Front Cover

U-Healthcare Monitoring Systems: Volume 1: Design and Applications

Copyright

Contents

Contributors

Preface

Chapter 1: Wearable U-HRM device for rural applications

1. Introduction

2. U-Healthcare System in India

3. Application

4. Open Issues and Problems

5. Requirements of a Healthcare System

6. Requirement of Wearable Devices

7. Implementation

8. Measurement of Heart Rate and Body Temperature

9. Discussion

10. Conclusion and Future Trends

Glossary

References

Chapter 2: A robust framework for optimum feature extraction and recognition of P300 from raw EEG

1. Introduction

2. Literature Survey

3. The Framework

3.1. Initialization

3.2. Model Setup

3.2.1. Preprocessors

3.2.2. Custom epoch extractor (Cepex)

3.3. Postprocessor

3.4. Classification

4. Results and Discussion

4.1. The Dataset

4.2. Framework Results

4.2.1. Preprocessing

4.2.2. Postprocessing

4.2.3. Classification

4.2.4. Performance comparison

4.2.5. Open source implementation

5. Conclusion and Future Work

References

Chapter 3: Medical image diagnosis for disease detection: A deep learning approach

1. Introduction

1.1. Related Work

2. Requirement of Deep Learning Over Machine Learning

2.1. Fundamental Deep Learning Architectures

2.1.1. Multilayer Perceptron

2.1.2. Deep Belief Networks

2.1.3. Stacked Auto-Encoder

2.1.4. Convolution Neural Networks

Convolution architecture

Convolution layers

Stride and pooling layers

Fully connected

2.1.5. Recurrent Neural Network

How does LSTM improve the RNN?

3. Implementation Environment

3.1. Toolkit Selection/Evaluation Criteria [13]

3.2. Tools and Technology Available for Deep Learning [13]

3.3. Deep Learning Framework Popularity Levels [14]

4. Applicability of Deep Learning in Field of Medical Image Processing [15]

4.1. Current Research Applications in the Field of Medical Image Processing

5. Hybrid Architectures of Deep Learning in the Field of Medical Image Processing [17]

6. Challenges of Deep Learning in the Fields of Medical Imagining [17]

7. Conclusion

References

Further Reading

Chapter 4: Reasoning methodologies in clinical decision support systems: A literature review

1. Introduction

2. Methods

2.1. Research Questions

2.2. Selection Criteria

2.3. Search Strategy

3. Literature Review and Results

3.1. Paper Screening

3.2. Selecting the Most Relevant Papers

3.3. Extracting and Analyzing Concepts

3.3.1. Rule-based reasoning

3.3.2. Ontology reasoning

3.3.3. Ontology-based fuzzy decision support system

3.3.4. Case-based reasoning

3.4. Current Challenges and Future Trends

4. Conclusion

References

Chapter 5: Embedded healthcare system for day-to-day fitness, chronic kidney disease, and congestive heart failure

1. Ubiquitous Healthcare and Present Chapter

2. Introduction

3. Frequency-Dependent Behavior of Body Composition

4. Bioimpedance Analysis for Estimation of Day-to-Day Fitness and Chronic Diseases

5. Measurement System for Body Composition Analysis Using Bioimpedance Principle

5.1. Measurement Electrodes

5.2. AFE4300 Body Composition Analyzer

5.3. Statistical Analysis

5.4. Validation of Developed Model

6. Database Generation

7. Predictive Regression Model for Day-to-Day Fitness

8. Predictive Regression Model for CKD

9. Predictive Regression Model for CHF

10. Discussion

11. Conclusion

References

Chapter 6: Comparison of multiclass and hierarchical CAC design for benign and malignant hepatic tumors

1. Introduction

2. Materials and Methods

2.1. Dataset Collection

2.2. Data Set Description

2.3. Data Collection Protocol

2.4. ROIs Selection

2.5. ROI Size Selection

2.6. Proposed CAC System Design

2.7. Feature Extraction Module

2.8. Classification Module

2.8.1. SSVM classifier

3. Results

3.1. Experiment 1: To Evaluate the Potential of the Three-Class SSVM Classifier Design for the Characterization of Benign ...

3.2. Experiment 2: To Evaluate the Potential of SSVM-Based Hierarchical Classifier Design for Characterization Between Be ...

3.3. Experiment 3: Performance Comparison of SSVM-Based Three-Class Classifier Design and SSVM-Based Hierarchical Classif ...

4. Discussion and Conclusion

References

Further Reading

Chapter 7: Ontology enhanced fuzzy clinical decision support system

1. Introduction

2. Problem Description

3. Related Work

4. The Combining of Ontology and Fuzzy Logic Frameworks

5. System Architecture and Research Methodology

5.1. Knowledge Acquisition

5.2. Semantic Modeling

5.3. The Fuzzy Modeling

5.3.1. Raw EHR data preprocessing

5.3.2. Features definition and fuzzification

5.3.3. Features selection and DT induction

5.4. Knowledge Reasoning

5.4.1. Initial fuzzy knowledge base construction

5.4.2. Enhancement of the generated fuzzy knowledge

5.4.3. The inference engine

5.4.4. The defuzzification process

5.4.5. Framework evaluation

6. Conclusion

References

Further Reading

Chapter 8: Improving the prediction accuracy of heart disease with ensemble learning and majority voting rule

1. Introduction

2. Review of Related Works

3. Ensemble Learning Systems

3.1. Diversity

3.2. Training Ensemble Members

3.3. Combining Ensemble Members

4. Materials and Methods

4.1. Logistic Regression

4.2. Multilayer Perceptron

4.3. Naïve Bayes

4.4. Combining Classifiers Using Majority Vote Rule

4.5. Performance Metrics

5. Result and Discussion

6. Conclusion and Future Directions

References

Further Reading

Chapter 9: Machine learning for medical diagnosis: A neural network classifier optimized via the directed bee colony opti ...

1. Introduction

2. Neural Network Dynamics

3. Directed Bee Colony Optimization Algorithm

4. Experimental Setup

5. Result and Discussion

6. Conclusion

References

Further Reading

Chapter 10: A genetic algorithm-based metaheuristic approach to customize a computer-aided classification system f

1. Introduction

2. Methodology for Designing a CAD System for Diagnosis of Abnormal Mammograms

2.1. Image Data Set Description

2.2. Enhancement Methods

2.2.1. Alpha trimmed mean filter

2.2.2. Contrast adjustment

2.2.3. Histogram equalization

2.2.4. Contrast limited adaptive histogram equalization

2.2.5. Recursive mean separated histogram equalization

2.2.6. Contra harmonic mean filter

2.2.7. Mean filter

2.2.8. Median filter

2.2.9. Hybrid median filter

2.2.10. Morphological enhancement

2.2.11. Morphological enhancement and contrast stretching

2.2.12. Unsharp masking

2.2.13. Unsharp masking and contrast stretching

2.2.14. Wavelet based subband filtering

2.3. Selection of ROIs

2.3.1. Selection of ROI size

2.4. Feature Extraction: Gabor Wavelet Transform Features

2.5. SVM Classifier

3. Experimental Results

3.1. Obtaining the Accuracies of Classification of Abnormal Mammograms After Enhancement With Alpha Trimmed Mean Filter

3.2. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Contrast Stret ...

3.3. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Histogram Equa ...

3.4. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With CLAHE

3.5. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With RMSHE

3.6. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Contra-Harmoni ...

3.7. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Mean Filter

3.8. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Median Filter

3.9. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Enhancement With Hybrid Median ...

3.10. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Morphological Enhancement

3.11. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Morphological Enhancement, Fol ...

3.12. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Unsharp Masking

3.13. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After UMCA

3.14. Obtaining the Accuracies of Classification of Diagnosis of Abnormal Mammograms After Wavelet-Based Subband Filtering

4. Comparison of Classification Performance of the Enhancement Methods

5. Genetic Algorithm-Based Metaheuristic Approach to Customize a Computer-Aided Classification System for Enhanced Mammograms

6. Conclusion

7. Future Scope

References

Further Reading

Chapter 11: Embedded healthcare system based on bioimpedance analysis for identification and classification of skin disea ...

1. Introduction

2. Need of Bioimpedance Measurement for Identification and Classification of Skin Diseases

3. System Developed for the Measurement of Human Skin Impedance

3.1. Skin Electrode

3.2. Impedance Converter IC AD5933

3.3. Microcontroller IC CY7C68013A

3.4. Personal Computer

4. Generation of a Database of Indian Skin Diseases

5. Impedance Indices for Identification and Classification of Skin Diseases

6. Identification of Skin Diseases

6.1. Wilcoxon Signed Rank Test

7. Measures of Classification of Skin Diseases

7.1. Box and Whisker Plot of Impedance Indices

7.2. Mean and Standard Deviation of Impedance Indices

8. Classification of Skin Diseases Using Modular Fuzzy Hypersphere Neural Network

9. Conclusion

References

Chapter 12: A hybrid CAD system design for liver diseases using clinical and radiological data

1. Introduction

2. Methodology Adopted

2.1. CAD System Design A

2.1.1. Dataset description

2.1.2. Feature extraction

2.1.3. Feature classification

2.1.4. Classification results

2.2. CAD System Design B

2.2.1. Dataset description

2.2.2. Feature extraction

2.2.3. Feature classification

2.2.4. Classification results

2.3. CAD System Design C: Hybrid CAD System

3. Discussion

4. Conclusion and Future Scope

References

Further Reading

Chapter 13: Ontology-based electronic health record semantic interoperability: A survey

1. Introduction

2. EHR and Its Interoperability

2.1. Introduction and Definitions

2.2. The Interoperability Benefits

2.3. The Different Interoperability Levels

2.4. EHR Semantic Interoperability Requirements

3. E-Health Standards and Interoperability

4. Ontologies and Their Role in EHR

5. Methods

5.1. Research Questions

5.2. Search Strategy

5.3. Search Results

5.4. Discussion

6. The Challenges of EHR Semantic Interoperability

7. Conclusion

References

Chapter 14: A unified fuzzy ontology for distributed electronic health record semantic interoperability

1. Introduction

1.1. EHR Clinical and Business Benefits and Outcomes

1.2. EHR Semantic Interoperability Barriers and Obstacles

1.2.1. The heterogeneity problem

1.2.2. Dynamics and complexities of healthcare systems

1.2.3. The challenges of standards

2. Related Work

3. Preliminaries

3.1. Techniques and Approaches of EHR Semantic Interoperability

3.2. EHR Standards

3.3. Ontologies

3.4. Terminologies

3.5. Semantic Interoperability Frameworks

3.6. Privacy and Security in EHR Systems

4. Methodology

4.1. The Proposed Framework

4.2. A Prototype Problem Example

4.3. A Comparison Study

5. Conclusion

References

Further Reading

Index

Back Cover