Intro
Preface
Organization
Contents
Data Mining and Machine Learning
Rule Induction of Automotive Historic Styles Using Decision Tree Classifier
1 Introduction
2 Artificial Intelligence and Style
2.1 Research Relevant to the Application of AI in Design
2.2 The Definition and Classification of Design
2.3 Potential of Using Data Mining and Decision Tree to Classify Styles
3 Method
3.1 Choice of Features and Style
3.2 Choice of Case Study
3.3 Classification Methods and Tools
4 Results
4.1 Decision Tree Classification Model Diagram

4.2 The Average Accuracy of Ten Decision Trees
4.3 Correlation Between Design Features and Accuracy
4.4 The Accumulated Number of Statistical Design Features
4.5 Entropy, Information Gain and Gain Ratio
5 Discussion
5.1 Case Study of Automotive-Style Classification
5.2 Summary
6 Conclusion
References
Deep Learning for Multilingual POS Tagging
1 Introduction
2 Related Work
2.1 Deep Neural Network
2.2 Max-Margin Tensor Neural Networks
2.3 Convolutional Neural Network
2.4 Recurrent Neural Network
3 Part-of-Speech Taggers
4 Experiments

4.1 Data Set
4.2 Model Setup
4.3 Results
5 Conclusion
References
Study of Machine Learning Techniques on Accident Data
1 Introduction
2 Dataset
3 The Methodology
3.1 Clustering to Subgroup Similar Types of Accidents
3.2 Classification/Predictive Models for Each Cluster
4 Experiments, Result Analysis and Discussion
4.1 Results of Cluster Analysis
4.2 Selecting Influential Attributes by Random Forest Analysis
4.3 Classification and Rule Generation
4.4 Rule Generation Using PART
5 Conclusion and Possible Future Work
References

Soil Analysis and Unconfined Compression Test Study Using Data Mining Techniques
1 Introduction
2 Related Work
3 Dataset
3.1 Mymensingh
3.2 Rangamati
4 Methodology and Results
4.1 Models
4.2 Accuracy Metric
4.3 Results
5 Conclusion
References
Self-sorting of Solid Waste Using Machine Learning
1 Introduction
1.1 Waste Recycling
1.2 Literature Review of Self-sorting Bins
2 Self-sorting Bin Design
2.1 Mechanical Design
2.2 Electrical Design
2.3 Sensors
3 Software Architecture
3.1 Classification Models
3.2 Combined Classifier

4 Classifiers Performance
5 Conclusion
References
Clustering Algorithms in Mining Fans Operating Mode Identification Problem
1 Introduction
2 Problem Description
3 Description of the Industrial Fan Station
4 Methodology
4.1 Source Data Characteristics and Preprocessing
4.2 Algorithms Description
5 Applications to Real-Life Data and Algorithms Comparison
6 Conclusions
References
K-Means Clustering for Features Arrangement in Metagenomic Data Visualization
1 Introduction
2 Related Work
3 Features Clustering in Synthetic Metagenomic Images