Textbook in PDF format

Artificial Intelligence for Neurological Disorders provides a comprehensive resource of state-of-the-art approaches for AI, big data analytics and machine learning-based neurological research. The book discusses many machine learning techniques to detect neurological diseases at the cellular level, as well as other applications such as image segmentation, classification and image indexing, neural networks and image processing methods. Chapters include AI techniques for the early detection of neurological disease and deep learning applications using brain imaging methods like EEG, MEG, fMRI, fNIRS and PET for seizure prediction or neuromuscular rehabilitation.
The goal of this book is to provide readers with broad coverage of these methods to encourage an even wider adoption of AI, Machine Learning and Big Data Analytics for problem-solving and stimulating neurological research and therapy advances.
About the editors
Overview
Objective
Organization
Early detection of neurological diseases using machine learning and deep learning techniques: A review
Support vector machine
Random forest
Logistic regression
Convolutional neural network
Literature review
Machine learning algorithms
Deep learning algorithms
Methodology and result analysis
Proposed method
A predictive method for emotional sentiment analysis by deep learning from EEG of brainwave dataset
Literature review
Materials and methods
IoT-based Muse headband
Feature selection
Datasets
Feature selection algorithms
Symmetric uncertainty
Deep learning model
LSTM classification
Result analysis
Conclusion and discussion
Machine learning and deep learning models for early-stage detection of Alzheimer's disease and its proli
How does AD affect the patient's life and normal functioning?
Can AD onset be avoided or at least be delayed?
Symptoms
Pathophysiology of AD
Management of AD
Introduction to machine learning and deep learning and their suitability to AD diagnosis
State of the art/national and international status
Further reading
Convolutional neural network model for identifying neurological visual disorder
Human visual system
Visual cortex
Vision disorders
Cortical blindness
Acquired cortical blindness
Congenital cortical blindness
Transient cortical blindness
Convolutional neural network
Image recognition
Image classification
Cognitive application
Neurological visual disorder identifying model
Receptive field
Activation map
Kernel filter
Recurrent neural network model for identifying neurological auditory disorder
Human auditory system
Neurological auditory disorder
Central auditory nervous system
Cortical deafness
Recurrent neural network
Speech recognition
Auditory event-related potentials
Sentence boundary disambiguation
Neurological auditory disorder identifying model
Audio segmentation
Phonetic recognition
Attention mechanism
Recurrent neural network model for identifying epilepsy based neurological auditory disorder
Related research
Multiperspective learning techniques
TSK fuzzy system
Proposed method
Shallow feature acquisition of EEG signals
Shallow feature construction in time-frequency domain
Acquisition of deep features based on deep learning
Frequency domain deep feature extraction network
Time-frequency domain deep feature extraction network
Multiview TSK blur system based on view weighting
Experimental study
Dataset
Validity analysis
Numerical analysis of deep feature extraction networks
Dementia diagnosis with EEG using machine learning
Prevalence of dementia worldwide
Electroencephalogram
Cognitive testing and EEG
Data acquisition
Preprocessing of EEG signal
Feature extraction
Linear approach
Nonlinear approach
Classification of dementia
Discussion
Computational methods for translational brain-behavior analysis
Computational physiology
Medical and data scientists
Translational brain behavioral pattern
Cognitive mapping and neural coding
Neuroelectrophysiology modeling
Clinical translation of cognitive mapping and neural coding
Systems biology in translational and computational biology
Application of system biology in translational brain tumor research
Clinical applications of deep learning in neurology and its enhancements with future directions
Medical data and artificial intelligence in neurology
Neurology-centered medical system
Clinical applications of artificial intelligence and deep learning
Artificial intelligence for medical imaging and precision medicine
Examples of neurology AI
Challenges of deep learning applied to neuroimaging techniques
AI for assessing response to targeted neurological therapies
Conclusion and future perspectives
Ensemble sparse intelligent mining techniques for cognitive disease
Cognitive disease
Machine learning and deep ensemble sparse regression network
Intelligent medical diagnostics with ensemble sparse intelligent mining techniques
High-dimensional data science in cognitive diseases
Diagnostic challenges with artificial intelligence
Conclusion and future perspectives
Cognitive therapy for brain diseases using deep learning models
Brain diseases affecting cognitive functions
Multimodal information
Connectome mapping
Post-operative seizure
Gene signature
Overview of deep learning techniques
Data preprocessing techniques
Early brain disease diagnosis using deep learning techniques
Artificial intelligence and cognitive therapies and immunotherapies
Conclusion and future perspectives
Cognitive therapy for brain diseases using artificial intelligence models
Brain diseases
Brain diseases and physiological signals
Artificial intelligence
Artificial intelligence, neuroscience, and clinical practice
Data acquisition and image interpretation
Artificial intelligence and cognitive behavioral therapy
Challenges and pitfalls
Conclusion and future direction
Clinical applications of deep learning in neurology and its enhancements with future predictions
Neural network systems, biomarkers, and physiological signals
Neurological techniques, biomedical informatics, and computational neurophysiology
Neurological techniques
Biomedical informatics
Computational neurophysiology
Data and image acquisition
Artificial intelligence and deep learning
Artificial intelligence and neurological disease prediction
Non-clinical health-related applications
Challenges and potential pitfalls of neurological techniques
Conclusion and future directions
An intelligent diagnostic approach for epileptic seizure detection and classification using machine learning
Epileptic seizure
Seizure localization
Physiological and pathophysiological signals
Chemical signals as physiological signals
Endocrine disorders as deviations from physiological signals
Neurotransmitter detection using artificial intelligence
Electrical signals as physiological signals
Action potentials
Application of electrical signals
Artificial intelligence and action potential detection
Electrocorticography and electroencephalography
Electroencephalography
Electrocardiograph recording and placement
Electroencephalography and other non-invasive techniques
Applications of electroencephalography
Electrocorticography
Role of data scientists in epileptic seizure detection
Intelligent diagnostic approaches: Machine learning and deep learning
Selecting appropriate machine learning classifiers and features
Conclusion and future research
Neural signaling and communication using machine learning
Electrophysiology of brain waves
Electrophysiology of alpha waves
Electrophysiology of beta waves
Electrophysiology of delta waves
Electrophysiology of theta waves
Electrophysiology of gamma waves
Electrophysiology of mu waves
Electrophysiology of sensorimotor rhythms
Neural signaling and communication
Neural signaling and communication
Electrical signals as physiological signals
Action potentials
Application of electrical signals
Brain-computer interface (data acquisition)
Algorithm classification of brain functions using machine learning
Artificial intelligence and neural signals, communications
Challenges and opportunities
Conclusion and future perspectives
Classification of neurodegenerative disorders using machine learning techniques
Patient datasets
Related medical examinations
Clinical tests
Biomarkers
Clinical tests and biomarkers
Classification of neurodegenerative diseases
Machine learning techniques as computer-assisted diagnostic systems
Multimodal analysis
Conclusion and future perspectives
New trends in deep learning for neuroimaging analysis and disease prediction
Deep learning techniques
Neuroimaging and data science
Cognitive impairment
Images, text, sounds, waves, biomarkers, and physiological signals
Artificial intelligence and disease diagnosis and prediction
Current challenges of heterogeneous multisite datasets and opportunities
Conclusion and future directions
Prevention and diagnosis of neurodegenerative diseases using machine learning models
Neurodegenerative diseases
Artificial intelligence (AI) and machine learning (ML)
AI and clinical practice
Neurodegenerative diseases and physiological signals
Neurodegenerative disease data acquisition
Challenges in data handling
Conclusion and future perspectives
Artificial intelligence-based early detection of neurological disease using noninvasive method based on speec...
Neurological disorders
Cognitive analysis-Psychological evaluation and physiological signals
Noninvasive screening methods for speech analysis
Computer-aided diagnosis (CAD) systems
Artificial intelligence and machine learning techniques
Deep learning-based techniques
Artificial intelligence and CAD systems for early detection of neurological disorders
Conclusion and future perspective
An insight into applications of deep learning in neuroimaging
Deep learning concepts
Recurrent neural network (RNN)
Convolutional neural network (CNN)
Self-organizing map (SOM)
Boltzmann machine (BM)
Restricted Boltzmann machine (RBM)
Autoencoder (AE)
Neuroimaging
Deep learning case studies in neurological disorders
Alzheimer's disease (AD)
Parkinson's disease (PD)
Attention-deficit/hyperactive disorder (ADHD)
Autism spectrum disorder (ASD)
Schizophrenia analysis
Dementia diagnosis
Open-source tool kits for deep learning
Challenges and future directions
Incremental variance learning-based ensemble classification model for neurological disorders
Literature review
Proposed incremental variance learning-based ensemble classification model for neurological disorders
Discrete wavelet transform
Result and comparison
Conclusion and future scope
A systematic review of adaptive machine learning techniques for early detection of Parkinson's disease
Feature engineering for identifying clinical biomarkers
Population-based metaheuristics for biomarker selection
Application of machine learning methods for diagnosing PD
Methodology and result analysis
Characteristics of chaotic maps
Proposed model
Further Reading
Back Cover