Applied Soft Computing最新文献_第10页

Semantic-based topic model for public opinion analysis in sudden-onset disasters

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2025.112700

Yulong Ma, Xinsheng Zhang, Runzhou Wang

{"title":"Semantic-based topic model for public opinion analysis in sudden-onset disasters","authors":"Yulong Ma, Xinsheng Zhang, Runzhou Wang","doi":"10.1016/j.asoc.2025.112700","DOIUrl":"10.1016/j.asoc.2025.112700","url":null,"abstract":"<div><div>Sudden-onset disasters have put forward more stringent requirements for the government to carry out public opinion analysis work. However, most existing topic models ignore the contextual semantics of disaster texts, and fail to balance the robustness and the training cost. To address these issues, a neural clustering topic model is proposed in this work. The topic probability distribution of the LDA model is integrated with the distribution semantic vector generated by a lite BERT. The fused vectors are reconstructed by a nonlinear manifold learning algorithm, and re-clustered into topics by a mini-batch based <em>k-</em>means++ algorithm. Compared to state-of-the-art models on three sudden-onset disaster datasets, the proposed model shows an increase of 1.79 % in average topic coherence and 33.87 % in topic diversity. Meanwhile, the inference time is reduced by 84.09 % on average. The visual study of the latent process of the proposed model reflects that its ability to compact intra-cluster vector distances and sparse inter-cluster vector distances is the potential reason for its better performance. It can be considered that the application of the proposed model can help the government enhance its ability to manage negative public opinions in sudden-onset disasters.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112700"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143212812","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}

引用次数: 0

An oversampling technique based on noise detection and geometry

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2025.112718

Pengfei Sun , Zhiping Wang , Liyan Jia , Lin Wang

{"title":"An oversampling technique based on noise detection and geometry","authors":"Pengfei Sun , Zhiping Wang , Liyan Jia , Lin Wang","doi":"10.1016/j.asoc.2025.112718","DOIUrl":"10.1016/j.asoc.2025.112718","url":null,"abstract":"<div><div>In the field of machine learning, one of the key techniques for dealing with imbalanced data issues is the SMOTE algorithm. Although SMOTE and its variants have shown good performance on many datasets, they generally do not make use of information from the majority class samples. In this paper, a more robust and reliable technique, noise detection and geometric oversampling (NG-SMOTE), will be employed to balance the data. NG-SMOTE first uses an ensemble filter to eliminate the noise samples in the original data, and then clusters the remaining minority samples to obtain <em>k</em> cluster centers. Then, the closest majority sample to each cluster center is found, and a hypersphere is constructed between the two samples. Finally, a sample is generated on the hypersphere and the new sample is interpolated between this sample and the cluster center. The above steps will be repeated until the dataset reaches balance. To verify the effectiveness of NG-SMOTE, we conducted comparative experiments with some oversampling techniques on 27 data sets. In the experiment, the proposed oversampling technology improved by 4 %-9 % compared to other oversampling technologies in Recall, AUC, F1-measure and G-mean respectively. In addition, the statistical test results showed significant differences except for SMOTE-ENN and IW-SMOTE.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112718"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143212813","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}

引用次数: 0

Late acceptance hill climbing based algorithm for Unmanned Aerial Vehicles (UAV) path planning problem

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112651

Emad Deilam Salehi, MohammadAmin Fazli

{"title":"Late acceptance hill climbing based algorithm for Unmanned Aerial Vehicles (UAV) path planning problem","authors":"Emad Deilam Salehi, MohammadAmin Fazli","doi":"10.1016/j.asoc.2024.112651","DOIUrl":"10.1016/j.asoc.2024.112651","url":null,"abstract":"<div><div>This research innovatively applies the Late Acceptance Hill-Climbing (LAHC) algorithm to unmanned aerial vehicle (UAV) path planning in complex urban environments, marked by irregularly shaped threat areas. Moving beyond conventional models that simplify threat representations, our approach meticulously calculates collision costs, factoring in both the size and proximity of threat areas to waypoints, thereby enhancing path safety and feasibility. The standout feature of the LAHC algorithm is its memory-based strategy, which is simple yet remarkably effective, as evidenced by its superior performance over leading meta-heuristic algorithms across various urban flight scenarios. The study’s findings are significant, revealing that LAHC not only excels in optimizing path costs but also outperforms in terms of the number of iterations to convergence and average execution time. Additionally, a detailed convergence and complexity analysis of LAHC is conducted, providing deeper insights into its operational efficiency. Key contributions of this study include the development of realistic benchmark flight environments, the introduction of a novel method for collision cost calculation in urban settings, and the successful demonstration of LAHC’s rapid optimization capabilities and high-quality solutions.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112651"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143212933","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}

引用次数: 0

Incomplete multi-view feature selection with adaptive consensus graph constraint for Parkinson's disease diagnosis

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2025.112739

Zhongwei Huang , Jianqiang Li , Jun Wan , Jianxia Chen , Zhi Yang , Ming Shi , Ran Zhou , Haitao Gan

{"title":"Incomplete multi-view feature selection with adaptive consensus graph constraint for Parkinson's disease diagnosis","authors":"Zhongwei Huang , Jianqiang Li , Jun Wan , Jianxia Chen , Zhi Yang , Ming Shi , Ran Zhou , Haitao Gan","doi":"10.1016/j.asoc.2025.112739","DOIUrl":"10.1016/j.asoc.2025.112739","url":null,"abstract":"<div><div>Parkinson's disease (PD) is a neurodegenerative condition common among the elderly, with optimal treatment ideally administered in its early stages. Given the high rate of misdiagnosis of PD, it is crucial to introduce a new method to assist in its diagnosis. However, the current challenge lies in the high dimensionality of medical neuroimaging data, coupled with the issue of missing data, both of which can impact the performance of the algorithm. To address this, we propose a novel semi-supervised feature selection method to aid the diagnosis and score prediction of PD. Specifically, this method introduces a low-dimensional consensus representation to explore the complete data structure. By integrating the similarity matrix of the low-dimensional consensus representation with adaptive learning, we derive the optimal similarity matrix for each data view. Subsequently, we use the similarity matrix from each view to input the missing data within the respective view. To validate our approach, we utilize data from the public Parkinson's Progression Markers Initiative (PPMI) dataset and simulate three scenarios: complete data, 15 % missing data in each view, and 30 % missing data in each view. Experimental results demonstrate that our method outperforms existing methods in both complete and incomplete datasets.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112739"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143212943","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}

引用次数: 0

Evolutionary induced survival trees for medical prognosis assessment

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112674

Malgorzata Kretowska, Marek Kretowski

{"title":"Evolutionary induced survival trees for medical prognosis assessment","authors":"Malgorzata Kretowska, Marek Kretowski","doi":"10.1016/j.asoc.2024.112674","DOIUrl":"10.1016/j.asoc.2024.112674","url":null,"abstract":"<div><div>Survival analysis focuses on predicting the time of a specific event, known as failure. In the analysis of survival data, it is crucial to fully leverage censored observations for which we do not have precise event time information. Decision trees are among the most frequently applied machine learning techniques for survival analysis, but to adequately address this issue, it is necessary to transform them into survival trees. This involves equipping the leaves with, for instance, local Kaplan–Meier estimators. Until now, survival trees have predominantly been generated using a greedy approach through classical top-down induction that uses local optimization. Recently, one of the most promising directions in decision tree approach is global learning. The paper proposes an evolutionary algorithm for survival tree induction, which concurrently searches for the tree structure, univariate tests in internal nodes, and Kaplan–Meier estimators in leaves. The fitness function is based on an integrated Brier score, and by introducing a penalty term related to the tree size, it becomes possible to control the interpretability of the obtained predictor. The work investigated, among other aspects, the impact of censoring, and the results obtained from both synthetic and real-life medical datasets are encouraging. The comparison of the predictive ability of the proposed method with already-known univariate survival trees shows statistically significant differences.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112674"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213066","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}

引用次数: 0

Equipping high-order fuzzy cognitive map with interpretable weights for multivariate time series forecasting

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2025.112724

Chenxi Ouyang, Fusheng Yu, Fei Yang

{"title":"Equipping high-order fuzzy cognitive map with interpretable weights for multivariate time series forecasting","authors":"Chenxi Ouyang, Fusheng Yu, Fei Yang","doi":"10.1016/j.asoc.2025.112724","DOIUrl":"10.1016/j.asoc.2025.112724","url":null,"abstract":"<div><div>Being a kind of fuzzy cognitive maps (FCMs), the high-order FCMs (HFCMs) are designed for multivariate time series (MTS) to forecast a future vector by using multiple past vectors rather than one past vector. The HFCM-based MTS forecasting model realizes the forecasting by using the causalities between past vectors and future vector, which are described by a set of real-valued weights falling in interval [-1, 1] and determined by some given training data. However, for sake of various uncertain factors in measuring and collecting the training data, the real-valued weights determined by such kind of obtained training data cannot exactly characterize the causalities between vectors. In other words, the trained real-valued weights may not be the true real-valued weights. In these scenarios, it becomes necessary to equip an HFCM with interval-valued weights, resulting in an interval high-order FCM (IHFCM). For an IHFCM, how to determine its interval-valued weights poses a significant challenge. Facing with this challenge, we first propose a principle of justifiable granularity for vector-valued input-output data (PJG-VID), which relies on two fundamental criteria: maximizing the coverage of actual vector-valued output by interval-valued vector-valued outputs and enhancing the semantic specificity of interval-valued weights. Utilizing PJG-VID, we then formulate an optimization problem to determine the interval-valued weights of an IHFCM. And finally, we develop an MTS forecasting model employing this novel IHFCM. The interval-valued weights determined through our method not only accurately capture the causalities between vectors but also facilitate a direct and semantically clear interpretation. As a result, the MTS forecasting model presented in this paper achieves remarkable performance in terms of forecasting accuracy and semantic interpretability.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112724"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213126","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}

引用次数: 0

Unsupervised discovery of 3D structural elements for scanned indoor scenes

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112680

Miloš Antić , Andrej Zdešar , José Antonio Iglesias , Araceli Sanchis , Igor Škrjanc

{"title":"Unsupervised discovery of 3D structural elements for scanned indoor scenes","authors":"Miloš Antić , Andrej Zdešar , José Antonio Iglesias , Araceli Sanchis , Igor Škrjanc","doi":"10.1016/j.asoc.2024.112680","DOIUrl":"10.1016/j.asoc.2024.112680","url":null,"abstract":"<div><div>This paper addresses the growing demand for effective 3D sensing applications by presenting a comprehensive point cloud segmentation method developed for large indoor spaces. Our approach recognises the challenges associated with (un)ordered data and presents a robust algorithm capable of dealing with irregularities caused by measurement inaccuracies, e.g. occlusion, noise, outliers and discontinuous data transitions. The method uses a multi-step filtering approach that sequentially navigates through Gaussian map, distance space and regular grid representations. Connected component analysis, structural rules and assumptions guide the unsupervised clustering of structural elements (SEs), e.g. walls, ceilings and floors. The method is adaptable to various datasets, including joint 2D-3D datasets such as true RGB-D data. A colour metric is introduced to account for illumination effects during scanning and to ensure the generalisability of the method. The importance of detecting SEs lies in their role as input to deep neural networks, which improve the accuracy of SLAM algorithms and influence the quality of subsequent indoor residual object detection. This paper introduces density-based clustering of objects using colour similarity measures and low-level features to further refine the segmentation by eliminating outliers and improving the detection of sharp shapes. The proposed method represents a sophisticated and versatile solution that overcomes scene complexity and makes an important contribution to applications in scene understanding, SLAM and indoor object recognition.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112680"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}

引用次数: 0

Deep generative approaches for oversampling in imbalanced data classification problems: A comprehensive review and comparative analysis

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112677

Mozafar Hayaeian Shirvan , Mohammad Hossein Moattar , Mehdi Hosseinzadeh

{"title":"Deep generative approaches for oversampling in imbalanced data classification problems: A comprehensive review and comparative analysis","authors":"Mozafar Hayaeian Shirvan , Mohammad Hossein Moattar , Mehdi Hosseinzadeh","doi":"10.1016/j.asoc.2024.112677","DOIUrl":"10.1016/j.asoc.2024.112677","url":null,"abstract":"<div><div>There are inherent issues with classifying imbalanced data, especially in classifying minority class samples. With an emphasis on the use of deep generative methodologies, this study offers a thorough investigation of oversampling strategies for imbalanced data classification. This paper begins with a summary of unbalanced data categorization and the need for oversampling techniques. Then traditional approaches including SMOTE, ADASYN, and random oversampling are introduced and discussed. This study then discusses deep generative models and how oversampling may be used to address imbalanced data problem using Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). A comparative study between deep generative and conventional oversampling techniques is performed concerning a comprehensive evaluation of the difficulties, restrictions, and possible risks associated with applying deep generative approaches. The paper concludes with recommendations for future researches and highlights the need for addressing challenges in oversampling approaches for imbalanced data classification.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112677"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213334","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}

引用次数: 0

Comprehensive application of transfer learning, unsupervised learning and supervised learning in debris flow susceptibility mapping

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112612

Ruiyuan Gao , Changming Wang , Di Wu , Hailiang Liu , Xiaoyang Liu

{"title":"Comprehensive application of transfer learning, unsupervised learning and supervised learning in debris flow susceptibility mapping","authors":"Ruiyuan Gao , Changming Wang , Di Wu , Hailiang Liu , Xiaoyang Liu","doi":"10.1016/j.asoc.2024.112612","DOIUrl":"10.1016/j.asoc.2024.112612","url":null,"abstract":"<div><div>Machine learning based debris flow susceptibility mapping (DFSM) is usually a simple supervised learning problem. Inadequate reliable samples in a single study area are usually one of the main factors limiting the performance of a model. This study is to provide a comprehensive and innovative approach for DFSM based on transfer learning, unsupervised learning and supervised learning, which is expected to reduce the limitations of the sample problem. A transfer learning approach called transfer component analysis (TCA) was utilized to project samples from different study areas into a common latent feature space to form a unified study area. The fuzzy C-mean (FCM) clustering algorithm belonging to unsupervised learning was used to cluster the unified study area into several homogeneous regions for independent processing to solve the spatial stratification heterogeneity problem. Another unsupervised learning algorithm named isolation forest (IF) was used to perform anomaly detection on all the samples to improve the reliability of negative samples. With all the datasets prepared, multiple random forest (RF) models representing supervised learning could be built. Traditional supervised learning models based on a single study area were also prepared for comparison. All the models were assessed based on the area under receiver operating characteristic curves (AUC) and statistical results. The results showed that the TCA method could effectively reduce the differences in feature distribution for different study areas. The application of FCM and IF could effectively deal with the problem of spatial stratification heterogeneity and improve the reliability of the negative samples respectively. The comprehensive model (AUC=0.93) proposed in this study is significantly better than that of traditional models (AUC=0.90 and 0.87) in terms of generalization ability, which could be widely applied when performing DFSM on a large scale.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112612"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213400","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}

引用次数: 0

ELICIT information-based robust large-scale minimum cost consensus model under social networks

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-02-01 DOI: 10.1016/j.asoc.2024.112647

Yefan Han , Bapi Dutta , Diego García-Zamora , Ying Ji , Shaojian Qu , Luis Martínez

{"title":"ELICIT information-based robust large-scale minimum cost consensus model under social networks","authors":"Yefan Han , Bapi Dutta , Diego García-Zamora , Ying Ji , Shaojian Qu , Luis Martínez","doi":"10.1016/j.asoc.2024.112647","DOIUrl":"10.1016/j.asoc.2024.112647","url":null,"abstract":"<div><div>Large-Scale Group Decision-Making (LSGDM) in social network context has emerged as a research focus in decision sciences. Social relationships implicated in the network influence Decision-Makers’ (DMs) preferences and group consensus. However, existing research often overlooks the potential impact of uncertain adjustment costs driven by social relationships among DMs on the Consensus-Reaching Process (CRP). To address this issue, this paper develops a new Extended Linguistic Expressions with Symbolic Translation (ELICIT) information-based robust large-scale minimum cost consensus model under social networks. Firstly, the ELICIT model is used to represent DMs’ preferences, enhancing preference elicitation under uncertain conditions. Secondly, DMs’ weights are objectively determined based on the following–follower network, and the social network cost function is integrated into the Comprehensive Minimum Cost Consensus (CMCC) model. Then, three robust consensus models are developed to manage the uncertain adjustment costs of DMs within the network. Afterward, an ELICIT-based PROMETHEE ranking method is designed. Finally, a case study on selecting Healthcare Waste (HCW) treatment technology is conducted. The implemented sensitivity and comparative analysis demonstrate the effectiveness and advantages of the proposed method.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"170 ","pages":"Article 112647"},"PeriodicalIF":7.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143213403","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}

引用次数: 0