Expert Systems with Applications最新文献

{"title":"A surrogate-assisted evolutionary algorithm with solution sets classification based on inter-dimensional correlation and its applications","authors":"Rui Zhang ,&nbsp;Zehua Dong ,&nbsp;Chaoli Sun ,&nbsp;Yanjun Zhang ,&nbsp;Xiaolu Bai","doi":"10.1016/j.eswa.2025.128177","DOIUrl":"10.1016/j.eswa.2025.128177","url":null,"abstract":"<div><div>To effectively mine the complex long-term dependencies correlations between high-dimensional decision variables, improve the quality of the candidate and real solution sets for evaluation, and expedite the efficiency of fitting the objective function, the paper proposes an algorithm called a surrogate-assisted evolutionary algorithm (SAEA) with solution sets classification based on inter-dimensional correlation for expensive multi-objective optimization (DCSCSAEA) in this study. The paper develops a surrogate model with inter-dimensional correlation called DCBiLSTM, which can carry out nonlinear fitting at a low computational cost, to mine the long-term dependencies correlations between high-dimensional decision variables. A step classification axis is designed based on the reference solutions screened by the division of the radial space, predicting the dominant relationship between the solutions in the space and the reference solutions on the classification axis, in order to classify solutions in the space of the solution set. The paper then divides the uncertainty in the prediction space and develop an adaptive “checkers” model infill criterion to determine the interval in which the predictive error falls. The paper uses the results to choose the corresponding strategy for screening the set of candidate solutions. Experiments on expensive multi-objective optimization problems (EMOPs) (20–100 variables) show DCSCSAEA outperforms five state-of-the-art SAEAs, yielding well-converged, diverse solutions. In real-world weld defect detection (21 variables), DCSCSAEA optimizes the network faster, reducing computational complexity and detection time by 52.14% and 20.39% respectively while maintaining comparable accuracy to state-of-the-art SAEAs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 128177"},"PeriodicalIF":7.5,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084208","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":"On the constrained online convex optimization with feedback delay","authors":"Heyan Huang,&nbsp;Ping Wu,&nbsp;Haolin Lu,&nbsp;Zhengyang Liu","doi":"10.1016/j.eswa.2025.127871","DOIUrl":"10.1016/j.eswa.2025.127871","url":null,"abstract":"<div><div>We investigate the problem of online convex optimization (OCO) under feedback delay, where feedback for a decision is received after a delay, and long-term constraints, where constraints can be violated in intermediate iterations but must be satisfied over the long run. Existing approaches are primarily limited to fixed delay settings and general convex loss functions. In this paper, we employ a stricter metric based on cumulative constraint violations. We first propose a novel algorithm tailored for the fixed <span><math><mi>d</mi></math></span>-slot delay setting, achieving a regret bound of <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msqrt><mrow><mi>d</mi><mi>T</mi></mrow></msqrt><mo>)</mo></mrow></mrow></math></span> and a cumulative constraint violation of <span><math><mi>O</mi></math></span> (<span><math><msup><mrow><mi>T</mi></mrow><mrow><mfrac><mrow><mn>1</mn></mrow><mrow><mn>4</mn></mrow></mfrac></mrow></msup></math></span>), demonstrating superior performance compared to existing results. Moreover, when the loss functions are strongly convex, the regret and violation bounds can be further reduced to <span><math><mi>O</mi></math></span> (<span><math><mrow><mi>d</mi><mo>ln</mo><mi>T</mi></mrow></math></span>) and <span><math><mi>O</mi></math></span> (<span><math><mrow><msqrt><mrow><mi>d</mi></mrow></msqrt><mo>ln</mo><mi>T</mi></mrow></math></span>), respectively. Additionally, we extend our algorithm to the more realistic re-indexed delay setting, achieving <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msqrt><mrow><mi>d</mi><mi>T</mi></mrow></msqrt><mo>)</mo></mrow></mrow></math></span> regret and <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msup><mrow><mi>T</mi></mrow><mrow><mfrac><mrow><mn>1</mn></mrow><mrow><mn>4</mn></mrow></mfrac></mrow></msup><mo>)</mo></mrow></mrow></math></span> cumulative constraint violation. Under strong convexity, these bounds are further improved to <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mover><mrow><mi>d</mi></mrow><mrow><mo>ˆ</mo></mrow></mover><mo>ln</mo><mi>T</mi><mo>)</mo></mrow></mrow></math></span> and <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msqrt><mrow><mover><mrow><mi>d</mi></mrow><mrow><mo>ˆ</mo></mrow></mover></mrow></msqrt><mo>ln</mo><mi>T</mi><mo>)</mo></mrow></mrow></math></span>, where <span><math><mrow><mover><mrow><mi>d</mi></mrow><mrow><mo>ˆ</mo></mrow></mover><mo>=</mo><msub><mrow><mo>max</mo></mrow><mrow><mi>t</mi><mo>∈</mo><mrow><mo>[</mo><mi>T</mi><mo>]</mo></mrow></mrow></msub><msub><mrow><mi>d</mi></mrow><mrow><mi>t</mi></mrow></msub></mrow></math></span> denotes the maximum delay.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 127871"},"PeriodicalIF":7.5,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084273","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":"Comparative performance analysis of optimization algorithms for hyperparameter tuning in LSBoost modeling of mechanical properties in FDM-printed nanocomposites","authors":"Mirsadegh Seyedzavvar ,&nbsp;Cem Boğa ,&nbsp;Behzad Hashemi Soudmand","doi":"10.1016/j.eswa.2025.128111","DOIUrl":"10.1016/j.eswa.2025.128111","url":null,"abstract":"<div><div>Hyperparameter tuning is essential for developing accurate machine learning models, yet its role in predicting the mechanical properties of 3D-printed nanocomposites remains underexplored. This study evaluates the performance of three optimization techniques—Bayesian Optimization (BO), Simulated Annealing (SA), and Genetic Algorithm (GA)—in tuning a Least Squares Boosting (LSBoost) model for predicting the mechanical properties of fused deposition modeling (FDM) 3D-printed polylactic acid (PLA)/silica (SiO₂) nanocomposites. The properties assessed include modulus of elasticity (<span><math><mrow><mi>E</mi></mrow></math></span>), yield strength (<span><math><mrow><msub><mi>S</mi><mi>y</mi></msub></mrow></math></span>), and toughness at ultimate strength (<span><math><mrow><msub><mi>K</mi><mi>u</mi></msub></mrow></math></span>), influenced by key process parameters: extrusion rate (ER), SiO₂ nanoparticle concentration (SC), deposition layer thickness (LT), infill density (ID), and infill geometry (IG). Tensile specimens were produced using a Taguchi L₂₇ orthogonal array and tested under uniaxial tension. Tuning of the LSBoost model minimized a composite objective function involving root mean square error (RMSE) and (1 − <span><math><mrow><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup></mrow></math></span>) loss metrics. Results demonstrated that GA achieved the best performance for yield strength prediction, with an RMSE of 1.9526 MPa and R² of 0.9713, while BO yielded the highest <span><math><mrow><msup><mrow><mi>R</mi></mrow><mn>2</mn></msup></mrow></math></span> (0.9776) for modulus of elasticity prediction with a test RMSE of 130.13 MPa. For toughness, GA produced the lowest test RMSE of 102.86 MPa and the highest R² of 0.7953 among the optimization methods. Generally, GA consistently outperformed BO and SA in optimizing the LSBoost model across most mechanical properties, highlighting its effectiveness for hyperparameter tuning in the context of FDM-fabricated nanocomposites.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 128111"},"PeriodicalIF":7.5,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084214","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":"LATS: Low resource abstractive text summarization","authors":"Chris van Yperen ,&nbsp;Flavius Frasincar ,&nbsp;Kamilah El Kanfoudi","doi":"10.1016/j.eswa.2025.128078","DOIUrl":"10.1016/j.eswa.2025.128078","url":null,"abstract":"<div><div>Text summarization is an increasingly crucial focus of Natural Language Processing (NLP), and state-of-the-art models such as PEGASUS have demonstrated remarkable potential to ever more efficient and accurate abstractive summarization. Nonetheless, recent developments of deep learning models that focus on training with large datasets can become at risk of sub-optimal generalization, inefficient training time, and can get stuck at local optima due to high-dimensional non-convex optimization domains. Current research in the field of NLP suggests that leveraging curriculum learning techniques to guide model training (enabling the model to learn from training data with increasing difficulty) could provide a means to achieve enhanced model performance. In this paper we investigate the effectiveness of curriculum learning strategies and data augmentation techniques on PEGASUS to increase performance with low-resource training data from the CNN/DM dataset. We introduce a novel text-summary pair complexity scoring algorithm along with two simple baseline difficulty measures. We find that our novel complexity sorting method consistently outperforms the baseline sorting methods and boosts performance of PEGASUS. The Baby-Steps curriculum learning strategy with this sorting method leads to performance improvements of 5.65 %, from a combined ROUGE F1-score of 83.28 to 87.99. When this strategy is combined with a data augmentation technique, Easy Data Augmentation, this leads to an improvement to 6.54 %. These statistics are relative to a baseline without curriculum learning or data augmentation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128078"},"PeriodicalIF":7.5,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072342","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":"Predefined-time adaptive fuzzy echo state network containment control of uncertain multiagent systems with prescribed performance","authors":"Xingyue Yang ,&nbsp;Chengdai Huang ,&nbsp;Jinde Cao ,&nbsp;Heng Liu","doi":"10.1016/j.eswa.2025.128046","DOIUrl":"10.1016/j.eswa.2025.128046","url":null,"abstract":"<div><div>Most control techniques that put constraining conditions to tracking performance usually involve the aid of barrier Lyapunov functions or integral-type functions to regulate tracking errors within a region surrounded by constants and coordinate axes, which may result in algebraic loop or singular problems. Aiming to drive the entire individuals of the multiagent systems (MASs) into a convex hull composed of multiple leaders with a preset performance freely modulated by decision-maker, in this paper, a predefined-time adaptive fuzzy echo state network containment control agreement with prescribed performance is developed for uncertain MASs subject to input saturation. A fuzzy echo state network, as a syncretism and escalation of conventional radial neural network, is utilized to approximate unknown nonlinear dynamics. A new log-type function is defined via combining coordinate transformation with the trait of the funnel function. Through applying the predefined-time Lyapunov stability criterion, theoretical analysis indicates that all signals of closed-loop network MASs are semiglobally practically predefined time bounded, and the errors evolve within the prescribed boundary customized by a funnel function in a predetermined time. Finally, the practicality of the presented approach is validated through an actual simulation example.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128046"},"PeriodicalIF":7.5,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072346","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":"Dual-image attention convolutional network for monitoring the shape of embankment materials during dam construction","authors":"Shuangping Li ,&nbsp;Bin Zhang ,&nbsp;Hang Zheng ,&nbsp;Zuqiang Liu ,&nbsp;Xin Zhang ,&nbsp;Linjie Guan ,&nbsp;Junxing Zheng ,&nbsp;Han Tang","doi":"10.1016/j.eswa.2025.128103","DOIUrl":"10.1016/j.eswa.2025.128103","url":null,"abstract":"<div><div>This research explores the influence of particle roundness on the macro-mechanical behavior of soils, emphasizing the need for effective classification methods. Traditional approaches, including Wadell’s 2D-based roundness and computational geometry (CG) techniques, are hindered by inefficiency, subjectivity, and sensitivity. To address these challenges, the study introduces a novel solution using a dual-graph attention convolution network (DGACN) for 3D point cloud classification. A dataset of 2400 soil particles, scanned via X-ray computed tomography, is utilized to train and evaluate the DGACN model. The results demonstrate an accuracy of 90.1%, showcasing the model’s robustness to defective data and its ability to accurately classify six roundness classes. Furthermore, the DGACN approach outperforms traditional CG methods in computational efficiency, being 53 times faster. This work establishes deep learning as a powerful and efficient tool for soil particle characterization, offering valuable contributions to geotechnical engineering and materials science research.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128103"},"PeriodicalIF":7.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072016","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":"An adaptive differential evolution algorithm based on individual-level intervention strategy for global optimization","authors":"Gaoji Sun ,&nbsp;Guanyu Yuan ,&nbsp;Libao Deng ,&nbsp;Chunlei Li ,&nbsp;Mingfa Zheng","doi":"10.1016/j.eswa.2025.128054","DOIUrl":"10.1016/j.eswa.2025.128054","url":null,"abstract":"<div><div>The differential evolution (DE) algorithm is a widely recognized metaheuristic with outstanding optimization performance and a straightforward structure. However, when DE relies exclusively on the difference information within the population to update individual positions, it can potentially cause premature convergence or stagnation, resulting in inferior performance on complex optimization problems. To enhance the optimization performance of DE effectively, we propose an adaptive DE variant, referred to as IIDE, which incorporates an individual-level intervention strategy based on a fitness state information-triggered mechanism and an opposition-based learning strategy. Furthermore, we introduce a novel mutation operator that utilizes a dynamic elite strategy and a dominant-inferior partitioning approach, along with targeted matching parameters derived from fitness state information, optimization progress information, or historical success information. To evaluate the optimization performance of IIDE, we compare it with the winner algorithm (L-SHADE) from the IEEE CEC 2014 testbed and six other high-performing DE variants developed in the past five years. The comparative results demonstrate that IIDE exhibits significant advantages in terms of statistical outcomes, optimal fitness values, and runtime efficiency.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128054"},"PeriodicalIF":7.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072101","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":"Learning discriminative features via deep metric learning for video-based person re-identification","authors":"Jiahe Wang,&nbsp;Xizhan Gao,&nbsp;Sijie Niu,&nbsp;Hui Zhao,&nbsp;Guang Feng,&nbsp;Jiaxin Lin","doi":"10.1016/j.eswa.2025.128123","DOIUrl":"10.1016/j.eswa.2025.128123","url":null,"abstract":"<div><div>Video-based person re-identification (Video-Re-ID) is a crucial application in practical scenarios and has gradually emerged as one of the most popular research topics in the field of computer vision. Although many efforts have been made, it still remains a challenge due to substantial variations among person videos and even within each video. For Video-Re-ID, we propose a synchronous intrA-video and intEr-video distance metric learning approach based on temporal ViT architecture, termed as TAE-ViT. The TAE-ViT model, in particular consists of a View Guide Patch Embedding (VGPE) module, a Spatial-Temporal Attention (STA) module and an Intra and Inter-video Distance Metric Learning (IIDML) module. The VGPE module is used to utilize diverse view information and extract discriminative features with perspective invariance. The STA module alternately learns the spatial and temporal information by using the spatial and temporal multi-head attention operation, respectively. The IIDML module simultaneously captures intra-video and inter-video distance metrics from the training videos. Specifically, the intra-video distance metric aims to compact each video representation, while the inter-video distance metric ensures that truly matched videos are closer in distance compared to incorrectly matched ones. Experimental results show that our method achieves the best mAP (86.7 %, 96.3 %, 97.3 %) on three public Video-ReID datasets and achieves the best Rank-1 (93.3 %, 96.6 %) on two datasets, reducing the error of state-of-the-art methods by 1.48-45.16 % on mAP and by 2.86 % on Rank-1. Its robust performance highlights its potential for real-world applications like intelligent surveillance and public safety. Our code will be available at <span><span>https://github.com/JingShenZhuangTaiYiChang/TAE-ViT</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128123"},"PeriodicalIF":7.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144068672","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":"Learning from imbalance: Cross-server power prediction in large data centers via domain adaptation regression","authors":"Ruichao Mo ,&nbsp;Weiwei Lin ,&nbsp;Guozhi Liu ,&nbsp;Haolin Liu ,&nbsp;Ligang He","doi":"10.1016/j.eswa.2025.127845","DOIUrl":"10.1016/j.eswa.2025.127845","url":null,"abstract":"<div><div>Machine learning (ML) models currently excel at predicting power consumption for servers in cloud data centers. The heterogeneity of server configurations violates the assumption of independent and identically distributed (i.i.d.) data, resulting in distribution shifts that pose significant challenges for cross-server power prediction. Additionally, the labels of power consumption data collected over a limited time show a natural imbalance, causing the power prediction performance to degrade when encountering missing labels. Therefore, learning meaningful knowledge from imbalanced power consumption data of real servers for cross-server power prediction remains challenging. To address this challenge, we consider imbalanced cross-server power prediction, formulated as a semi-supervised domain adaptation regression problem in scenarios where few labeled data points of target servers are available. Consequently, an <u>i</u>mbalanced <u>c</u>ross-<u>s</u>erver <u>p</u>ower prediction method, named <em><strong>ICSP</strong></em>, is proposed. To prevent learning biased knowledge from imbalanced data, unbalanced optimal transport is employed to align the joint probability distribution of the source and target servers. Moreover, by incorporating the few labels of target servers as a priori constraints, the performance of <em><strong>ICSP</strong></em> in coping with distribution shift is further improved. Extensive experiments on a real-world dataset demonstrate the superiority of <em><strong>ICSP</strong></em> over existing domain adaptation regression methods for imbalanced cross-server power prediction.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 127845"},"PeriodicalIF":7.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084270","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":"Multi-class traffic assignment using multi-view heterogeneous graph attention networks","authors":"Tong Liu,&nbsp;Hadi Meidani","doi":"10.1016/j.eswa.2025.128072","DOIUrl":"10.1016/j.eswa.2025.128072","url":null,"abstract":"<div><div>Solving traffic assignment problem for large networks is computationally challenging when conventional optimization-based methods are used. In our research, we develop an innovative surrogate model for a traffic assignment when multi-class vehicles are involved. We do so by employing heterogeneous graph neural networks which uses a multiple-view graph attention mechanism tailored to different vehicle classes, along with additional links connecting origin-destination pairs. We also integrate the node-based flow conservation law intothe loss function. As a result, our model adheres to flow conservation while delivering highly accurate predictions for link flows and utilization ratios. Through numerical experiments conducted on urban transportation networks, we demonstrate that our model surpasses traditional neural network approaches in convergence speed and predictive accuracy in both user equilibrium and system optimal versions of traffic assignment.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"286 ","pages":"Article 128072"},"PeriodicalIF":7.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072098","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}