Expert Systems最新文献

{"title":"Benchmarking Arabic Transformer-Based Language Model Embeddings for Document Clustering: A Comparative Study","authors":"Rana Husni Al Mahmoud,&nbsp;Hanan Saleet","doi":"10.1111/exsy.70456","DOIUrl":"https://doi.org/10.1111/exsy.70456","url":null,"abstract":"<div>\u0000 \u0000 <p>Recent advances in transformer-based language models have substantially improved semantic text representations for Arabic natural language processing. However, their effectiveness for unsupervised document clustering has not been comprehensively investigated across different clustering algorithms, preprocessing strategies and document representations. This study presents a comparative evaluation of six transformer-based embedding models, namely AraGPT2, arabertv0.2, CAMeLBERT, AraELECTRA, AraBERTv2, and Multilingual-MiniLM, together with a TF-IDF lexical baseline, for Arabic document clustering. The evaluation was conducted on five Arabic datasets spanning both general-domain and domain-specific corpora using four clustering algorithms: <i>K</i>-Means++, Spherical <i>K</i>-Means, Hierarchical Agglomerative Clustering (HAC) and Spectral Co-Clustering. To investigate the influence of text representation, six preprocessing configurations were considered by varying stemming and document-length reduction strategies. Clustering performance was assessed using Normalised Mutual Information (NMI), Accuracy, Purity, Adjusted Rand Index (ARI), Macro <i>F</i>1-score, V-Measure and Entropy. Furthermore, the experimental results were statistically validated using the Friedman test, average-rank analysis, and Holm-corrected Wilcoxon signed-rank post hoc comparisons. The experimental results demonstrate that preserving the original lexical and morphological structure of Arabic text generally yields superior clustering performance for contextual embedding models compared with light stemming. The influence of document length was found to be dataset- and representation-dependent, with full-document representations achieving the strongest overall performance, while shorter representations frequently remained competitive. TF-IDF provided a strong lexical baseline, particularly for general-domain datasets. Among the evaluated embedding models, AraBERTv2 achieved the best overall average rank, closely followed by arabertv0.2, and the post hoc statistical analysis revealed no significant difference between the two models. CAMeLBERT consistently exhibited stable and competitive performance across all datasets, whereas AraELECTRA produced the weakest clustering results. From the clustering perspective, Spherical <i>K</i>-Means demonstrated the most consistent overall performance, while HAC achieved the highest clustering quality in several of the best-performing embedding configurations. Overall, this study provides a comprehensive benchmark for transformer-based Arabic document clustering and offers practical guidance for selecting embedding models, preprocessing strategies, document representations, and clustering algorithms for unsupervised Arabic text analysis.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 12","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Interpretable Dynamic Graph Learning via Dual-Granularity Large Language Model Alignment","authors":"Yingjie Xie,&nbsp;Wenjun Wang,&nbsp;Tianpeng Li,&nbsp;Xiaoming Li,&nbsp;Lin Yuanbo Wu","doi":"10.1111/exsy.70454","DOIUrl":"https://doi.org/10.1111/exsy.70454","url":null,"abstract":"<div>\u0000 \u0000 <p>Dynamic graph-level embedding aims to learn whole-graph representations from temporal snapshots. Existing methods predominantly follow a single-vector paradigm that encodes each snapshot as a continuous latent vector, suffering from two key limitations: (1) Stage–Snapshot Entanglement, where within-stage fluctuations and cross-stage transitions are conflated without explicit granularity distinction; and (2) Implicit Structural Semantics, where meaningful structural properties remain buried in latent coordinates and are never exposed as interpretable, language-compatible units. To address these issues, we propose DyGLLM, an LLM-compatible framework that constructs and aligns dual-granularity structural representations for dynamic graph understanding. Specifically, DyGLLM maps temporally coherent evolution regimes into selective structural tokens <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mfenced>\u0000 <msub>\u0000 <mi>SEG</mi>\u0000 <mi>k</mi>\u0000 </msub>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ leftlangle {mathrm{SEG}}_krightrangle $$</annotation>\u0000 </semantics></math>, providing explicit stage-level anchors in the LLM token space. It further constructs graph fingerprints to verbalize each snapshot's prototype deviation, temporal variation and topological profile into language-readable structural descriptions. A hybrid structure QA alignment mechanism with LoRA fine-tuning is then introduced to align structural tokens and graph fingerprints with the LLM's representation space, enabling the model to interpret and reason over explicit structural contexts. Extensive experiments on five dynamic graph benchmarks demonstrate that DyGLLM achieves consistently competitive performance across graph similarity ranking, temporal anomaly detection and change point detection, validating the effectiveness of the proposed dual-granularity structural representation.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 12","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Heterophily-Aware Motif-Guided Contrastive Learning for Robust Social Recommendation","authors":"Yinghe Wang,&nbsp;Yuankun Xu,&nbsp;Chulei Xiang","doi":"10.1111/exsy.70457","DOIUrl":"https://doi.org/10.1111/exsy.70457","url":null,"abstract":"<div>\u0000 \u0000 <p>The homophily principle serves as the core foundation of graph neural network (GNN) based social recommendation, which assumes socially connected users share similar preferences and enables neighbourhood aggregation for user representation learning. Most existing methods directly aggregate information from original social graphs, but this strategy is severely suboptimal due to the prevalent low preference-aware homophily in real-world social networks. We further reveal that nonpreference-driven social connections introduce massive noise into GNN aggregation, leading to representation degradation, over-smoothing and even performance decline. Existing efforts mostly focus on individual subproblems of social denoising, high-order modelling or representation enhancement and fail to provide a systematic solution for these cascading challenges. In this paper, we propose H2Rec, a heterophily-aware motif-guided contrastive learning framework for low-homophily social recommendation. It integrates a dual-branch social aggregation module, a homophily-enhanced contrastive alignment objective and a user-adaptive fusion mechanism to suppress noise and learn robust user representations end-to-end. Extensive experiments on real-world benchmarks show that H2Rec significantly outperforms state-of-the-art methods on mainstream evaluation metrics.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 12","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Rethink-RAG: Dynamic Retrieval Decision and Cooperative Verification for Reliable Multi-Hop Question Answering","authors":"Zhiming Li,&nbsp;Chao Gao,&nbsp;ZiXuan Wang,&nbsp;Xincheng Wang,&nbsp;YanChang Lu,&nbsp;Dianlong You","doi":"10.1111/exsy.70455","DOIUrl":"https://doi.org/10.1111/exsy.70455","url":null,"abstract":"<div>\u0000 \u0000 <p>Reliable multi-hop question answering is important for knowledge-intensive expert systems, where a wrong intermediate fact can propagate into an incorrect final decision. Existing Retrieval-Augmented Generation (RAG) methods often retrieve for every sub-question, even when the language model can answer a step from parametric knowledge, and this indiscriminate retrieval can introduce irrelevant or contradictory evidence. We propose Rethink-RAG, a training-free framework that combines dynamic retrieval decision with a cooperative answer verification pipeline. The dynamic retrieval decision module generates diverse rewrites of each sub-question and applies majority voting to decide whether external retrieval is required. The cooperative verification pipeline then filters retrieved documents, quantifies support and opposition through token-logit evidence, and arbitrates each candidate sub-answer with an adaptive confidence threshold. Experiments on 2WikiMultihopQA, HotpotQA, and MuSiQueQA show that Rethink-RAG improves answer reliability on knowledge-intensive reasoning tasks, achieving 49.00% ACC on 2WikiMultihopQA and 49.60% ACC on HotpotQA with the Llama3-8B evaluator. Additional revision experiments quantify the latency/API-call trade-off, sensitivity to the decision-boundary factor, and the limitations observed on MuSiQueQA, giving a more complete view of the framework's practical operating range.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 12","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Superiority-Probabilistic-Based Products Ranking Method: Integrating Users' Consensus Experiences and Consumers' Individual Preferences","authors":"Wenlong Cui,&nbsp;Weiwei Li,&nbsp;Pingtao Yi","doi":"10.1111/exsy.70443","DOIUrl":"https://doi.org/10.1111/exsy.70443","url":null,"abstract":"<div>\u0000 \u0000 <p>In the information edge, online reviews have emerged as a pivotal factor in consumers' purchasing decisions. In reality, we are accustomed to obtaining rigid product rankings from online reviews. However, online reviews naturally contain varied and sometimes conflicting viewpoints; the rigid ranking results are not completely reasonable. To address this problem, the paper proposes a superiority-probabilistic-based ranking model by integrating both users' consensus experiences and consumers' individual preferences. Firstly, the users' experiences, primarily represented by star ratings and textual reviews, are transformed into the individual evaluation domains (IEDs) through sentiment analysis. Then, the IEDs are further fused into the comprehensive evaluation domain (CED) by highlighting the users' consensus experiences. Subsequently, an individual-preference-oriented indicator weighting method is introduced by referring to the sequential relationship analysis (SRA) method. Based on the above preparations, the superiority-probability-based pairwise comparison matrix (SPM) is calculated through a thorough sampling of CED and the iterative aggregation of it with the indicator weights. The SPM reflects the relative superiority probability among any products, from which the probabilistic ranking of products can be derived. The case study illustrates the validity and practicability of the proposed methods. The research contribution establishes a superiority-probabilistic-based products ranking framework, providing consumers with more detailed purchase recommendations.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"SAM-CompAug: Segment Anything-Assisted Synthetic Data Augmentation for Industrial Part Detection","authors":"Ou Ye,&nbsp;Zhan Wang,&nbsp;Wenchao Zhang,&nbsp;Zhenhua Yu","doi":"10.1111/exsy.70447","DOIUrl":"https://doi.org/10.1111/exsy.70447","url":null,"abstract":"<div>\u0000 \u0000 <p>Against the backdrop of the rapid advancement of intelligent manufacturing, part detection, as a core task within industrial vision systems, faces limitations due to the scarcity of high-quality and fine-grained datasets. To address this challenge, we propose a data augmentation method named SAM-CompAug to enhance model robustness. The proposed methodology synergizes the Segment Anything Model (SAM) with bounding box prompts to generate high-fidelity instance masks, while employing a minimum centre-point distance matching strategy for precise label alignment. Furthermore, a Visibility-aware Composite Placement Strategy is introduced to systematically generate synthetic samples with realistic occlusion patterns, overlapping configurations and scale variations in synthetic samples. Leveraging this augmentation method, we construct the Part detection Dataset (PartID), a synthetic dataset for industrial part detection. PartID encompasses 13 categories of industrial parts, comprising a total of 51,000 images and 903,164 annotated instances, thereby enriching the training data and enhancing network robustness for part detection in real-world scenarios. Meanwhile, to mitigate the challenge of scale variance in part detection, a multi-scale perception module, GLMF, is designed and integrated into the YOLOv8n and YOLOv12n frameworks, thereby enhancing the model's robustness and adaptability across varying part scales. Experimental results demonstrate that PartID delivers significant performance gains on the model and exhibits strong transferability in cross-domain scenarios. Comparative experiments reveal that the strategy of pre-training on synthetic data followed by fine-tuning on real data achieves improvements of 1.7%, 0.3%, 0.4% and 0.9% in mAP50–95, mAP50, Precision and Recall, respectively, relative to the baseline algorithm. Our implementation is publicly available at: https://github.com/zhan-wz/MAYOLO.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 Multi-Task YOLO for Intelligent Transportation: Roadside Illegal Parking Detection and Parking-Line Segmentation","authors":"Shijian Liu,&nbsp;Ying Shi,&nbsp;Yufei Xie,&nbsp;Ningxin Shi","doi":"10.1111/exsy.70425","DOIUrl":"https://doi.org/10.1111/exsy.70425","url":null,"abstract":"<div>\u0000 \u0000 <p>Due to the mismatch between the rapid growth of cars and limited parking resources, illegal parking has become a critical problem in urban intelligent transportation systems. The core tasks for illegal parking judgement are object detection and parking line segmentation. The complex relationships among objects, sample imbalance, and the slender structure of parking lines make these tasks challenging. To address these issues, we propose an adaptive multi-task YOLO network, termed Parking-YOLO, which includes a feature extraction enhancement strategy, a Slide Loss-based classification strategy, and an adaptive feature fusion strategy. The experimental results show that the first strategy improves detection accuracy by an average of 2.6% and enhances the understanding of complex relationships among objects. The second strategy reduces the TIDE classification error contribution by 54.3% by focusing more on a few hard samples. The last strategy increases the parking line segmentation accuracy by 1.4%, as it better adapts to the slender structure of parking lines. Additionally, the Parking-YOLO outperforms mainstream object detection, semantic segmentation, and multi-task learning models, and its inference speed meets real-time requirements. Finally, we implement the roadside illegal parking judgement system, demonstrating its potential for intelligent transportation and roadside parking management.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Frequency-Enhanced Single-Channel EEG Sleep Staging via Cross-Frequency Interaction","authors":"Huihui Zhou,&nbsp;Aiping Liu,&nbsp;Heng Cui,&nbsp;Chun-Ren Phang,&nbsp;Feng Wan,&nbsp;Yanyan Wang,&nbsp;Xun Chen","doi":"10.1111/exsy.70439","DOIUrl":"https://doi.org/10.1111/exsy.70439","url":null,"abstract":"<div>\u0000 \u0000 <p>Automatic sleep staging using single-channel electroencephalography (EEG) is important for reducing the acquisition complexity of sleep monitoring and may support future wearable and home-based applications. Although recent deep learning models have demonstrated promising performance, they usually prioritize time waveform representations or frequency domain features in isolation, neglecting the synergy between these two domains. Moreover, the intrinsic cross-frequency interactions in sleep EEG signals are rarely modelled explicitly in existing studies. To address these limitations, we propose a frequency-enhanced single-channel sleep staging framework via cross-frequency interaction. The proposed model simultaneously learns temporal-domain representations from raw EEG signals and frequency-domain representations derived from the short-time Fourier transform (STFT). To better capture oscillatory dynamics in sleep EEG, amplitude and phase components are explicitly decoupled and independently projected to construct amplitude and phase tokens. A cross-attention mechanism inspired by phase–amplitude coupling (PAC) is introduced to explicitly capture cross-frequency interactions, in which phase information modulates amplitude responses within the frequency domain. Finally, temporal and spectral features are fused and further modelled using sequence learning to capture sleep stage transitions across successive epochs. Experiments conducted on two public datasets, Sleep-EDF and MASS-SS3, demonstrate the effectiveness of the proposed approach. The model achieves 87.0% accuracy and 82.0% macro F1-score on Sleep-EDF, and 87.8% accuracy and 83.1% macro F1-score on MASS-SS3. These results indicate that the proposed dual-domain and cross-frequency interaction modelling framework can effectively improve the discriminative capability of single-channel sleep staging models.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Intelligent Rock Tunnel Engineering: Reframing the Industry With Signal Processing and Artificial Intelligence","authors":"Hongye Zhao,&nbsp;Ben-Guo He,&nbsp;Hongpu Li,&nbsp;Huawei Xu,&nbsp;Jiahua Guan","doi":"10.1111/exsy.70394","DOIUrl":"https://doi.org/10.1111/exsy.70394","url":null,"abstract":"<div>\u0000 \u0000 <p>The transformation of rock tunnel engineering (RTE), a pivotal component of modern infrastructure, is driven by advances in signal processing and artificial intelligence (AI). This review synthesizes the existing literature to examine how time-series, image, and manually collected data are acquired, preprocessed, and utilized in RTE. These data are applied to various aspects, including geotechnical property analysis, construction optimization, safety assurance, and operational maintenance optimization. We summarize the core algorithms and identify prevailing challenges such as data heterogeneity and data silos. Future research should focus on multi-source data fusion and large models, while microseismic-based rock-burst prediction also warrants further exploration. Overall, the fusion of signal processing and AI significantly enhances the efficiency, accuracy, and safety of tunnel projects, offering a robust pathway towards sustainable next-generation underground infrastructure.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Sparse Adaptive Momentum Attack Against Federated Recommender Systems and Its Countermeasures","authors":"Zhongliang Zhang,&nbsp;Yilei Hong,&nbsp;Zhao Huang,&nbsp;Qilei Li,&nbsp;Xin Zhang","doi":"10.1111/exsy.70417","DOIUrl":"https://doi.org/10.1111/exsy.70417","url":null,"abstract":"<div>\u0000 \u0000 <p>Federated Recommendation Systems (FRS) have emerged as a promising privacy-preserving paradigm for personalised services. However, their decentralised nature exposes them to untargeted poisoning attacks that aim to degrade system utility. Existing attacks often prove suboptimal as they fail to account for three fundamental characteristics of FRS: dynamics (evolving representation trajectories), sparsity (inherent sparsity of parameter updates) and robustness (self-corrective mechanism of training). In this paper, we propose the Sparse Adaptive Momentum Attack (SAMA), which hijacks FRS optimisation dynamics by functioning as a malicious accelerator. SAMA integrates momentum-aligned trajectory tracking, critical item selection and closed-loop adaptive strength control to inject precisely calibrated perturbations into high-velocity embeddings. Extensive experiments on two real-world datasets demonstrate that SAMA consistently outperforms seven state-of-the-art attack baselines, inducing severe performance collapse. Specifically, on the Steam dataset with a 7% malicious ratio, SAMA reduces HR@10 and NDCG@10 by 99.4% and 99.6%, respectively. Under a lower malicious ratio of 3%, the attack still results in a 64.5% reduction in HR@10. Furthermore, SAMA proves its potency by effectively evading three mainstream robust aggregation defences including Trimmed Mean, Krum and Multi-Krum. To counter this sophisticated threat, we further introduce InertiaDamp, a direction-aware defence mechanism that suppresses abnormal parameter acceleration by quantifying evolutionary inertia. Experimental results validate that InertiaDamp not only effectively neutralises SAMA but also enhances the global model's convergence stability and final recommendation utility.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 11","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}