Knowledge Science, Engineering and Management [electronic resource] : 14th International Conference, KSEM 2021, Tokyo, Japan, August 14–16, 2021, Proceedings, Part III /

Knowledge Management with Optimization and Security(KMOS) -- An Adversarial Training Method for Improving Model Robustness in Unsupervised Domain Adaptation -- Context-Aware Anomaly Detection in Attributed Networks -- An Efficient Hybrid Approach to Detecting and Correcting Auxiliary Word Errors in Chinese Text -- Traffic Accident Prediction Methods Based on Multi-factor Models -- Combining BERT and Multiple Embedding Methods with the Deep -- Neural Network for Humor Detection -- An Efficient Link Prediction Model in Dynamic Heterogeneous -- Information Networks Based on Multiple Self-attention -- A Clustering-prediction Pipeline for Customer Churn Analysis -- Fine-grained Unbalanced Interaction Network for Visual Question Answering -- Swarm Intelligence-Based Feature Selection: An Improved Binary Grey Wolf Optimization Method -- Integrating Real-time Entity Resolution with Top-N Join Query Processing -- Incorporating Question Information to Enhance the Performance of Automatic Short Answer Grading -- Integrating Task Information into Few-Shot Classifier by Channel Attention -- Rumor Verification on Social Media with Stance-Aware Recursive Tree -- Aspect and Opinion Terms Co-Extraction using Position-Aware Attention and Auxiliary Labels -- Beyond Laplacian Smoothing for Semi-Supervised Community Detection -- Landscape-Enhanced Graph Attention Network for Rumor Detection -- An Overview of Methods for Acquiring and Generating Decision Models -- Fine-Grained Image Classification Based on Target Acquisition and Feature Fusion -- LogAttn: Unsupervised Log Anomaly Detection with an AutoEncoder based Attention Mechanism -- DNEA: Dynamic Network Embedding Method for Anomaly Detection -- Adversarial Constraint Evaluation on Biomedical Text Mining -- Enhanced Self-node Weights Based Graph Convolutional Networks for Passenger Flow Prediction -- Interpretation of Learning-based Automatic Source Code Vulnerability Detection Model Using LIME -- Efficient Depth Completion Network based on Dynamic Gated Fusion -- A Blockchain Based Framework for Smart Greenhouse Data Management -- Medication Combination Prediction via Attention Neural Networks with Prior Medical Knowledge -- CelebHair: A New Large-Scale Dataset for Hairstyle Recommendation based on CelebA -- Image super-resolution based on residual block dense connection -- EGIM: Evolution Graph based Interest Modeling for Click-Through Rate Prediction -- Visualizing the Finer Cluster Structure of Large-Scale and High-Dimensional Data -- Learning Resource Recommendation in E-learning Systems based on Online Learning Style -- Alignment-Based Graph Network for Judicial Examination Task -- Embedding-based Network Alignment Using Neural Tensor Networks -- Detecting Parkinson’s Disease according to Gender Using Speech Signals -- Theoretical Study of Exponential Best-Fit: Modeling hCG for Gestational Trophoblastic Disease -- Lane Keeping Algorithm for Autonomous Driving via Safe Reinforcement Learning -- BS-KGS: Blockchain Sharding Empowered Knowledge Graph Storage -- Faster Nonlocal UNet for Cell Segmentation in Microscopy Images -- An Improved YOLO Algorithm for Object Detection in All Day Scenarios -- EMRM: Enhanced Multi-source Review-based Model for Rating Prediction -- Blockchain-as-a-Service Powered Knowledge Graph Construction -- Finetuned YOLOv3 For Getting Four Times The Detection Speed -- A Systematic Approach for maintainable business Process Models -- Improved Evolution Algorithm that Guides the Direction of Individual Mutation for Influence Maximization in Social Networks -- Incorporating Common Knowledge and Specific Entity Linking Knowledge for Machine Reading Comprehension -- Readmission Prediction with Knowledge Graph Attention and RNN-based Ordinary Differential Equations -- Detecting SDCs in GPGPUs through an Efficient Instruction Duplication Mechanism -- GAN-enabled Code Embedding for Reentrant Vulnerabilities Detections -- Attention Based Short-Term Metro Passenger Flow Prediction -- Thematic Analysis of Twitter as a Platform for Knowledge Management -- Cross-chain-based Decentralized Identity for Mortgage Loans -- Blockchain-based Privacy-preserving Medical Data Sharing Scheme Using Federated Learning -- An Edge Trajectory Protection Approach Using Blockchain -- Approach Based on Ontology and Machine Learning for Identifying Causes Affecting Personality Disorder Disease on Twitter -- QBT: Efficient and Flexible Resource Allocation Method for Data Center of State Grid Scenario.

This three-volume set constitutes the refereed proceedings of the 14th International Conference on Knowledge Science, Engineering and Management, KSEM 2021, held in Tokyo, Japan, in August 2021. The 164 revised full papers were carefully reviewed and selected from 492 submissions. The contributions are organized in the following topical sections: knowledge science with learning and AI; knowledge engineering research and applications; knowledge management with optimization and security.