Breath Analysis for Medical Applications

ISBN-13: 9789811043215 / Angielski / Twarda / 2017 / 309 str.

David Zhang; Dongmin Guo; Ke Yan

Opis

This book describes breath signal processing technologies and their applications in medical sample classification and diagnosis. First, it provides a comprehensive introduction to breath signal acquisition methods, based on different kinds of chemical sensors, together with the optimized selection and fusion acquisition scheme. It then presents preprocessing techniques, such as drift removing and feature extraction methods, and uses case studies to explore the classification methods. Lastly it discusses promising research directions and potential medical applications of computerized breath diagnosis. It is a valuable interdisciplinary resource for researchers, professionals and postgraduate students working in various fields, including breath diagnosis, signal processing, pattern recognition, and biometrics.

Spis treści

PART I: Background

Chapter 1: Introduction

1.1 Background

1.2 Motivation of Breath Analysis

1.3 Relative Technologies

1.4 Outline of this Book

REFERENCES

Chapter 2: Literature Review

2.1 Introduction

2.2 Development of Breath Analysis

2.3 Breath Analysis by GC

2.4 Breath Analysis by E-nose

2.5 Summary

REFERENCES

PART II: Breath Acquisition Systems

Chapter 3: A Novel Breath Acquisition System Design

3.1 Introduction

3.2 Breath Analysis

3.3 Description of the System 

3.4 Experiments 

3.5 Results and Discussion 

3.6 Summary

REFERENCES

Chapter 4: An LDA Based Sensor Selection Approach

4.1 Introduction

4.2 LDA based Approach: Definition and Algorithm

4.3 Sensor Selection 

4.4 Comparison Experiment and Performance Analysis

4.5 Summary

REFERENCES

Chapter 5: Sensor Evaluation in a Breath Acquisition System

5.1 Introduction

5.2 System Description

5.3 Sensor Evaluation Methods 

5.4 Experiments and Discussion

5.5 Summary

REFERENCES

PART III: Breath Signal Pre-Processing

Chapter 6: Improving the Transfer Ability of Prediction Models

6.1 Introduction

6.2 Methods Design

6.3 Experimental Details 

6.4 Results and Discussion

6.5 Summary

REFERENCES

Chapter 7: Learning Classification and Regression Models for Breath Data Drift based on Transfer Samples

7.1 Introduction

7.2 Related Work

7.3 Transfer-Sample-Based Multitask Learning (TMTL) 

7.4 Selection of Transfer Samples

7.5 Experiments

7.6 Summary

REFERENCES

Chapter 8: A Transfer Learning Approach with Autoencoder for Correcting Instrumental Variation and Time-Varying Drift

8.1 Introduction

8.2 Related Work

8.3 Drift Correction Autoencoder (DCAE) 

8.4 Selection of Transfer Samples

8.5 Experiments

8.6 Summary

REFERENCES

Chapter 9: A New Drift Correction Algorithm by Maximum Independence Domain Adaptation

9.1 Introduction

9.2 Related work

9.3 Proposed Method

9.4 Experiments

9.5 Summary

REFERENCES

PART IV: Feature Extraction and Classification

Chapter 10: An Effective Feature Extraction Method for Breath Analysis

10.1 Introduction

10.2 Breath Analysis System and Breath Samples

10.3 Feature Extraction based on Curve-Fitting Models 

10.4 Experiments and Analysis

10.5 Summary

REFERENCES

Chapter 11: Feature Selection and Analysis on Correlated Breath Data

11.1 Introduction

11.2 SVM-RFE

11.3 Improved SVM-RFE with Correlation Bias Reduction 

11.4 Datasets and Feature Extraction

11.5 Results and Discussion

11.6 Summary

REFERENCES

Chapter 12: Breath Sample Identification by Sparse Representation-based Classification

12.1 Introduction

12.2 Sparse Representation Classification

12.3 Overall Procedure 

12.4 Experiments and Results

12.5 Summary

REFERENCES

PART V: Medical Applications

Chapter 13: Monitor Blood Glucose Level via Sparse Representation Approach

13.1 Introduction

13.2 System Description and Breath Signal Acquisition

13.3 Sparse Representation Classification 

13.4 Experiments and Results

13.5 Summary

REFERENCES

Chapter 14: Diabetics Detection by Means of Breath Signal Analysis

14.1 Introduction

14.2 Breath Analysis System

14.3 Breath Sample Classification and Decision Making

14.4 Experiments 

14.5 Results and Discussion 

14.6 Summary

REFERENCES

Chapter 15: A Breath Analysis System for Diabetes Screening and Blood Glucose Level Prediction

15.1 Introduction

15.2 System Description

15.3 System Optimization

15.4 Experiments with Simulated Samples 

15.5 Experiments with Breath Samples

15.6 Summary

REFERENCES

<

Chapter 16: Book Review and Future Work

16.1 Book Recapitulation

16.2 Future Work

O autorze

David Zhang graduated in Computer Science from Peking University. He received his MSc in 1982 and his PhD in 1985 in Computer Science from the Harbin Institute of Technology (HIT), respectively. From 1986 to 1988 he was a Postdoctoral Fellow at Tsinghua University and then an Associate Professor at the Academia Sinica, Beijing. In 1994 he received his second PhD in Electrical and Computer Engineering from the University of Waterloo, Ontario, Canada. He is a Chair Professor since 2005 at the Hong Kong Polytechnic University where he is the Founding Director of the Biometrics Research Centre (UGC/CRC) supported by the Hong Kong SAR Government in 1998. He is Founder and Editor-in-Chief, International Journal of Image and Graphics (IJIG); Founder and Series Editor, Springer International Series on Biometrics (KISB); Organizer, the 1^st International Conference on Biometrics Authentication (ICBA); Associate Editor of more than ten international journals including IEEE Transactions and so on. He was selected as a Highly Cited Researcher in Engineering by Thomson Reuters in 2014, 2015 and 2016, respectively. Professor Zhang is a Croucher Senior Research Fellow, Distinguished Speaker of the IEEE Computer Society, and a Fellow of both IEEE and IAPR.

Dongmin Guo received her B.S. and M.S. degrees at School of Automation, Northwestern Polytechnical University Xi'an, China in 2003 and 2006, respectively and received her Ph.D. degree at the Hong Kong Polytechnic University, Hong Kong, in 2011. She is currently working as a research associate in Radiology Department, Wake Forest University Health Sciences. Her research interests include bioinformatics and machine learning.

Ke Yan received his B.S. and Ph.D. degrees both from the Department of Electronic Engineering, Tsinghua University, Beijing, China. He was the winner of the 2016 Tsinghua University Excellent Doctoral Dissertation Award. He is currently a postdoctoral fellow in the Lab of Diagnostic Radiology Research, National Institutes of Health, USA. He is studying deep learning methods to analyze medical images. His research interests include computer vision, machine learning, and their biomedical applications.