Artificial Intelligence and Smart Vehicles : First International Conference, ICAISV 2023, Tehran, Iran, May 24-25, 2023, Revised Selected Papers

✍ Scribed by Mehdi Ghatee; S. Mehdi Hashemi

• Publisher: Springer Nature Switzerland
• Year: 2023
• Tongue: English
• Leaves: 230
• Series: Communications in Computer and Information Science
• Edition: 1
• Category: Library

✦ Synopsis

This book constitutes the refereed proceedings of the First International Conference on Artificial Intelligence and Smart Vehicles, ICAISV 2023, held in Tehran, Iran, during May 24-25, 2023.
The 14 full papers included in this book were carefully reviewed and selected from 93 submissions. They were organized in topical sections as follows: machine learning, data mining, machine vision, image processing, signal analysis, decision support systems, expert systems, and their applications in smart vehicles.

✦ Table of Contents

Preface
Organization
Contents
Local and Global Contextual Features Fusion for Pedestrian Intention Prediction
1 Introduction
2 Related Works
3 The Proposed Methodology
3.1 Global Context
3.2 Local Context
3.3 Body Pose
3.4 Model Architecture
4 Experiments
4.1 Dataset
4.2 Implementation Details
4.3 Quantitative and Qualitative Evaluation
5 Conclusion
References
Routes Analysis and Dependency Detection Based on Traffic Volume: A Deep Learning Approach
1 Introduction
2 Literature Review
3 Methods
3.1 CNN
3.2 LSTM
3.3 Proposed Model
3.4 Describing the Route of the Road Network Using Graph Theory
3.5 Definition of the Database Related to the Amount of Traffic on the Routes
3.6 Forecasting the Next Routes Using Deep Learning
3.7 Analyzing Distance Matrices and Determining the Impact Rate
4 Experiments and Results
4.1 Analysis and Investigation
4.2 Comparing CNN and LSTM Models
4.3 Comparing with the Related Works
5 Conclusion
References
Road Sign Classification Using Transfer Learning and Pre-trained CNN Models
1 Introduction
2 Related Works
3 Methodology
3.1 Data Preprocessing
3.2 Transfer Learning
3.3 Method Details
4 Results and Analysis
4.1 Performance and Metrics
4.2 Class Metrics
4.3 Accuracy and Loss Plots
4.4 Confusion Matrix
5 Conclusion
6 Future Works
References
Improving Safe Driving with Diabetic Retinopathy Detection
1 Introduction
2 Literature Review
3 Proposed Method
3.1 ResNet Architecture
3.2 Baseline Model Description
3.3 Proposed Model Improvement
4 Experiments and Results
4.1 Dataset
4.2 Evaluation Metric
4.3 Experimental Results
5 Conclusions
References
Convolutional Neural Network and Long Short Term Memory on Inertial Measurement Unit Sensors for Gait Phase Detection
1 Introduction
2 Experimental Setup and Data Collection
2.1 Experimental Setup
2.2 Segmentation and Labeling
3 Proposed Architecture
3.1 ``Improved Sequence Learning with RNN and CNN''
3.2 Efficient Hyperparameter Tuning for CNN-LSTM Classifier
4 Experimental Results
4.1 Performance Evaluation
4.2 Results and Discussion
5 Conclusion
References
Real-Time Mobile Mixed-Character License Plate Recognition via Deep Learning Convolutional Neural Network
1 Introduction
2 Related Works
2.1 License Plate Detection
2.2 Character Segmentation
2.3 Character Recognition
3 Proposed Models
3.1 Data Preparation
3.2 Training Dataset for LP Detection
4 Results and Discussion
4.1 Detection
4.2 Recognition
5 Conclusions
References
Evaluation of Drivers’ Hazard Perception in Simultaneous Longitudinal and Lateral Control of Vehicle Using a Driving Simulator
1 Introduction
2 Hazard Perception
2.1 Observation
2.2 Environmental Cognition
2.3 Decision Making
2.4 Decision Implementation
3 Driving Motivations: Determinative Behavioral Factors
4 Detecting Algorithm of Driving Behavior Anomalies
4.1 Hazard Functions
5 Scenarios
6 Hazard Perception Assessment and Behavioral Abnormalities
6.1 Perceptual Anomalies in Reaction Time
6.2 Decision-Making Anomalies
6.3 Decision-Implementation Anomalies (Low-Gain)
6.4 Decision-Implementation Anomalies (High-Gain)
7 Conclusion
References
Driver Identification by an Ensemble of CNNs Obtained from Majority-Voting Model Selection
1 Introduction
2 Proposed System
2.1 Data Pre-processing
2.2 Identification
2.3 Network Training Method
3 Experimental Results
3.1 Sensitivity Analysis on Learning Models
3.2 Sensitivity Analysis on Segmentation Window Length
3.3 Sensitivity Analysis on Decision Window Length
3.4 Sensitivity Analysis on Training Data Length
4 Performance of the Proposed Model
5 Conclusion
References
State-of-the-Art Analysis of the Performance of the Sensors Utilized in Autonomous Vehicles in Extreme Conditions
1 Introduction
2 Theoretical Definitions
2.1 Automation Levels and Architecture
2.2 Dataset
3 Related Works
4 Research Analysis
4.1 The Sensor Ecosystem for AVs
4.2 Autonomous Driving
4.3 AV Performance Under Challenging Circumstances
4.4 Sensor Fusion
5 Discussion
6 Conclusion
References
Semantic Segmentation Using Events and Combination of Events and Frames
1 Introduction
2 Related Work
3 The Proposed Segmentation Models
3.1 Event-Based Semantic Segmentation Model
3.2 Event-Frame-Based Semantic Segmentation Model
4 Experiment
4.1 Our Networks on DDD17 Dataset
4.2 Our Networks on Event-Scape Dataset
5 Conclusion
References
Deep Learning-Based Concrete Crack Detection Using YOLO Architecture
1 Introduction
2 YOLO Network
3 Dataset Preparation and Evaluation Metrics
4 Experimental Setup
5 Results and Discussion
6 Conclusions
References
Generating Control Command for an Autonomous Vehicle Based on Environmental Information
1 Introduction
2 Related Works
3 Implementation Details
3.1 Data Preprocessing
3.2 Augmentation
3.3 Network Architecture
3.4 Loss Function and Optimization
4 Results and Discussion
4.1 Ablation Studies
5 Conclusion
References
Fractal-Based Spatiotemporal Predictive Model for Car Crash Risk Assessment
1 Introduction
2 Methodology
2.1 Fractal Theory
2.2 Hurst Exponent
2.3 Singular Value Decomposition
2.4 Deep Learning
3 Results
3.1 Maximum Mean Discrepancy
4 Conclusion
References
Author Index

✦ Subjects

Computer Science; Artificial Intelligence; Computer Imaging, Vision, Pattern Recognition and Graphics; Signal, Image and Speech Processing; Computer Communication Networks; Machine Learning