Bio-Inspired Optimization for Medical Data Mining.

Format:

Book

Author/Creator:

Srivastava, Sumit.

Contributor:

Anand, Abhineet.

Kumar, Abhishek.

Saini, Bhavna.

Rathore, Pramod Singh.

Language:

English

Subjects (All):

Medical informatics--Data processing.

Medical informatics.

Data mining.

Physical Description:

1 online resource (334 pages)

Edition:

1st ed.

Place of Publication:

Newark : John Wiley & Sons, Incorporated, 2024.

Summary:

This book is a comprehensive exploration of bio-inspired optimization techniques and their potential applications in healthcare. Bio-Inspired Optimization for Medical Data Mining is a groundbreaking book that delves into the convergence of nature's ingenious algorithms and cutting-edge healthcare technology. Through a comprehensive exploration of state-of-the-art algorithms and practical case studies, readers gain unparalleled insights into optimizing medical data processing, enabling more precise diagnosis, optimizing treatment plans, and ultimately advancing the field of healthcare. Organized into 15 chapters, readers learn about the theoretical foundation of pragmatic implementation strategies and actionable advice. In addition, it addresses current developments in molecular subtyping and how they can enhance clinical care. By bridging the gap between cutting-edge technology and critical healthcare challenges, this book is a pivotal contribution, providing a roadmap for leveraging nature-inspired algorithms. In this book, the reader will discover Cutting-edge bio-inspired algorithms designed to optimize medical data processing, providing efficient and accurate solutions for complex healthcare challenges; How bio-inspired optimization can fine-tune diagnostic accuracy, leading to better patient outcomes and improved medical decision-making; How bio-inspired optimization propels healthcare into a new era, unlocking transformative solutions for medical data analysis; Practical insights and actionable advice on implementing bio-inspired optimization techniques and equipping effective real-world medical data scenarios; Compelling case studies illustrating how bio-inspired optimization has made a significant impact in the medical field, inspiring similar success stories. Audience This book is designed for a wide-ranging audience, including medical professionals, healthcare researchers, data scientists, and technology enthusiasts.

Contents:

Cover

Series Page

Title Page

Copyright Page

Contents

Preface

Chapter 1 Bioinspired Algorithms: Opportunities and Challenges

1.1 Introduction

1.1.1 Definition and Significance of Bioinspired Algorithms

1.1.2 Overview of the Chapter

1.2 Bioinspired Principles and Algorithms

1.2.1 Evolutionary Algorithms

1.2.2 Swarm Intelligence Algorithms

1.2.3 Artificial Neural Networks

1.2.4 Other Bioinspired Algorithms

1.3 Opportunities of Bioinspired Algorithms

1.3.1 Solving Complex Optimization Problems

1.3.2 Robustness in Dealing With Uncertainty and Noise

1.3.3 Parallel and Distributed Computing

1.3.4 Application Areas and Success Stories

1.4 Challenges of Bioinspired Algorithms

1.4.1 Parameter Tuning and Algorithm Configuration

1.4.2 Lack of Theoretical Analysis and Understanding

1.4.3 Risk of Premature Convergence

1.4.4 Computational Cost for Large-Scale Problems

1.4.5 Ethical Considerations and Limitations

1.5 Prominent Bioinspired Algorithms

1.5.1 Genetic Algorithms

1.5.2 Particle Swarm Optimization

1.5.3 Ant Colony Optimization

1.5.4 Artificial Neural Networks

1.6 Applications of Bioinspired Algorithms

1.6.1 Optimization Problems

1.6.2 Pattern Recognition and Machine Learning

1.6.3 Swarm Robotics

1.6.4 Other Domains

1.7 Future Research Directions

1.7.1 Improving Efficiency and Scalability

1.7.2 Enhancing Interpretability and Explainability

1.7.3 Integration With Other Computational Techniques

1.7.4 Addressing Ethical Concerns

1.8 Conclusion

1.8.1 Summary of Key Points

1.8.2 Implications and Future Prospects of Bioinspired Algorithms

References

Chapter 2 Evaluation of Phytochemical Screening and In Vitro Antiurolithiatic Activity of Myristica fragrans by Titrimetry Method Using Machine Learning

2.1 Introduction.

2.2 Methodology

2.2.1 Collection of Plant Material

2.2.2 Qualitative Analysis of Phytochemicals

2.2.3 Study of In Vitro Antiurolithiatic Activity Using Titrimetry Method

2.2.3.1 Preparation of Calcium Oxalate

2.2.3.2 Preparation of Semipermeable Membrane From Eggs

2.2.3.3 In Vitro Antiurolithiatic Test Using Titrimetry Method

2.3 Result and Discussion

2.3.1 In Vitro Antiurolithiatic Activity Test

2.3.2 Analysis of Dissolved Calcium Oxalate

2.4 Conclusion

Chapter 3 Parkinson's Disease Detection Using Voice and Speech- Systematic Literature Review

3.1 Introduction

3.2 Research Questions

3.3 Method

3.3.1 Search Strategy

3.3.2 Inclusion Criteria

3.3.3 Subprocesses Involved in PD Detection Process

3.3.4 Data Sets

3.3.4.1 Parkinson's Data Set-UCI Machine Learning Dataset

3.3.4.2 PC-GITA Dataset

3.3.4.3 mPower Dataset

3.3.4.4 Mobile Device Voice Recordings (MDVR-KCL) Dataset

3.3.4.5 Italian Parkinson's Voice and Speech (IPVS) Dataset

3.3.4.6 Parkinson Speech Dataset With Multiple Types of Sound Recordings Dataset

3.3.4.7 Parkinson's Telemonitoring Dataset

3.4 Algorithms

3.5 Features

3.5.1 Acoustic Features

3.5.1.1 Jitter (Local, Absolute)

3.5.1.2 Jitter (Local)

3.5.1.3 Jitter (rap)

3.5.1.4 Jitter (ppq5)

3.5.1.5 Shimmer (Local)

3.5.1.6 Shimmer (local, dB)

3.5.1.7 Shimmer (apq3)

3.5.1.8 Shimmer (apq5)

3.5.2 Spectogram-Based Methods

3.5.2.1 MFCC

3.6 Conclusion

Chapter 4 Tumor Detection and Classification

4.1 Introduction

4.2 Methods Used for Detection of Tumors

4.3 Methods Used for Classification of Tumours

4.3.1 Segmentation

4.3.2 Region Growing Method

4.3.3 Seeded Region Growing Method

4.3.4 Unseeded Region Growing Method

4.3.5 .-Connected Method

4.3.6 Threshold Based Method.

4.3.7 K-Means Method

4.3.8 Watershed Method

4.3.9 Comparison of Different Segmentation Techniques Based on the Advantages and Disadvantages

4.3.10 Comparison of Different Segmentation Techniques Based on Accuracy

4.3.11 Comparison of Region Based and Threshold Based Segmentation Techniques Based on Different Parameters

4.4 Machine Learning

4.4.1 Supervised Learning

4.4.2 Unsupervised Learning

4.4.3 Reinforcement Learning

4.4.4 K-Nearest Neighbour (KNN)

4.4.5 Support Vector Machine (SVM)

4.4.6 Random Forest

4.5 Deep Learning (DL)

4.5.1 Convolutional Neural Networks (CNN)

4.5.1.1 Convolution Layer

4.5.1.2 Pooling Layer

4.5.1.3 Architecture of CNN

4.5.1.4 Comparison of Different Variations of CNN Techniques

4.5.2 Long Short-Term Memory (LSTM)

4.5.3 Artificial Neural Network (ANN)

4.5.4 Accuracy of Different Models Discussed Above

4.5.5 Accuracy of Other Different Techniques Being Used

4.6 Performance Metrics

4.6.1 Accuracy

4.6.2 Precision

4.6.3 Recall

4.6.4 Specificity

4.6.5 F1-Measure

4.7 Method Wise Trend of Using Techniques for Detection of Brain Tumor

4.8 Conclusion

Chapter 5 Advancements in Tumor Detection and Classification

5.1 Introduction

5.2 Imaging Techniques Used in Tumor Detection and Classification

5.2.1 X-Ray

5.2.2 CT Scan

5.2.3 MRI

5.2.4 Ultrasound

5.3 Molecular Biology Techniques

5.3.1 PCR

5.3.2 FISH

5.3.3 Next-Generation Sequencing

5.3.4 Western Blotting

5.4 Machine Learning and Artificial Intelligence

5.5 Tumor Classification

5.5.1 TNM Staging System

5.5.2 Histological Grading

5.5.3 Molecular Subtyping

5.6 Challenges and Future Directions

Chapter 6 Classification of Brain Tumor Using Machine Learning Techniques: A Comparative Study

6.1 Introduction.

6.2 Related Work

6.3 Datasets

6.4 Experimental Setup

6.5 Results and Discussion

6.5.1 Evaluation Metrics

6.6 Conclusion

6.6.1 Significance of the Study

Chapter 7 Exploring the Potential of Dingo Optimizer: A Promising New Metaheuristic Approach

7.1 Introduction

7.2 Architecture of Dingo Optimizer

7.3 Initialization Process

7.3.1 Population Size

7.3.2 Dingo Population Initialization

7.3.3 Fitness Assessment

7.3.4 Best Dingo

7.3.5 Recordkeeping

7.4 Iteration Phase

7.6 Other Optimization Techniques

7.7 Conclusion

Chapter 8 Bioinspired Genetic Algorithm in Medical Applications

8.1 Introduction

8.2 The Genetic Algorithm

8.3 Radiology

8.4 Oncology

8.5 Endocrinology

8.6 Obstetrics and Gynecology

8.7 Pediatrics

8.8 Surgery

8.9 Infectious Diseases

8.10 Radiotherapy

8.11 Rehabilitation Medicine

8.12 Neurology

8.13 Health Care Management

8.14 Conclusion

Chapter 9 Artificial Immune System Algorithms for Optimizing Nanoparticle Design in Targeted Drug Delivery

9.1 Introduction

9.2 Artificial Immune Cells

9.3 The Artificial Immune System Architecture

Chapter 10 Diabetic Retinopathy Detection by Retinal Blood Vessel Segmentation and Classification Using Ensemble Model

10.1 Introduction

10.2 Literature Review

10.3 Proposed System

10.4 Conclusion and Future Scope

Chapter 11 Diabetes Prognosis Model Using Various Machine Learning Techniques

11.1 Introduction

11.1.1 Disease Identification

11.1.2 Data, Information, and Knowledge

11.1.3 Knowledge Discovery in Databases

11.1.4 Predictive Analytics

11.1.5 Supervised Learning and Machine Learning

11.1.6 Predictive Models

11.1.7 Data Validation and Cleaning

11.1.8 Discretization.

11.2 Literature Review

11.2.1 Neural Networks

11.2.2 Trees

11.2.3 K-Nearest Neighbors

11.3 Proposed Model

11.3.1 Predictive Models in Health

11.4 Experimental Results and Discussion

11.4.1 Prediction of Diabetes with Artificial Neural Networks Supervised Learning Algorithms

11.4.2 Improving the Prediction Ratio of Diabetes Diagnoses Using Fuzzy Logic and Neural Networks

11.4.3 ARIC: Type 2 Diabetes Risk Predictive Model

11.4.4 Evaluation of Neural Network Algorithms for Prediction Models of Type 2 Diabetes

11.4.5 Reliable and Objective Recommendation System for the Diagnosis of Chronic Diseases

11.5 Conclusion

Chapter 12 Diagnosis of Neurological Disease Using Bioinspired Algorithms

12.1 Introduction

12.1.1 Neurological Diseases

12.1.2 Introduction to Bioinspired Algorithms

12.1.3 Types of Bioinspired Algorithms Commonly Used in Healthcare

12.1.4 Advantages and Limitations of Bioinspired Algorithms

12.1.5 Limitations

12.1.6 Applications of Bioinspired Algorithms in Healthcare

12.1.7 Benefits of Bioinspired Algorithms in Healthcare Over Traditional Approaches

12.2 Neurological Disease Diagnosis

12.2.1 Bioinspired Algorithms for Neurological Disease Diagnosis

12.2.2 Neural Networks in Neurological Disease Diagnosis

12.2.2.1 How NNs Can Be Trained Using Bioinspired Optimization Techniques

12.2.3 Other Bioinspired Algorithms in Neurological Disease Diagnosis

12.3 Challenges and Future Directions

12.4 Conclusion

Chapter 13 Optimizing Artificial Neural-Network Using Genetic Algorithm

13.1 Introduction

13.1.1 ANN

13.1.2 Genetic Algorithm

13.2 Methodology

13.2.1 Mathematical Working

13.3 Brief Study on Existing Implementations

13.3.1 Using Different Types of ANNs

13.3.2 Using MLPs.

13.4 Comparative Study on Different Implementations.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

9781394214211

1394214219

9781394214204

1394214200

OCLC:

1442928126