Emerging Trends and Applications of Deep Learning for Biomedical Data Analysis / edited by Smita Sharma [and three others].

Format:

Book

Contributor:

Sharma, Smita, editor.

Language:

English

Subjects (All):

Deep learning (Machine learning).

Medicine--Data processing.

Medicine.

Physical Description:

1 online resource (361 pages)

Edition:

First edition.

Place of Publication:

London, England : Elsevier, [2025]

Summary:

Emerging Trends and Applications of Deep Learning for Biomedical Data Analysis introduces the latest emerging trends and applications of deep learning in biomedical data analysis. This book delves into various use cases where deep learning is applied in industrial, social, and personal contexts within the biomedical domain. By gaining a comprehensive understanding of deep learning in biomedical data analysis, readers will develop the skills to critically evaluate research papers, methodologies, and emerging trends. In 11 chapters, this book provides insights into the fundamentals of the latest research trends in the applications of deep learning in biosciences. With several case studies and use cases, it familiarizes the reader with a comprehensive understanding of deep learning algorithms, architectures, and methodologies speci cally applicable to biomedical data analysis. This title is an ideal reference for researchers across the biomedical sciences.- Provides a succinct overview of the cutting-edge technologies that are altering disease diagnosis, patient monitoring, and medical research- Bridges the gap between biomedical engineering and deep learning by providing a comprehensive resource for comprehending the intersection of these disciplines- Investigates how deep learning may change healthcare by providing new insights, diagnostics, and treatments via intelligent biomedical systems

Contents:

Front Cover

Emerging Trends and Applications of Deep Learning for Biomedical Data Analysis

Copyright

Contents

List of contributors

About the editors

1 Deep learning, artificial intelligence, and bioinformatics promises innovations and imminent forecasts in SARS-COVID-19 genome data analysis

1.1 Introduction

1.2 COVID-19-a global pandemic

1.3 Genomics of COVID-19

1.4 Applications of deep learning in COVID-19 genomics studies

1.5 Role of artificial intelligence in COVID-19 genomics research

1.6 Usage of bioinformatics tools, software, and databases in COVID-19 genomics investigation

1.7 Challenges and prospects of deep learning, artificial intelligence, and bioinformatics in COVID-19 genomics

1.8 Conclusion

References

2 Integration of IoT and AI for potato leaf disease detection: enhancing agricultural efficiently and sustainability

2.1 Introduction

2.2 Literature survey

2.3 Classification process for potato leaf diseases

2.3.1 Capturing images

2.4 Image preliminary processing

2.5 Image augmentation

2.6 Feature extraction

2.6.1 Classification

2.7 Evaluation and recognition

2.8 Methods and materials

2.8.1 Convolutional neural network model

2.9 Transfer learning

2.10 Pretrained network model

2.11 Proposed model

2.12 Result and discussion

2.13 Conclusion

2.14 Future work

3 A hybridized long-short-term memory networks-based deep learning model using reptile search optimization for COVID-19 prediction

3.1 Introduction

3.2 Materials and methods

3.2.1 Data collection

3.3 Data preprocessing

3.4 Data normalization

3.5 Proposed methodology

3.6 Methodology

3.6.1 Long-short-term memory

3.7 Reptile search algorithm

3.8 Encircling phase (global search or exploration)

3.9 Hunting phase (local search or exploitation).

3.10 Optimized long-short-term memory networks-reptile search algorithm model

3.11 Model evaluation

3.12 Results

3.13 Conclusion

4 Improving coronavirus classification accuracy with transfer learning and chest radiograph analysis

4.1 Introduction

4.2 Related works

4.3 Materials and methods

4.3.1 Data preprocessing

4.3.2 Deep transfer learning

4.3.3 Convolutional neural networks

4.3.3.1 VGG16 and VGG19

4.3.3.2 ResNet50 and ResNet101

4.3.4 Model evaluation

4.3.4.1 Performance matrix for classification

4.4 Results and discussion

4.5 Conclusion

5 A hybrid deep neural network using the Levenberg-Marquart algorithm applied to the nonlinear magnetohydrodynamic Jeffery-Hamel blood flow problem

5.1 Introduction

5.2 Mathematical modeling

5.3 Solution methodology

5.3.1 Finite element method

5.3.2 Artificial neural network

5.3.3 Levenberg-Marquardt scheme

5.4 Result and discussion

5.4.1 Effect of Reynolds number, inclination angel, and nanoparticle percentage composition on velocity profile

5.5 Conclusion

Ethical statement

Acknowledgment

Declaration of interest statement

Funding

Data availability statement

6 An image segmentation method using intuitionistic fuzzy k-means and convolutional neural networks in multiclass image classification

6.1 Introduction

6.2 Related works

6.3 Methodology

6.3.1 Data description

6.3.2 Intuitionistic fuzzy k-means clustering algorithms

6.3.3 Convolutional neural networks

6.3.3.1 VGG16 and VGG19

6.3.3.2 ResNet50 and ResNet 101

6.3.3.3 DenseNet201 and AlexNet

6.4 Results and discussion

6.4.1 Results of Intuitionistic fuzzy k-means algorithm

6.4.2 Results of convolutional neural networks with transfer learning

6.5 Conclusion

References.

7 Deep learning for wearable sensor data analysis

7.1 Introduction

7.2 Literature review

7.3 Methodology

7.3.1 Dataset

7.3.2 Methodology and data preprocessing

7.3.2.1 Data visualization and exploration

7.3.2.2 Data preprocessing

7.3.3 Machine learning and deep learning models

7.3.3.1 AdaBoost classifier

7.3.3.2 Multinomial logistic regression

7.3.3.3 XGBoost

7.3.3.4 Extra tree classifier

7.3.3.5 Random forest

7.3.3.6 Light boost classifier

7.3.4 Model evaluation metrics

7.3.5 Hyperparameter tuning

7.3.5.1 Boosting type

7.3.5.1.1 Gradient Boosting Decision Tree (Gdbt)

7.3.5.1.2 Dropouts meet Multiple Additive Regression Trees (Dart)

7.3.5.1.3 Gradient-based One-Side Sampling (Goss)

7.3.5.1.4 Random forest (RF)

7.3.5.2 Learning rate

7.4 Result and discussion

7.4.1 Results

7.4.2 Evaluating the input parameters affecting the model (LBC)

7.5 Conclusion

8 Unveiling emotions in real-time: a novel approach to face emotion recognition

8.1 Introduction

8.2 Convolutional neural network

8.3 Objective

8.4 Literature survey

8.5 Proposed work

8.5.1 Haar cascade classifier

8.5.1.1 Code for face detection phase

8.5.1.2 Output of face detection phase

8.5.2 Implementation

8.5.2.1 Dataset creation

8.6 Pseudocode for training the model

8.7 Results

8.7.1 Accuracy

8.8 Future work

Further reading

9 Unleashing the power of convolutional neural networks for diabetic retinopathy detection in ophthalmology

9.1 Introduction

9.2 Literature review

9.3 System methodology

9.3.1 Image data acquisition

9.3.2 Preprocessing and data augmentation

9.3.3 ResNet152V2 architecture

9.3.4 Quadratic weighted kappa

9.4 Result and discussion

9.4.1 Quadratic weighted kappa

9.4.2 Loss

9.4.3 Accuracy.

9.4.4 F1 score

9.5 Conclusion and future work

10 Case studies and use cases of deep learning for biomedical applications

10.1 Introduction

10.2 Impact of deep learning in bio-engineering

10.2.1 Medical diagnosis

10.2.2 Drug development

10.2.3 Personalized medicine development

10.2.4 Neuro engineering

10.3 Evolution of artificial neural networks

10.4 Applications of deep learning-bio informatics

10.4.1 Next generation sequencing with deep learning

10.4.2 Variant calling

10.5 Explainable artificial intelligence in bio informatics

10.6 Conclusion

11 A convolutional neural network-based deep ensemble method for computed tomography scan image-based lung cancer diagnosis

11.1 Introduction

11.2 Related work

11.3 Dataset

11.4 Methodology

11.4.1 Preprocessing

11.4.1.1 Conversion of images to grayscale

11.4.1.2 Applying Gaussian Blur filter

11.4.1.3 Otsu's thresholding

11.4.1.4 Normalization of images

11.4.2 Data augmentation

11.4.3 Proposed ensemble convolutional neural network model

11.5 Experimental results and discussion

11.6 Conclusion

Index

Back Cover.

Notes:

Includes bibliographical references and index.

Description based on publisher supplied metadata and other sources.

Description based on print version record.

ISBN:

0-443-26766-9

0-443-26765-0

OCLC:

1518441148