Note: Intro -- Preface -- Organization -- Conference Sponsor - Services Society Services Society (S2) is a nonprofit professional organization that has been created to promote worldwide research and technical collaboration in services innovation among academia and industrial professionals. Its members are volunteers from industry and academia with common interests. S2 is registered in the USA as a "501(c) organization," which means that it is an American tax-exempt nonprofit organization. S2 collaborates with other professional organiza -- About the Services Conference Federation (SCF) -- Contents -- Research Track -- Infant Sound Classification on Multi-stage CNNs with Hybrid Features and Prior Knowledge -- 1 Introduction -- 2 Infant Sound Analysis and Hybrid Features -- 2.1 Infant Sound Analysis -- 2.2 Hybrid Features of Infant Sound -- 3 Multi-stage CNNs Model and Prior Knowledge Generation -- 3.1 Hybrid Feature Multi-stage CNNs Model -- 3.2 Prior Knowledge Generation -- 4 Experiments and Results -- 4.1 Datasets -- 4.2 Experimental Results -- 5 Conclusions -- References -- Building Vector Representations for Candidates and Projects in a CV Recommender System -- 1 Introduction -- 1.1 Recommender Systems -- 1.2 CV Recommender -- 2 Related Work -- 2.1 Job Recommendation -- 2.2 Latent Semantic Indexing -- 2.3 GloVe Representations -- 2.4 Recent NLP Models -- 2.5 Representations Index -- 3 Methods -- 3.1 Skill Extraction -- 3.2 Extracting LSI Features -- 3.3 Extracting GloVe Features -- 4 Evaluation -- 5 Conclusion -- References -- Candidate Classification and Skill Recommendation in a CV Recommender System -- 1 Introduction -- 1.1 Recommender Systems -- 1.2 CV Recommender -- 2 Related Work -- 2.1 Job Recommendation -- 2.2 Numeric Representations -- 2.3 Clustering Algorithms -- 3 Methods -- 3.1 Skill Extraction -- 3.2 Skill Clustering. , 3.3 Candidate Classification -- 3.4 Skill Recommendation -- 4 Evaluation -- 4.1 Candidate Classification -- 4.2 Skill Recommendation -- 5 Conclusion -- References -- A Novel Method to Estimate Students' Knowledge Assessment -- 1 Introduction -- 2 Related Studies and Background -- 3 Representation -- 4 Problem Definition and Solution -- 4.1 Problem Statement -- 4.2 Solution -- 5 Implementation and Validation -- 5.1 Experiment Overview -- 5.2 Validation Test and Analysis Results -- 6 Conclusion -- References -- Answer Selection Based on Mixed Embedding and Composite Features -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Attention Based BiLSTM Model -- 3.2 Mixed Embedding -- 3.3 Composite Features -- 3.4 The Comprehensive Model -- 4 Experiments and Discussion -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Experimental Result -- 4.4 Discussion -- 5 Conclusions -- References -- A Neural Framework for Chinese Medical Named Entity Recognition -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Problem Definition -- 3.2 Model -- 4 Experiment -- 4.1 Experiment Setup -- 4.2 Results -- 5 Conclusion -- References -- An Annotated Chinese Corpus for Rumor Veracity Detection -- 1 Introduction -- 2 Related Work -- 2.1 English Data Collection -- 2.2 Chinese Data Collection -- 3 Corpus Construction -- 4 Baseline Methods -- 5 Conclusion -- References -- Attention-Based Asymmetric Fusion Network for Saliency Prediction in 3D Images -- 1 Introduction -- 2 Related Work -- 3 The Proposed Method -- 3.1 Overall Architecture -- 3.2 Hierarchical RGB-D Feature Extraction -- 3.3 Global Guidance Module -- 3.4 Channel Attention Module -- 3.5 Refinement -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Datasets -- 4.3 Evaluation Criteria -- 4.4 Ablation Studies and Analysis -- 4.5 Comparison with Other Saliency Prediction Models -- 5 Conclusion. , References -- Review Spam Detection Based on Multi-dimensional Features -- 1 Introduction -- 2 Related Work -- 3 Model -- 3.1 Formal Definition of Problem -- 3.2 Method -- 4 Experiment -- 4.1 Dataset -- 4.2 Experimental Evaluation Index and Experimental Setup -- 4.3 Comparison Model -- 4.4 Analysis of Experimental Results -- 4.5 Effects of User Interactive Behavioral Features -- 4.6 Effects of Extracting Text Features from Capsule Network -- 4.7 Effects of Nesting Depth of NLSTM -- 5 Conclusion -- References -- Application Track -- Rehabilitation XAI to Predict Outcome with Optimal Therapies -- 1 Background and Purpose -- 2 Related Works -- 3 Proposed Rehabilitation XAI System -- 3.1 System Configuration -- 3.2 Medical Record Data Used for Learning -- 3.3 Learning Data Generation -- 3.4 Explainable Pattern Recognition Using K-NN with Tuned Weight -- 3.5 Suggestion of Optimal Therapies -- 4 Evaluation -- 4.1 Comparison of Execution Time Between CPU and GPU -- 4.2 Precision and Recall of Each Pattern -- 4.3 Dependency of Precision and Recall on Hospitals -- 4.4 Dependency of Precision and Recall on Amount of Data -- 4.5 Prediction of Outcome -- 5 Conclusion -- References -- A Mobile Application Using Deep Learning to Automatically Classify Adult-Only Images -- 1 Introduction -- 2 Dataset -- 2.1 Image Flipping -- 2.2 Image Rotation -- 2.3 Image Greyscale -- 2.4 Image with Noise -- 3 Model Selection and Training -- 4 Results -- 5 iOS Application Development -- 5.1 Architecture Design -- 6 Related Work -- 7 Conclusions and Future Work -- References -- Short Paper Track -- OSAFe: One-Stage Anchor Free Object Detection Method Considering Effective Area -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Overall Network Architecture -- 3.2 Area Mapping -- 3.3 Overlapping Area Judging -- 3.4 Bounding Box Regression -- 3.5 Loss Function -- 4 Experiment. , 4.1 Comparison with Different Size of Feature Maps -- 4.2 Comparison with Different IoU Thresholds for NMS -- 4.3 Comparison with State-of-the-Art -- 5 Conclusion -- References -- Attention-Based Interaction Trajectory Prediction -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Problem Definition -- 3.2 Overall Flowchart -- 3.3 Extract Trajectory Features -- 3.4 Pedestrian Interaction -- 3.5 Trajectory Feature Fusion -- 4 Experiment -- 5 Conclusion -- References -- Author Index.

Note: Intro -- Preface -- Organization -- Contents -- Population-Based Variable Neighborhood Descent for Discrete Optimization -- 1 Introduction -- 2 Proposed Algorithm -- 3 Evaluation -- 3.1 Capacity Vehicle Routing Problem -- 3.2 Time Complexity Analysis -- 3.3 Usage Advice -- 4 Conclusion -- References -- The Constrained GAN with Hybrid Encoding in Predicting Financial Behavior -- 1 Introduction -- 2 Related Work -- 3 Designed Method -- 3.1 Hybrid Encoding -- 3.2 Constrained GAN -- 3.3 Integrated Classifiers -- 3.4 Algorithm Framework -- 4 Experiments -- 4.1 Data Analysis -- 4.2 The Result of Different Encoding Methods -- 4.3 Generating Positive Samples -- 4.4 The Constrained GAN -- 5 Conclusion -- References -- ECGAN: Image Translation with Multi-scale Relativistic Average Discriminator -- 1 Introduction -- 2 Related Works -- 3 ECGAN with Multi-Scale Relativistic Average Discriminator -- 3.1 Multi-Scale Relativistic Average Discriminator -- 3.2 Complementary Cycle-Consistent Loss -- 3.3 Residual-in-Residual Dense Block -- 4 Experiment -- 4.1 Datasets -- 4.2 Evaluation Metrics -- 4.3 Training Information -- 4.4 Experimental Results and Analysis -- 4.5 Quantitative Evaluation -- 4.6 Qualitative Evaluation -- 4.7 Ablation Experiments -- 5 Conclusion -- References -- Pork Registration Using Skin Image with Deep Neural Network Features -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Feature Extraction Using the VGG-16 Pretrain Model -- 2.2 Feature Pre-Matching -- 2.3 Dynamic Inlier Selection -- 2.4 Gaussian Mixture Model -- 2.5 Registration Using the EM Algorithm -- 3 Experiment and Result Analysis -- 3.1 Experiment Design -- 3.2 Results Analysis -- 4 Conclusion and Future Work -- References -- ORB-Based Multiple Fixed Resolution Approach for On-Board Visual Recognition -- 1 Introduction -- 2 Feature Point Detection Techniques -- 2.1 ORB -- 2.2 SIFT. , 2.3 SURF -- 3 Non-Feature Point Techniques -- 3.1 Local Binary Patterns -- 3.2 Histogram Intersection -- 4 Classification Techniques -- 4.1 Bag of Features -- 5 Multiple Fixed Resolution Based On-Board Component Recognition Algorithm -- 5.1 Algorithm -- 5.2 Image Capture -- 5.3 Object Detection -- 5.4 Object Recognition -- 6 Results -- 6.1 Web Server Processing -- 6.2 Augmented Reality Application -- 7 Training -- 8 Testing -- 8.1 Motherboard Image Dataset -- 8.2 Motherboard Component Dataset -- 8.3 Object Detection Testing -- 8.4 Object Recognition Testing -- 9 Conclusion -- References -- GRASP Method for Vehicle Routing with Delivery Place Selection -- 1 Introduction -- 2 Problem Definition -- 3 Related Work -- 4 Proposed Algorithm -- 4.1 Assigning Customers to Delivery Stations -- 4.2 Defining Routes to Delivery Stations -- 5 Results -- 6 Conclusion -- References -- Indexed Search -- Abstract -- 1 Introduction -- 1.1 Breadth First Search (BFS) -- 1.2 A* Search Algorithm -- 2 Indexed Search -- 2.1 New Node Generation -- 2.2 Creating Indices -- 2.3 Prevent Duplications and Cycles -- 3 Algorithm Components -- 4 Indexed Breadth First Search (IBFS) -- 4.1 Indexed a* Search -- 5 Experimental Results and Implementations -- 6 Comparing IBFS with BFS -- 6.1 Comparing IA* with A* -- 7 Conclusions and Future Works -- References -- Cognitively-Inspired Agent-Based Service Composition for Mobile and Pervasive Computing -- 1 Introduction and Motivation -- 2 Overview -- 2.1 Preliminaries -- 2.2 System Architecture -- 3 Approach -- 4 Evaluation -- 5 Related Work -- 6 Conclusions and Future Work -- References -- Accelerating Deep Learning Inference on Mobile Systems -- 1 Introduction -- 2 Related Work -- 3 Requirements -- 4 The PolimiDL Framework -- 4.1 Generation-Time Optimizations -- 4.2 Compile-Time Optimizations -- 4.3 Initialization-Time Optimizations. , 4.4 Configuration Time Optimizations -- 4.5 Run-Time Optimizations -- 4.6 Layers Coverage -- 4.7 Limits to Generalization -- 5 Evaluation -- 5.1 Experimental Setup -- 5.2 Experimental Results -- 6 Conclusion and Future Work -- References -- Design of Mobile Service of Intelligent Large-Scale Cyber Argumentation for Analysis and Prediction of Collective Opinions -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Framework -- 3.1 The Mobile Service Architecture -- 3.2 The Front-End -- 3.3 User Interface -- 3.4 The Backend -- 4 Collective Analytics Models -- 4.1 Collective Intelligence Index -- 4.2 Polarization Index -- 4.3 Prediction of Collective Opinions -- 5 Discussion and Analysis -- 5.1 Example: Issue: Guns on Campus -- 6 Conclusion and Future Work -- References -- ResumeVis: Interactive Correlation Explorer of Resumes -- 1 Introduction -- 2 Related Work -- 2.1 The Visualization of Humanities -- 2.2 The Visualization of Correlations -- 3 The Resume Data Set -- 3.1 Data Collection -- 3.2 Data Distribution -- 4 System Design -- 4.1 Parallel Coordinates with Multi-valued Attributes -- 4.2 Interaction -- 5 Experiments -- 5.1 Case Study 1: Which Attributes Related to Income? -- 5.2 Case Study 2: Are There Differences Between Different Majors? -- 6 Conclusion -- References -- Named Entity Recognition in Clinical Text Based on Capsule-LSTM for Privacy Protection -- 1 Introduction -- 2 Related Work -- 2.1 Named Entity Recognition -- 2.2 Clinical De-Identification for Privacy Protection -- 3 Proposed Approach -- 3.1 Overall Architecture -- 3.2 Long-short Term Memory -- 3.3 Capsule Network -- 3.4 Capsule-LSTM -- 3.5 Training and Inference -- 4 Experimental Details -- 4.1 Dataset -- 4.2 Model Comparison -- 4.3 Results and Analysis -- 5 Conclusion -- References -- Domain Knowledge Enhanced Error Correction Service for Intelligent Speech Interaction. , 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Overall Architecture -- 3.2 Corpus Processing -- 3.3 Error Correction -- 3.4 Error Correction as a Service -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results -- 5 Conclusion and Future Work -- References -- Author Index.

Note: Intro -- Preface -- Organization -- Services Society -- Services Conference Federation (SCF) -- Contents -- Research Track -- Push-Based Forwarding Scheme Using Fuzzy Logic to Mitigate the Broadcasting Storm Effect in VNDN -- 1 Introduction -- 2 Vehicular Named Data Networking (VNDN) -- 2.1 Content Store (CS) -- 2.2 Pending Interest Table (PIT) -- 2.3 Forwarding Information Base (FIB) -- 2.4 Consumer Vehicle -- 2.5 Producer Vehicle -- 3 Push-Based Data Forwarding in VNDN -- 4 Proposed Push-Based Data Forwarding Scheme with Fuzzy Logic -- 4.1 K-Means Clustering -- 4.2 Selection of Cluster Head (CH) Using Fuzzy Logic -- 4.3 Proposed Data Packet Format -- 4.4 Proposed Scheme for Producer -- 4.5 Proposed Scheme for Consumer -- 4.6 Critical Data Forwarding Procedure by the Proposed Scheme -- 5 Simulation Environment and Results -- 6 Conclusion -- References -- DCRNNX: Dual-Channel Recurrent Neural Network with Xgboost for Emotion Identification Using Nonspeech Vocalizations -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 Dual-Channel Neural Network Model -- 3.2 Introducing Attention Mechanism in Two-Channel Model -- 3.3 XGBoost Classifier -- 3.4 Model Fusion Using L2 Norm -- 4 Experiments -- 4.1 Datasets Used -- 4.2 Experimental Setup -- 4.3 Experimental Results -- 4.4 Introduce Attention Mechanism -- 4.5 Data Augmentation -- 5 Conclusion -- References -- STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Background Knowledge -- 3.2 The Proposed STaR Model -- 3.3 Discussions -- 4 Experiments -- 4.1 Experiments Settings -- 4.2 Main Results -- 5 Analysis -- 5.1 Further Comparison with ComplEx -- 5.2 Imbalance Ratio Among KGs -- 5.3 Improvements on WN18RR Come from Modeling Non-commutativity Pattern -- 6 Conclusion -- References -- Application Track. , Frequently Asked Question Pair Generation for Rule and Regulation Document -- 1 Introduction -- 2 Related Work -- 2.1 QA Pair Generation -- 2.2 FAQ Pair Generation -- 3 Data Collection and Analysis -- 3.1 Data Collection -- 3.2 Data Analysis -- 4 Methodology -- 4.1 Rule-Based FAQ Pair Generation -- 4.2 Pipeline Framework -- 5 Experiment -- 5.1 Experiment Setting -- 5.2 Evaluation Metrics -- 5.3 Analysis Experiment -- 5.4 Human Evaluation -- 5.5 Case Study -- 6 Conclusion -- References -- Chinese Text Classification Using BERT and Flat-Lattice Transformer -- 1 Introduction -- 2 Related Work -- 2.1 Traditional and Embedding-Based Text Classification -- 2.2 Neural Network Text Classification -- 2.3 Chinese Text Classification -- 2.4 Transformer Related Theory -- 3 Approaches -- 3.1 Converting Lattice into Flat Structure -- 3.2 Relative Position Encoding of Spans -- 3.3 Classifier and Optimization -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Overall Performance -- 5 Conclusion -- References -- Indicator-Specific Recurrent Neural Networks with Co-teaching for Stock Trend Prediction -- 1 Introduction -- 2 Related Work -- 2.1 Technical Indicators -- 2.2 Stock Trend Prediction Model -- 2.3 Co-teaching for Noisy Data -- 3 Dataset -- 3.1 Data Acquisition -- 3.2 Data Processing -- 3.3 Dataset Construction -- 4 Methodology -- 4.1 Task Definition -- 4.2 Model Overview -- 4.3 Feature Extraction Module -- 4.4 Feature-Based Attention Module -- 4.5 Prediction Module -- 4.6 Co-teaching -- 5 Experiment -- 5.1 Experimental Setting -- 5.2 Results and Analysis -- 5.3 Ablation Study -- 5.4 Case Study -- 6 Conclusion -- References -- SATMeas - Object Detection and Measurement: Canny Edge Detection Algorithm -- 1 Introduction -- 2 Methods -- 2.1 General Idea -- 2.2 Platform and Technology Used -- 2.3 Object Detection and Object Measurement -- 3 Results -- 3.1 Advantages. , 3.2 Disadvantages -- 4 Conclusion -- References -- Multi-Classification of Electric Power Metadata based on Prompt-tuning -- 1 Introduction -- 2 Related Works -- 2.1 Short Text Classification -- 2.2 Prompt -- 2.3 Verbalizer -- 3 Methodology -- 3.1 Task Formulation -- 3.2 Pre-trained Model with Electric Power Knowledge -- 3.3 Deep Prompt-Tuning Module -- 3.4 Exterior Knowledge-Based Verbalizer -- 4 Experiment -- 4.1 Dataset -- 4.2 Parameter Settings -- 4.3 Evaluation Metrics -- 4.4 Experiments -- 5 Conclusion -- References -- Dual-Branch Network Fused with Attention Mechanism for Clothes-Changing Person Re-identification -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Network -- 3.2 Loss Function -- 4 Experiments -- 4.1 Dataset -- 4.2 Experimental Details -- 4.3 Experimental Results -- 4.4 Visual Analysis -- 5 Conclusion -- References -- Infant Cry Classification Based-On Feature Fusion and Mel-Spectrogram Decomposition with CNNs -- 1 Introduction -- 2 Spectrograms vs. Mel-Spectrograms -- 3 Model Architecture -- 3.1 Spectrogram Feature Extractor -- 3.2 Mel-Spectrogram Feature Extractor -- 4 Experimental Setup and Results -- 4.1 Datasets -- 4.2 Experimental Setup -- 4.3 Results and Analysis -- 5 Conclusion -- References -- Author Index.

Note: Intro -- Title Page -- Copyright Page -- Preface -- Acknowledgments -- Table of Contents -- Contributors -- 12 Protein Structure Prediction by Protein Threading -- 12.1 Introduction -- 12.2 Protein Domains, Structural Folds, and Structure Space -- 12.3 Fitting a Protein Sequence onto a Protein Structure -- 12.4 Calculating Optimal Sequence-Structure Alignments -- 12.4.1 PROSPECT -- 12.4.2 RAPTOR -- 12.4.3 Tree-Decomposition-Based Threading Algorithm -- 12.4.3.1 Graph Representation -- 12.4.3.2 Tree Decomposition of Structure Graph -- 12.4.3.3 Tree-Decomposition-Based Alignment Algorithm -- 12.4.3.4 Time Complexity Analysis -- 12.5 Assessing Statistical Significance of Threading Alignments -- 12.6 Structure Prediction Using Protein Threading -- 12.6.1 Database of Template Structures -- 12.6.2 Threading Energy Function -- 12.6.3 Threading Algorithm -- 12.6.4 Assessing Prediction Reliability -- 12.7 Improving Threading-Based Structure Prediction -- 12.7.1 Application of Experimental Data as Threading Constraints -- 12.7.2 Improving Structural Quality through Molecular Dynamics and Energy Minimization -- 12.8 Challenging Issues -- Energy Function -- Threading Algorithm and Implementation -- Statistical Significance Analysis of Threading Results -- Consensus Building and Subdomain Threading -- 12.9 Summary -- Suggested Further Reading -- Acknowledgments -- References -- 13 De Novo Protein Structure Prediction -- 13.1 Introduction -- 13.2 Methods and Algorithms -- 13.2.1 Energy Functions -- 13.2.2 Knowledge-Based Energies -- 13.2.3 Simplified Representations -- 13.2.4 Lattice Methods -- 13.2.5 Fragment Assembly -- 13.2.6 Continuous Torsional Distributions -- 13.2.7 Selection of the Best Conformers -- 13.2.8 PROTINFO, an Example de Novo Prediction Protocol -- 13.2.9 Other de Novo Structure Prediction Protocols -- 13.3 Discussion. , 13.3.1 Faster Computers and Larger Databases -- 13.3.2 Future Directions -- Acknowledgments -- References -- 14 Structure Prediction of Membrane Proteins -- 14.1 Introduction -- 14.2 Secondary Structure Prediction Methods for Membrane Proteins -- 14.2.1 Basic Characteristics -- 14.2.1.1 Hydrophobicity -- 14.2.1.2 Hydrophobic Moment -- 14.2.1.3 The Positive-Inside Rule -- 14.2.2 The Prediction Methods for the Topology of Transmembrane Helices -- 14.2.2.1 Physicochemical Methods Based on Various Hydrophobicity Scales -- Hydropathy Analysis -- An Example -- ALOM2 -- DAS -- PRED-TMR -- SOSUI -- TMFinder -- TopPred -- 14.2.2.2 Statistical (Propensity Based) Methods -- MEMSAT -- TMAP -- TMPRED -- SPLIT -- An Example -- 14.2.2.3 Learning Algorithm-Based Methods -- TMHMM -- HMMTOP -- PHDhtm -- ENSEMBLE -- SVMtm -- 14.2.2.4 Accessibility -- 14.2.3 The Prediction Methods for the Topology of Transmembrane Barrels -- 14.2.3.1 Methods -- B2TMPRED -- BBF -- BETA-TM -- BIOSINO-HMM -- BOMP -- HMM-B2TMR -- OM_Topo_predict -- PRED-TMBB -- ProfTMB -- TBBPred -- TMBETA-NET -- 14.2.3.2 Accessibility -- 14.2.4 Accuracy Measures of Secondary Structure Prediction Algorithms -- 14.2.4.1 Accuracy Measures -- Per-Residue Accuracy -- Per-Segment Accuracy -- 14.2.4.2 Performance of Secondary Structure Predictors -- 14.3 Tertiary Structure Prediction Methods for Membrane Proteins -- 14.3.1 Molecular Determinants of Helix-Helix Interactions -- 14.3.2 Potential (Scoring) Functions of Helix-Helix Interactions -- 14.3.2.1 Potential Functions Based on Physical Models -- 14.3.2.2 "Statistical Potentials -- 14.3.2.3 "Optimal Potential -- 14.3.3 Algorithms for Optimizing Helix-Helix Packing -- References -- 15 Structure Prediction of Protein Complexes -- 15.1 Introduction -- 15.1.1 Protein Docking: Definition -- 15.1.2 Protein-Protein Interactions: Underlying Principles. , 15.1.3 Will the Proteins Interact? -- 15.1.4 Input Structures -- 15.1.5 History of Docking -- 15.2 Unbound Docking: Current Approaches -- 15.2.1 Rigid Body Docking: Search -- 15.2.1.1 Fast Fourier Transform -- 15.2.1.2 Other Search Techniques -- 15.2.2 Rigid Body Docking: Scoring -- 15.2.2.1 Shape Complementarity -- 15.2.2.2 Electrostatics -- 15.2.2.3 Desolvation and Statistical Potentials -- 15.2.2.4 Hydrogen Bonding -- 15.2.3 Refinement -- 15.2.4 Clustering -- 15.2.5 Side Chain Searching -- 15.2.6 Backbone Searching -- 15.3 Evaluation of Docking Algorithms -- 15.3.1 Determining Accuracy of Predictions -- 15.3.2 Docking Benchmark -- 15.3.3 CAPRI Experiment -- 15.4 Case Study: ZDOCK and RDOCK -- 15.4.1 ZDOCK Algorithm -- 15.4.1.1 Angular Search -- 15.4.1.2 ZDOCK Scoring -- 15.4.2 RDOCK -- 15.4.2.1 RDOCK: Energy Minimization -- 15.4.2.2 RDOCK: Scoring -- 15.4.3 6D Refinement -- 15.4.3.1 Development of a Scoring Function -- 15.4.3.2 Exploring the Search Space -- 15.4.3.3 Results -- 15.5 Summary/Future Directions -- 15.5.1 CAPRI Success/Lessons -- 15.5.2 New Developments -- Recommended Reading -- Books -- Review Articles -- References -- 16 Structure-Based Drug Design -- 16.1 Introduction to Modern Drug Discovery -- 16.1.1 Current Drug Discovery Process -- 16.1.2 Role of Protein Structure in Modern Pharmaceutical Sciences -- 16.1.3 Structure-Based Drug Design -- 16.2 Protein Therapeutics -- 16.2.1 Cytokines -- 16.2.2 Antibodies -- 16.2.3 Engineered Enzymes -- 16.2.4 Summary of Protein Therapeutics -- 16.3 Receptor-Based Drug Design -- 16.3.1 Docking -- 16.3.1.1 Search Algorithms -- 16.3.1.2 Scoring Functions -- 16.3.1.3 Input Receptor Structures -- 16.3.1.4 Validation of Docking Algorithms -- 16.3.2 Lead Discovery -- 16.3.2.1 VS Library Generation -- 16.3.2.2 Validation of Docking as a VS Tool -- 16.3.3 Lead Optimization. , 16.3.4 Comparison Studies of Docking Tools -- 16.3.5 Summary of Receptor-Based Drug Design -- 16.4 Ligand-Based Drug Design -- 16.4.1 Pharmacophore Modeling -- 16.4.2 Quantitative Structure-Activity Relationship (QSAR) -- 16.4.2.1 Training Set Compilation -- 16.4.2.2 Descriptor Selection -- 16.4.2.3 Model Generation -- A. Linear Models -- B. Nonlinear Models -- 16.4.2.4 Model Validation -- 16.4.2.5 3D-QSAR -- 16.4.2.6 QSAR Summary -- 16.4.3 Summary of Ligand-Based Drug Design -- 16.5 Future Reading -- 16.6 Conclusions -- References -- 17 Protein Structure Prediction as a Systems Problem -- 17.1 Introduction: The Complexity of Protein Structure Prediction -- 17.2 Consensus-Based Approach for Protein Structure Prediction -- 17.3 Pipeline Approach for Protein Structure Prediction -- 17.4 Expert System for Protein Structure Prediction -- 17.5 From Structure to Function -- 17.6 Benchmark and Evaluation -- 17.7 Genome-Scale Protein Structure Prediction -- 17.7.1 Overview of Three Cyanobacterial Genomes -- 17.7.2 Global Analysis of Protein Structural Folds in Three Genomes -- 17.7.3 Computational Analysis of Predicted Carboxysome Proteins -- 17.8 Summary -- 1. Protein representation -- 2. High-resolution protein structure prediction -- 3. Membrane protein structure prediction -- 4. Effects of protein interaction -- 5. New computational technology development -- Suggested Further Reading -- Acknowledgments -- References -- 18 Resources and Infrastructure for Structural Bioinformatics -- 18.1 Introduction -- 18.2 PDB and Related Databases/Servers -- 18.3 Structure Visualization -- 18.4 Protein Sequence and Function Databases -- 18.5 Structural Bioinformatics Tools -- 18.6 RNA Structure Modeling and Prediction -- 18.7 General Online Resources -- 18.8 Major Journals and Further Readings -- 18.9 Professional Societies, Conferences, and Events -- 18.10 Summary. , Acknowledgments -- References -- Appendix 1 Biological and Chemical Basics Related to Protein Structures -- A 1.1 Amino Acid Residues -- A 1.2 Nucleic Acids -- A 1.3 Protein Structures -- Suggested Further Readings -- Appendix 2 Computer Science for Structural Informatics -- A 2.1 Introduction -- A 2.2 Efficient Data Structures -- A 2.2.1 Hash Tables -- A 2.2.2 Suffix Trees -- A 2.2.3 Disjoint Sets -- A 2.2.4 Heaps -- A 2.2.5 Other Data Structures -- A 2.3 Computational Complexity and NP-Hardness -- A 2.3.1 Concept of Computational Complexity -- A 2.3.2 Optimization Problems -- A 2.4 Algorithmic Techniques -- A 2.4.1 Exhaustive Enumeration -- A 2.4.2 Dynamic Programming -- A 2.4.3 Integer Programming -- A 2.4.4 Branch-and-Bound -- A 2.4.5 A* Search -- A 2.4.6 Dead-End-Elimination Algorithm -- A 2.4.7 Greedy Algorithms -- A 2.4.8 Reduction Techniques -- A 2.4.9 Divide-and-Conquer Algorithms -- A 2.5 Parallel Computing -- A 2.6 Programming -- A 2.7 Summary -- Further Reading -- A 2.8 Acknowledgments -- References -- Appendix 3 Physical and Chemical Basis for Structural Bioinformatics -- A 3.1 Introduction -- A 3.2 Physics Concepts -- A 3.2.1 Units -- A 3.2.2 Potential Energy Surface -- A 3.2.3 Coordinate Systems -- A 3.3 Basic Chemistry -- A 3.3.1 Chemical Reactions -- A 3.3.2 Formation of the Peptide Bond -- A 3.4 Physical Forces in Proteins and Nucleic Acids -- A 3.4.1 Covalent Bond -- A 3.4.2 Electrostatic Interactions -- A 3.4.3 van der Waals Interactions -- A 3.4.4 Hydrogen Bond -- A 3.4.5 Disulfide Bond -- A 3.4.6 Solvation -- A 3.4.7 Hydrophobic Interactions -- A 3.5 Concepts from Statistical Physics and Thermodynamics -- A 3.5.1 Temperature -- A 3.5.2 The Most Probable Distribution -- A 3.5.3 Entropy -- A 3.5.4 Information Entropy -- A 3.5.5 Enthalpy -- A 3.5.6 Free Energy -- A 3.5.6.1 Helmholtz Free Energy -- A 3.5.6.2 Gibbs Free Energy. , A 3.5.7 Kinetic Barrier.

Note: Intro -- Preface -- Organization -- Conference Sponsor - Services Society -- About the Services Conference Federation (SCF) -- Contents -- Research Track -- A Combination of Resampling Method and Machine Learning for Text Classification on Imbalanced Data -- 1 Introduction -- 2 Methods and Experiments -- 2.1 Methods -- 2.2 Experimental Details -- 3 Results and Discussions -- 3.1 Evaluation Metrics -- 3.2 Results of Different Resampling Methods -- 3.3 Result Discussions of Different Machine Learning Algorithm -- 4 Conclusions -- References -- A Privacy Knowledge Transfer Method for Clinical Concept Extraction -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 Clinical Concept Extraction and Sequence Labeling -- 3.2 Voting-Based Multi-teacher Knowledge Transfer -- 3.3 Knowledge Distillation -- 4 Methodology -- 4.1 Framework Overview -- 4.2 Sequence Distillation -- 4.3 Heterogeneous Knowledge Aggregation -- 5 Experiment -- 5.1 Dataset -- 5.2 Experiment Settings -- 5.3 Results and Analysis -- 6 Conclusion -- References -- Multimodal Social Media Sentiment Analysis Based on Cross-Modal Hierarchical Attention Fusion -- 1 Introduction -- 2 Related Work -- 2.1 Text Sentiment Analysis -- 2.2 Image Sentiment Analysis -- 2.3 Multimodal Sentiment Analysis -- 3 Proposed Multimodal Sentiment Analysis Approach -- 3.1 Feature Extraction -- 3.2 Cross-Modal Global Feature Fusion -- 3.3 Cross-Modal High-Level Semantic Fusion -- 3.4 Sentiment Classification -- 4 Experiments -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Experimental Settings -- 4.4 Experimental Results -- 4.5 Ablation Analysis -- 5 Conclusion -- References -- Application Track -- Quantum Attention Based Language Model for Answer Selection -- 1 Introduction -- 2 Related Work -- 2.1 Attention Mechanism -- 2.2 Quantum Inspired Models -- 3 Basic Concepts -- 4 Quantum Attention Based Language Model. , 4.1 Word Encoder -- 4.2 Quantum Attention and Sentence Representation -- 4.3 Sentence feature selection and Matching -- 5 Experiment -- 5.1 Experimental Setup -- 5.2 Baselines -- 5.3 Experiment Settings -- 5.4 Experimental Results and Discussion -- 6 Conclusion -- References -- LightBERT: A Distilled Chinese BERT Model -- 1 Introduction -- 2 Preliminaries -- 2.1 Transformer Layer -- 2.2 Knowledge Distillation -- 3 Methodology -- 3.1 Student Architecture -- 3.2 Pre-training Distillation -- 3.3 Multi-step Distillation -- 4 Experiment -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Baselines -- 4.4 Results on CLUE -- 4.5 Effects of Teacher Assistants -- 5 Conclusion -- References -- Tool Recognition Based on Computer Vision in Nuclear Power Motor Maintenance Scene -- 1 Introduction -- 1.1 Object of Foreign Object Detection -- 1.2 Preliminary Experiment and Conclusion -- 1.3 Self-built Tool Data Set -- 1.4 Introduction of Tool Definition -- 2 Target Detection Framework Based on Faster R-CNN -- 2.1 Region Proposal Network (RPN) -- 2.2 Anchor Boxes -- 3 Improved Faster R-CNN -- 3.1 Data Set Optimization -- 3.2 Network Depth Optimization -- 3.3 Anchor Optimization -- 4 Analysis of Experimental Results -- 4.1 Experimental Environment -- 4.2 Experimental Conclusion -- 5 Conclusion -- References -- Manipulator Posture Estimation Method Based on Multi-eye Vision and Key Point Detection -- 1 Introduction -- 2 System Framework -- 3 Related Work -- 3.1 Introduction to HRNet -- 3.2 Stereoscopic Spatial Mapping -- 4 Robotic Arm Key Point Detection -- 4.1 Data Set Introduction and Model Training -- 4.2 HRNet Robotic Arm Key Point Detection Accuracy Analysis -- 5 Analysis of Test Results -- 5.1 Building the Test Environment and Camera Mapping Matrix -- 5.2 Result Analysis -- 6 Conclusion -- References -- 3D Pose Estimation of Manipulator Based on Multi View. , 1 Introduction -- 2 Position and Pose Measurement System Based on Binocular Vision -- 2.1 Pose Measurement Model Based on Binocular Vision -- 3 Position and Pose Measurement System Based on Binocular Vision -- 3.1 Pinhole Camera Model -- 3.2 Pinhole Camera Model -- 4 The Model of Three Vision Measurement System -- 5 Experiment -- 5.1 Camera Calibration -- 5.2 Experimental Environment Layout -- 6 Conclusion -- References -- Federated Learning for 6G Edge Intelligence: Concepts, Challenges and Solutions -- 1 Introduction -- 2 Federated Learning Based Edge Intelligence -- 2.1 Service Based Architecture and Edge Computing -- 2.2 Isolated Data Islands Dilemma in Edge Units -- 2.3 Federated Learning for Distributed Model Training -- 3 Challenging Problems -- 3.1 Heterogeneous Modeling -- 3.2 Efficiency Improvement -- 3.3 Security Reinforcement -- 4 Promising Solutions -- 4.1 Federated Modeling for Heterogeneous Edge Units -- 4.2 Efficient Training for High-Dimensional Models -- 4.3 Security Reinforcement for Decentralized Architecture -- 5 Conclusion -- References -- Author Index.

Note: Models and Algorithms for Biomolecules and Molecular Networks -- Contents -- List of Figures -- List of Tables -- Foreword -- Acknowledgments -- 1: Geometric Models of Protein Structure and Function Prediction -- 1.1 Introduction -- 1.2 Theory and Model -- 1.2.1 Idealized Ball Model -- 1.2.2 Surface Models of Proteins -- 1.2.3 Geometric Constructs -- 1.2.4 Topological Structures -- 1.2.5 Metric Measurements -- 1.3 Algorithm and Computation -- 1.4 Applications -- 1.4.1 Protein Packing -- 1.4.2 Predicting Protein Functions from Structures -- 1.5 Discussion and Summary -- References -- Exercises -- 2: Scoring Functions for Predicting Structure and Binding of Proteins -- 2.1 Introduction -- 2.2 General Framework of Scoring Function and Potential Function -- 2.2.1 Protein Representation and Descriptors -- 2.2.2 Functional Form -- 2.2.3 Deriving Parameters of Potential Functions -- 2.3 Statistical Method -- 2.3.1 Background -- 2.3.2 Theoretical Model -- 2.3.3 Miyazawa-Jernigan Contact Potential -- 2.3.4 Distance-Dependent Potential Function -- 2.3.5 Geometric Potential Functions -- 2.4 Optimization Method -- 2.4.1 Geometric Nature of Discrimination -- 2.4.2 Optimal Linear Potential Function -- 2.4.3 Optimal Nonlinear Potential Function -- 2.4.4 Deriving Optimal Nonlinear Scoring Function -- 2.4.5 Optimization Techniques -- 2.5 Applications -- 2.5.1 Protein Structure Prediction -- 2.5.2 Protein-Protein Docking Prediction -- 2.5.3 Protein Design -- 2.5.4 Protein Stability and Binding Affinity -- 2.6 Discussion And Summary -- 2.6.1 Knowledge-Based Statistical Potential Functions -- 2.6.2 Relationship of Knowledge-Based Energy Functions and Further Development -- 2.6.3 Optimized Potential Function -- 2.6.4 Data Dependency of Knowledge-Based Potentials -- References -- Exercises. , 3: Sampling Techniques: Estimating Evolutionary Rates and Generating Molecular Structures -- 3.1 Introduction -- 3.2 Principles of Monte Carlo Sampling -- 3.2.1 Estimation Through Sampling from Target Distribution -- 3.2.2 Rejection Sampling -- 3.3 Markov Chains and Metropolis Monte Carlo Sampling -- 3.3.1 Properties of Markov Chains -- 3.3.2 Markov Chain Monte Carlo Sampling -- 3.4 Sequential Monte Carlo Sampling -- 3.4.1 Importance Sampling -- 3.4.2 Sequential Importance Sampling -- 3.4.3 Resampling -- 3.5 Applications -- 3.5.1 Markov Chain Monte Carlo for Evolutionary Rate Estimation -- 3.5.2 Sequential Chain Growth Monte Carlo for Estimating Conformational Entropy of RNA Loops -- 3.6 Discussion and Summary -- References -- Exercises -- 4: Stochastic Molecular Networks -- 4.1 Introduction -- 4.2 Reaction System and Discrete Chemical Master Equation -- 4.3 Direct Solution of Chemical Master Equation -- 4.3.1 State Enumeration with Finite Buffer -- 4.3.2 Generalization and Multi-Buffer dCME Method -- 4.3.3 Calculation of Steady-State Probability Landscape -- 4.3.4 Calculation of Dynamically Evolving Probability Landscape -- 4.3.5 Methods for State Space Truncation for Simplification -- 4.4 Quantifying and Controlling Errors From State Space Truncation -- 4.5 Approximating Discrete Chemical Master Equation -- 4.5.1 Continuous Chemical Master Equation -- 4.5.2 Stochastic Differential Equation: Fokker-Planck Approach -- 4.5.3 Stochastic Differential Equation: Langevin Approach -- 4.5.4 Other Approximations -- 4.6 Stochastic Simulation -- 4.6.1 Reaction Probability -- 4.6.2 Reaction Trajectory -- 4.6.3 Probability of Reaction Trajectory -- 4.6.4 Stochastic Simulation Algorithm -- 4.7 Applications -- 4.7.1 Probability Landscape of a Stochastic Toggle Switch -- 4.7.2 Epigenetic Decision Network of Cellular Fate in Phage Lambda. , 4.8 Discussions and Summary -- References -- Exercises -- 5: Cellular Interaction Networks -- 5.1 Basic Definitions and Graph-Theoretic Notions -- 5.1.1 Topological Representation -- 5.1.2 Dynamical Representation -- 5.1.3 Topological Representation of Dynamical Models -- 5.2 Boolean Interaction Networks -- 5.3 Signal Transduction Networks -- 5.3.1 Synthesizing Signal Transduction Networks -- 5.3.2 Collecting Data for Network Synthesis -- 5.3.3 Transitive Reduction and Pseudo-node Collapse -- 5.3.4 Redundancy and Degeneracy of Networks -- 5.3.5 Random Interaction Networks and Statistical Evaluations -- 5.4 Reverse Engineering of Biological Networks -- 5.4.1 Modular Response Analysis Approach -- 5.4.2 Parsimonious Combinatorial Approaches -- 5.4.3 Evaluation of Quality of the Reconstructed Network -- References -- Exercises -- 6: Dynamical Systems and Interaction Networks -- 6.1 Some Basic Control-Theoretic Concepts -- 6.2 Discrete-Time Boolean Network Models -- 6.3 Artificial Neural Network Models -- 6.3.1 Computational Powers of ANNs -- 6.3.2 Reverse Engineering of ANNs -- 6.3.3 Applications of ANN Models in Studying Biological Networks -- 6.4 Piecewise Linear Models -- 6.4.1 Dynamics of PL Models -- 6.4.2 Biological Application of PL Models -- 6.5 Monotone Systems -- 6.5.1 Definition of Monotonicity -- 6.5.2 Combinatorial Characterizations and Measure of Monotonicity -- 6.5.3 Algorithmic Issues in Computing the Degree of Monotonicity -- References -- Exercises -- 7: Case Study of Biological Models -- 7.1 Segment Polarity Network Models -- 7.1.1 Boolean Network Model -- 7.1.2 Signal Transduction Network Model -- 7.2 ABA-Induced Stomatal Closure Network -- 7.3 Epidermal Growth Factor Receptor Signaling Network -- 7.4 C. Elegans Metabolic Network -- 7.5 Network For T-Cell Survival and Death in Large Granular Lymphocyte Leukemia -- References. , Exercises -- Glossary -- Index -- End User License Agreement.