Note: Intro -- Preface -- Contents -- Part I: Background -- Chapter 1: Introduction: Computational Pulse Diagnosis -- 1.1 Principle of Pulse Signal -- 1.2 Traditional Pulse Diagnosis -- 1.3 Computational Pulse Signal Analysis -- 1.4 Summary -- References -- Part II: Pulse Signal Acquisition -- Chapter 2: Compound Pressure Signal Acquisition -- 2.1 Introduction -- 2.2 Application Scenario and Requirement Analysis -- 2.3 System Architecture -- 2.3.1 Mechanical Structure -- 2.3.2 Sensor -- 2.3.3 Circuit -- 2.3.4 Summary -- 2.4 System Evaluation -- 2.4.1 Sampled Pulse Signals -- 2.4.2 Computational Pulse Diagnosis -- 2.4.3 Comparisons with Other Pulse Sampling Systems -- 2.5 Summary -- References -- Chapter 3: Pulse Signal Acquisition Using Multi-sensors -- 3.1 Introduction -- 3.2 Framework of the Proposed System -- 3.2.1 Pulse Collecting -- 3.2.2 Pulse Processing and Interaction Design -- 3.3 Design of the Different Sensor Arrays -- 3.3.1 Pressure Sensor -- 3.3.2 Photoelectric Sensor Array -- 3.3.3 Combination of Pressure and Photoelectric Sensor Arrays -- 3.4 Multichannel Optimization -- 3.4.1 Selection of Base Channel -- 3.4.2 Multichannel Selection -- 3.5 The Optimization of Different Sensors Fusion -- 3.6 Experimental Results -- 3.6.1 Experiment 1 -- 3.6.2 Experiment 2 -- 3.7 Summary -- References -- Part III: Pulse Signal Preprocessing -- Chapter 4: Baseline Wander Correction in Pulse Waveforms Using Wavelet-Based Cascaded Adaptive Filter -- 4.1 Introduction -- 4.1.1 Pulse Waveform Analysis -- 4.1.2 Related Works on Baseline Drift Removal -- 4.2 The Proposed CAF -- 4.2.1 The Design of CAF -- 4.2.2 Detection Level of Baseline Drift Using ER -- 4.2.2.1 Why Detect ER -- 4.2.2.2 How to Compute the ER of Pulse Signal -- 4.2.3 The Discrete Meyer Wavelet Filter -- 4.2.3.1 Design of the Discrete Meyer Wavelet Filter. , 4.2.3.2 Performance of Discrete Meyer Wavelet Filter on Pulse Waveform -- 4.2.4 Cubic Spline Estimation Filter -- 4.2.4.1 Detecting Pulse's Onsets -- 4.2.4.2 Cubic Spline Estimation -- 4.3 Simulated Signals: Experimental Results and Analysis -- 4.3.1 Experimental Results of the CAF for Different Baseline Drifts -- 4.3.2 Experimental Results for Different ER Thresholds -- 4.3.3 Experimental Results for Several Typical Pulses -- 4.4 Experimental Results for Actual Pulse Records -- 4.5 Summary -- References -- Chapter 5: Detection of Saturation and Artifact -- 5.1 Introduction -- 5.2 Saturation and Artifact -- 5.2.1 Saturation -- 5.2.2 Artifact -- 5.3 The Detection of Saturation and Artifact -- 5.3.1 The Preprocessing and the Priority -- 5.3.2 Saturation Detection -- 5.3.3 Artifact Detection -- 5.4 Experimental Results -- 5.4.1 Saturation Detection -- 5.4.2 Artifact Detection -- 5.5 Summary -- References -- Chapter 6: Optimized Preprocessing Framework for Wrist Pulse Analysis -- 6.1 Introduction -- 6.2 Description of Pulse Database -- 6.2.1 Data Acquisition -- 6.2.2 Time Domain Characteristic -- 6.2.3 Frequency Domain Characteristic -- 6.3 Proposed Pulse Preprocessing Method -- 6.3.1 Pulse Denoising -- 6.3.2 Interval Selection -- 6.3.3 Baseline Drift Removal -- 6.3.4 Period Segmentation and Normalization -- 6.4 Experiments on Actual Pulse Database -- 6.4.1 Comparison of Pulse Denoising -- 6.4.2 Optimal Segmentation Strategy -- 6.4.3 Preprocessing for Pulse Diagnosis -- 6.5 Summary -- References -- Part IV: Pulse Signal Feature Extraction -- Chapter 7: Arrhythmic Pulse Detection -- 7.1 Introduction -- 7.2 Clinical Value of Pulse Rhythm Analysis -- 7.3 The Approach to Automatic Recognition of Pulse Rhythms -- 7.3.1 Lempel-Ziv Complexity Analysis -- 7.3.2 Definitions and Basic Facts -- 7.3.2.1 Definitions -- 7.3.2.2 Rules -- 7.3.2.3 Lemma. , 7.3.2.4 The Seven Pulse Patterns' Characteristics in Rhythms -- 7.3.3 Automatic Recognition of Pulse Patterns Distinctive in Rhythm -- 7.3.3.1 Preprocessing the Pulse Waveform -- 7.3.3.2 Pulse Interval Extraction and Calculation of its VC and VR -- 7.3.3.3 Symbolizing Pulse Interval Series and Subsequence Extraction -- 7.3.3.4 Arrhythmic Pulse Recognition Based on Lempel-Ziv Complexity Analysis -- 7.4 Experiments -- 7.5 Summary -- References -- Chapter 8: Spatial and Spectrum Feature Extraction -- 8.1 Introduction -- 8.2 Data Acquisition and Preprocessing -- 8.3 Feature Extraction -- 8.3.1 Spatial Feature Extraction of Blood Flow Velocity Signal -- 8.3.2 EMD-Based Spectrum Feature Extraction -- 8.3.2.1 Hilbert-Huang Transform -- 8.3.2.2 Feature Extraction by Hilbert-Huang Transform -- 8.4 Experimental Result and Discussion -- 8.5 Summary -- References -- Chapter 9: Generalized Feature Extraction for Wrist Pulse Analysis: From 1-D Time Series to 2-D Matrix -- 9.1 Introduction -- 9.2 Wrist Pulse Acquisition and Preprocessing Methods -- 9.2.1 Wrist Pulse Acquisition Platform -- 9.2.2 Wrist Pulse Preprocessing -- 9.3 Conventional Pulse Feature -- 9.3.1 Time Domain Feature -- 9.3.2 Frequency Domain Feature -- 9.4 2-D Pulse Feature Extraction -- 9.4.1 Motivation -- 9.4.2 Matrix Description for Pulse Waveforms -- 9.5 Experiments -- 9.5.1 Diabetes Diagnosis -- 9.5.2 Pregnancy Diagnosis -- 9.6 Summary -- References -- Chapter 10: Characterization of Inter-Cycle Variations for Wrist Pulse Diagnosis -- 10.1 Introduction -- 10.2 The Quasiperiodic Pulse Signals -- 10.3 Characterization of Inter-Cycle Variations -- 10.3.1 Preprocessing -- 10.3.2 The Simple Combination Method -- 10.3.3 Multi-scale Entropy -- 10.3.4 The Complex Network Method -- 10.4 Experimental Results -- 10.4.1 Datasets -- 10.4.2 Experiments and Results -- 10.5 Summary -- References. , Part V: Pulse Analysis and Diagnosis -- Chapter 11: Edit Distance for Pulse Diagnosis -- 11.1 Introduction -- 11.2 The Pulse Waveform Classification Modules -- 11.2.1 Pulse Waveform Acquisition -- 11.2.2 Pulse Waveform Preprocessing -- 11.2.3 Feature Extraction and Classification -- 11.3 The EDCK and GEKC Classifiers -- 11.3.1 Edit Distance with Real Penalty -- 11.3.2 DFWKNN and KDFKNN -- 11.3.3 The EDKC Classifier -- 11.3.4 The GEKC Classifier -- 11.4 Experimental Results -- 11.5 Summary -- References -- Chapter 12: Modified Gaussian Models and Fuzzy C-Means -- 12.1 Introduction -- 12.2 Wrist Pulse Signal Collection and Preprocessing -- 12.3 Feature Extraction and Feature Selection -- 12.3.1 A Two-Term Gaussian Model -- 12.3.2 Feature Selection -- 12.4 FCM Clustering -- 12.5 Experimental Result -- 12.6 Summary -- References -- Chapter 13: Modified Auto-regressive Models -- 13.1 Introduction -- 13.2 The Proposed Method -- 13.2.1 Feature Extraction via AR Modelling -- 13.2.2 SVM Classification -- 13.2.3 The Selection of Doppler Ultrasonic Diagnostic Parameters -- 13.3 Experimental Results -- 13.3.1 Data Description -- 13.3.2 Experimental Results by Using the AR Features -- 13.3.3 Experimental Results by Using the Doppler Parameters as Additional Features -- 13.4 Conclusions and Future Work -- References -- Chapter 14: Combination of Heterogeneous Features for Wrist Pulse Blood Flow Signal Diagnosis via Multiple Kernel Learning -- 14.1 Introduction -- 14.2 Pulse Signal Feature Extraction -- 14.2.1 Nontransform-Based Feature Extraction -- 14.2.1.1 AR Model -- 14.2.1.2 Time Series Matching -- 14.2.2 Transform-Based Feature Extraction -- 14.3 Pulse Signal Classification Based on MKL -- 14.3.1 Kernel Functions -- 14.3.2 SimpleMKL -- 14.4 Experimental Results and Discussion -- 14.4.1 Classification Experimental of Wrist Blood Flow Signal. , 14.4.2 Other Pulse Classification Application -- 14.5 Summary -- References -- Part VI: Comparison and Discussion -- Chapter 15: Comparison of Three Different Types of Wrist Pulse Signals -- 15.1 Introduction -- 15.2 Measurement Mechanism -- 15.2.1 Measurement Mechanism of Pressure Sensors -- 15.2.2 Measurement Mechanism of Photoelectric Sensors -- 15.2.3 Measurement Mechanism of Ultrasonic Sensors -- 15.3 Dependency and Complementarity -- 15.3.1 Assumptions -- 15.3.2 Relationship Among Blood Velocity, Radius, and Pressure in Steady Laminar Flow -- 15.3.3 Influence of Physiological and Pathological Factors -- 15.3.4 Summary -- 15.4 Case Studies -- 15.4.1 Method -- 15.4.2 Diabetes Experiment -- 15.4.3 Arteriosclerosis Experiment -- 15.5 Summary -- References -- Chapter 16: Comparison Between Pulse and ECG -- 16.1 Introduction -- 16.2 Methods -- 16.2.1 Analysis of ECG and Wrist Pulse Signals -- 16.2.2 Acquisition of ECG and Wrist Pulse Signal -- 16.2.3 Construction of the Dataset -- 16.2.4 Entropy-Based Complexity Analysis -- 16.2.5 Classification Accuracy and Statistical Test -- 16.2.5.1 Feature Extraction of Wrist Pulse Blood Flow Signal -- 16.2.5.2 Feature Extraction of ECG Signal -- 16.2.5.3 Classifiers -- 16.2.5.4 McNemar Test -- 16.3 Results -- 16.3.1 Comparison of Complexity Measures -- 16.3.2 Comparison of Classification Performance -- 16.3.3 Typical Examples of Wrist Pulse Blood Flow and ECG Signals -- 16.3.4 Classification Accuracy and McNemar Test -- 16.4 Summary -- References -- Chapter 17: Discussion and Future Work -- 17.1 Recapitulation -- 17.2 Future Work -- References -- Index.