內容大鋼
The motivation for this textbook started with the successful practice of machine learning in intelligent transportation systems. This book is intended to cover the basic concepts, typical machine learning algorithms and specific applications to transportation systems. This textbook focuses on typical machine learning algorithms, including feature engineering, instance -based learning, decision tree learning, support vector machine, neural networks, ensemble learning, outlier mining, clustering, imbalanced data classification, model evaluation and model interpretation.
目錄
Chapter 1 Introduction to Machine Learning
1.1 Definition of Machine Learning
1.2 History of Machine Learning
1.2.1 Artificial Intelligence, Machine Learning, and Deep Learning
1.2.2 Fields Related to Machine Learning
1.3 Workflow of Machine Learning
1.4 Types of Machine Learning Algorithms
1.4.1 Supervised Learning
1.4.2 Unsupervised Learning
1.4.3 Semi-supervised Learning
1.4.4 Reinforced Learning
1.5 Organization of the Textbook
1.6 Summary
Chapter 2 Feature Engineering
2.1 Data Normalization
2.1.1 Min-max Normalization
2.1.2 Standard Normalization
2.2 Data Discretization
2.2.1 Binning
2.2.2 Clustering Analysis
2.2.3 Entropy-based Discretization
2.2.4 Correlation Analysis
2.3 Feature Selection
2.3.1 Filter Feature Selection
2.3.2 Wrapper Feature Selection
2.3.3 Embedded Methods
2.4 Feature Extraction
2.4.1 Principal Components Analysis
2.4.2 Linear Discriminant Analysis
2.4.3 Autoencoder
2.5 Summary
Chapter 3 Instance-Based Learning
3.1 Overview of IBL
3.2 Components of KNN
3.2.1 Measure the Similarity between Instances
3.2.2 How to Choose K
3.2.3 Assign the Class Label
3.2.4 Time Complexity
3.3 Variants of KNN
3.3.1 Attribute Weighted KNN
3.3.2 Distance Weighted KNN
3.4 Strengths and Weaknesses of KNN
Chapter 4 Decision Tree Learning
4.1 Decision Tree Representation
4.1.1 Component of Decision Tree
4.1.2 How to use Decision Trees for Classification?
4.1.3 How to Generate Rules from Decision Trees?
4.1.4 Popular Algorithms to Generate Decision Trees
4.2 ID3 Algorithm
4.2.1 Select the best Attribute
4.2.2 Information Gain
4.2.3 Information Gain for Continuous-valued Attributes
4.2.4 Pseudoeode of ID3
4.3 C4.5 Algorithm
4.4 CART Algorithm
4.4.1 Gini Index
4.4.2 Binary Split Point for Muhivalued Attribute
4.4.3 Flowchart of Generating Tree
4.4.4 Develop Regression Trees by CART Algorithm
4.5 Overfitting and Tree pruning
4.5.1 Overfitting
4.5.2 Pruning Decision Trees
4.6 Pros and Cons of Decision Trees
……
Chapter 5 Support Vector Machines
Chapter 6 Neural Networks
Chapter 7 Ensemble Learning
Chapter 8 Outlier Mining
Chapter 9 Clustering
Chapter 10 Imbalanced Data Classification
Chapter 11 Model Evaluation
Chapter 12 Model Interpretation
Chapter 13 Application of Machine Learning in Transportation
Chapter 14 Course Projects
[