Data science . Part I : 7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021, Taiyuan, China, September 17-20, 2021, Proceedings / / Jianchao Zeng [and four others], (editors)

• Pubblicazione: Singapore : , : Springer, , 2022; ©2021
• Descrizione fisica: 1 online resource (558 pages)
• Disciplina: 006.3
• Soggetto topico: Data mining
• Persona (resp. second.): ZengJianchao
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Big Data Management and Applications -- A Blockchain-Based Scheme of Data Sharing for Housing Provident Fund -- 1 Introduction -- 2 Motivation -- 3 Related Works -- 4 System Design Overview -- 5 The Specific Program -- 5.1 Data Sharing -- 5.2 Data Storing -- 5.3 Data Exchange -- 5.4 Authorization -- 5.5 Federal Computing -- 6 Case Study -- 6.1 Sichuan & -- Chongqing HPF System Integration -- 6.2 Extension of HPF Policy and Management in Chongqing -- 7 Conclusion and Future Work -- References -- Social Media and Recommendation Systems -- Item Recommendation Based on Monotonous Behavior Chains -- 1 Introduction -- 1.1 User-Commodity Interaction Monotonous Behavior Chain -- 1.2 Bipartite Link Prediction Considers Matrix Completion -- 2 Related Work -- 3 Problem Definition -- 3.1 User-Item Bipartite Graph Representation of Each Stage of Monotone Behavior Chain -- 3.2 Graph Link Prediction Solves the Matrix Completion Problem -- 4 Method -- 4.1 Graph Auto-encoder -- 4.2 Graph Encoder -- 4.3 Monotonic Behavior Decoder -- 4.4 Model Training -- 5 Experimental Setup -- 5.1 Datasets -- 5.2 Comparison Methods and Evaluation Methods -- 5.3 Parameter Settings -- 5.4 Experimental Results -- 6 Conclusions and Future Work -- References -- Design and Implementation of Collaborative Filtering Recommendation Algorithm for Multi-layer Networks -- 1 Introduction -- 2 Pre-requisite Knowledge -- 2.1 User-Based Collaborative Filtering Algorithm -- 2.2 Project-Based Collaborative Filtering Algorithm -- 2.3 Bipartite Graph Recommendation Algorithm -- 3 Recommendation Algorithms for Two-Layer Networks -- 3.1 Problem Formulation -- 3.2 Dataset Pre-processing -- 3.3 Two-Layer Network Characterization Analysis -- 3.4 Recommendation Algorithm Implementation -- 3.5 Algorithm Implementation Process. ; 4 Experimental Results -- 4.1 Evaluation Criteria -- 4.2 Selection of Parameters -- 4.3 Experimental Results -- 5 Summary and Prospect -- References -- Integrating Local Closure Coefficient into Weighted Networks for Link Prediction -- 1 Introduction -- 2 Related Works -- 3 Preliminaries -- 3.1 Notation -- 3.2 Problem Definition -- 3.3 General Weighted Similarity Metric -- 3.4 The Local Closure Coefficient -- 3.5 Weighted Local Closure Coefficient -- 3.6 Metric Extension -- 4 Experiments -- 4.1 Datatset -- 4.2 Comparison Methods and Evaluation Metric -- 4.3 Experiment Results -- 5 Conclusion -- References -- A Transformer Model-Based Approach to Bearing Fault Diagnosis -- 1 Introduction -- 2 Related Work -- 2.1 Status of Fault Diagnosis -- 2.2 Status of the Transformer -- 3 Fault Diagnosis Method Based on Transformer Model -- 3.1 Data Pre-processing Using the Short-Time Fourier Transform -- 3.2 Transformer-Based Approach to Image Classification -- 4 Experiment -- 4.1 Data Set Description -- 4.2 Experimental Setup Details and Benchmarking Algorithms -- 4.3 Experimental Results and Comparison Experiments -- 5 Conclusion and Future Works -- References -- Research and Simulation of Mass Random Data Association Rules Based on Fuzzy Cluster Analysis -- 1 Introduction -- 2 Construction of Association Rule Pattern for Mass Random Data Based on Fuzzy Cluster Analysis -- 2.1 The Principle of Fuzzy Cluster Analysis -- 3 Simulation Experiment Analysis -- 3.1 Raw Data Matrix Normalization -- 3.2 Dynamic Clustering -- 3.3 Dynamic Clustering Diagram -- 4 Conclusion -- References -- Predicting Stock Price Movement with Multiple Data Sources and Machine Learning Models -- 1 Introduction and Literature -- 2 Methodology -- 2.1 Data and Variables -- 2.2 Machine Learning Models -- 2.3 Model Evaluation Criteria -- 2.4 Model Validation -- 3 Results and Discussion. ; 3.1 Performance of Three Models Using Multiple Data Sources -- 3.2 Comparison of Bull and Bear Markets -- 3.3 Comparison of Inactive and Active Periods -- 4 Conclusion -- References -- Data-Driven Prediction of Foodborne Disease Pathogens -- 1 Introduction -- 2 Related Works -- 2.1 Methods Based on Surveillance Platform Data -- 2.2 Methods Based on Rapid Detection Technology -- 2.3 Methods Based on Machine Learning -- 3 Methods -- 3.1 Data Description -- 3.2 Data Preprocessing -- 3.3 Model Building -- 4 Experiments -- 4.1 Evaluation Criteria -- 4.2 Result -- 4.3 Limitations -- 5 Conclusion -- References -- Infrastructure for Data Science -- Intelligent Storage System of Machine Learning Model Based on Task Similarity -- 1 Introduction -- 2 Related Work -- 3 System Architecture -- 4 Key Technologies -- 4.1 Similarity Verification -- 4.2 Scoring and Model Storage -- 5 Demonstration Scenarios -- References -- A Localization Algorithm in Wireless Sensor Network Based on Positioning Group Quality -- 1 Introduction -- 2 Related Works -- 3 Problem Identification and LA-PGQ Algorithm -- 3.1 Problem Identification -- 3.2 The Average Hop Size (AHS) -- 3.3 The LA-PGQ Algorithm -- 4 Simulation Results and Analysis -- 4.1 Simulation Results with Varying the Ratio of the Beacon Nodes -- 4.2 Simulation Results with Varying Communication Radius -- 5 Conclusions -- References -- A Collaborative Cache Strategy Based on Utility Optimization -- 1 Instruction -- 2 Related Work -- 3 System Architecture Construction -- 3.1 Hybrid CDN-P2P Architecture Model -- 3.2 The Aggregation of SPS -- 4 Problem Formulation and Algorithm -- 4.1 The Utility Optimization of ISP -- 4.2 The Collaborative Cache Strategy Based on Utility Optimization -- 5 Experiment Evaluation -- 5.1 Simulation Setting -- 5.2 Simulation Results -- 6 Conclusion -- References. ; Research on Route Optimization of Battlefield Collection Equipment Based on Improved Ant Algorithm -- 1 Introduction -- 2 The Optimization Model of the Battlefield Collecting Equipment Path -- 2.1 Problem Description -- 2.2 Build Path Optimization Model -- 3 Improved Ant Algorithm -- 3.1 Principles of Ant Algorithm -- 3.2 The Basic Model of the Improved Ant Algorithm -- 3.3 Improved Ant Algorithm Process -- 4 Simulation Result -- 5 Conclusion -- References -- Parallel Region Reconstruction Technique for Sunway High-Performance Multi-core Processors -- 1 Introduction -- 2 Related Works -- 3 Parallel Region Reconstruction Technique -- 3.1 OpenMP Programming Model and Problem Analysis -- 3.2 Parallel Region Merging -- 3.3 Parallel Region Extending -- 3.4 Implementation of Parallel Region Reconstruction Technique -- 4 Experimental Evaluation -- 4.1 Experimental Environment, Benchmarks and Test Content -- 4.2 Experimental Results and Analyses -- 5 Conclusion -- References -- Thread Private Variable Access Optimization Technique for Sunway High-Performance Multi-core Processors -- 1 Introduction -- 2 Related Works -- 3 The Privileged Instruction-Based Thread-Private Variable Access Technique -- 3.1 Technique Realization Mode of Thread Private Variables in Sunway and Its Problems -- 3.2 Threaded Private Variable Access Techniques Based on Privileged Instructions -- 4 Experimental Evaluation -- 4.1 Experimental Environment, Benchmarks and Test Content -- 4.2 Experimental Results and Analyses -- 5 Conclusion -- References -- Basic Theory and Techniques for Data Science -- Anti-obfuscation Binary Code Clone Detection Based on Software Gene -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Overview -- 3.2 Basic Block Semantic Embedding -- 3.3 Semantic Embedding of Function Control Flow Graph -- 4 Experiments -- 4.1 Explore Instruction Segmentation Methods. ; 4.2 Model Training -- 4.3 p@n Test -- 5 Discussion -- 6 Conclusions -- References -- The Construction of Case Event Logic Graph for Judgment Documents -- 1 Introduction -- 2 Related Work -- 3 Construction Method -- 3.1 Research Framework -- 3.2 Construction of Event Logic Graph -- 4 Model -- 5 Experiment -- 6 Conclusion -- References -- Machine Learning for Data Science -- Improved Non-negative Matrix Factorization Algorithm for Sparse Graph Regularization -- 1 Introduction -- 2 NMF, GNMF Algorithm -- 3 New-SGNMF Algorithm Design -- 3.1 Algorithm Model of New-SGNMF -- 3.2 Algorithm Solution of New-SGNMF -- 3.3 Convergence Analysis of the Algorithm -- 3.4 New-SGNMF Algorithm Steps -- 4 Experimental Analysis -- 4.1 Experimental Database -- 4.2 Comparison of Different Algorithms -- 4.3 Evaluation Criteria Used -- 4.4 Experimental Result -- 5 Conclusions and Future Work -- References -- MA Mask R-CNN: MPR and AFPN Based Mask R-CNN -- 1 Introduction -- 2 Related Work -- 2.1 ResNet -- 2.2 FPN -- 2.3 ResNet + FPN Backbone -- 2.4 Attention Mechanism -- 3 Our Method -- 3.1 Multi-resolution Parallel ResNet (MPR) -- 3.2 Attention FPN (AFPN) -- 4 Experiments Results and Analysis -- 4.1 Main Result -- 4.2 Ablation Study -- 4.3 Bounding Box Detection Results -- 5 Conclusions -- References -- Generative Adversarial Network Based Status Generation Simulation Approach -- 1 Introduction -- 2 Background and Related Work -- 2.1 Background -- 2.2 Related Work -- 3 Problem Definition -- 3.1 Influencing Factors Analysis -- 3.2 Status Generation for Electric Equipment -- 4 Proposed Approach -- 4.1 Conditional Information Modeling -- 4.2 Adversarial Training -- 4.3 Optimization -- 5 Experiments -- 5.1 Training Data and Baselines -- 5.2 Analysis -- 6 Conclusion -- References. ; Research on Attitude Solving Algorithm of Towing Cable Based on Convolutional Neural Network Fusion Extended Kalman Filter.
• Sommario/riassunto: "This two volume set (CCIS 1451 and 1452) constitutes the refereed proceedings of the 7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021 held in Taiyuan, China, in September 2021. The 81 papers presented in these two volumes were carefully reviewed and selected from 256 submissions. The papers are organized in topical sections on big data management and applications; social media and recommendation systems; infrastructure for data science; basic theory and techniques for data science; machine learning for data science; multimedia data management and analysis; ​social media and recommendation systems; data security and privacy; applications of data science; education research, methods and materials for data science and engineering; research demo." -- Publisher's description.
• Titolo autorizzato: Data Science
• ISBN: 981-16-5940-0
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910502658803321
• Lo trovi qui: Univ. Federico II
• Serie: Communications in computer and information science ; ; 1451.