Intelligent Computing Theories and Application: 18th International Conference, ICIC 2022, Xi'an, China, August 7–11, 2022, Proceedings, Part II (Lecture Notes in Computer Science Book 13394)

This two-volume set of LNCS 13393 and LNCS 13394 constitutes - in conjunction with the volume LNAI 13395 - the refereed proceedings of the 18th International Conference on Intelligent Computing, ICIC 2022, held in Xi'an, China, in August 2022. The 209 full papers of the three proceedings volumes were carefully reviewed and selected from 449 submissions. This year, the conference concentrated mainly on the theories and methodologies as well as the emerging applications of intelligent computing. Its aim was to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. Therefore, the theme for this conference was “Advanced Intelligent Computing Technology and Applications”. Papers focused on this theme were solicited, addressing theories, methodologies, and applications in science and technology. Preface Organization Contents – Part II Biomedical Data Modeling and Mining A Comparison Study of Predicting lncRNA-Protein Interactions via Representative Network Embedding Methods 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Survey of Network Embedding Methods 2.3 LncRNA-Protein Interactions Prediction 3 Results and Discussion 4 Conclusion References GATSDCD: Prediction of circRNA-Disease Associations Based on Singular Value Decomposition and Graph Attention Network 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Feature Representation 2.3 Singular Value Decomposition for Feature Noise Reduction 2.4 Graph Attention Network Embedding Features 2.5 Neural Network for Prediction 2.6 Evaluation Criteria 3 Experiments and Results 3.1 GATSDCD Performance 3.2 Impact of Parameters 3.3 Ablation Study 3.4 Performance Comparison with Other Methods 3.5 Case Study 4 Conclusion References Anti-breast Cancer Drug Design and ADMET Prediction of ERa Antagonists Based on QSAR Study 1 Introduction 2 Related Work 3 Method 3.1 Dataset and Data Processing 3.2 Hierarchical Clustering 3.3 Model Building 3.4 Multiple Stepwise Regression 3.5 Fisher Discrimination 4 Experimental Results 4.1 MLP Results 4.2 Results of Stepwise Regression 4.3 Optimization of Candidate Compounds Based on Fisher Discriminant 5 Conclusion References Real-Time Optimal Scheduling of Large-Scale Electric Vehicles Based on Non-cooperative Game 1 Introduction 2 Mathematical Models of New Energy Microgrid and Electric Vehicle Charging and Discharging Behavior 2.1 The Price Function of Selling Electricity of New Energy Microgrid 2.2 Modeling of Electric Vehicle Charging and Discharging Behavior 3 Optimization Objective 4 Decentralized Electric Vehicle Control Method Based on Non-cooperative Game 4.1 Non-cooperative Game Model 4.2 Broadcast Programming for Strategy Solving 5 Experimental Results 5.1 Evaluation Index 5.2 Experimental Results 6 Conclusion References TBC-Unet: U-net with Three-Branch Convolution for Gliomas MRI Segmentation 1 Introduction 2 Related Work 3 Proposed Method 3.1 TBC Module 3.2 Loss Function 4 Experiments and Results 4.1 Dataset 4.2 Metrics for Evaluation 4.3 Experiment Detail 4.4 Ablation Study 4.5 Results 5 Conclusion References Drug–Target Interaction Prediction Based on Graph Neural Network and Recommendation System 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Attribute Representation 2.3 Graph Convolutional Network 2.4 Neural Factorization Machine 2.5 Architecture 3 Result and Discussion 3.1 Evaluation Criteria 3.2 Performance Evaluation of GCNNFM Using 5-Fold Cross-Validation 3.3 Compared GCNNFM with Different Machine Learning Algorithms 3.4 Compared GCNNFM with Existing State-of-the-Art Prediction Methods 4 Conclusions References NSAP: A Neighborhood Subgraph Aggregation Method for Drug-Disease Association Prediction 1 Introduction 2 Dataset 3 Method 3.1 Neighborhood Graph Extraction 3.2 Metagraph and Contextual Graph Extraction 3.3 Metagraph and Contextual Graph Aggregation 3.4 Link Prediction 4 Experiment 4.1 Comparison Methods 4.2 Comparison of Results 4.3 Parameter Sensitivity Analysis 5 Conclusion References Comprehensive Evaluation of BERT Model for DNA-Language for Prediction of DNA Sequence Binding Specificities in Fine-Tuning Phase 1 Introduction 2 Materials and Methods 2.1 Dataset 2.2 Model Architectures 2.3 Training and Fine-Tuning 3 Results and Analysis 3.1 Relatively Small Learning Rate Leads to Better Performance 3.2 DNABERT with Different k Value of k-mer Embedding Achieves Similar Performances 3.3 DNABERT Achieves Outstanding Performance Overall 4 Conclusion References Identification and Evaluation of Key Biomarkers of Acute Myocardial Infarction by Machine Learning 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 DEG Screening 2.3 GO, KEGG, DO and GSEA Enrichment Analysis 2.4 Screening and Identification of Gene Prediction Model for Early Diagnosis 2.5 The Immune Cell Infiltration Analysis 3 Results 3.1 Preprocessing and Analysis of AMI-Related Differentially Expressed Genes 3.2 GO, KEGG, DO and GSEA Enrichment Analysis of Differential Genes 3.3 Screening and Identification of Gene Prediction Model for Early Diagnosis 3.4 Immune Infiltration Analyses 4 Discussion References Glioblastoma Subtyping by Immuogenomics 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 Cluster Analysis 2.3 Evaluation of Tumor Components 2.4 GO, KEGG Pathway and GSEA Analysis 2.5 Statistical Methods 3 Results 3.1 Clinical Information of Patients in the Cancer Genome Atlas Dataset 3.2 Immune Typing and Immune Scoring 3.3 Correlation Between Immune Typing and Human Leukocyte Antigen, Smoking and Some Immune Genes 3.4 Distribution and Gene Enrichment Analysis of Tumor-Infiltrating Immune Cells in Immunophenotyping 4 Discussion References Functional Analysis of Molecular Subtypes with Deep Similarity Learning Model Based on Multi-omics Data 1 Introduction 2 Methodology 2.1 Dataset Collection and Processing 2.2 The Proposed Workflow 2.3 Performance Evaluation Metrics 3 Experimental Results 3.1 Performance Validation 3.2 Clinical Characteristics Analysis of Ovarian Subtypes 3.3 Biological Function Analysis of Breast Molecular Subtypes 4 Conclusion and Discussion References Predicting Drug-Disease Associations by Self-topological Generalized Matrix Factorization with Neighborhood Constraints 1 Introduction 2 Related Work 3 Materials and Methods 3.1 Materials and Preprocessing 3.2 Weighted Similarity Data Fusion 3.3 NSGMF for DDAs Prediction 4 Experiments 4.1 Ablation Studies 4.2 Comparison with State-of-the-Art DDAs Prediction Methods 4.3 Case Studies 5 Conclusion References Intelligent Computing in Computational Biology iEnhancer-BERT: A Novel Transfer Learning Architecture Based on DNA-Language Model for Identifying Enhancers and Their Strength 1 Introduction 2 Materials and Methods 2.1 Benchmark Datasets 2.2 Methods 2.3 Two-Stage Identification Framework 2.4 Baseline Method 2.5 Performance Evaluation Metrics 3 Experimental Results 3.1 Different k-mer Pre-training Models 3.2 Effect of Pre-training on Model Performance 3.3 Effect of Different Fine-Tuning Methods 3.4 Performance Comparison with Existing Methods 4 Discussion and Conclusion References GCNMFCDA: A Method Based on Graph Convolutional Network and Matrix Factorization for Predicting circRNA-Disease Associations 1 Introduction 2 Materials and Methods 2.1 Known CircRNA-Disease Association 2.2 Disease Semantic Similarity Network 2.3 CircRNA Functional Similarity Network 2.4 Gaussian Interaction Profile Kernel Similarity for CircRNA and Disease 2.5 Combine Multiple Similarity (CircRNA and Disease) 2.6 Feature Extraction Based on Graph Convolution Networks 2.7 CircRNA-disease Association Prediction and Loss Function 3 Results and Discussion 3.1 Experimental Setup 3.2 Performance Analysis 3.3 Compared with Other Methods 3.4 Parameters Setting 3.5 Case Studies 4 Conclusions References Prediction of MiRNA-Disease Association Based on Higher-Order Graph Convolutional Networks 1 Introduction 2 Material and Methods 2.1 Human MiRNA-disease Associations Database 2.2 MiRNA Functional Similarity 2.3 Disease Semantic Similarity 2.4 Gaussian Interaction Profile Kernel Similarity for MiRNAs and Diseases 2.5 Integrated Similarity for MiRNAs and Diseases 2.6 MIXHOPMDA 3 Results 3.1 Experiment Settings 3.2 Performance Evaluation 3.3 Effect of Number of Projection Dimensions 3.4 Effect of Number of Layers 3.5 Effect of Number of the Value of P 3.6 Comparison with Other Latest Methods 4 Case Studies 5 Conclusion References SCDF: A Novel Single-Cell Classification Method Based on Dimension-Reduced Data Fusion 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Normalization 2.3 Determining the Optimal Number of Low-Dimensional Components 2.4 Concatenation 2.5 Classification Using Fused Data 3 Result 3.1 The Optimal Number of Low-Dimensional Components 3.2 The Accuracy of Classification with SCDF 4 Conclusion References Research on the Potential Mechanism of Rhizoma Drynariae in the Treatment of Periodontitis Based on Network Pharmacology 1 Introduction 2 Material and Method 2.1 Screening of the Active Ingredients of Rhizoma Drynariae and Corresponding Targets 2.2 Periodontitis Related Targets Retrieval 2.3 Common Targets of Rhizoma Drynariae and Periodontitis 2.4 Network of Rhizoma Drynariae Active Ingredient and Periodontal Disease Target 2.5 Protein-Protein Interaction (PPI) Network 2.6 GO and KEGG Pathway Analysis 3 Results 3.1 Active Compounds and Corresponding Targets in Rhizoma Drynariae 3.2 GO and KEGG Pathway Analysis 3.3 The Potential Targets of Drynaria for the Treatment of Periodontitis 3.4 Active Ingredient-Target Network Diagram 3.5 Establishment of PPI Network Diagram and Selection of Core Targets 3.6 GO and KEGG Pathway Analysis 3.7 Drug Component-Core Target Molecular Docking Verification Analysis 4 Discussion References Predicting Drug-Disease Associations via Meta-path Representation Learning based on Heterogeneous Information Net works 1 Introduction 2 Materials and Method 2.1 Dataset 2.2 Meta-path-Based Random Walks 2.3 Skip-Gram 2.4 Performance Evaluation Indicators 3 Experiments 3.1 Evaluation Performance of MRLDDA 3.2 Comparison of Different Representations of Drugs and Diseases 3.3 Comparison with State-of-the-Art Algorithms 4 Conclusion References An Enhanced Graph Neural Network Based on the Tissue-Like P System 1 Introduction 2 Related Work 2.1 Graph Neural Network 2.2 The Tissue-Like P System 3 An Enhanced Graph Neural Network Based on the Tissue-like P System 3.1 The General Framework of the Tissue-Like P System 3.2 The Implementation Process of the P System 4 Experiment 4.1 Datasets 4.2 GNN Model 4.3 Experimental Settings 4.4 Results and Parameter Analysis 5 Conclusion References Cell Classification Based on Stacked Autoencoder for Single-Cell RNA Sequencing 1 Introduction 2 Methods 2.1 Overview 2.2 Data Processing and Normalization 2.3 ScSAERLs Model Structure and Training Procedure 3 Results 3.1 Datasets 3.2 Evaluation Indicators 3.3 Intra-dataset Evaluation 3.4 Inter-dataset Evaluation 3.5 Performance of Identifying Cell Types not in the Reference 3.6 Model Optimization 4 Discussion and Conclusion References A Novel Cuprotosis-Related Gene Signature Predicts Survival Outcomes in Patients with Clear-Cell Renal Cell Carcinoma 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 Construction of Prognosis Model of Cuprotosis-Related Genes 3 Results 3.1 Prognostic DEGs Related to Cuprotosis Identification 3.2 Construct a Prognostic Model 3.3 Independent Prognostic Value of Copper Death Related Gene Model 3.4 Functional Analysis and Immune Cell Correlation Analysis in TCGA Cohort 4 Discussion References Identification of miRNA-lncRNA Underlying Interactions Through Representation for Multiplex Heterogeneous Network 1 Introduction 2 Methodology 2.1 Dataset 2.2 Structural Information Extraction Based on GATNE 3 Experiments and Results 3.1 Experimental Setting 3.2 Systemic Comparison with Other Models 4 Conclusions References ACNN: Drug-Drug Interaction Prediction Through CNN and Attention Mechanism 1 Introduction 2 Materials and Methods 2.1 Data Description and Preprocessing 2.2 Proposed Model 3 Experiments and Results 3.1 Evaluation Metrics 3.2 Experimental Setup 3.3 Influence of CNN Blocks 3.4 Influence of Attention Block 3.5 Comparison with Existing State-of-the-Art Methods 3.6 Predicted Novel Interactions 4 Conclusion References Elucidating Quantum Semi-empirical Based QSAR, for Predicting Tannins’ Anti-oxidant Activity with the Help of Artificial Neural Network 1 Introduction 2 Methodology 2.1 Dataset and Initial Optimization 2.2 Descriptors Computation 2.3 Feature Selection and Multiple Linear Regressions (MLR) 2.4 Artificial Neural Network (ANN) 3 Results and Discussion 4 Conclusion References Drug-Target Interaction Prediction Based on Transformer 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Data Representation 2.3 Model Architecture 2.4 Model Parameters 3 Results and Discussion 3.1 Evaluation Metrics 3.2 Performance on Datasets 4 Conclusion References Protein-Ligand Binding Affinity Prediction Based on Deep Learning 1 Introduction 2 Data Set and Data Representation 2.1 Data Set 2.2 Data Representation 3 Method 3.1 Model Description 4 Results and Discussion 5 Conclusion References Computational Genomics and Biomarker Discovery Position-Defined CpG Islands Provide Complete Co-methylation Indexing for Human Genes 1 Introduction 2 Materials and Methods 2.1 Data Source 2.2 Methods 3 Results 3.1 Position-Defined CGIs with Variable CpG Length Intervals Exhibit Distinct CpG Distributions 3.2 Position-Defined CGIs Are Different from Density-Defined CGIs in Association with Human Genes 3.3 Position-Defined CGIs Have Different Methylation Statuses as Compared to Density-Defined CGIs in Gene Structural and Functional Categories 4 Discussion and Conclusion References Predicting the Subcellular Localization of Multi-site Protein Based on Fusion Feature and Multi-label Deep Forest Model 1 Introduction 2 Materials and Methods 2.1 Data Set 2.2 Feature Extraction Methods 2.3 Multi-label Deep Forest (MLDF) 3 Results and Discussion 3.1 Model Validation and Performance Evaluation 3.2 Performance of Different Features 3.3 Better Performance of MLDF 4 Conclusion References Construction of Gene Network Based on Inter-tumor Heterogeneity for Tumor Type Identification 1 Introduction 2 Methods and Data 2.1 Methods 2.2 Data and Preprocessing 2.3 Networks Construction 2.4 Network Embedding 2.5 Constructing Patient Features 2.6 Supervised Classification Model 2.7 Unsupervised Classification Model 3 Results 3.1 Pan-Cancer Classification 3.2 Cancer Subtype Classification 4 Discussion References A Novel Synthetic Lethality Prediction Method Based on Bidirectional Attention Learning 1 Introduction 2 Methods 2.1 Construction of Protein Amino Acid Sequence Features 2.2 Construction of Protein Topological Features 2.3 Bidirectional Attention Learning 3 Experiment and Result 3.1 Dataset 3.2 Experimental Setup 3.3 Performance Comparison of Different Models 3.4 Case Study 4 Conclusions References A Novel Trajectory Inference Method on Single-Cell Gene Expression Data 1 Introduction 2 Methods 2.1 Cell Partition and Clustering 2.2 Consensus Clustering 2.3 Initial Tree Structure and Elastic Principal Graph Embedding 2.4 Cell Pseudotime Ordering 3 Experiments and Results 3.1 Datasets and Data Prepossessing 3.2 Evaluation Metrics 3.3 Reconstruction of Cell Lineages Tree 3.4 Performance Comparison 4 Conclusion References Bioinformatic Analysis of Clear Cell Renal Carcinoma via ATAC-Seq and RNA-Seq 1 Introduction 2 Materials and Methods 2.1 Download of ATAC-Seq and Transcriptome Data of Renal Clear Cell Carcinoma Tissue Samples 2.2 Quality Control 2.3 Data Analysis 2.4 Correlation Analysis 3 Results 3.1 Quality of ATAC-Seq Data in Renal Clear Cell Carcinoma 3.2 GO and KEGG Pathway Enrichment Analysis 3.3 Correlation Between the Key Genes and the Peaks 4 Discussion References The Prognosis Model of Clear Cell Renal Cell Carcinoma Based on Allograft Rejection Markers 1 Introduction 2 Materials and Methods 2.1 Data Acquisition and Preprocessing 2.2 Differentially Expressed Allograft Rejection Associated Genes (DE-ARGs) and Functional Enrichment Analyses 2.3 Independent Prognostic Value of the Immune-Associated Prognostic Signature 2.4 Statistical Analysis 3 Results 3.1 Identification and Functional Analyses of DE-ARGs 3.2 Risk Prediction Analysis 3.3 Survival Analysis 4 Discussion References Membrane Protein Amphiphilic Helix Structure Prediction Based on Graph Convolution Network 1 Introduction 2 Materials and Methods 2.1 Dataset 2.2 Node Features Extraction 2.3 Graph Feature Extraction 3 Prediction Model 3.1 Graph Convolutional Network Based Model 3.2 Model Training and Evaluation 3.3 Evaluation Indicators 4 Results and Discussion 4.1 Node Features Importance Comparison 4.2 The Length of Sliding Window Comparison 4.3 Comparison with Existing Methods 4.4 Conclusion References The CNV Predict Model in Esophagus Cancer 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 Differentially Expressed Genes (DEGs) Screened Between Cancer and Para-Neoplasm Tissues 2.3 DNA CNVs Annotation and Relate Analysis 2.4 Establishment of Risk Prediction Model 2.5 Independence of Risk Score from Other Clinical Features 2.6 Functional Enrichment and GO Analysis 2.7 Statistical Analysis 3 Results 3.1 Differential Gene Analysis of Esophageal Cancer 3.2 Identification of CNV-Driven Genes in ES Patients 3.3 Screening of Prognostic CNV Driver Genes 4 Discussion References TB-LNPs: A Web Server for Access to Lung Nodule Prediction Models 1 Introduction 2 Materials and Methods 2.1 Implementations 2.2 Functionalities and Documentation 3 Discussion References Intelligent Computing in Drug Design A Targeted Drug Design Method Based on GRU and TopP Sampling Strategies 1 Introduction 2 Methods 2.1 Dataset 2.2 Targeted Drug Generation Process 3 Experimental Results 3.1 Generation of Untargeted Molecular Structures 3.2 Generation of Targeted Drug Molecules 3.3 Molecular Docking Results 4 Conclusion References KGAT: Predicting Drug-Target Interaction Based on Knowledge Graph Attention Network 1 Introduction 2 Methods 2.1 Construction of Knowledge Graph 2.2 Knowledge Graph Attention Network 2.3 Model Prediction 3 Experiments 3.1 Datasets 3.2 Experimental Settings 3.3 Results 4 Conclusion References MRLDTI: A Meta-path-Based Representation Learning Model for Drug-Target Interaction Prediction 1 Introduction 2 Methods 2.1 The Framework of MRLDTI 2.2 Gathering the Meta-path Relations of Drugs and Targets 2.3 Learning the Representations of Drugs and Targets 2.4 Discovering Unknown DTIs 3 Results 3.1 Evaluation Criteria 3.2 Performance Evaluation of MRLDTI 3.3 Comparison with State-of-the-Art Models 4 Conclusion References Single Image Dehazing Based on Generative Adversarial Networks 1 Introduction 2 GAN 3 MSF-GAN 3.1 Parameters 3.2 Attention Mechanism 3.3 Discriminators 3.4 Loss Function 4 Experiments 4.1 Data Sets 4.2 Results 5 Conclusion References K-Nearest Neighbor Based Local Distribution Alignment 1 Introduction 2 Related Work 2.1 Domain Adaptation 2.2 MMD 3 Methods 4 Experiment and Analysis 5 Conclusion References A Video Anomaly Detection Method Based on Sequence Recognition 1 Introduction 2 Related Work 3 Proposed Anomaly Detection Method 3.1 Feature Extraction 3.2 Bi-LSTM Model 3.3 Sequence Recognition Network Model 3.4 Abnormal Event Location 4 Experiments 4.1 Dataset 4.2 Analysis of the Proposed Method 5 Conclusions References Drug-Target Binding Affinity Prediction Based on Graph Neural Networks and Word2vec 1 Introduction 2 Materials and Methods 2.1 Overview of Our Model 2.2 Dataset 2.3 Drug Representation 2.4 Protein Representation 2.5 Deep Learning on Molecular Graphs 3 Experiments and Results 3.1 Evaluation Metrics 3.2 Results and Discussion 4 Conclusions References Drug-Target Interaction Prediction Based on Attentive FP and Word2vec 1 Introduction 2 Method 2.1 Datasets 2.2 Representing Drug Molecules 2.3 Representing Target Proteins 2.4 Representation of Drug-Target Pair 2.5 Evaluation Criteria 3 Experiment 3.1 Performance on Human Dataset and C.elegans Dataset 3.2 Comparison with the Results of Existing Papers 4 Conclusion References Unsupervised Prediction Method for Drug-Target Interactions Based on Structural Similarity 1 Introduction 2 Methods 2.1 Datasets 2.2 Extraction of Interaction Pairs 2.3 Prediction of Interaction Pairs Based on OpBGM Model 3 Experimental Results 3.1 Analysis of Clustering 3.2 Docking Verification 4 Conclusion References Drug-Target Affinity Prediction Based on Multi-channel Graph Convolution 1 Introduction 2 Methods 2.1 Molecular Representation 2.2 Multichannel Graph Convolution Structure 2.3 Model Structure 3 Results and Discussion 3.1 Dataset 3.2 Metrics 3.3 Performance of Various Channels 3.4 Performance of Various Activation Functions 3.5 Performance of Various Pooling Methods 3.6 Performance of Various Methods 4 Conclusions References An Optimization Method for Drug-Target Interaction Prediction Based on RandSAS Strategy 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Constructing Heterogeneous Networks 2.3 Prediction Based on RandSAS Strategy 3 Experimental Results 3.1 Evaluation Criteria 3.2 Experiment of Proportional Division of Samples 3.3 Drug Similarity Threshold Adjustment Experiments 4 Conclusion References A Novel Cuprotosis-Related lncRNA Signature Predicts Survival Outcomes in Patients with Glioblastoma 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 Construction and Validation of Risk Models 2.3 Construction of Predictive Signatures of Cuprotosis-Related lncRNA 2.4 Statistical Analysis 3 Results 3.1 Data Preprocessing 3.2 Construction and Validation of Risk Models 3.3 Construction of a Cuprotosis-Related lncRNA Prognostic Model 3.4 Enrichment Analysis of Cuprotosis-Related Genes 3.5 Mutational Signature of GBM 3.6 GBM Immune Function, Immune Escape and Immunotherapy Analysis 4 Conclusion 5 Discussion References Arbitrary Voice Conversion via Adversarial Learning and Cycle Consistency Loss 1 Introduction 2 Related Work 3 Methodology 3.1 Problem Formulation 3.2 Network Architecture 3.3 Loss Function 3.4 Training Details 4 Experiment 4.1 Experiment Setup 4.2 Objective Evaluation 5 Conclusion References MGVC: A Mask Voice Conversion Using Generating Adversarial Training 1 Introduction 2 Related Work 3 Methodology 3.1 Network Architecture 3.2 Loss Function 3.3 Training Details 4 Experiment 4.1 Experiment Setup 4.2 Objective Evaluation 5 Conclusion References Covid-19 Detection by Wavelet Entropy and Genetic Algorithm 1 Introduction 2 Dataset 3 Methodology 3.1 Wavelet Entropy 3.2 Feedforward Neural Network 3.3 Genetic Algorithm 3.4 K-Fold Cross-Validation 4 Experiment Results and Discussions 4.1 WE Results 4.2 Statistical Results 4.3 Comparison to State-of-the-Art Approaches 5 Conclusions References COVID-19 Diagnosis by Wavelet Entropy and Particle Swarm Optimization 1 Introduction 2 Dataset 3 Methodology 3.1 Wavelet Entropy 3.2 Feedforward Neural Network 3.3 Particle Swarm Optimization 3.4 K-fold Cross Validation 4 Experiment Results and Discussions 4.1 WE Results 4.2 Statistical Results 4.3 Comparison to State-of-the-Art Approaches 5 Conclusions References Theoretical Computational Intelligence and Applications An Integrated GAN-Based Approach to Imbalanced Disk Failure Data 1 Introduction 2 Related Technology 2.1 Generating Models 2.2 Classic Machine Learning Method 3 Evaluation Metrics 4 Dataset and Feature Selection 4.1 Dataset Selection 4.2 Feature Selection 4.3 Data Normalization Process 5 Experiment and Analysis 5.1 Dataset 5.2 Experimental Settings 5.3 Comparison of Experimental Results 5.4 Result Analysis 6 Conclusions References Disk Failure Prediction Based on Transfer Learning 1 Introduction 2 Related Methods 2.1 ANN-BP 2.2 Transfer Learning 2.3 Maximum Mean Difference 3 Experiment 3.1 Experimental Data 3.2 Data Preprocessing 3.3 Evaluation Indicators 3.4 Transfer Learning Model Construction 3.5 Result Analysis 4 Conclusions References Imbalanced Disk Failure Data Processing Method Based on CTGAN 1 Introduction 2 Related Work 3 Related Methods 3.1 CTGAN 3.2 Machine Learning Model 4 Experimental Analysis and Results 4.1 Experimental Setup 4.2 Data Augmentation 4.3 Experimental Procedure 4.4 Evaluation Metrics 4.5 Results Analysis 5 Conclusion References SID2T: A Self-attention Model for Spinal Injury Differential Diagnosis 1 Introduction 2 Background 2.1 Somatosensory Evoked Potentials 2.2 Self-attention and Vision Transformer 3 Materials and Methods 3.1 Dataset 3.2 Model Architecture 4 Experiments and Results 4.1 Experiment Setup 4.2 Performance Measures 4.3 Results 5 Conclusions References Predicting Protein-DNA Binding Sites by Fine-Tuning BERT 1 Introduction 2 Materials and Methods 2.1 Benchmark Dataset 2.2 Model 3 Result and Discussion 3.1 Competing Methods 4 Conclusion References i6mA-word2vec: A Newly Model Which Used Distributed Features for Predicting DNA N6-Methyladenine Sites in Genomes 1 Introduction 2 Materials and Methods 2.1 Dataset 2.2 Feature Encoding 2.3 Convolutional Neural Network 3 Prediction Accuracy Assessment 4 Result and Discussion 4.1 Comparison with the Different k Values Based on the Same Dataset 4.2 Comparison with the Different Datasets Based on the Same k Value 4.3 Comparison with the Existing Classical Methods 5 Conclusion References Oxides Classification with Random Forests 1 Introduction 2 Methods and Materials 2.1 Materials 2.2 Characteristic Variables 2.3 Methods 2.4 Parameter Optimization 2.5 Model Execution 2.6 Evaluation Index 3 Model Results and Analysis 3.1 Performance Evaluation of the Model 3.2 Model Selection 4 Conclusion References Protein Sequence Classification with LetNet-5 and VGG16 1 Introduction 2 Methods and Materials 2.1 Data 2.2 Methods 3 Results and Discussions 3.1 LetNet-5 Experimental Result 3.2 VGG16 Experimental Result 3.3 Comparison of the Experimental Results Between LetNet-5 and VGG16 4 Conclusions References SeqVec-GAT: A Golgi Classification Model Based on Multi-headed Graph Attention Network 1 Introduction 2 Materials and Methods 2.1 Data 2.2 SeqVec-GAT Classifier 2.3 Evaluation Metrics and Methods 3 Results 4 Conclusion References Classification of S-succinylation Sites of Cysteine by Neural Network 1 Introduction 2 Methods 2.1 Feature Encoding 2.2 Construction of Classifier 2.3 Performance Evaluation of Predictors 3 Results and Discussion 3.1 Performance Comparison of LOO Cross Validation Under Different Classifiers 3.2 Different Feature Extraction Methods Produce Different Prediction Results 3.3 The Superior Performance of Deep Learning 4 Conclusion References E. coli Proteins Classification with Naive Bayesian 1 Introduction 2 Data Collection and Processing 2.1 Data Set 2.2 Dataset Construction 3 Model Building 3.1 The Establishment of Grey Relational Degree-Naive Bayesian Model 3.2 Decision Tree Model Establishment 3.3 Gaussian Process Modeling 3.4 Feature Fusion 3.5 Boosting 4 Results 5 Conclusion References COVID-19 and SARS Virus Function Sites Classification with Machine Learning Methods 1 Introduction 2 Materials and Methods 2.1 Data 2.2 Data Processing 2.3 Vectorization of Sequence Features 3 Classification Algorithms 3.1 Adaboost Algorithm 3.2 Voting Classifier Algorithm 3.3 Methods and Evaluation Indicators 4 Results and Discussion 5 Conclusion References Identification of Protein Methylation Sites Based on Convolutional Neural Network 1 Introduction 2 Data Collection and Processing 2.1 Data Set 2.2 Convolutional Neural Network 2.3 Overfitting Inhibition 3 Evaluation Indicators and Methodologies 4 Result 5 Conclusion References Image Repair Based on Least Two-Way Generation Against the Network 1 Introduction 2 Method and Material 2.1 Build-Against the Network 2.2 Mask Treatment 2.3 The Generator Model 3 Results 3.1 The Operation of the Image Repair Model 3.2 A Wide Range of Opencv Built-In Image Repair Algorithms 3.3 Contrast with Normal Generated Image Repair Against the Network 4 Conclusion References Prediction of Element Distribution in Cement by CNN 1 Introduction 2 Related Work 2.1 SEM Prediction 2.2 Convolutional Neural Networks 3 Methodology 4 Result 5 Conclusion 6 Feature Work References An Ensemble Framework Integrating Whole Slide Pathological Images and miRNA Data to Predict Radiosensitivity of Breast Cancer Patients 1 Introduction 2 Materials and Methods 2.1 Dataset and Preprocessing 2.2 WSI Feature Extraction 2.3 miRNA Feature Extraction 2.4 Ensemble Model Construction 2.5 Evaluation Metrics 3 Results and Discussion 3.1 Predicting Radio Sensitivity with WSI Information 3.2 Predicting Radio Sensitivity with miRNA Information 3.3 Predicting Radio Sensitivity Based on Integration of WSI and miRNA Information 4 Conclusion References Bio-ATT-CNN: A Novel Method for Identification of Glioblastoma 1 Introduction 2 Preliminaries 2.1 Data 2.2 Pathway 2.3 Comparison with Methods 2.4 ATT-CNN Architecture 2.5 Grad-CAM 3 Experimental Results 3.1 Data 3.2 Comparison with Benchmark Methods 3.3 Model Performance 4 Discussion 5 Conclusion References STE-COVIDNet: A Multi-channel Model with Attention Mechanism for Time Series Prediction of COVID-19 Infection 1 Introduction 2 Materials and Methods 2.1 Spatial Feature Channel 2.2 Temporal Feature Channel 2.3 Environmental Feature Channel 2.4 Fusion Prediction Module 3 Datasets 3.1 COVID-19 Cases Dataset 3.2 Environmental Information Datasets 3.3 Data Preprocessing 4 Experiments 4.1 Experimental Setup 4.2 Comparison with Existing Models 4.3 Ablation Experiments 4.4 Explainability Analysis 5 Conclusion References KDPCnet: A Keypoint-Based CNN for the Classification of Carotid Plaque 1 Introduction 2 Materials and Methods 2.1 Dataset 2.2 Method 3 Experiments and Results 3.1 Implementation Detail 3.2 Evaluation Metrics 3.3 Result 4 Conclusion and Discussion References Multi-source Data-Based Deep Tensor Factorization for Predicting Disease-Associated miRNA Combinations 1 Introduction 2 Materials and Method 2.1 miRNA-miRNA-Disease Association Tensor 2.2 miRNA Similarity and Disease Similarity 2.3 Method Overview 3 Experiments 3.1 Experimental Setup 3.2 Baselines 3.3 Experimental Results 3.4 Ablation Study 3.5 Running Time Analysis 3.6 Case Study 4 Conclusion References Correction to: Multi-source Data-Based Deep Tensor Factorization for Predicting Disease-Associated miRNA Combinations Correction to: Chapter “Multi-source Data-Based Deep Tensor Factorization for Predicting Disease-Associated miRNA Combinations” in: D.-S. Huang et al. (Eds.): Intelligent Computing Theories and Application, LNCS 13394, https://doi.org/10.1007/978-3-031-13829-4_72 Author Index