Data Science: 7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021, Taiyuan, China, September 17–20, ... in Computer and Information Science, 1452)

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. Preface Organization Contents – Part II Contents – Part I Social Media and Recommendation Systems Natural Language Inference Using Evidence from Knowledge Graphs 1 Introduction 2 Related Work 3 Model Architecture 3.1 Clue Extraction 3.2 Evidence and Sentence Encoding 3.3 Evidence Integration 3.4 Final Classifier 4 Experiments 4.1 Datasets and Knowledge Resources 4.2 Effectiveness of Different KGs and Clue Encoders 4.3 Experiments on MedNLI 4.4 Experiments on SciTail 4.5 Implementation Details 5 Conclusion and Future Works References Construction of Multimodal Chinese Tourism Knowledge Graph 1 Introduction 2 Related Work 3 MCTKG Construction 3.1 Semi-structured Knowledge Extraction 3.2 Entity Expansion 3.3 Ontology Construction 3.4 Attribute Normalization 3.5 Automatic Generation Algorithm of Tourist Routes 3.6 MCTKG Sharing Platform 4 Experiments 4.1 Attribute Normalization Evaluation 4.2 Route Evaluation 5 Conclusion References Study on Binary Code Evolution with Concrete Semantic Analysis 1 Introduction 2 Approach Overview 2.1 Motivation Example 2.2 Problem Statement 2.3 Frame of Overview 3 Methodology 3.1 Comparing Similarity 3.2 Locating Difference 3.3 Analyzing Semantic Patterns 3.4 Identifying Evolution 4 Evaluation 4.1 Locating Difference 4.2 What Semantics Are Evolved 5 Related Work 6 Conclusion References Research on COVID-19 Internet Derived Public Opinions Prediction Based on the Event Evolution Graph 1 Introduction 2 The Method and Steps of Building the Event Evolution Graph 2.1 Data Acquisition and Preprocessing 2.2 Causal Judgment and Event Extraction 2.3 Text Vectorization and Event Clustering 3 An Empirical Study of COVID-19 Network Public Opinion Event Evolution Graph 3.1 COVID-19 Event Data Acquisition and Preprocessing 3.2 COVID-19 Event Data Acquisition and Preprocessing 3.3 The Construction of Event Evolution Graph 4 Analysis and Discussion 5 Conclusion References A Text Correlation Algorithm for Stock Market News Event Extraction 1 Introduction 2 Related Work 2.1 Extraction of Stock Market News Information 2.2 Text Correlation Algorithm 3 Our Proposed Method 3.1 Word Vector Model 3.2 Structured Event and Event Vector 3.3 Text Correlation Algorithm Based on Matching and Clustering 4 Experiments 4.1 Data Collection and Preprocessing 4.2 Relevance Between Words 4.3 Correlation Between Event Triples 4.4 Relevance Between Texts 4.5 Correlation Between Text Sets 4.6 Interpretable Information of Correlation Calculation 5 Conclusion References Citation Recommendation Based on Community Merging and Time Effect 1 Introduction 2 Problem Statement 3 Community Merging 4 CMTE-PathSim Model 4.1 Meta Path-Based Feature Space 4.2 Citation Probability 4.3 Time Effect 4.4 Citation Recommendation 5 Experiments 5.1 Dataset and Methods Setup 5.2 Verifying Time Effect Factor 5.3 Comparison with Benchmark Algorithm 6 Conclusions and Future Work References Sentiment Analysis for MOOC Course Reviews 1 Introduction 2 Related Work 3 MOOC Text Comment Sentiment Analysis Model 3.1 ALBERT Pre-trained Language Model 3.2 BiGRU Neural Network Model 3.3 Capsule Network 3.4 Attention Mechanism 3.5 Fully Connected Layer 4 Experimental Analysis 4.1 Introduction to the Data Set 4.2 Evaluation Standard 4.3 Experimental Comparison Model 4.4 Analysis of Experimental Results 5 Conclusion References Analyzing Interpretability Semantically via CNN Visualization 1 Introduction 2 Related Work 3 Interpretation by Filters Screening and Semantic Labeling 3.1 Data Preparation 3.2 Screening Convolution Features 3.3 Deconvolutional Visualization 3.4 Semantic Annotation of Filters 4 Experiments 4.1 Visualization of Screened Filters 4.2 The Coincidence Degree of Interpretable Regions and Expert Regions 4.3 Semantic Consistency of Filters 5 Conclusion References Probing Filters to Interpret CNN Semantic Configurations by Occlusion 1 Introduction 2 Related Work 3 Proposed Method 3.1 Dataset and Semantic Configurations 3.2 Probe Filters to Recognize Specified Visual Semantic Concepts by Occluding 3.3 Visualization for Evaluation 4 Experiment 4.1 Dataset and Experimental Setup 4.2 Annotation Task 4.3 Experiment Result 5 Conclusion References Targeted BERT Pre-training and Fine-Tuning Approach for Entity Relation Extraction 1 Introduction 2 Related Work 2.1 Methods with Distant Supervision 2.2 Methods with Pre-trained Language Model 3 Methodology 3.1 Separated Pipeline Model Architecture 3.2 Verb-mLM Task for Relation Classification Model 3.3 Entity-MLM Task for Entity-Pair Annotation Model 3.4 Inter-layer Sharing Attention Mechanism 4 Experiments 4.1 Datasets 4.2 Experiment on Entity Relation Classification 4.3 Experiment on Entity-Pair Annotation 4.4 Results Analysis 5 Conclusion References Data Security and Privacy Security-as-a-Service with Cyberspace Mimic Defense Technologies in Cloud 1 Introduction 2 Background 3 SECaaS 3.1 User's Perception Module 3.2 Decision Module 3.3 Multi-compiler 3.4 Cyberspace Mimic Environments 4 Experiments 4.1 Security Experiments 4.2 Performance Evaluation 5 Related Works 5.1 Multi-compiler 5.2 MVEE 6 Conclusion and Future Works References Searchable Encryption System for Big Data Storage 1 Introduction 2 Functional Interaction Model and System Architecture 2.1 Functional Interaction Model 2.2 System Architecture 3 Main Cryptographic Algorithm 3.1 Key Management Algorithm 3.2 File Classification Encryption/Decryption Algorithm 3.3 Symmetric Searchable Encryption Algorithm 3.4 Dynamic Update of Cipher Index 4 Deployment and System Test 4.1 Deployment 4.2 System Test 4.3 Advantage Analysis 5 Conclusion References Research on Plaintext Resilient Encrypted Communication Based on Generative Adversarial Network 1 Introduction 2 Adversarial Neural Cryptography 2.1 GANs Principle 2.2 Adversarial Neural Cryptography Model 2.3 Function Design 3 Plaintext Leakage in the Original Model 3.1 Neural Network Design in the Original Model 3.2 Leakage Experiments Under the Original Model 4 Model Optimization 4.1 Increase Decryption Speed 4.2 Decrease the Correct Rate of Attacker’s Cracking 5 Conclusions References An Improved LeNet-5 Model Based on Encrypted Data 1 Introduction 2 Preliminaries 2.1 Homomorphic Encryption 2.2 Convolutional Neural Network 2.3 LeNet-5 Model 3 Improved LeNet-5 Model in Ciphertext Domain 3.1 Mapping from the Plaintext Domain to the Ciphertext Domain 3.2 Improved LeNet-5 Model 4 Model Analysis 4.1 Feasibility Analysis 4.2 Efficiency Analysis 5 Conclusions References Design and Implementation of Intrusion Detection System Based on Neural Network 1 Introduction 2 Related Technologies 2.1 Intrusion Detection System 2.2 BP Neural Network 3 Design of Intrusion Detection System Based on Neural Network 3.1 System Framework 3.2 Event Collector 3.3 Event Analyzer 4 Intrusion Detection Experiment Based on Neural Network 4.1 Experimental Environment 4.2 Experimental Results and Analysis 5 Conclusions References IoT Security Situational Awareness Based on Q-Learning and Bayesian Game 1 Introduction 2 Related Works 3 Q-Learning Algorithm 3.1 Markov Decision Process 3.2 Q-Learning Method 4 IoT Security Situational Awareness Model Based on Q-Learning and Bayesian Game 4.1 Characteristics of IoT Security 4.2 Model Selection and Definition 4.3 Selection of the Optimal Defense Strategy 4.4 IoT Security Situational Assessment 4.5 Model Algorithm 5 Experimental Simulation 5.1 Experimental Setup 5.2 Analysis of Results 6 Conclusion References Protecting Web Application Code and Sensitive Data with Symmetric and Identity-Based Cryptosystems 1 Introduction 2 Symmetric and Public Key Cryptographic Algorithms 2.1 Symmetric Cryptographic Algorithms 2.2 Public-Key Cryptographic Algorithms 3 Web Security Scheme for Protecting Sensitive Data and Program Code 3.1 The Idea and General Architecture 3.2 The Security Scheme 3.3 Experimental Results and Performance 3.4 Security Analysis 4 Conclusion References IoT Honeypot Scanning and Detection System Based on Authorization Mechanism 1 Introduction 2 Related Work 2.1 Network Scanning and Detection 2.2 IoT Honeypot 3 IoT Honeypot Scanning and Detection System Based on Authorization Mechanism 3.1 Authorization System 3.2 Honeypot System 4 Experiments 5 Conclusion References Privacy Protection Model for Blockchain Data Sharing Based on zk-SNARK 1 Introduction 2 Related Works 3 Preliminaries 3.1 zk-SNARK 3.2 CP-ABE 3.3 Blockchain Data Sharing Model 4 Privacy Protection Model for Blockchain Data Sharing 4.1 Privacy Protection Model 4.2 Privacy Protection Algorithms 5 Conclusion References Hierarchical Identity-Based Conditional Proxy Re-encryption Scheme Based RLWE and NTRU Variant 1 Introduction 2 Preliminaries 2.1 RLWE 2.2 Operation Definition 2.3 HIBE-CPRE Model Definition 2.4 HIBE-CPRE Security Model Definition 3 HIB-CPRE Scheme 4 Property Analysis 4.1 Decryption Correctness of the Original Ciphertext Authorized to Senior Users 4.2 Decryption Correctness of the Transformed Ciphertext Authorized to Senior Users 4.3 Decryption Correctness of the Original Ciphertext Authorized to Ordinary Users 4.4 Decryption Correctness of the Transformed Ciphertext Authorized to Ordinary Users 4.5 Unidirectionality 4.6 Collusion Resistance 5 Security Analysis 5.1 N.HIB-CPRE Security Analysis 5.2 R.HIB-CPRE Security Analysis 6 Comparison 7 Conclusions References Applications of Data Science Intelligent Service Robot for High-Speed Railway Passengers 1 Introduction 2 The Working Process of Robot 2.1 Set the Robot Route and Pass the Passenger Seat Number and Face Information 2.2 Collect Current Position Face Information and Compare with Passenger Information 2.3 Detect Whether the Passenger Wears a Mask and Accurate Voice Broadcast Reminders 3 The Realization Function of Robot 4 Introduction and Analysis of Key Technologies 4.1 Target Detection Based on Deep Learning R-CNN Model 4.2 Face Mask Recognition and Detection Based on Deep Learning 4.3 Face Recognition Technology Based on Opencv 4.4 Behavioral Action Recognition Technology Using Convolutional Neural Network or Cyclic Neural Network and its Extended Model 4.5 Robot Self-service Vending Machine Management and Control System Based on JAVA SMM Framework 5 Conclusion References An M-ALO-SVR Model to Predict Output of Industry-University-Research Collaboration Network in China 1 Introduction 2 Related Work 2.1 SVR Algorithm 2.2 Ant Lion Optimizer (ALO) 3 Prediction Model for Innovation Output 3.1 Prediction Model 3.2 Modified Ant Lion Optimizer (M-ALO) 4 Empirical Research 4.1 Sample Selection and Index System 4.2 Performance Evaluation of the Model 4.3 Comparison of Different Models 4.4 Discussion 5 Conclusion References Prediction of Enzyme Species by Graph Neural Network 1 Introduction 2 Data Source and Preprocessing 2.1 Data Source 2.2 Data Preprocessing 3 Experimental Method and Specific Content 3.1 Graph Neural Network 3.2 K Nearest Neighbor 3.3 Support Vector Machines 3.4 Random Forest 3.5 Multi-layer Perception 4 Experimental Results and Discussion 5 Future Work References Construction of the Integration System of Cultural Resources and Products in Li Miao Region Tourism 1 Introduction 2 Characterization of Integration of Cultural Resources and Products in Li Miao Region Tourism 2.1 Construction of Mathematical Relationship Between Cultural Resources and Products 2.2 Introduction of Cultural Resources and Product Information in Li Miao Region Tourism 3 Construction of Integration System of Cultural Resources and Products in Li Miao Region Tourism 3.1 The Determination of the Integration Mechanism of Cultural Resources and Products 3.2 Determination of Fusion System Procedures 4 Experimental Results and Analysis 4.1 Comparison of Fusion Rate 4.2 Comparison of Build Integrity 5 Conclusions References Research on Non Intrusive Intelligent Monitoring System for Elevator State 1 Introduction 2 Hardware Platform and Technology Route 3 Feature Extraction and Pre-processing 3.1 Automatic Sensor Correction 3.2 Acceleration Signal Decomposition 4 Estimation of Elevator Dynamics Characteristics 5 Elevator Operating Position Estimation 5.1 State Transition Function 5.2 Map Initialization 5.3 Unscented Kalman Filter 6 Vibration Analysis 7 Experimental Results and Analysis 8 Conclusion References Research on Application of Frontier Technologies at Smart Airport 1 Definition of Smart Airport 2 The Current Development State of Smart Airports 2.1 Basic Airport Operation 2.2 Agile Airport Operation 2.3 Smart Airport Operations 2.4 Full Artificial Intelligence Airport 3 Construction Needs of Domestic Smart Airport 3.1 The Own Development Needs of Airports 3.2 Passenger Travel Demand 3.3 Airline Demand 3.4 Needs of Other Stakeholder Units 4 The Application of Frontier Technologies in Domestic Smart Airports 4.1 Application of Permanent Luggage Tags 4.2 Application of Biometric Identification Technology 4.3 Application of Interactive Wayfinding Technology 4.4 Self-service Baggage Handling Technology 4.5 Big Data and Artificial Intelligence Technologies 5 Conclusion References Design and Evaluation of an Exergame System of Knee with the Azure Kinect 1 Introduction 2 System Design 2.1 Overall Design 2.2 The Azure Kinect and Human Bone Tracking 2.3 Knee Function Evaluation 2.4 Knee Exergame Design 3 Methods 3.1 Participants 3.2 Instrumentation and Procedure 3.3 Data Analysis and Statistical Testing 4 Result 5 Discussion 6 Conclusion References Study on the Influencing Factors and Countermeasures of Tourism Development in Sanya City Based on Grey Relational Analysis 1 Introduction 2 Introduction of Grey Correlation Analysis Method 3 Grey Correlation Analysis of the Influence Factors of Tourism Development in Sanya City 3.1 Data Selection 3.2 Grey correlation data calculation 3.3 Grey Correlation Analysis of Marine Tourism Industry 4 Evaluation of Comprehensive Strength of Tourism in Sanya City 4.1 Data Selection 4.2 Determination of Index Weight 4.3 Comprehensive Strength Evaluation and Analysis 5 Suggestions on Tourism Development in Sanya City 5.1 Developing a Seasonal Tourism Development Plan References Blockchain-Based Power-Out Insurance Design and Practical Exploration 1 Introduction 2 Power-Out Insurance 2.1 Requirements Analyses of Power-Out Insurance 2.2 Power-Out Insurance Business in Traditional Way 3 Blockchain Technology Overview 4 Blockchain-Based Power-Out Insurance 4.1 Value of Blockchain in Power-Out Insurance 4.2 Blockchain-Based Power-Out Insurance Architecture Design 5 Social Benefits Analyses 6 Blockchain Application Challenges in Power-Out Insurance 6.1 Power Law Compensation Issues 6.2 Blockchain Technical Problems to Be Solved 7 Conclusion References Education Research, Methods and Materials for Data Science and Engineering “Golden Course” Construction of Software Engineering Basic Course Based on Blended Learning 1 Introduction 2 Problems and Research Status 3 Design of “Four-Phase Iteration” Mixed Teaching Model and “Dual Elements and Combination” Assessment Model 3.1 “Four-Phase Iteration” Mixed Teaching Model 3.2 “Dual Elements and Combination” Assessment Model Design 4 Analysis of Teaching Practice Results 4.1 Comparison of OBE Achievement Scale 4.2 Comparative Analysis of Test Scores 5 Conclusion References Learning Behavior-Aware Cognitive Diagnosis for Online Education Systems 1 Introduction 2 Related Work 3 Problem Definition 4 Method 4.1 Course Graph Construction 4.2 Graph Representation Learning 4.3 Modeling Process 5 Experiments 5.1 Dataset Description 5.2 Experiment Setup 5.3 Experiment Result 5.4 Discussion 6 Conclusion References Implementation of Online Teaching Behavior Analysis System 1 Introduction 2 Research Status 3 System Design and Implementation 3.1 Face Recognition Detection Module 3.2 Human Behavior Analysis Module 3.3 System Implementation 3.4 Classroom Evaluation and SMS Push Module 4 Conclusion 5 Thanks References Teaching Reform and Research of Data Structure Course Based on BOPPPS Model and Rain Classroom 1 Introduction 2 BOPPPS Model 3 Rain Classroom 4 The Teaching Reform of Data Structure Course Based on BOPPPS Model and Rain Classroom 4.1 Pre-class 4.2 In-class 4.3 After-Class 4.4 Implementation Effect Evaluation 5 Conclusion References An Empirical Study on Teachers’ Informationized Teaching Ability in Higher Vocational Colleges 1 Introduction 2 Research Method and Process 2.1 Investigation Object, Method and Content 2.2 Reliability Analysis 2.3 Information Enrichment Using Factor Analysis 3 Conclusions 3.1 We Should Continue to Take Informationization Teaching as a Breakthrough to Improve the Effectiveness of Teaching 3.2 We Should Optimize the Information Teaching Environment as the Premise 3.3 We Should Focus on The establishment of Curriculum Informationization Teaching Team 3.4 We Need to Strengthen Top-Level Design and Improve Systems and Mechanisms References Research on Teaching Evaluation of Courses Based on Computer System Ability Training 1 Introduction 2 Problems in Traditional Teaching Evaluation 3 Teaching Evaluation Orientation and Subjects Based on Computer System Ability Training 3.1 Evaluation Orientation 3.2 Multiple Evaluation Subjects 4 Hierarchical Teaching Evaluation Evaluation Index 4.1 Level 2 Indexes of Teaching Content Evaluation 4.2 Level 2 Indexes of Teaching Implementation 4.3 Level 2 Indexes of Learning Experience 4.4 Level 2 Indexes of Teaching Effect 5 Multi-dimensional Evaluation Results 6 Conclusion References Study on Vocational College Students’ Communicative Competence of Intercultural Communication 1 Research Background 2 Research Design 2.1 Variables 2.2 Questionnaire Design and Data Statistical Method 2.3 Research Participants 3 Empirical Research Procedure 3.1 Reliability and Validity Test 3.2 Description Statistics 3.3 Student’s t Test 3.4 Correlation Analysis 4 Some Suggestions to Improve Students’ Communicative Competence of Intercultural Communication 4.1 Make Full Use of the International Competitions and Conferences in Hainan 4.2 English Teaching Should Adapt Teaching Content and Methods to Cultivating Students’ Communicative Competence of Intercultural Communication 5 Conclusion References Exploration and Practice for the Cultivation Mode of College Students' Innovation Ability 1 Introduction 2 Method and Experiments 2.1 University-Enterprise Cooperation Platform 2.2 Curriculums 2.3 Operational Mechanism 3 Performance 3.1 Student Satisfaction 3.2 Enterprise Satisfaction 3.3 Competition Results 3.4 Academic Achievements 3.5 Teaching Material Achievements 4 Conclusion References An Analysis and Validation Toolkit to Support the Undergraduate Course of Computer Organization and Architecture 1 Introduction 2 Background and Challenges 2.1 The COA Lab Projects 2.2 Challenges for COA Labs 3 The Analysis and Validation Toolkit 3.1 Basic Ideas 3.2 Test Cases for Waveform Simulation Analysis and Validation 3.3 Test Cases for On-Board Testing Analysis and Verification 4 Results 5 Conclusion References Evaluation and Prognostics of the Higher Education Based on Neural Network and AHP-PLS Structural Equations 1 Introduction 2 The Preparatory Work 2.1 AHP—Satty Scale Method 2.2 PLS Structural Equations 2.3 BP Neural Network 3 Evaluation and Prediction of the Health Status of the Higher Education System 3.1 The Evaluation Basis and Ideas 3.2 PLS Structural Equation 3.3 Theoretical Basis for Using BP Neural Network to Predict the Future Scale of the Higher Education System 4 Case Analysis 5 Conclusion References Construction of Multiple Linear Regression Prediction Model of PRETCO-A Scores and Its Positive Backwash Effect on Teaching 1 Introduction 2 Data and Methods 2.1 Data Collection and Description 2.2 Modeling Procedures 3 Positive Backwash Effect of the Model 3.1 Determination of Experimental Samples 3.2 Experimental Procedures 3.3 Analysis of Experimental Results 4 Conclusions References Research Demo Demos of Passing Turing Test Successfully 1 Introduction 2 Making Machine Remember the Pronunciation and Meaning of Singular Character Word by Word Encoding 3 Making Machine Remember the Boundary of Each Word 4 UI Machine Learning Before Turing Test 5 UI Machine Learning to Remember the Pronunciation of Each Word 6 UI Machine Learning to Remember the Characters of Each Chinese Word 7 Demos of Passing Turing Test 8 The Works Related to This Study 9 Conclusion References Author Index "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