Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part II / edited by De-Shuang Huang, Xiankun Zhang, Yijie Pan.

Format:

Book

Author/Creator:

Huang, De-Shuang.

Contributor:

Zhang, Xiankun.

Pan, Yijie.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 14863

Language:

English

Subjects (All):

Computational intelligence.

Computer networks.

Machine learning.

Application software.

Computational Intelligence.

Computer Communication Networks.

Machine Learning.

Computer and Information Systems Applications.

Local Subjects:

Computational Intelligence.

Computer Communication Networks.

Machine Learning.

Computer and Information Systems Applications.

Physical Description:

1 online resource (535 pages)

Edition:

1st ed. 2024.

Place of Publication:

Singapore : Springer Nature Singapore : Imprint: Springer, 2024.

Summary:

This 13-volume set LNCS 14862-14874 constitutes - in conjunction with the 6-volume set LNAI 14875-14880 and the two-volume set LNBI 14881-14882 - the refereed proceedings of the 20th International Conference on Intelligent Computing, ICIC 2024, held in Tianjin, China, during August 5-8, 2024. The total of 863 regular papers were carefully reviewed and selected from 2189 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 that focused on this theme were solicited, addressing theories, methodologies, and applications in science and technology.

Contents:

Intro

Preface

Organization

Contents - Part II

Machine Learning and Swarm Intelligence in Optimization and Industrial Applications

Multi-server Cooperative Offloading Strategy for Dependent Tasks Based on Improved Genetic Algorithm

1 Introduction

2 System Model

2.1 Multi-user with Multi-server System Model

2.2 Task Scheduling Model with Dependencies

2.3 Problem Formulation

3 Task Offloading Strategy Based on Improved Genetic Algorithm

3.1 Coding and Population Initialization

3.2 Design of Chromosome Fitness Function

4 Evaluation

4.1 Experimental Settings

4.2 Experiment and Result Analysis

5 Conclusion

References

A 3D Liver Semantic Segmentation Method Based on U-shaped Feature Fusion Enhancement

2 Methodology

2.1 Architecture Overview

2.2 Swin Transformer Based Encoder

2.3 U-shaped Feature Fusion Module

2.4 Decoder

3 Experiments

3.1 Datasets and Implementation Details

3.2 Data Pre-processing

3.3 Evaluation Metrics

3.4 Ablation Experiments

3.5 Comparative Experiments

3.6 Model Robustness Validation

4 Conclusion

Dynamic Elite Individual Setting Based Heterogeneous Comprehensive Learning Particle Swarm Optimization

2 Particle Swarm Optimization

3 Dynamic Elite Individual Setting Based Heterogeneous Comprehensive Learning Particle Swarm Optimization

4 Experimental Description

4.1 Test Functions and Compared Algorithms

4.2 Parameter Evaluation

4.3 Performance Evaluation

Fault Diagnosis Network for Rotating Machinery Based on Multiscale Feature Fusion

2 Related Work

2.1 Time and Frequency Domain

2.2 Multimodal Feature Fusion

2.3 Attention Mechanisms

3 Proposed Method

3.1 Data Preprocessing

3.2 Network Architecture.

4 Experimental Study

4.1 Case One

4.2 Another Case

An Advanced Deep Learning-Based High-Resolution CT Images Construction Method for Cement Hydration Microstructure

2.1 Microstructure Images of Cement Hydration

2.2 Image Super-Resolution

3 Motivation

4 Methodology

4.1 Data Preparation

4.2 Refined Degradation Model

4.3 Networks and Training

5 Experiments

5.1 Method Effectiveness Verification

5.2 Assessment Against Alternative Approaches

5.3 Application on Aged 2CT Imaging Equipment

6 Conclusion

FD-DUNet: Frequency Domain Global Modeling Enhances Receptive Field Expansion UNet for Efficient Medical Image Segmentation

2.1 The Overall Architecture

2.2 Components of the Architecture

3 Experiments and Discussion

3.1 Datasets and Evaluation Metrics

3.2 Implementation Details

3.3 Comparison with State-of-The-Art Methods

3.4 Ablation Analysis

BayesTSF: Measuring Uncertainty Estimation in Industrial Time Series Forecasting from a Bayesian Perspective

2 Preliminaries

2.1 Multivariate Time Series Forecasting

2.2 Deep Ensemble

2.3 Bayesian Framework.

3 Bayesian Time Series Forecasting Toolbox

3.1 Variational Inference

3.2 Monte Carlo Sampling Method

4 Experiments

4.2 Experimental Results

PESAM: Privacy-Enhanced Segment Anything Model for Medical Image Segmentation

2.1 Fine-Tuning on Medical Images

2.2 Federated Learning

3 Method

3.1 Preliminaries

3.2 Full Fine-Tuning in PESAM

3.3 Local Aggregation in PESAM

4 Experiment

4.1 Tasks and Datasets

4.2 Experimental Setup.

4.3 Experimental Result

4.4 Ablation Study for PESAM

Automatic Multi-label Classification of Interictal Epileptiform Discharges (IED) Detection Based on Scalp EEG and Transformer

2.1 Data Acquisition

2.2 Preprocessing

2.3 IED Conformer

2.4 Evaluation Metrics

3 Results and Discussion

3.1 Comparison with the State-Of-The-Art

3.2 Limitations and Future Work

Fast Path Planning Algorithm for 3D Indoor Scene Roaming Based on Path Table

2 Mapping for 3D Indoor Scenes

2.1 Indoor Scene Description

2.2 Indoor Structural Characteristics

3 Indoor Path Planning Algorithm Based on the Path Table

4 Fast Path Planning Algorithm for Indoor Roaming Based on Path Table

5 Roam Path Smoothing

6 Experimental Results and Discussion

7 Conclusion

An Optimization Method Based on Drift Data and Time Series Information

2 Basic Concepts and Notations

3.1 Drift Separation and Supplement Algorithm

3.2 Data Weighting Algorithm Based on Time Series Information

3.3 Extra Weighting Algorithm for Potential Drift Data

4.1 Experiment on Synthetic Data

4.2 Experiment on Synthetic Data

5 Conclusions

IG-GRD: A Model Based on Disentangled Graph Representation Learning for Imaging Genetic Data Fusion

2 Methods

2.1 Overall Framework

2.2 Datasets and Preprocessing

2.3 Construction of the Imaging Graph and Genetic Graph

2.4 Disentangled Graph Representation Learning

2.5 Multimodal Fusion

2.6 Loss Functions

2.7 Feature Importance Evaluation

3 Experimental Results

3.1 Model Performance

3.2 Comparison with Other Methods

3.3 Feature Extraction of Imaging Genetic Data.

4 Conclusion

Automatic Meibomian Gland Segmentation and Assessment Based on TransUnet with Data Augmentation

3 Methodology

3.1 Data Preparation

3.2 MG Segmentation

3.3 Data Augmentation

3.4 Evaluation

4 Experimental Results

4.1 Traditional Algorithm Methods

4.2 Deep Learning Methods

4.3 TransUnet with Data Augmentation

4.4 Automatic Assessment of MGD Grades

Graph Embedding-Based Deep Multi-view Clustering

2 Proposed Method

2.1 The Loss Function of the G-DMC

2.2 Initialization of the Graph Affinity Matrix

2.3 Optimization of the G-DMC

3.1 Datasets, Methods in Comparison, and Evaluation Metrics

3.3 Experimental Results

3.4 Ablation Experiment

Nature-Inspired Intelligent Computing, Optimization and Applications

A Multi-action Reinforcement Learning Framework via Pointer Graph Neural Network for Flexible Job-Shop Scheduling Problems with Resource Transfer

2 Related Works

3 Problem Description

3.1 Mathematical Model

3.2 Mathematical Model

4 Method

4.1 Markov Decision Process Formulation

4.2 Feature Extraction Architecture: HGMN

4.3 Multi-action Collaborative Architecture: Multi-PGN

4.4 Multiple Actor-Critic Architecture: Multi-PPO

5.1 Experimental Configurations

5.2 Experimental Configurations

5.3 Discussion

Surrogate-Assisted Evolutionary Neural Architecture Search with Isomorphic Training and Prediction

2 Isomorphic Training and Prediction-Assisted Evolutionary-Based NAS

2.1 Encoding

2.2 Isomorphic Predictor

2.3 Evolutionary Framework

3 Experimental Results.

3.1 Performance-Based Comparison

3.2 Comparison of Surrogate Model

Explainable Deep Learning with Human Feedback for Perioperative Complications Prediction

3 Our Approach

3.1 Problem Definition

3.2 Incorporate Human Feedback into Modeling

3.3 Align with Domain Knowledge Using Regularization

3.4 Learning and Prediction with Explanations

4 Experiments and Results

4.1 Dataset Introduction

4.2 Metrics Description

4.3 Experimental Result

Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization

2 Related Work and Motivation

2.1 Constrained Multiobjective Optimization Problem

2.2 Large Language Models

2.3 Motivation

3 The Proposed Algorithm

3.1 The General Framework of CMOEA-LLM

3.2 Reproduction with LLM-Aided Search

3.3 Prompt Engineering for the LLM

4.1 Experiment Settings

4.2 Results on the DASCMOP Test Suite

4.3 Results on the Real-World CMOPs

An Indicator-Based Firefly Algorithm for Many-Objective Optimization

2 Firefly Algorithm

3 Proposed Approach

3.1 Fitness Evaluation Based on Convergence Indicator

3.2 Convergence Guided Search Strategy

3.3 Random Search Model

3.4 Environmental Selection

3.5 Framework of Proposed Approach

4 Experimental Study

4.1 Benchmark Problems and Parameter Settings

4.2 Computational Results

Knowledge Distillation with Classmate

3 Our Method

3.1 KDC Mechanism

3.2 Formulation

3.3 Algorithm Overview

4.1 Datasets and Settings

4.2 Main Results

4.3 Combination with Curriculum Learning.

4.4 Justification on Effectiveness of KDC.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

981-9755-81-6

OCLC:

1451461565