PART Ⅰ：DIAGNOSIS METHODS IN TRADITIONAL CHINESE MEDICINE

Chapter 1 Introduction

1.1 Diagnosis Methods in Traditional Chinese Medicine

1.1.1 Tongue Diagnosis

1.1.2 Pulse Diagnosis

1.1.3 Breath Odor Diagnosis

1.2 Computerized TCM Diagnosis

1.2.1 Computerized Tongue Diagnosis

1.2.2 Computerized Pulse Diagnosis

1.2.3 Computerized Breath Odor Diagnosis

1.3 Summary

References

PART Ⅱ：COMPUTERIZED TONGUE IMAGE ANALYSIS

Chapter 2 Tongue Image Acquisition and Preprocessing

2.1 Tongue Image Acquisition

2.1.1 Requirement Analysis

2.1.2 System Design and Implementation

2.1.3 Performance Analysis

2.2 Color Correction

2.2.1 Color Correction Algorithms

2.2.2 Evaluation of Correction Algorithms

2.2.3 Discussion

2.3 Summary

References

Chapter 3 Automated Tongue Segmentation

3.1 Bi-Elliptical Deformable Contour

3.1.1 Bi-Elliptical Deformable Template for the Tongue

3.1.2 Combined Model for Tongue Segmentation

3.1.3 Results and Analysis

3.2 Snake with Polar Edge Detector

3.2.1 The Segmentation Algorithm

3.2.2 Experimental Results

3.3 Gabor Magnitude-based Edge Detection and Fast Marching

3.3.1 2D Gabor Magnitude-based Edge Detection

3.3.2 Contour Detection Using Fast Marching and Active Contour Model

3.3.3 Experimental Results

3.4 Summary

References

Chapter 4 Tongue Image Feature Analysis

4.1 Color Feature Analysis

4.1.1 Exploratory Tongue Color Analysis

4.1.2 Statistical Analysis of Tongue Color Distribution

4.2 Tongue Texture Analysis

4.3 Tongue Shape Analysis

4.3.1 Shape Correction

4.3.2 Extraction of Shape Features

4.3.3 Tongue Shape Classification

4.4 Extraction of Other Local Pathological Features

4.4.1 Petechia

4.4.2 Tongue Crack

4.4.3 Tongueprint

4.4.4 Sublingual Veins

4.5 Summary

References

Chapter 5 Computerized Tongue Diagnosis

5.1 Bayesian Network for Computerized Tongue Diagnosis

5.1.1 Quantitative Pathological Features Extraction

5.1.2 Bayesian Networks

5.1.3 Experimental Results

5.2 Diagnosis Based on Hyperspectral Tongue Images

5.2.1 Hyperspectral Tongue Images

5.2.2 The SVM Classifier Applied to Hyperspectral Tongue Images

5.2.3 Experimental Results

5.3 Summary

References

PART Ⅲ：COMPUTERIZED PULSE SIGNAL ANALYSIS

Chapter 6 Pulse Signal Acquisition and Preprocessing

6.1 Pressure Pulse Signal Acquisition

6.1.1 Application Scenario and Requirement Analysis

6.1.2 System Architecture

6.1.3 Multi-Channel Pulse Signals

6.2 Baseline Wander Correction of Pulse Signals

6.2.1 Detecting the Onsets of Pulse Wave

6.2.2 Wavelet Based Cascaded Adaptive Filter

6.2.3 Results on Actual Pulse Signals

6.3 Summary

References

Chapter 7 Feature Extraction of Pulse Signals

7.1 Spatial Feature Extraction

7.1.1 Fiducial Point-based Methods

7.1.2 Approximate Entropy

7.2 Frequency Feature Extraction

7.2.1 Hilbert-Huang Transform

7.2.2 Wavelet and Wavelet Packet Transform

7.3 AR Model

7.4 Gaussian Mixture Model

7.4.1 Two-term Gaussian Model

7.4.2 Feature Selection

7.4.3 FCM Clustering

7.5 Summary

References

Chapter 8 Classification of Pulse Signals

8.1 Pulse Waveform Classification

8.1.1 Modules of Pulse Waveform Classification

8.1.2 The EDFC and GEKC Classifiers

8.1.3 Experimental Results

8.2 Arrhythmic Pulses Derection

8.2.1 Clinical Value of Pulse Rhythm Analysis

8.2.2 Automatic Recognition of Pulse Rhythms

8.2.3 Experimental Results

8.3 Combination of Heterogeneous Features for Pulse Diagnosis

8.3.1 Multiple Kernel Learning

8.3.2 Experimental Results and Discussion

8.4 Summary

References

PART Ⅳ：COMPUTERIZED ODOR SIGNAL ANALYSIS

Chapter 9 Breath Analysis System：Design and Optimization

9.1 Breath Analysis

9.2 Design of Breath Analysis System

9.2.1 Description of the System

9.2.2 Signal Sampling and Preprocessing

9.3 Sensor Selection

9.3.1 Linear Discriminant Analysis

9.3.2 Sensor Selection in Breath Analysis System

9.3.3 Comparison Experiment and Performance Analysis

9.4 Summary

References

Chapter 10 Feature Extraction and Classification of Breath Odor Signals

10.1 Feature Extraction of Odor Signals

10.1.1 Geometry Features

10.1.2 Principal Component Analysis

10.1.3 Wavelet Packet Decomposition

10.1.4 Gaussian Function Representation

10.1.5 Gaussian Basis Representation

10.1.6 Experimental Results

10.2 Common Classifiers for Odor Signal Classification

10.2.1 K Nearest Neighbor

10.2.2 Artificial Neural Network

10.2.3 Support Vector Machine

10.3 Sparse Representation Classification

10.3.1 Data Expression

10.3.2 Test Sample Representation by Training Samples

10.3.3 Samples Sampling Errors

10.3.4 Voting Rules

10.3.5 Identification Steps

10.4 Support Vector Ordinal Regression

10.4.1 Problem Analysis

10.4.2 Basic Idea of Support Vector Regression

10.4.3 Support Vector Ordinal Regression

10.4.4 The Dual Problem

10.4.5 Identification Steps

10.5 Evaluation on Classification methods

10.5.1 Evaluation on SRC

10.5.2 Evaluation on SRC

10.6 Summary

References

Index