge and multi-modal large language model","authors":"Ziming Li ,&nbsp;Mingde Li ,&nbsp;Wei Wang ,&nbsp;Qinghua Huang","doi":"10.1016/j.eswa.2025.128555","DOIUrl":"10.1016/j.eswa.2025.128555","url":null,"abstract":"<div><div>Ultrasound report generation is a critical component of computer-aided diagnosis, aimed at alleviating the workload of radiologists during scanning procedures and enhancing diagnostic efficiency. Despite advancements in automatic report generation technologies, the development of a unified framework for generating reports across diverse anatomical regions in ultrasound imaging remains a significant challenge. In this study, we propose a novel and efficient multimodal large language model framework specifically designed for ultrasound report generation. Our framework leverages fuzzy theory to extract essential anatomical knowledge from statistical features, thereby providing more accurate and context-aware guidance throughout the report generation process. Furthermore, we propose a novel evaluation metric designed to assess both the precision and the clinical significance of the generated reports, leveraging insights derived from deep domain expertise. In contrast to traditional evaluation methods, this metric offers a more comprehensive and clinically meaningful assessment. To validate the efficacy of our framework, we conduct extensive experiments on both a publicly available dataset and a proprietary dataset collected from the First Affiliated Hospital of Sun Yat-sen University. We also supplemented our proprietary ultrasound dataset with an external validation set collected from Foshan Sanshui Hospital and The First Affiliated Hospital of Guangzhou. Experimental results demonstrate that our approach consistently achieves state-of-the-art performance across multiple evaluation metrics, highlighting its robustness and adaptability. These findings underscore the potential of our framework in advancing the accuracy and clinical applicability of ultrasound report generation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"292 ","pages":"Article 128555"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Meta-relation-based heterogeneous graph neural network with deep reinforcement learning for flexible job shop scheduling","authors":"Yuzhi Zhang,&nbsp;Shidu Dong,&nbsp;Zhenfang Yuan,&nbsp;Ting Wen,&nbsp;Jianfeng Xiao,&nbsp;Zhuo Diao","doi":"10.1016/j.eswa.2025.128411","DOIUrl":"10.1016/j.eswa.2025.128411","url":null,"abstract":"<div><div>The flexible job-shop scheduling problem is a critical challenge in the smart manufacturing industry. Recent methods that combine graph neural networks with deep reinforcement learning have significantly improved scheduling performance by capturing the complex features of jobs and machines. However, existing approaches still exhibit notable limitations: they often neglect the semantic relationships between nodes and fail to fully account for the heterogeneous characteristics of the relations. To address these issues, this study proposes a deep reinforcement learning approach based on a meta-relation-based heterogeneous graph neural network for solving the flexible job-shop scheduling problem. The proposed method explicitly defines distinct meta-relations to encode semantic information among different nodes and employs specially designed graph embedding techniques to capture the heterogeneity of relational structures. Experimental results on publicly available benchmark instances demonstrate that the proposed approach outperforms traditional heuristic algorithms and several state-of-the-art deep reinforcement learning models. Moreover, although the model is trained on small-scale scheduling problems, it exhibits strong generalization capability when applied to large-scale instances.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128411"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MobileNet- and attention-based MLP-Mixer architecture for geographical-region recognition of a marine fish (Perciformes: Carangidae) using otolith images","authors":"Ömerhan Dürrani ,&nbsp;Seda İşgüzar ,&nbsp;Andaç İmak ,&nbsp;Tuncay Ateşşahin ,&nbsp;Zafer Cömert ,&nbsp;Syeda Zahra Dürrani ,&nbsp;Muammer Türkoğlu","doi":"10.1016/j.eswa.2025.128585","DOIUrl":"10.1016/j.eswa.2025.128585","url":null,"abstract":"<div><div>Fishery management is crucial to sustain marine ecosystems by preventing overfishing and ensuring a fair distribution of fishing quotas. Accurately identifying the geographical origins of fish stocks is a key challenge in region-specific management strategies. Otoliths, calcified structures found in the heads of all fish species (except sharks and rays), provide insights into the life history and geographical origins of these fish. Traditional otolith analysis is time-consuming and error-prone because of manual inspection. Our study presents a novel approach using deep learning and computer vision to automate the geographical recognition of fish using otolith images. We propose a model that integrates MobileNet, which is known for its efficiency, with an advanced Mlp-Mixer that incorporates an attention mechanism to extract enhanced features. When tested on a diverse dataset of otolith images from five regions, the proposed model achieved a remarkable 96% accuracy, significantly outperforming traditional methods. This high accuracy demonstrates the potential to revolutionise fishery management by providing a fast, reliable, and automated solution for geographical region identification. In conclusion, the proposed method demonstrates the transformative potential of combining MobileNet and an attention-based Mlp-Mixer for automated fish geographic recognition using otolith images. This innovative method addresses the limitations of traditional manual inspection and paves the way for more effective and sustainable fishery management practices.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128585"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive fuzzy convolution networks for uncertainty-aware image analysis in ambiguous environments","authors":"Saeed Iqbal ,&nbsp;Xiaopin Zhong ,&nbsp;Muhammad Attique Khan ,&nbsp;Zongze Wu ,&nbsp;Amir Hussain ,&nbsp;Shrooq Alsenan ,&nbsp;Weixiang Liu","doi":"10.1016/j.eswa.2025.128407","DOIUrl":"10.1016/j.eswa.2025.128407","url":null,"abstract":"<div><div>In complex and ambiguous situations, effective image analysis is severely hampered by the instability and unpredictability of convolutional frameworks and fuzzy systems, especially when it comes to managing noise-induced uncertainties and nonlinear interactions. The innovative framework Adaptive Fuzzy Convolution Networks (AFCN) is presented in this paper to tackle the problems of nonlinear interactions and noise-induced uncertainties in image processing in ambiguous situations. To improve feature extraction and uncertainty management, the suggested technique combines context-aware fuzzy aggregation operators, adaptive kernel parameterization, and dynamic nonlinearity modulation. Stability in fuzzy systems under different noise situations is ensured by the framework’s use of a feedback-driven method to modify the nonlinearity parameter (<span><math><msub><mi>γ</mi><mi>k</mi></msub></math></span>) depending on noise characterisation. Multiscale fuzzy convolution with adaptive kernel parameters (center <span><math><mrow><msub><mi>ξ</mi><mrow><mi>s</mi><mo>,</mo><mi>k</mi></mrow></msub><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span> and spread <span><math><mrow><msub><mi>σ</mi><mrow><mi>s</mi><mo>,</mo><mi>k</mi></mrow></msub><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span>) that react to localized uncertainty gradients are also incorporated into the model, allowing for reliable feature extraction in noisy environments. A hybrid regularization approach that combines fuzzification and <span><math><msub><mi>L</mi><mn>2</mn></msub></math></span> regularization is presented in order to smooth uncertainty propagation over multiscale convolutions and reduce overfitting. The capacity of AFCN to dynamically adjust to noise while maintaining structural integrity and reducing error measures like F-MAE and F-MSE is what makes it innovative. State-of-the-art performance is demonstrated by experimental assessments on several datasets, with an accuracy of 97.2 %, an F1 Score of 97.3 %, and exceptionally low error metrics like F-MAE of 0.005 and F-MSE of 0.010. These developments make AFCN a potent instrument for practical uses like autonomous driving, where resilience to background noise is crucial, and medical imaging, where accurate feature recognition is crucial.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"292 ","pages":"Article 128407"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Precision farming: Using an IoT multimodal data-driven deep network to optimize irrigation in wheat crops","authors":"Osama Elsherbiny ,&nbsp;Lei Zhou ,&nbsp;Yong He ,&nbsp;Zhengjun Qiu","doi":"10.1016/j.eswa.2025.128583","DOIUrl":"10.1016/j.eswa.2025.128583","url":null,"abstract":"<div><div>Monitoring water demand and irrigation frequency in wheat crop can be challenging as it requires a deep understanding of the crop growth stage, environmental conditions, and soil moisture levels. However, with the advancements in the Internet of Things (IoT) and deep learning, it has become feasible to develop a data-driven approach capable of delivering highly accurate predictions. This research explores a potentially intelligent solution for tracking the frequency of wheat irrigation and its water requirements. The implemented setup integrates deep networks, such as convolutional neural network (CNN) and deep neural network (DNN), along with pre-trained networks like VGG16, VGG19, ResNet50, ResNet101, and MobileNet. The experimental data was collected through IoT-based sensors, including a digital camera, wind speed, soil moisture, air temperature, and relative humidity. During the process of gathering plant images, environmental factors (EF) were also recorded. The analysis outcomes indicated that the fusion of VGG16–EF features with CNN boosted the precision of the expected irrigation frequency and plant water status (96.2% for validation). These characteristics significantly outperformed those of other transfer learning features. Moreover, the hybrid model consisting of CNN_VGG19, CNN_EF, and DNN_EF attained the highest validation performance (97.9%), with precision, F-measure, recall, and intersection over union values of 98%, 97.9%, 97.9%, 95.9%, respectively. The planned framework outlines a roadmap for the automated detection of irrigation frequency and water status throughout a plant’s life cycle. In the future, the proposed methodology could play a crucial role in analyzing crop growth traits for precision farming and agricultural irrigation management.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128583"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep adaptive gradient-triplet hashing for cross-modal retrieval","authors":"Congcong Zhu ,&nbsp;Wei Hu ,&nbsp;Jinkui Hou ,&nbsp;Qibing Qin ,&nbsp;Wenfeng Zhang ,&nbsp;Lei Huang","doi":"10.1016/j.eswa.2025.128566","DOIUrl":"10.1016/j.eswa.2025.128566","url":null,"abstract":"<div><div>Due to its low storage and high computing efficiency, deep cross-modal hashing has a wide application prospect in large-scale cross-modal retrieval. However, fixed gradients and manually set similarity margins in traditional triplet loss hinder the model’s ability to adapt to varying sample difficulties, leading to poor discrimination of hard negatives and degraded hash code quality, especially when positive-negative distances exceed the preset margin. In addition, most deep cross-modal hashing methods learn both similarity and quantization, and the interaction between the two can break the embedding, resulting in sub-optimal hash codes. In this paper, the Deep Adaptive Gradient-triplet Hashing (DAGtH) framework is proposed to embed heterogeneous modalities data into a discrimative discrete space and capture neighborhood relationships in primitive space. Specially, by setting suitable gradients to triples with different hardness, a new adaptive gradient-triplet loss is proposed to preserve the consistency of neighborhood relationships in original space, prompting intra-class compactness and inter-class separability of heterogeneous modalities. Meanwhile, by dividing the learning process into two parts, the Householder quantization loss is introduced into cross-modal retrieval to reduce lossy compression from the quantization. First, performing similarity learning in the embedding space. Second, the orthogonal transformation is optimized to reduce the distance between embedded and discrete binary code. To validate the effectiveness of our proposed DAGtH framework, comprehensive experiments are conducted on three benchmark datasets, and our approach achieves the increase of 0.61 %–13.8 % in mean average precision (mAP) at different bit lengths compared to the state-of-the-art hashing, which demonstrates that DAGtH achieves optimal retrieval performance. The code for our DAGtH framework can be found here: <span><span>https://github.com/QinLab-WFU/OUR-DAGtH</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128566"},"PeriodicalIF":7.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}