医学生物识别 数字化中医数据分析 英文版PDF|Epub|txt|kindle电子书版本网盘下载

医学生物识别 数字化中医数据分析 英文版PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

PART Ⅰ：DIAGNOSIS METHODS IN TRADITIONAL CHINESE MEDICINE3

Chapter 1 Introduction3

1.1 Diagnosis Methods in Traditional Chinese Medicine3

1.1.1 Tongue Diagnosis3

1.1.2 Pulse Diagnosis5

1.1.3 Breath Odor Diagnosis6

1.2 Computerized TCM Diagnosis7

1.2.1 Computerized Tongue Diagnosis7

1.2.2 Computerized Pulse Diagnosis11

1.2.3 Computerized Breath Odor Diagnosis14

1.3 Summary17

References17

PART Ⅱ：COMPUTERIZED TONGUE IMAGE ANALYSIS29

Chapter 2 Tongue Image Acquisition and Preprocessing29

2.1 Tongue Image Acquisition29

2.1.1 Requirement Analysis31

2.1.2 System Design and Implementation33

2.1.3 Performance Analysis43

2.2 Color Correction49

2.2.1 Color Correction Algorithms51

2.2.2 Evaluation of Correction Algorithms53

2.2.3 Discussion61

2.3 Summary67

References68

Chapter 3 Automated Tongue Segmentation73

3.1 Bi-Elliptical Deformable Contour73

3.1.1 Bi-Elliptical Deformable Template for the Tongue74

3.1.2 Combined Model for Tongue Segmentation78

3.1.3 Results and Analysis84

3.2 Snake with Polar Edge Detector91

3.2.1 The Segmentation Algorithm91

3.2.2 Experimental Results99

3.3 Gabor Magnitude-based Edge Detection and Fast Marching104

3.3.1 2D Gabor Magnitude-based Edge Detection105

3.3.2 Contour Detection Using Fast Marching and Active Contour Model109

3.3.3 Experimental Results111

3.4 Summary114

References114

Chapter 4 Tongue Image Feature Analysis117

4.1 Color Feature Analysis117

4.1.1 Exploratory Tongue Color Analysis118

4.1.2 Statistical Analysis of Tongue Color Distribution124

4.2 Tongue Texture Analysis143

4.3 Tongue Shape Analysis144

4.3.1 Shape Correction144

4.3.2 Extraction of Shape Features149

4.3.3 Tongue Shape Classification153

4.4 Extraction of Other Local Pathological Features158

4.4.1 Petechia158

4.4.2 Tongue Crack160

4.4.3 Tongueprint160

4.4.4 Sublingual Veins161

4.5 Summary162

References163

Chapter 5 Computerized Tongue Diagnosis167

5.1 Bayesian Network for Computerized Tongue Diagnosis167

5.1.1 Quantitative Pathological Features Extraction167

5.1.2 Bayesian Networks169

5.1.3 Experimental Results171

5.2 Diagnosis Based on Hyperspectral Tongue Images178

5.2.1 Hyperspectral Tongue Images179

5.2.2 The SVM Classifier Applied to Hyperspectral Tongue Images180

5.2.3 Experimental Results183

5.3 Summary186

References187

PART Ⅲ：COMPUTERIZED PULSE SIGNAL ANALYSIS191

Chapter 6 Pulse Signal Acquisition and Preprocessing191

6.1 Pressure Pulse Signal Acquisition191

6.1.1 Application Scenario and Requirement Analysis192

6.1.2 System Architecture193

6.1.3 Multi-Channel Pulse Signals201

6.2 Baseline Wander Correction of Pulse Signals206

6.2.1 Detecting the Onsets of Pulse Wave207

6.2.2 Wavelet Based Cascaded Adaptive Filter209

6.2.3 Results on Actual Pulse Signals221

6.3 Summary223

References224

Chapter 7 Feature Extraction of Pulse Signals227

7.1 Spatial Feature Extraction227

7.1.1 Fiducial Point-based Methods227

7.1.2 Approximate Entropy229

7.2 Frequency Feature Extraction230

7.2.1 Hilbert-Huang Transform230

7.2.2 Wavelet and Wavelet Packet Transform232

7.3 AR Model234

7.4 Gaussian Mixture Model236

7.4.1 Two-term Gaussian Model236

7.4.2 Feature Selection240

7.4.3 FCM Clustering242

7.5 Summary242

References243

Chapter 8 Classification of Pulse Signals245

8.1 Pulse Waveform Classification245

8.1.1 Modules of Pulse Waveform Classification246

8.1.2 The EDFC and GEKC Classifiers251

8.1.3 Experimental Results255

8.2 Arrhythmic Pulses Derection257

8.2.1 Clinical Value of Pulse Rhythm Analysis257

8.2.2 Automatic Recognition of Pulse Rhythms259

8.2.3 Experimental Results272

8.3 Combination of Heterogeneous Features for Pulse Diagnosis274

8.3.1 Multiple Kernel Learning275

8.3.2 Experimental Results and Discussion279

8.4 Summary282

References283

PART Ⅳ：COMPUTERIZED ODOR SIGNAL ANALYSIS289

Chapter 9 Breath Analysis System：Design and Optimization289

9.1 Breath Analysis289

9.2 Design of Breath Analysis System291

9.2.1 Description of the System291

9.2.2 Signal Sampling and Preprocessing296

9.3 Sensor Selection299

9.3.1 Linear Discriminant Analysis299

9.3.2 Sensor Selection in Breath Analysis System304

9.3.3 Comparison Experiment and Performance Analysis314

9.4 Summary317

References317

Chapter 10 Feature Extraction and Classification of Breath Odor Signals321

10.1 Feature Extraction of Odor Signals321

10.1.1 Geometry Features322

10.1.2 Principal Component Analysis324

10.1.3 Wavelet Packet Decomposition324

10.1.4 Gaussian Function Representation325

10.1.5 Gaussian Basis Representation331

10.1.6 Experimental Results334

10.2 Common Classifiers for Odor Signal Classification336

10.2.1 K Nearest Neighbor337

10.2.2 Artificial Neural Network337

10.2.3 Support Vector Machine337

10.3 Sparse Representation Classification338

10.3.1 Data Expression338

10.3.2 Test Sample Representation by Training Samples339

10.3.3 Samples Sampling Errors340

10.3.4 Voting Rules341

10.3.5 Identification Steps342

10.4 Support Vector Ordinal Regression342

10.4.1 Problem Analysis342

10.4.2 Basic Idea of Support Vector Regression343

10.4.3 Support Vector Ordinal Regression344

10.4.4 The Dual Problem345

10.4.5 Identification Steps346

10.5 Evaluation on Classification methods347

10.5.1 Evaluation on SRC347

10.5.2 Evaluation on SRC351

10.6 Summary355

References355

Index359