Artificial Intelligence in Biomedical and Modern Healthcare Informatics

1st Edition - September 27, 2024
Imprint: Academic Press
Editors: M. A. Ansari, R.S Anand, Pragati Tripathi, Rajat Mehrotra, Md Belal Bin Heyat
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 8 7 0 - 5
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 1 8 7 1 - 2

Artificial Intelligence in Biomedical and Modern Healthcare Informatics provides a deeper understanding of the current trends in AI and machine learning within healthcare diagnosis… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Artificial Intelligence in Biomedical and Modern Healthcare Informatics provides a deeper understanding of the current trends in AI and machine learning within healthcare diagnosis, its practical approach in healthcare, and gives insight into different wearable sensors and its device module to help doctors and their patients in enhanced healthcare system.

The primary goal of this book is to detect difficulties and their solutions to medical practitioners for the early detection and prediction of any disease.

The 56 chapters in the volume provide beginners and experts in the medical science field with general pictures and detailed descriptions of imaging and signal processing principles and clinical applications.

With forefront applications and up-to-date analytical methods, this book captures the interests of colleagues in the medical imaging research field and is a valuable resource for healthcare professionals who wish to understand the principles and applications of signal and image processing and its related technologies in healthcare.

Title of Book
Cover image
Title page
Table of Contents
Copyright
Contributors
About the editors
Preface
Acknowledgments
Chapter 1. Evaluating the role of artificial intelligence in modern public health: A future-oriented analysis of medical social work practices
1 Introduction
2 Health crises in India
3 Artificial intelligence: Need to reflect public health
3.1 Intentionality
3.2 Intelligence
3.3 Adaptability
4 Encounters: Public health
4.1 Major challenges
4.1.1 Data privacy
4.1.2 Ethical complications
4.1.3 Data bias
4.1.4 Challenges for social work profession
5 Solutions: Social work perspective
6 Summary and conclusion
Chapter 2. Upshots of healthcare with AI
1 Introduction
1.1 Need of AI in healthcare
1.2 Artificial intelligence
1.3 Implementation of AI
1.4 Machine learning
1.5 Relationship between AI, ML, and DL
1.6 AI effectiveness on various sectors
2 AI-Supporting technologies
2.1 AI in healthcare
3 Conclusion
Chapter 3. Artificial intelligence and machine learning–assisted robotic surgery: Current trends and future scope
1 Introduction
2 The need for AI/ML in biomedical applications
3 Types of biomedical applications for patient monitoring using AI
4 Scope of surgical robots
5 Artificial intelligence models for robotics surgery
6 Challenges and future directions of robotics surgery
7 Conclusion
Chapter 4. A deep perspective of blockchain applications in healthcare sector and Industry 4.0
1 Introduction
1.1 Blockchain concept
1.2 Brief history of blockchain technology in Industry 4.0
1.3 Blockchain types and consensus mechanism
1.4 Block chain characteristics
1.4.1 Decentralization
1.4.2 Transparency
1.4.3 Autonomy
1.4.4 Security
1.4.5 Immutability
1.4.6 Traceability
1.4.7 Anonymity
1.4.8 Democratized
1.4.9 Integrity
1.4.10 Programmability
1.4.11 Fault tolerance
1.5 Features of a unified blockchain and relevant challenges
2 Blockchain applications and use cases
2.1 Cryptocurrency
2.1.1 Hyperledger
3 Cryptocurrencies
4 Blockchain and healthcare systems
4.1 Healthcare blockchain and barriers or difficulties
4.1.1 Inadequate expertise their deployment in the related fields
4.1.2 Delayed adoption of paperless working
4.1.3 The government enforcements or efforts for deployment
4.1.4 Failureness in bringing out cost-effectiveness
4.1.5 Inadequate personal space
4.1.6 Motivational crisis
4.1.7 The unacceptance of cryptocurrencies
4.1.8 Inadequate security mechanisms
4.1.9 Lack of unified healthcare system
4.1.10 Slowness of information and communication technology can create life risks
5 Proposed algorithms
6 Conclusion
Chapter 5. Analyzing the role of machine learning techniques in healthcare systems
1 Introduction
2 Related work
3 Issues and challenges of ML
3.1 Applications of machine learning in healthcare: Use cases
3.1.1 Treatment, diagnosis, and prediction of mental illness
3.2 Case study on prediction of cardiovascular diseases using machine learning
4 Result and discussion
5 Conclusion
Chapter 6. Artificial intelligence, machine learning and deep learning in biomedical fields: A prospect in improvising medical healthcare systems
1 Introduction
2 Artificial intelligence (AI), machine learning (ML) and deep learning (DL) in biomedical research
2.1 Drug discovery
2.2 Disease diagnosis and prognosis
2.3 Electronic health records (EHRs)
2.4 Personalized medicine
2.5 Medical robotics
2.6 Diseases identification and diagnosis
2.7 Medical imaging
2.8 Drug discovering & manufacturing
2.9 Personalized medical treatment
2.10 Disease prediction
3 Application of AI via modeling with large scale brain imaging data in cognitive brain disorders: A deep insight
3.1 Network approach to analyzed brain imaging data
3.2 Machine learning method for classification and analysis of brain imaging data
3.3 Deep neural network (DNN)
4 Machine learning in breast cancer screening
5 Risk and ethical issues with artificial intelligence in biomedical sciences
6 Conclusions and prospects
Chapter 7. Artificial intelligence in respiratory diseases with special insight through bioinformatics
1 Introduction
2 Bioinformatics: The modern AI in biology
3 Respiratory diseases and current situations
4 Contribution of AI and bioinformatics in respiratory disease care
4.1 In pneumonia
4.2 In RSV
4.3 In asthma
4.4 In COVID-19
5 Future of AI
6 Conclusions
Chapter 8. Electroencephalography (EEG) in epilepsy care: An introduction
1 Overview
2 Historical perspective of EEG
3 Neuronal basis of EEG
4 EEG and its implications in human brain
4.1 Scalp versus intracranial EEG recordings
4.2 Challenges in EEG signal processing
5 EEG in tackling epilepsy
5.1 Brief overview of epilepsy in India
5.2 EEG in seizure detection
5.3 EEG in seizure prediction
Chapter 9. A review on brain–computer interface and its applications
1 Introduction
2 Neuroimaging approaches
2.1 Electroencephalography
2.2 Magnetoencephalography
2.3 Electrocorticography
2.4 Functional magnetic resonance imaging
2.5 Near-infrared spectroscopy
3 Control signals in BCIs
3.1 Visual evoked potentials
3.2 Slow cortical potentials
3.3 P300 evoked potentials
3.4 Sensorimotor rhythms (mu and beta rhythms)
4 Types of BCIs
5 Feature extraction and selection
6 Classification algorithms
7 Applications of BCIs
8 Conclusions
Chapter 10. Recent trends in metabolomics, machine learning and artificial intelligence
1 Introduction
1.1 Basics of metabonomics
2 Conceptual basis for metabonomics
3 Metabonomics approach to disease diagnosis
4 How it is used for cancer biomarker detection
4.1 Metabonomics and cancer research
5 Different metabolic profiling techniques
6 Sample handling for robust data generation
7 Pattern recognition techniques for metabolomics
8 Self-organizing maps
9 Websites and databases available online and offline
Chapter 11. A comprehensive review on state-of-the-art imagined speech decoding techniques using electroencephalography
1 Introduction
1.1 EEG-based speech imagery BCI system
1.2 EEG signal acquisition
1.3 Neural evidence of imagined speech
1.4 Publicly available datasets
2 Review based on signal processing techniques
2.1 Preprocessing and artifact removal techniques
2.2 Feature extraction and selection
2.3 Classification methods
2.3.1 Machine learning based
2.3.2 Deep learning based
2.3.3 Transfer learning method
3 Review based on choice of parameters
3.1 Choice of dominant frequency band
3.2 Channel selection
3.3 Choice of imagined prompt
3.4 Mode of stimulus presentation
3.5 Repeated trials of imagery
4 Conclusion and future directions
Chapter 12. Parkinson's disease diagnosis, treatment, and future scope: An epilogue
1 Introduction
2 The pathophysiology behind Parkinson's disease
3 The progression and stages of the Parkinson's disease
3.1 First stage
3.2 Second stage
3.3 Third stage
3.4 Fourth stage
3.5 Fifth stage
4 One disease with various symptoms
4.1 Bradykinesia
4.2 Freezing of gait
4.3 Impaired posture and balance
4.4 Tremors
4.5 Speech and writing changes
5 Recent trends in the treatment of Parkinson's disease
5.1 Drug delivery systems
5.2 Deep brain stimulation
5.3 Nigra cell transplantation
5.4 Walking stick and video games
5.5 Diagnostic and clinical assessment devices
Chapter 13. Recent advances in removal of artifacts from EEG signal records
1 Introduction
2 Background
2.1 Characteristics of EEG
2.2 EEG artifacts and their types
2.2.1 Ocular artifacts
2.2.2 Muscle artifacts
2.2.3 Cardiac artifacts
2.2.4 Extrinsic artifacts
3 Single artifacts elimination techniques
3.1 Regression methods
3.2 Wavelet transform
3.3 Blind source separation
3.3.1 Principal component analysis
3.3.2 Independent component analysis
3.3.3 Canonical correlation analysis
3.3.4 Source imaging–based method
3.4 Empirical mode decomposition
3.5 Filtering methods
3.5.1 Adaptive filtering
3.5.2 Wiener filtering
4 Hybrid methods
4.1 Empirical mode decomposition-–blind source separation
4.2 Wavelet–blind source separation
4.3 Blind source separation–support vector machine
5 Comparative analysis
6 Conclusions
Chapter 14. Computer-aided diagnosis in healthcare: Case study on lung cancer diagnosis
1 Introduction
2 Statistics on lung cancer
3 Types of lung cancer
4 Lung cancer staging
5 Diagnosis of lung cancer
5.1 Imaging test
5.2 Sputum cytology
5.3 Bronchoscopy and biopsy
5.4 Needle biopsy
6 Lung cancer treatment
7 Convolutional neural network
8 Deep learning architecture for lung cancer diagnosis
Chapter 15. AI and its role in predictive preclinical models for drug efficacy testing
1 Introduction
1.1 How do we interpret AI today?
2 Tools/software available so far
3 Role of AI in drug efficacy
3.1 Software tools for checking drug efficacy
3.2 Molecular modeling and simulation software
3.3 Data analysis and visualization software
3.4 Parameters for drug efficacy tools
4 Case study 1: Efficacy of a novel drug in a rat model of hypertension
5 Case study 2: Efficacy of a novel drug in a rat model of hypertension
6 Results
7 Challenges
Chapter 16. Machine learning–based solutions for brain tumor detection: Comparative study and limitations
1 Introduction
2 Machine learning techniques
2.1 Convolutional neural network
2.2 Support vector machines
2.3 CNN–SVM hybrid
2.4 Artificial neural network
2.5 Long short-term memory
2.6 CNN-LSTM hybrid
3 Literature review on ML solutions for detection of brain tumor
4 Conclusion
Chapter 17. Indoor and home-based poststroke rehabilitation techniques—A systemic review
1 Introduction
2 Methodology
2.1 Search strategy
2.2 Inclusion and omission criteria
3 Techniques
3.1 Classical indoor therapy
3.1.1 Cupping therapy
3.2 Physical therapy
3.2.1 Physiotherapy
3.2.2 Modern technology supported materials
4 Discussion
4.1 Motivation
4.2 Home environment design
5 Conclusion
Chapter 18. A comprehensive study on implementable antennas for medical applications
1 Introduction
2 Antenna inside body
2.1 Single-band antenna inside body
2.2 Multiband antenna inside body
2.3 Wideband antenna inside body
3 Conclusion
Chapter 19. Deep learning for bone age assessment: Current status and future prospects
1 Introduction
2 Literature review
3 Methodology
3.1 Dataset
3.2 Segmentation
3.2.1 U-Net-based segmentation
3.2.2 FC DenseNet
3.2.3 Deep learning based methods
3.3 Regression
3.4 Evaluation
4 Results
5 Discussions
6 Conclusions and future directions
Chapter 20. Emerging applications of artificial intelligence in analyzing EEG signals for the healthcare sector
1 Introduction
2 AI technologies used in healthcare and biomedical signals
3 Advantages of AI in healthcare and biomedical signals
4 Challenges of AI in healthcare and biomedical signals
5 Electroencephalogram
6 Historical background of EEG
7 Types of brain waves (according to frequency)
7.1 Alpha waves (frequency range from 8 to 13Hz)
8 Beta waves (frequency range from 13Hz to about 30Hz)
9 Theta waves (frequency range from 4 to 8Hz)
10 Delta waves (frequency range up to 4Hz)
11 Artificial intelligence can be used in EEG for Alzheimer's disease in several ways, including
12 Future of AI in analysis of EEG in the healthcare sector
13 Conclusion
Conflict of interest statement
Chapter 21. Epilepsy detection system using CWT and deep CNN
1 Introduction
2 Materials
3 Methods
4 Review of automatic detection of epilepsy
4.1 Dataset of the University of Bonn
4.2 Statistical analysis of the University of Bonn Dataset
4.3 Time and frequency analysis of the University of Bonn Dataset
5 Discussion
6 Conclusion
Informed consent
Funding
Chapter 22. Isolated Indian Sign Language Recognition with multihead attention transformer based network and MediaPipe's landmarks
1 Introduction
2 Related work
3 Methodology
3.1 Dataset
3.2 Extraction of keyframes
3.3 Key point extraction using MediaPipe
3.4 Multihead video transformer network
4 Implementation details
5 Results and discussion
6 Conclusion
Chapter 23. Diagnosis of Parkinson's disease based on biological and imaging-derived features using machine learning and deep learning
1 Introduction
2 Techniques and data
2.1 Description of PPMI data
2.2 Detail of features
2.3 Data interpretation
2.4 Classifiers
2.4.1 Support vector machine
2.4.2 Naïve Bayes
2.4.3 K-nearest neighbors
2.4.4 Decision tree
2.4.5 Random forest
2.4.6 Classification and regression trees
2.4.7 Extreme gradient boosting
2.4.8 Deep neural network
3 Experimental results
3.1 Metrics and distribution of data
3.2 Classification results
3.2.1 Machine learning results
3.2.2 Deep learning results
4 Discussion
5 Conclusion
Declarations
Chapter 24. Braintumor and feature detection from MRI and CT scan using artificial intelligence
1 Introduction
2 Literature review
3 Methodology
4 Extraction of gray-level co-occurence matrix
5 Results and discussion
5.1 Analysis of Haralick texture features
5.2 Brain tumor detection GUI
5.3 Classification of brain tumor images using convolution neural network
6 Conclusion
Chapter 25. Neuromodulation via brain stimulation: A promising therapeutic perspective for Alzheimer's disease
1 Introduction
2 Neuromodulation and its modalities
3 Role and worth of brain stimulation techniques in Alzheimer's disease
3.1 Deep brain stimulation
3.1.1 Working principle
3.1.2 Outcomes of animal studies
3.1.3 Outcomes of human studies
3.1.4 Merits and demerits
3.2 Transcranial magnetic stimulation
3.2.1 Working principle
3.2.2 Outcomes of animal studies
3.2.3 Outcomes of human studies
3.2.4 Merits and demerits
3.3 Transcranial electrical stimulation
3.3.1 Working principle
3.3.2 Outcomes of animal studies
3.3.3 Outcomes of human studies
3.3.4 Merits and demerits
3.4 Focused ultrasound therapy
3.4.1 Working principle
3.4.2 Outcomes of animal studies
3.4.3 Outcomes of human studies
3.4.4 Merits and demerits
3.5 Photobiomodulation
3.5.1 Working principle
3.5.2 Outcomes of animal studies
3.5.3 Outcomes of human studies
3.5.4 Merits and demerits
3.6 Visual and auditory stimulation
3.6.1 Working principle
3.6.2 Outcomes of animal studies
3.6.3 Outcomes of human studies
3.6.4 Merits and demerits
4 Conclusion
Declaration of interest
Disclosure statement
Chapter 26. A biosensor for the detection of viruses using one-dimensional photonic crystals
1 Introduction
2 Biosensors
2.1 Operating principle
3 Types of biosensors
3.1 Photonic biosensors
3.2 Electrochemical biosensors
3.3 Piezoelectric biosensors
3.4 Characteristics of SARS-CoV-2
4 Background
4.1 Identification of COVID-19 by photonic
4.2 Laser spectrum with molecules
4.2.1 Enhanced detection of viruses by laser
5 Conclusion
Chapter 27. Artificial intelligence–based seizure detection systems in electroencephalography: Transforming healthcare for accurate diagnosis and treatment
1 Introduction
2 Understanding nonstationary signals
2.1 Delta waves
2.2 Theta waves
2.3 Alpha waves
2.4 Beta waves
2.5 Gamma waves
2.6 Mu waves
2.7 K-complex waves
2.8 V Waves
2.9 Lambda waves
2.10 Spike waves
2.11 Sleep spindles
3 AI-based seizure detection systems
4 Machine learning and deep learning methods
4.1 Support vector machines
4.2 Artificial neural networks
4.3 Convolutional neural networks
4.4 Recurrent neural networks
4.5 Long short-term memory networks
5 Domain knowledge in building robust AI models
6 Conclusion
Chapter 28. Artificial intelligence and image enhancement–based methodologies used for detection of tumor in MRIs of human brain
1 Introduction
2 Related work
3 Methodology
3.1 Brain tumor
3.2 Brain strokes
3.2.1 Functional magnetic resonance imaging
3.2.2 Computed tomography
3.2.3 Electroencephalography
3.2.4 Positron emission tomography
3.2.5 Magnetoencephalography
3.2.6 Near infrared spectroscopy
3.2.7 Importance of AI in medical imaging
3.2.8 Histogram equalization and image enhancement–based technique for detection of brain tumor
3.2.9 Morphological operations in image enhancement
4 Conclusion and future scope
Chapter 29. Machine learning-based workload identification using functional near-infrared spectroscopy (fNIRS) data
1 Introduction
2 Workload measuring
3 Measuring workload models
3.1 Demands-control model
3.2 Conflicting roles and ambiguity model
3.3 The demands-control-balance model
3.4 The burnout model
3.5 Spector and Jex's self-report measures
4 Data acquisition methods for workload measuring
4.1 Electroencephalography
4.2 Functional near-infrared spectroscopy
5 FNIRS data acquisition
6 Preprocessing fNIRS data
6.1 Filtering
6.2 fNIRS-based feature extraction
6.2.1 Signal mean
6.2.2 Signal median
6.2.3 Skewness and kurtosis
7 Machine learning algorithms for workload classification and data source
8 Labeling data
8.1 K-means clustering
9 Result and discussion
10 Conclusion
11 Future scope
Chapter 30. Forecasting the COVID-19 pandemic through hybridization of Machine Intelligent Algorithms
1 Introduction
2 Input dataset and its preprocessing
3 Artificially intelligent learning–based forecast models
3.1 Least square support vector regression
4 Conclusions
Chapter 31. Suppression of noise signals from computed tomography and ultrasound medical images and performance evaluation
1 Introduction
1.1 Medical imaging
1.1.1 CT images
1.1.2 Ultrasound images
1.1.3 X-ray images
1.1.4 Magnetic resonance imaging images
1.2 Types of noise signals
1.2.1 Gaussian noise
1.2.2 Speckle noise
2 Literature survey
3 Methodology
3.1 Wavelet transform
3.1.1 Discrete wavelet transform
3.1.2 Dual tree complex wavelet transform
3.2 Dual-tree complex wavelet transform-based de-noising using adaptive thresholding
3.2.1 Dual-tree complex wavelet transform calculation
3.2.2 Coefficient modification with bivariate thresholding
3.2.3 Inverse dual-tree complex wavelet transform computation for de-noising
4 Results and discussion
4.1 Denoising of computed tomography scan images
4.2 Denoising of ultrasound images
5 Conclusion and future scope
Chapter 32. Prediction of nonalcoholic fatty liver disease using machine learning
1 Introduction
2 Literature survey
2.1 Classification algorithms for strategic analysis
2.2 Prediction of nonalcoholic fatty liver
3 Existing system and its limitations
3.1 Current algorithm
4 Proposed system
4.1 System architecture
4.2 Block diagram
4.3 Advantages
4.4 Proposed method and algorithm
4.5 A convolutional neural network example
5 Results and discussions
6 Conclusion
Chapter 33. Performance evaluation of diabetes with machine learning algorithms
1 Introduction
2 Literature review
3 Proposed model
3.1 Methodology
4 Results and discussion
4.1 Data description
4.2 Data preprocessing
4.3 Feature selection
4.4 Classification using K-nearest neighbor
4.5 Classification using gradient boosting classifier
4.6 Classification using LGBM
4.7 Classification using logistic regression
4.8 Performance evaluation
5 Conclusions
Chapter 34. Various segmentation techniques for medical images and the role of IoT
1 Introduction
2 Segmentation
3 Current segmentation methods
3.1 Medical imaging modalities
3.2 Magnetic resonance imaging
3.3 Brain MRI
3.4 MR liver imaging
3.5 Computed tomography imaging
3.6 Brain CT imaging
3.7 Liver CT Imagination
3.8 Chest imaging
3.9 Tummy and hip CT imagery
3.10 Spine CT imagery
4 Depiction of therapeutic imageries
4.1 Methods based on gray-level features
4.1.1 Amplitude segmentation based on histogram features
4.1.2 Edge based segmentation
4.1.3 Region-based segmentation
4.2 Method based on the textural features
4.3 Other segmentation schemes
4.3.1 Breakdown using model
5 Artificial intelligence tools for segmentation and classification
5.1 Supervised methods
5.2 Unsupervised methods
6 How AI tools can be useful for segmentation of CT and MR images
6.1 Methods available for MR image segmentation
6.2 Passion inhomogeneity amendment
6.3 Partial volume effect correction
7 Expertise
7.1 Hardware
7.1.1 Transistor regularity identification (radiofrequency identification)
7.1.2 Cyberspace protocol (Internet protocol)
7.1.3 Barcode
7.1.4 Tuner fidelity (Wi-Fi)
7.1.5 ZigBee
7.1.6 Machine learning
7.2 Package
7.2.1 Middleware
7.2.2 Browsing and searching
8 Conclusion
Chapter 35. Augmented mass detection of breast cancer in mammogram images using deep intelligent neural network model
1 Introduction
2 Literature survey
3 Importance of deep learning in mammogram image
4 Proposed augmented mass detection of breast cancer architecture
4.1 Preprocessing
4.2 Training network
4.3 SVM for classification
5 Experimental results
6 Results and discussion
7 Conclusion
Chapter 36. CNC machines in production and manufacturing of medical devices
1 Introduction
2 Role of CNC machining in healthcare
3 Standards of production of medical devices
4 Significance of tool positioning
5 Methods of tool positioning
6 Coordinate systems for tool positioning
7 Positioning control system
8 Control resolution of a CNC machine
9 Open- and closed-loop machining systems
10 Automated tool positioning using feedback control
11 Image processing for CNC tool monitoring
12 Convolutional neural networks for image processing–based automation
13 Other technologies
14 Conclusions
Chapter 37. Analysis and prediction of cardiomyopathy using artificial intelligence
1 Introduction
2 Heart disease
2.1 Coronary heart disease
2.2 Heart arrhythmias
2.3 Congenital heart defects
2.3.1 Some common types of CHD include
2.4 Heart valve disease
2.5 Pericardial disease
2.6 Cardiomyopathy
3 Prevalence and effect of cardiomyopathy
4 Diagnosis of heart disease
5 Diagnosis of cardiomyopathy
6 Cardiac magnetic resonance imaging
7 Augmented artificial intelligence approach using an artificial neural network
8 Case study on cardiomyopathy diagnosis from cardiovascular MRI
8.1 Data augmentation
8.2 Experimental result
8.2.1 Effect of performance with augmentation technique
8.2.2 Effect of performance with activation function
8.3 Comparison with state-of-the-art architecture
9 Analysis of hyperparameters on the proposed model
Chapter 38. A preemptive approach to polycystic ovary syndrome diagnosis using machine learning
1 Introduction
2 Related work
3 Dataset used
4 Methodology
4.1 Dataset cleaning and transformation
4.2 Feature selection
4.2.1 Information gain
4.2.2 Forward feature selection
4.2.3 Backward feature elimination
4.2.4 Recursive feature elimination
4.2.5 LASSO regularization
5 Results
6 Conclusion
Chapter 39. Mapping the landscape of human activity recognition techniques in health monitoring for chronic disease management
1 Introduction
2 Background and related work
2.1 Background
2.2 Related reviews
3 Concept map of HAR framework
3.1 Data acquisition
3.2 Data preprocessing
3.3 Filtering
3.4 Windowing and segmentation
3.5 Feature extraction
3.6 Feature selection
3.7 Learning algorithm
3.8 Evaluation metrics
4 Open research challenges
5 Conclusions
Chapter 40. Analysis and organization of mycological skin contaminations by means of medicinal imagery
1 Introduction
2 Analysis of medical images for skin disease detection
2.1 Acquisition of unprocessed image
2.2 Preprocessing
2.3 Segmentation
2.4 Parameterization
2.5 Postprocessing
2.6 Image recognition
2.7 Final image
3 Skin fungal disease detection
3.1 Limitations
3.1.1 Skin disease detection using shade-created imagery recovery
3.1.2 Skin disease detection using infrared thermal imaging
3.1.3 Skin disease detection using data mining
4 Conclusions
Chapter 41. A sensitive biosensor for the detection of blood components using 2D photonic crystals
1 Introduction
2 Design a ring resonator–based biosensors
3 Simulation results
4 Conclusion
Chapter 42. Machine learning assisted EEG signal classification for automated diagnosis of mental stress
1 Introduction
2 Stress detection
2.1 Stress detection using EEG signal
3 Methodology: EEG signal processing
3.1 Preprocessing
3.2 Signal decomposition
3.3 Features extraction
3.3.1 Sample entropy
3.3.2 Handling imbalanced data
3.4 Feature selection
4 Machine learning classification of EEG signal for stress detection
4.1 Multilead approach
4.2 Lead-specific approach
5 Conclusion
Chapter 43. CNN based deep learning model for skin cancer detection using dermatoscopic images
1 Introduction
2 Methods
2.1 Data acquisition
2.2 Preprocessing dataset
2.3 Model architecture
2.4 Training
2.5 Comparison between VGG19 and the proposed model
3 Results and discussions
4 Conclusion
Chapter 44. Bioelectrical impedance analysis body composition estimation of fat mass percentage in people with spinal cord injury
1 Introduction
2 Materials and methods
2.1 Bioelectrical impedance analysis
2.1.1 BIA measurement
3 Statistical analysis
4 Results
4.1 Validation of FMP-BIA by comparing FMP with equations
5 Discussion
5.1 The study limitation
6 Conclusion
Statement of ethics
Conflict of interest
Chapter 45. Advanced EEG signal processing and feature extraction concepts
1 Introduction
1.1 EEG signal recording
1.1.1 10–20 system nomenclature
1.2 EEG frequency bands are mentioned in the following which signifies the various brain states
1.3 EEG signal and various applications
2 Proposed method
2.1 Various libraries are present for EEG signal processing
2.2 Steps for EEG signal processing
3 Results and discussion
3.1 EEG signal decomposition
4 Conclusion
Chapter 46. Fractal analysis on biomedical signal
1 Introduction
2 Multifractal analysis
2.1 Algorithm for MF-DFA consists of mainly preprocessing of time-series and scaling analysis
2.1.1 Preprocessing of time-series
2.1.2 Scaling analysis
3 Result
4 Conclusion
Chapter 47. Detection of metastasis osteosarcoma using deep fuzzy gradient recurrent convolutional neural network
1 Introduction
2 Related works
3 Proposed work
3.1 Input image
3.2 Image preprocessing
3.2.1 Median filter
3.3 Image segmentation
3.3.1 Fuzzy rank correlation
3.4 Feature extraction using deep probabilistic hough transform
3.5 Image classification using deep fuzzy gradient recurrent convolutional neural network
3.5.1 Pooling layer
3.5.2 Full connection layer
3.5.3 Output layer
4 Performance analysis
4.1 Accuracy
4.2 F1-score
4.3 Sensitivity
4.4 Specificity
5 Conclusion
Chapter 48. Deep learning based fatigue detection using functional connectivity
1 Introduction
1.1 Electroencephalography signal-based fatigue detection using computational intelligence
2 Proposed model
2.1 Data acquisition
2.2 Preprocessing of EEG signals
2.2.1 Downsampling
2.2.2 Filtering
2.2.3 Channel locations
2.2.4 Re-referencing
2.2.5 Bad channels removal
2.2.6 Interpolation
2.2.7 Epoch
2.2.8 Artifact removal
2.2.9 ICA decomposition
2.3 Classification
2.3.1 Implementation of machine learning models
2.3.2 Implementation of the deep learning model
3 Results and discussion
4 Conclusion
Chapter 49. Brain tumor diagnosis using image classifier
1 Introduction
1.1 Brain tumor
1.2 Major types of brain tumors
1.3 Signs and symptoms
1.4 Causes of brain tumor
1.5 Exiting system to detect brain tumor
1.5.1 Neurological examination
1.5.2 Brain scan
1.5.3 Magnetic resonance imaging
1.5.4 Computed tomography
2 Methodology
2.1 Artificial intelligence
2.2 Brain tumor
2.3 Operation of neural networks
2.4 Transfer learning
2.5 Activation function
2.6 Convolutional neural network
2.7 Requirements for systems
2.7.1 Software tools needed
2.7.2 Hardware equipment needed
2.8 Datasets
2.8.1 Kaggle dataset
2.8.2 BRaTS MICCAI dataset
3 Steps to detect tumor
3.1 Data augmentation
3.2 Image pre-processing
3.3 Segmentation
3.4 Feature extraction
3.5 Machine learning training and testing
4 Result analysis and discussion
5 Conclusion
6 Future scope
Chapter 50. ISL recognition system in real time using TensorFlow API
1 Introduction
2 Related work
3 Methodology
3.1 CNN-based proposed model
3.1.1 Dataset preparation and preprocessing
3.1.2 MobileNet SSD model
3.1.3 CNN—results and discussion
3.2 LSTM-ased proposed model
3.2.1 Dataset acquisition
3.2.2 LSTM model architecture
3.2.3 LSTM—results and discussion
4 Conclusion and future work
Chapter 51. Exploring the exciting potential and challenges of brain computer interfaces
1 Introduction
1.1 Types of BCIs
1.2 BCI system structure
2 Proposed method
3 Results and discussion
4 Conclusion
Chapter 52. Transmission dynamics of COVID-19 virus disease
1 Introduction
2 Materials and methods
2.1 Mathematical formulation of the proposed model
2.2 Positivity solution
2.3 Disease free equilibrium state is obtain as follows
2.4 Disease-free equilibrium state
2.5 Endemic equilibrium point
2.6 Reproductive number (Ro)
3 Results and discussion
3.1 Stability analysis or disease-free equilibrium (DFE)
3.2 Simulation results
3.3 Discussion
4 Conclusion
Chapter 53. Design of high voltage biphasic pulse generation circuit with 3-level isolation suitable for AED applications
1 Introduction
1.1 Literature survey
2 Design methodology
2.1 High voltage generator
2.2 Energy storage capacitor
2.3 Three-level isolation circuit
2.4 Flyback HV converter
2.5 Flyback transformer design
3 LTSPICE simulation of high voltage charging and discharging
4 Real time implementation and testing
5 Calibration chart
6 Conclusion
Chapter 54. A novel scheme of brain tumor detection from MRIs using K-means segmentation and histogram analysis
1 Introduction
2 Planned procedure
2.1 Classification
3 K-means fragmentation
3.1 Peak signal to noise ratio
4 Results and discussion
4.1 MRI classification outcomes
5 Conclusion
Chapter 55. Analyzing post COVID-19 effects on self-consciousness and awareness toward health: A neuroscience framework
1 Introduction
2 Existing work
3 Methods and materials
3.1 Data description
3.2 Clustering
3.3 Predictors of self-consciousness and awareness
3.3.1 Effect on self-consciousness and awareness
3.3.2 Influential factor for self-consciousness and awareness
4 Discussion
5 Conclusion
Chapter 56. Crowdsourcing and artificial intelligence based modeling framework for effective Public Healthcare Informatics and Smart eHealth System
1 Introduction
1.1 What is crowdsourcing?
1.2 The scale of crowdsourcing
2 Need and development of crowdsourcing in knowledge discovery process
3 Crowdsourcing and artificial intelligence shaping the refined knowledge discovery processes
4 The use of crowdsourcing in the public health sector
4.1 Knowledge discovery and management
4.2 Peer-vetted creative production, knowledge
4.3 Distributed human intelligence and tasking
4.4 Broadcasting and searching methodology
5 Advantages of crowdsourcing
5.1 Cost-effective
5.2 Crowdsourcing
5.3 Fresh perspective
5.4 Range
5.5 Marketing
5.6 Hiring
6 Disadvantages of crowdsourcing
6.1 Secrecy and privacy issues and their ethical handling
6.2 Plagiarism and information leakages
6.3 Intellectual property rights–related issues and lack of handlings rules
6.4 Tenderfeet
6.5 Risk
7 System architecture for crowdsourced—Public health disease surveillance–disaster preparedness healthcare system
8 Blockchain-enabled crowdsourcing structure with scattered job consignments and clarification accreditation
9 Conclusion
Index

M. A. Ansari

Dr. M.A. Ansari holds PhD degree on Signal and Imaging Processing from Indian Institute of Technology Roorkee. He has 18 years of experience in teaching and research. Currently he is Professor at School of Engineering, Gautam Buddha University, where he supervised 4 PhD and 63 MTech students to date. He authored several book chapters and published almost 30 peer-reviewed articles in international journals. Dr. Ansari main research interests are medical image coding, biomedical instrumentation and control, and digital signal and image processing.

Affiliations and expertise

Professor, School of Engineering, Gautam Buddha University, India

R.S Anand

R. S. Anand received the B.E., M.E., and Ph.D. degrees from the University of Roorkee, Roorkee, India, in 1985, 1987, and 1992, respectively.,He is currently a Professor with the Electrical Engineering Department, IIT Roorkee, Roorkee. He has authored or coauthored more than 200 research papers in journals and conferences. His current research interests include medical signal and image processing, ultrasonic nondestructive evaluation (NDE), medical diagnosis, and speech signal processing.,Dr. Anand is a Life Member of the Ultrasonic Society of India.

Affiliations and expertise

Professor, Department of Electrical Engineering ,Indian Institute of Technology, Roorkee, India

Pragati Tripathi

Pragati Tripathi received an M.Tech degree in power electronics from Gautam Buddha University, Greater Noida, India, in 2018. She is working as a Research Scholar with the School of Engineering, Gautam Buddha University. She has also been associated with IIT Delhi and served as a Research Associate with Sharda University, Greater Noida. Her research interests include signal processing, brain mapping, and neuroscience.

Affiliations and expertise

Biomedical Laboratory Department of Electrical Engineering, Gautam Buddha University. India

Rajat Mehrotra

Rajat Mehrotra is an Assistant Professor in the Electrical & Electronics Engineering Department at GL Bajaj Institute of Technology & Management, Greater Noida, India. He received his BTech in Electrical and Electronics Engineering from the Dr. A.P.J. Abdul Kalam Technical University, Lucknow (Formerly UPTU), in 2008 and his MTech in Telecommunication Engineering from the same university, in 2014 and his PhD. in the field of Medical Image Processing. His research interests include digital image processing, biomedical imaging, and deep learning. Currently, he is involved in research with the School of Engineering at Gautam Buddha University, Greater Noida. He has published his research in various journals of international repute. He has more than 14 years of experience in teaching and research. He has also published multiple patents in his area of research.

Affiliations and expertise

Bajaj Institute of Technology ,GL Bajaj Institute of Technology & Management, Greater Noida, India

Md Belal Bin Heyat

Md Belal Bin Heyat received the B.tech degree in E.I. from Integral University, Lucknow, UP, India in 2014. He is successfully completed Master of Technology degree in Electronics Circuit & System, department of electronics and communication engineering from Integral University, Lucknow, Uttar Pradesh, India in 2016. He has author and co-author in number of International journals, National journals, Symposium and Conferences. He is an editor and reviewer for three international and national journals. His research interests include electronics, communication engineering, instrumentation, therapy, medical and biomedical engineering.

Affiliations and expertise

Shenzhen University School of Computer Science and Software Engineering Shenzhen, Guangdong, China

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Artificial Intelligence in Biomedical and Modern Healthcare Informatics

Purchase options

World Book Day Celebration!

Institutional subscription on ScienceDirect

M. A. Ansari

R.S Anand

Pragati Tripathi

Rajat Mehrotra

Md Belal Bin Heyat

Related books