Advanced Intelligent Computing Technology and Applications

Name: Advanced Intelligent Computing Technology and Applications | 20th International Conference, ICIC 2024, Tianjin, China, August 5-8, 2024, Proceedings, Part V
Brand: Springer
Price: 85.59 EUR
Availability: OnlineOnly

20th International Conference, ICIC 2024, Tianjin, China, August 5-8, 2024, Proceedings, Part V

De-Shuang Huang Xiankun Zhang Chuanlei Zhang(Herausgeber*in)

Springer (Verlag)

Erschienen am 31. Juli 2024

XVIII, 487 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-981-97-5675-9 (ISBN)

85,59 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents - Part V
Intelligent Control and Automation
A Parallel Intelligent Search and Rescue System for Swarm Robots Based on Digital Twin
1 Introduction
2 System Design Details
2.1 System Framework Design
2.2 Real-Time Twin Model Modeling Module
2.3 Parallel Decision Path Planning Module
3 System Application Example
3.1 Real-Time Twin Model Module Simulation Validation
3.2 Real-Scene System Verification
4 Conclusion and Discussion
References
Formal Verification of Path Planning Safety and Reachability in Unmanned Surface Vehicles
1 Introduction
2 Background
2.1 Model Checking
2.2 Linearly Priced Timed Automata
2.3 Linear-Time Temporal Logic
2.4 UPPAAL Model Checking Tool
3 Method
3.1 Representation of Energy
3.2 Reference and Formal Models
3.3 Safety and Reachability Properties
3.4 Specification of Requirements
4 Verification
4.1 Results
5 Conclusion
References
Refine Camera Calibration with Global Geometry Constraints
1 Introduction
2 Related Work
2.1 Parameter Estimation
2.2 Calibration Process
3 The Proposed Calibration Framework
3.1 Global Pose Constraint
3.2 Calibration Data Filter Mechanism
4 Experiments
4.1 Hardware and Software
4.2 Calibration Accuracy Exploration
4.3 Calibration Consistency Exploration
4.4 Different Camera Lens Exploration
5 Conclusion
References
OCP: An Online Contingent Planning Method for Robot Tasks with Incomplete Knowledge
1 Introduction
2 Related Works
3 The Online Contingent Planning Method
3.1 Overview of OCP
3.2 ExPDDL: Extensions to PDDL for Modelling Uncertainty
3.3 Online Contingent Planning Algorithm
4 Experiment
4.1 Evaluations on Contingent Benchmarks
4.2 Simulation Experiment
4.3 Real-Robot Experiment
5 Conclusions
References
YOLO-Underwater: A Real-Time Object Detection Framework for Enhanced Underwater Robotics Operations
1 Introduction
2 Related Work
3 Method
3.1 YOLOv7
3.2 ConvNeXt
3.3 SimAM
4 Experiment
5 Conclusion
References
YOLO-Underwater-Tiny: High-Efficiency Object Detection in Underwater Robots
1 Introduction
2 Method
2.1 YOLOv7-Tiny
2.2 Reparameterized Lightweight Backbone Layer of MobileOne
2.3 Ghost
3 Experiment
3.1 Experiment on Replacing Convolution with Ghost Convolution
3.2 Ablation Experiments and Model Comparisons in Underwater Environments
3.3 Comparative Experiments on Underwater Environments of Multiple Types of Models
4 Conclusion
References
Shared Subnet Synthesis of Object-Oriented Petri Net Based Representation for Embedded Systems
1 Introduction
2 Basic Concepts
3 Synthesis Operation and Property Analysis
4 Applications
5 Conclusion
References
Deep Reinforcement Learning Based on Graph Neural Network for Flexible Job Shop Scheduling Problem with Lot Streaming
1 Introduction
2 Problem Description and Model Formula
3 Proposed DRL Methods for FJSPLS
3.1 Markov Decision Process Formulation
3.2 Enhanced Disjunctive Graph and HGFE
3.3 Decision-Making by Dual Agents
3.4 Network Structure and Training
4 Computational Experiments
5 Conclusions
References
Robust Adaptive Neural Network-Based Funnel Tracking Control of a Class of Perturbed Euler-Lagrange Systems
1 Introduction
2 Problem Statement
2.1 Dynamic of Euler-Lagrange Systems
2.2 Formulations of Neural Networks
3 Main Results
3.1 Controller Design
3.2 Stability Analysis
4 Simulation Example
5 Conclusion
References
SeqAttention-Net: Design of a Deep Neural Network for Bearing Fault Detection Based on Small Sample Datasets
1 Introduction
2 Related Work
3 Methods
3.1 Transformer
3.2 Fast Fourier Transform
4 Experiment
4.1 Baseline
4.2 Datasets
4.3 Data Preprocessing
4.4 Evaluation Indicators
4.5 Experimental Results
5 Summary
References
Adaptive Fixed-Time Sliding-Mode Trajectory Tracking Control of a Cart-Pendulum Robot Against Actuator Attacks
1 Introduction
2 Research Model with Preliminaries
2.1 Cart-Pendulum Robot Model
2.2 False Data Injection Attacks
2.3 Control Intents
3 Integral Sliding-Mode Adaptive Control Law Generation
3.1 Estimated Value of Unknown Attack Weight
3.2 Fixed Time Integral Sliding-Mode Control Law
4 Simulation Results
5 Conclusions
References
VirtualOffshore: An Interactive 3D Offshore Environment for Embodied Agents
1 Introduction
2 Related Works
2.1 Embodied Agent
2.2 Simulation Environment
3 Offshore Environment
3.1 Unity Simulator
3.2 WebSocket Endpoints
3.3 User Interface
4 Offshore Task Planning Challenge
4.1 Atomic Actions
4.2 States
4.3 Goals
5 Benchmark Experiments
5.1 Baseline Models
5.2 Results
6 Conclusion
References
Agent Can Say No: Robot Task Planning by Natural Language Feedback Between Planner and Executor
1 Introduction
2 Related Work
2.1 Task Planning
2.2 LLMs as the Robot Planner
3 Method
3.1 Cloud Component
3.2 Local Component
3.3 Action Decision
4 Experiments
4.1 Generalization Experiments
4.2 Comparative Experiments
5 Conclusion
References
A Real-Time Exoskeleton Control Strategy for Multiple Gaits Based on Continuous State Variable Driving and MiniRocket Recognition
1 Introduction
2 System Model
3 Continuous State Variable Driven Control Strategy
4 Gait Recognition Based on MiniRocket
5 Experimental Results
5.1 Initial Setup and Adjustment
5.2 Gait Recognition Accuracy
5.3 Gait Phase Estimation for Three Types of Gaits
6 Conclusion
References
Scheduling Strategy to Minimize Makespan for Energy-Efficient Parallel Applications in Heterogeneous Computing Systems
1 Introduction
2 Related Works
3 Model
3.1 Application Model
3.2 Energy Model
3.3 Problem Definition
4 Algorithm
4.1 Pre-allocation of Energy Consumption
4.2 A Proposed Algorithm to Minimize the Scheduling Length
4.3 Example of the Proposed Algorithm
5 Experiment
5.1 Fast Fourier Transform Application
5.2 Gaussian Elimination Application
6 Conclusion
References
An Enhanced Driving Trajectory Prediction Method Based on Generative Adversarial Imitation Learning
1 Introduction
2 State of the Art
3 Driving Trajectory Prediction
3.1 Multimodal Trajectory Model
3.2 High-Definition Driving Scene Map Construction
3.3 Strategy Learning
3.4 Trajectory Scheme Generation
4 Simulation and Result Analysis
4.1 Evaluation Indicators
4.2 Training
4.3 Models Comparison and Analysis
4.4 Ablation System
4.5 Results Analysis
5 Conclusions
References
Subtask-Aware Energy Allocation Algorithm for Parallel Applications Scheduling on Heterogeneous Computing Systems
1 Introduction
2 Related Work
3 Model and Problem Definition
3.1 Application Model
3.2 Energy Model
3.3 Problem Definition
4 Subtask-Aware Scheduling Algorithm
4.1 Task Prioritization Phase
4.2 Energy Distribution Phase
4.3 Task Allocation Phase
4.4 Algorithm Description
4.5 Example of the SEA-PAS Algorithm
5 Experiments
5.1 Experimental Results for FFT Applications
5.2 Experimental Results for GE Applications
6 Conclusion
References
A Dynamic Model of Multi-state LVAD Based on LSTM Neural Network
1 Introduction
2 Cardiovascular-LVAD Model
3 Data of Multi State
3.1 Afterload and Preload
3.2 Heart Failure
3.3 Suction
4 Dynamics Model Based on LSTM
4.1 LSTM Neural Network
4.2 Train Progress of LSTM
5 Evaluation
5.1 Non-suction State
5.2 Suction State
6 Conclusion
References
Large-Scale Electroplating Scheduling: A Hierarchical Temporal Planning Approach
1 Introduction
2 Problem Definition
3 Our HIT Approach
3.1 Generating Skeletons and Sub-goals
3.2 Generating Final Plans
3.3 Overview of HIT
4 Experiment
4.1 Results of Problems with Different Numbers of Products
4.2 Results of Problems with Unexpected Events
4.3 Case Study
5 Conclusion
References
Intelligent Image/Document Retrievals
Blockchain-Based Equilibrium Anchors Game Pricing Method for Data Element
1 Introduction
2 Description of Problem
3 Game Pricing Approach for Data Elements in Blockchain
3.1 Average Value Line (AVL)
3.2 Anchor Bidding Game
4 Experimentation and Evaluation
4.1 Experimental Data Configuration
4.2 Analysis of Experimental Results
5 Conclusion
References
Ethical Challenges and Governance of Smart Algorithms Empowering Financial Technology
1 Background
2 Ethical Challenges and Technical Governance of Intelligent Algorithms in Financial Technology
2.1 Data Privacy and Security
2.2 Algorithmic Discrimination
2.3 Algorithm Distortion
2.4 Algorithm Black Box
2.5 Large Model Risks
2.6 Disputes Over Responsibility Attribution
3 Other Governance Approaches of Intelligent Algorithms in Financial Technology
3.1 Organizational Supervision
3.2 Formulate Relevant Legal Regulations
4 Conclusion and Outlook
References
A Federated Anti-money Laundering Detection Model with Bidirectional Graph Attention Network
1 Introduction
1.1 Motivation
1.2 Contribution
2 The Proposed FALD-BGAT Model
2.1 Local Model Using BGAT
2.2 Global Model
3 Experiment and Comparison
3.1 Experimental Settings
3.2 Experimental Results Under Local Goal
4 Conclusion
References
Hybrid Deep Generative and Sequential Learning Approach for Stock Market Prediction
1 Introduction
2 Background Knowledge
2.1 Variational Autoencoder
2.2 LSTM
3 Hybrid Deep Generative and Sequential Learning Approach for Stock Market Prediction
4 Experiment Results
4.1 Experimental Setup
4.2 Experiment Results and Analysis
5 Conclusion
References
Trusted Secure Routing Schemes Based on Intelligent Computing: A Brief Review
1 Introduction
2 Related Works
2.1 Trust-Based Planar Secure Routing Protocol
2.2 Trust-Based Hierarchical Secure Routing Protocol
3 Trusted Secure Routing Schemes Based on Intelligent Computing
3.1 Evaluation Metrics
3.2 Comparison and Analysis of Trust-Based Secure Routing Schemes
3.3 Challenges and Trends on Trust-Based Secure Routing Schemes
4 Future Research Directions
4.1 Energy-Aware Trusted Routing
4.2 Node Dynamics-Based Trusted Routing
5 Conclusion
References
Energy-Efficient Cloud-Edge Collaborative Computing: Joint Task Offloading, Resource Allocation, and Service Caching
1 Introduction
2 Related Work
3 System Model
3.1 Communication Model
3.2 Service Caching Model
3.3 Computing Model
3.4 Problem Formulation
4 Deep Reinforcement Learning Solution
5 Experiment Evaluation
5.1 Simulation Setup
5.2 Simulation Results
6 Conclusion
References
Image Processing Task Offloading in UAV-Assisted MEC System
1 Introduction
2 System Model and Problem Formulation
2.1 Communication Model
2.2 Computation Model
2.3 Problem Formulation
3 Solution
3.1 Markov Decision Process Settings
3.2 DDPG-Based Solution Training
4 Experiments
5 Conclusion
References
EnvAwareLoc: Precision Localization Network Based on the Introduction of Environmental Information
1 Introduction
2 System Model
2.1 Data Preprocessing
2.2 BLocNet: Bluetooth Location Networks
2.3 EALocNet: Locating Networks for Introducing Environmental Information
3 Experimental Results
3.1 Dataset Construction
3.2 Analysis of BLocNet Results
3.3 Analysis of EALocNet Results
4 Conclusion
References
MA-YOLOv8 Algorithm for Mining Area Object Detection Based on High-Resolution Remote Sensing Images
1 Introduction
2 Dataset and Data Preprocessing
2.1 Dataset Collection and Production
2.2 Data Preprocessing
3 Algorithm Improvement
3.1 Model Improvement Based on Spatial Pyramid Pooling Structure
3.2 Model Improvement Based on Cross Stage Local Network Structure
4 Experimental Analysis
5 Summary
References
Addressing Catastrophic Forgetting in Federated Learning on Resource-Constrained Devices: A Feature Replay Approach
1 Introduction
2 Related Work
2.1 Continual Learning and Federated Learning
3 Problem Definition
4 Proposed Method
4.1 Server Workflow
4.2 Client Workflow
5 Experiments
5.1 Datasets
5.2 Settings
5.3 Metrics
5.4 Results and Analysis
6 Conclusion
References
Joint Computation Offloading and Task Caching Strategy for MEC-Enabled IIoT
1 Introduction
2 Related Work
3 System Model
3.1 Communication Model and Computation Model
3.2 Cache Model and Priority Queue Model
3.3 Problem Formulation
4 Problem Solution
4.1 Establishment of MDP
4.2 DDPG-LL Design
5 Performance Evaluation
5.1 Simulation Setting
5.2 Strategies Comparison
5.3 Results Analysis
6 Conclusion
References
An Inverse Retrieval Method via Query Generation for Xiaohongshu's Search Engine
1 Introduction
2 Proposed Retrieval Method
2.1 Classical Retrieval
2.2 Inverse Retrieval
2.3 Document to Query (Doc2Query)
3 Our Released Dataset
3.1 Documents
3.2 Queries
4 Experiments on Public Dataset
4.1 Datasets
4.2 Methods
4.3 Metrics
4.4 Main Results
4.5 Evaluation on Query Generation by Doc2Query
5 Experiments on Internal Dataset
5.1 Offline Experiments
5.2 Online A/B Test
6 Conclusion
References
RREH: Reconstruction Relations Embedded Hashing for Semi-paired Cross-Modal Retrieval
1 Introduction
2 Proposed Method
2.1 Notations
2.2 Reconstruction Factors Learning
2.3 Hash Learning
2.4 Optimization
3 Experiment
3.1 Datasets
3.2 Experimental Settings
3.3 Performance Evaluation
3.4 Parameter Analysis
3.5 Ablation Study
4 Conclusion
References
Exemplar-Free Deep Incremental Hashing for Efficient Image Retrieval
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Preliminaries
3.2 Framework Overview
3.3 Deep Hash Functions
3.4 Exemplar-Free Deep Incremental Hashing Loss
3.5 Optimization
3.6 Out-of-Sample Extension
4 Experiment
4.1 Evaluation Setup
4.2 Accuracy Comparison
4.3 Anti-forgetting Evaluation
4.4 Ablation Study
4.5 Visualization
5 Conclusion
References
Super-Resolution-Based Change Detection Network with Self-attention for Images with Different Resolutions
1 Introduction
2 Related Work
2.1 Super-Resolution Neural Network
2.2 Attention Mechanisms
2.3 Deep-Learning-Based CD Methods
3 Methods
3.1 Model Architecture System
3.2 SR Module with Self-attention
3.3 Improvement of Loss Function
4 Experiments
4.1 Datasets
4.2 Experimental Details and Parameters
4.3 Experimental Results
4.4 Ablation Experiments
5 Conclusion
References
An Optimized Self-representation Subspace Clustering Model Based on Adversarial Autoencoder
1 Introduction
2 Related Works
3 Model Construction and Optimization
3.1 Model Structure
3.2 Loss Function
4 Experiment and Analysis
4.1 Experimental Setup and Evaluation Criteria
4.2 Ablation Study
4.3 Experimental Result Analysis
5 Conclusion
References
Cross-modal Recipe Retrieval with Hierarchical Transformers and Pretrained Food Image Encoder
1 Instruction
2 Relate Work
2.1 Food Computing
2.2 Cross-modal Recipe Retrieval
3 Method
3.1 Problem Definition
4 Experiments
4.1 Experiment Settings
5 Conclusion
References
Secure Federated Learning Scheme Based on Differential Privacy and Homomorphic Encryption
1 Introduction
2 Related Work
3 Method
3.1 Problem Formulation
3.2 Client Update
3.3 DP-Privacy Preservation
3.4 Laplace Mechanism
3.5 CKKS Secure Transmission
3.6 Server Aggregation
3.7 Security Analysis
4 Experiments
4.1 Experiments Settings
4.2 Experiments Results
5 Conclusion
References
SHAF: Semantic-Guided Hierarchical Alignment and Fusion for Composed Image Retrieval
1 Introduction
2 Related Work
3 Method
3.1 Our Model Architecture
3.2 Semantic-Guided Hierarchical Alignment
3.3 Dynamic Feature Fusion
4 Experiments
4.1 Experimental Settings
4.2 Performance Comparison (RQ1)
4.3 Ablation Studies (RQ2)
4.4 Parameter Analysis (RQ3)
4.5 Qualitative Results (RQ4)
5 Conclusion
References
Lightweight Sensor Data Fusion Based on Dynamic Correlation Maintence - A Case Study on Smart Home
1 Introduction
2 Proposed Lightweight Sensor Data Fusion Based on Dynamic Correlation Maintence
2.1 Sensor Grouping Based on Correlation Analysis
2.2 Dynamic Substitution Functions Selection Algorithm for Varying Power
2.3 Dynamic Adjustment Algorithm for Sensor Grouping
3 Smart Home Environment and Experimental Results
3.1 Case Study on Smart Home Environment
3.2 Experiments Setting
3.3 Experimental Comparison with Static Correlation Based Dimension Reduction
3.4 Experimental Comparison with Static Correlation Based Data Reduction
4 Conclusion
References
Semantic Enhancement Network Integrating Label Knowledge for Multi-modal Emotion Recognition
1 Introduction
2 Methodology
2.1 Uni-Modal Representation Learning
2.2 Joint Representation Learning Module
2.3 Decision-Making Module
3 Experiments
3.1 Dataset, Preprocessing and Experiment Setup
3.2 The Comparison of the Experimental Results
3.3 The Visualization of the Confusion Matrix
3.4 Ablation Experiment
4 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken