Green, Pervasive, and Cloud Computing: 18th International Conference, GPC 2023, Harbin, China, September 2224, 2023, Proceedings, Part I (Lecture Notes in Computer Science, 14503)

This book constitutes the refereed proceedings of the 18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023, held in Harbin, China, during September 23–24, 2023. The 38 full papers and 1 short paper included in this book were carefully reviewed and selected from 111 submissions. They were organized in topical sections as follows: Industrial Digitization and Applications, Edge Intelligence, Mobile Sensing and Computing, Cyber-Physical-Social Systems, Pervasive and Green Computing and Wireless and Ubiquitous Networking. Preface Organization Contents – Part I Contents – Part II Industrial Digitization and Applications UEBCS: Software Development Technology Based on Component Selection 1 Introduction 2 Related Work 2.1 SoftWare Reuse 2.2 Software Component 3 Methodology 3.1 Code Retrieval 3.2 Code Analysis 3.3 Grading Strategy 4 Conclusion References A Data Security Protection Method for Deep Neural Network Model Based on Mobility and Sharing 1 Introduction 2 Related Research Work 3 Algorithm Design 3.1 Build Trigger 3.2 SHA256 Algorithm 3.3 Generate Key Samples 3.4 Watermark Verification 4 Experiment 4.1 Fidelity 4.2 False Detection 4.3 Defense Against Fine-Tuning Attacks 4.4 Defense Against Pruning Attacks 5 Experiment References A Method for Small Object Contamination Detection of Lentinula Edodes Logs Integrating SPD-Conv and Structural Reparameterization 1 Introduction 2 Materials and Methods 2.1 Data Acquisition 2.2 Data Pre-processing 2.3 SRW-YOLO Model Construction 2.4 Model Training and Evaluation 3 Results and Discussion 3.1 Model Visualization Analysis 3.2 Analysis of Experimental Results 4 Conclusion References A Study of Sketch Drawing Process Comparation with Different Painting Experience via Eye Movements Analysis 1 Introduction 2 Related Works 2.1 Research on the Application of Eye Tracker in Art 2.2 Studies Using Eye Trackers to Analyze Differences Between Professional and Non-Professional Subjects 2.3 Cross-Cultural Communication Using Sketch Can Effectively Communicate the Study 3 Methodology 3.1 Hardware 3.2 System Design and Experimental Process 3.3 Area of Interest (AOI) Setting 4 Experiments, Analysisi and Discussion 4.1 Experimental Environment 4.2 Subjects 4.3 Analysis Results and Discussion 5 Conclusion References Review of Deep Learning-Based Entity Alignment Methods 1 Introduction 2 Problem Definition and Common Datasets 2.1 Problem Definition 2.2 Common Datasets 3 Entity Alignment Based on Deep Learning 3.1 Cross Knowledge Graph Entity Alignment Based on Relationship Prediction 3.2 Semi Supervised Neighborhood Matching Model for Global Entity Alignment 3.3 Entity Alignment Method Through Abstract and Attribute Embedding 4 Conclusion References VMD-AC-LSTM: An Accurate Prediction Method for Solar Irradiance 1 Introduction 2 Related Works 3 Methodology 3.1 Variational Modal Decomposition 3.2 Multi-head Self-attention 3.3 Time Encoding 3.4 One-Dimensional Convolutional Neural Network 3.5 Bidirectional Long Short Term Memory 4 VMD-AC-BiLSTM 5 Experiment 5.1 Dataset 5.2 Evaluation Indicators 5.3 Experimental Analysis 6 Conclusion References Anomaly Detection of Industrial Data Based on Multivariate Multi Scale Analysis 1 Introduction 2 Related Work 2.1 Multivariate Time Series Anomaly Detection 2.2 Time Correlations 2.3 Multiple Correlations 3 Method 3.1 Problem Definition 3.2 Model Architecture 3.3 Residual Network 4 Experiment 4.1 Datasets 4.2 Baselines 4.3 Experimental Setup 4.4 Evaluation Metrics 4.5 Results 4.6 Ablation Experiment 5 Conclusions References Research on Script-Based Software Component Development 1 Software Component Technology 1.1 Component Technology 1.2 Software Architecture 2 Software Reuse 2.1 Code Reuse 2.2 Design Reuse 2.3 Analysis Reuse 2.4 Reuse of Test Information 3 Domain Engineering 3.1 The Three Basic Stages of Domain Engineering 4 Our Approach 5 Conclusion References Integration Model of Deep Forgery Video Detection Based on rPPG and Spatiotemporal Signal 1 Introduction 2 Related Work 2.1 Deep Fake Methods 2.2 Deep Fake Detectors 3 Method 3.1 Integration Model 3.2 rPPG 3.3 R3D 3.4 Stacking 3.5 Bayesian Optimization 4 Experiment 4.1 Datasets 4.2 Comparison 4.3 Generalization Testing 4.4 Ablation 5 Conclusion References A Design of Hybrid Transactional and Analytical Processing Database for Energy Efficient Big Data Queries 1 Introduction 2 Related Work 2.1 The HTAP Databases 2.2 Massively Parallel Processing Architecture 3 The Framework of MPP Database Based on Shared PG Clusters 3.1 The OLTP Workload Manager 3.2 The Distributed Planner and Distributed Executor 4 Evaluation 4.1 Dataset 4.2 Experimental Setting 4.3 Performance Comparison of the MPP Database vs. the Single PG Database 4.4 Performance Comparison w.r.t the Number of CPU Cores 5 Conclusion References Chinese Medical Named Entity Recognition Based on Pre-training Model 1 Introduction 2 Related Work 2.1 Named Entity Recognition 2.2 Pre-trained Models 3 Chinese Medical Named Entity Recognition Based on Pre-training Model 3.1 Pre-training 3.2 Data Collection and Processing 3.3 Embedding Layer 3.4 Hybrid Encoding Layer 3.5 Normalization Layer 3.6 Adversarial Training 4 Experiment Results and Analysis 4.1 Dataset 4.2 Evaluation Metrics 4.3 Comparative Experiments 4.4 Ablation Experiments 5 Conclusion References A Function Fitting System Based on Genetic Algorithm 1 Introduction 1.1 Project Background 1.2 Market and Competition 1.3 Project Content 2 Feasibility Study and Demand Analysis 2.1 Feasibility Study 2.2 Requirement Analysis 3 Basic Theory 4 Detailed Design 5 System Test 5.1 The Result of Tests 5.2 Evaluation of Tests 6 Conclusion References A Rumor Detection Model Fused with User Feature Information 1 Introduction 2 Related Work 3 UFIM Model 3.1 Definition of Problem 3.2 Model Architecture 3.3 Data Preprocessing 3.4 Feature Extraction 4 Experiment Results and Analysis 4.1 Dataset and Parameter Settings 4.2 Baseline Model Comparison Experiment 5 Conclusion References Design and Implementation of a Green Credit Risk Control Model Based on SecureBoost and Improved-TCA Algorithm 1 Introduction and Motivation 2 Related Work 3 Green Credit Risk Control Model Based on SecureBoost and Improved TCA 3.1 Subsection SecureBoost Algorithm 3.2 TCA and BDA Algorithms 3.3 Feature Transfer Learning Based on Improved-TCA 4 Experimental Results 4.1 Experimental Environment 4.2 Dataset 4.3 Vertical Federated Learning 4.4 Feature-Based Transfer Learning 5 Conclusion References Unsupervised Concept Drift Detection Based on Stacked Autoencoder and Page-Hinckley Test 1 Introduction 2 Related Work 2.1 Supervised Detection Algorithms 2.2 Semi-supervised Detection Algorithms 2.3 Unsupervised Detection Algorithms 3 Method 3.1 Window Setting 3.2 Training of SAE 3.3 Measuring Dissimilarity in Distributions 3.4 Dynamic Threshold Setting 4 Experiment 4.1 Validity of Reconstruction Error for Measuring Dissimilarity in Distributions 4.2 Evaluate the Detection Capability of DD-SAPH 4.3 Comparison with Other Unsupervised Methods Under Classification Task 5 Conclusion and Future Work References An Industrial Robot Path Planning Method Based on Improved Whale Optimization Algorithm 1 Introduction 2 Related Work 2.1 Robot Path Planning 2.2 Swarm Intelligence Optimization 2.3 Motivation 3 Improved Whale Optimization Algorithm 3.1 The Classic Algorithm 3.2 Chaotic Mapping Initialization 3.3 Jumping Mechanism 4 Experiments and Analysis About the Proposed Algorithm 4.1 Test Functions 4.2 Ablation Experiments 5 Robot Path Planning Based on IWOA 5.1 Problem Modeling 5.2 Experiments and Results Analysis 6 Conclusion References Intrusion Detection System Based on Adversarial Domain Adaptation Algorithm 1 Introduction 2 Related Works 2.1 Research on Intrusion Detection Method Based on Deep Learning 2.2 Research on Adversarial Network Algorithm Based on GAN 2.3 Research on Algorithms Based on Transfer Learning 3 IDS Based on Adversarial Domain Adaptation Algorithm 3.1 Spatiotemporal Feature Extraction Module Based on CNN and RNN 3.2 Anomaly Detection Module Based on Discriminator Loss and Residual Loss 3.3 Intrusion Detection Algorithm Based on Adversarial Domain Adaptation 4 Experiment and Result Analysis 4.1 Experimental Setup 4.2 Results and Analysis 5 Summary and Outlook References Small-Sample Coal-Rock Recognition Model Based on MFSC and Siamese Neural Network 1 Introduction 2 Proposed Method 2.1 Mel Spectrum Feature Extraction 2.2 Network Architecture and Training 3 Experiments 3.1 Datasets 3.2 Experimental Environment 3.3 Parameter Tuning 3.4 Results and Discussions 4 Conclusion References Elemental Attention Mechanism-Guided Progressive Rain Removal Algorithm 1 Introduction 2 Related Work 2.1 Model-Driven Image-Based Rain Removal Algorithms 2.2 Data-Driven Image-Based Rain Removal Algorithm 3 Model Introduction 3.1 EAPRN Model Framework 3.2 Network Architectures 3.3 Element-Wise Attention Module 4 Experiments and Results 4.1 Introduction to the Dataset 4.2 Loss Function 4.3 Recursion Count 4.4 Rain Streaks Chart with Attention Chart Display 4.5 Synthetic Rainy Image De-rainy Qualitative Analysis 4.6 Qualitative Assessment of De-rainy Images 5 Conclusion References Author Index