M. G. Sumithra, PhD, is a professor at Anna University Chennai, India. With 25 years of teaching experience, she has published more than 70 technical papers in refereed journals, 3 book chapters, and 130 research papers in national and international conferences. She is a Nvidia Deep Learning Institute Certified Instructor for "Computer Vision".Rajesh Kumar Dhanaraj, PhD, is a professor in the School of Computing Science and Engineering at Galgotias University, Greater Noida, India. He has contributed around 25 authored and edited books on various technologies, 17 patents, and more than 40 articles and papers in various refereed journals and international conferences. He is a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE).Mariofanna Milanova, PhD, is a professor in the Department of Computer Science at the University of Arkansas, Little Rock, USA. She is an IEEE Senior Member and Nvidia’s Deep Learning Institute University Ambassador. She has published more than 120 publications, more than 53 journal papers, 35 book chapters, and numerous conference papers. She also has two patents.Balamurugan Balusamy, PhD, is a professor in the School of Computing Science and Engineering, Galgotias University, Greater Noida, India. He is a Pioneer Researcher in the areas of big data and IoT and has published more than 70 articles in various top international journals.V. Chandran holds an M.E degree in VLSI Design from Government College of Technology, Coimbatore, and is a Nvidia Certified Instructor for Deep learning for Computer Vision.

• Preface xiii1 Introduction to Brain–Computer Interface: Applications and Challenges 1Jyoti R. Munavalli, Priya R. Sankpal, Sumathi A. and Jayashree M. Oli1.1 Introduction 11.2 The Brain – Its Functions 31.3 BCI Technology 31.3.1 Signal Acquisition 51.3.1.1 Invasive Methods 61.3.1.2 Non-Invasive Methods 81.3.2 Feature Extraction 101.3.3 Classification 111.3.3.1 Types of Classifiers 121.4 Applications of BCI 131.5 Challenges Faced During Implementation of BCI 17References 212 Introduction: Brain–Computer Interface and Deep Learning 25Muskan Jindal, Eshan Bajal and Areeba Kazim2.1 Introduction 262.1.1 Current Stance of P300 BCI 282.2 Brain–Computer Interface Cycle 292.3 Classification of Techniques Used for Brain–Computer Interface 382.3.1 Application in Mental Health 382.3.2 Application in Motor-Imagery 382.3.3 Application in Sleep Analysis 392.3.4 Application in Emotion Analysis 392.3.5 Hybrid Methodologies 402.3.6 Recent Notable Advancements 412.4 Case Study: A Hybrid EEG-fNIRS BCI 462.5 Conclusion, Open Issues and Future Endeavors 47References 493 Statistical Learning for Brain–Computer Interface 63Lalit Kumar Gangwar, Ankit, John A. and Rajesh E.3.1 Introduction 643.1.1 Various Techniques to BCI 643.1.1.1 Non-Invasive 643.1.1.2 Semi-Invasive 653.1.1.3 Invasive 673.2 Machine Learning Techniques to BCI 673.2.1 Support Vector Machine (SVM) 693.2.2 Neural Networks 693.3 Deep Learning Techniques Used in BCI 703.3.1 Convolutional Neural Network Model (CNN) 723.3.2 Generative DL Models 733.4 Future Direction 733.5 Conclusion 74References 754 The Impact of Brain–Computer Interface on Lifestyle of Elderly People 77Zahra Alidousti Shahraki and Mohsen Aghabozorgi Nafchi4.1 Introduction 784.2 Diagnosing Diseases 794.3 Movement Control 844.4 IoT 854.5 Cognitive Science 864.6 Olfactory System 884.7 Brain-to-Brain (B2B) Communication Systems 894.8 Hearing 904.9 Diabetes 914.10 Urinary Incontinence 924.11 Conclusion 93References 935 A Review of Innovation to Human Augmentation in Brain-Machine Interface – Potential, Limitation, and Incorporation of AI 101 T. Graceshalini, S. Rathnamala and M. Prabhanantha Kumar5.1 Introduction 1025.2 Technologies in Neuroscience for Recording and Influencing Brain Activity 1035.2.1 Brain Activity Recording Technologies 1045.2.1.1 A Non-Invasive Recording Methodology 1045.2.1.2 An Invasive Recording Methodology 1045.3 Neuroscience Technology Applications for Human Augmentation 1065.3.1 Need for BMI 1065.3.1.1 Need of BMI Individuals for Re-Establishing the Control and Communication of Motor 1075.3.1.2 Brain-Computer Interface Noninvasive Research at Wadsworth Center 1075.3.1.3 An Interface of Berlin Brain-Computer: Machine Learning-Dependent of User-Specific Brain States Detection 1075.4 History of BMI 1085.5 BMI Interpretation of Machine Learning Integration 1115.6 Beyond Current Existing Methodologies: Nanomachine Learning BMI Supported 1165.7 Challenges and Open Issues 1195.8 Conclusion 120References 1216 Resting-State fMRI: Large Data Analysis in Neuroimaging 127 M. Menagadevi , S. Mangai, S. Sudha and D. Thiyagarajan6.1 Introduction 1286.1.1 Principles of Functional Magnetic Resonance Imaging (fMRI) 1286.1.2 Resting State fMRI (rsfMRI) for Neuroimaging 1286.1.3 The Measurement of Fully Connected and Construction of Default Mode Network (DMN) 1296.2 Brain Connectivity 1296.2.1 Anatomical Connectivity 1296.2.2 Functional Connectivity 1306.3 Better Image Availability 1306.3.1 Large Data Analysis in Neuroimaging 1316.3.2 Big Data rfMRI Challenges 1336.3.3 Large rfMRI Data Software Packages 1346.4 Informatics Infrastructure and Analytical Analysis 1376.5 Need of Resting-State MRI 1376.5.1 Cerebral Energetics 1376.5.2 Signal to Noise Ratio (SNR) 1376.5.3 Multi-Purpose Data Sets 1386.5.4 Expanded Patient Populations 1386.5.5 Reliability 1386.6 Technical Development 1386.7 rsfMRI Clinical Applications 1396.7.1 Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) 1396.7.2 Fronto-Temporal Dementia (FTD) 1406.7.3 Multiple Sclerosis (MS) 1416.7.4 Amyotrophic Lateral Sclerosis (ALS) and Depression 1436.7.5 Bipolar 1446.7.6 Schizophrenia 1456.7.7 Attention Deficit Hyperactivity Disorder (ADHD) 1476.7.8 Multiple System Atrophy (MSA) 1476.7.9 Epilepsy/Seizures 1476.7.10 Pediatric Applications 1496.8 Resting-State Functional Imaging of Neonatal Brain Image 1496.9 Different Groups in Brain Disease 1516.10 Learning Algorithms for Analyzing rsfMRI 1516.11 Conclusion and Future Directions 154References 1547 Early Prediction of Epileptic Seizure Using Deep Learning Algorithm 157T. Jagadesh, A. Reethika, B. Jaishankar and M.S. Kanivarshini7.1 Introduction 1587.2 Methodology 1647.3 Experimental Results 1697.4 Taking Care of Children with Seizure Disorders 1727.5 Ketogenic Diet 1727.6 Vagus Nerve Stimulation (VNS) 1727.7 Brain Surgeries 1737.8 Conclusion 173References 1758 Brain–Computer Interface-Based Real-Time Movement of Upper Limb Prostheses Topic: Improving the Quality of the Elderly with Brain-Computer Interface 179S. Vairaprakash and S. Rajagopal8.1 Introduction 1808.1.1 Motor Imagery Signal Decoding 1818.2 Literature Survey 1828.3 Methodology of Proposed Work 1848.3.1 Proposed Control Scheme 1858.3.2 One Versus All Adaptive Neural Type- 2 Fuzzy Inference System (OVAANT2FIS) 1878.3.3 Position Control of Robot Arm Using Hybrid BCI for Rehabilitation Purpose 1878.3.4 Jaco Robot Arm 1898.3.5 Scheme 1: Random Order Positional Control 1898.4 Experiments and Data Processing 1928.4.1 Feature Extraction 1958.4.2 Performance Analysis of the Detectors 1978.4.3 Performance of the Real Time Robot Arm Controllers 1988.5 Discussion 2008.6 Conclusion and Future Research Directions 202References 2039 Brain–Computer Interface-Assisted Automated Wheelchair Control Management-Cerebro: A BCI Application 205 Sudhendra Kambhamettu, Meenalosini Vimal Cruz, Anitha S., Sibi Chakkaravarthy S. and K. Nandeesh Kumar9.1 Introduction 2069.1.1 What is a BCI? 2079.2 How Do BCI’s Work? 2079.2.1 Measuring Brain Activity 2089.2.1.1 Without Surgery 2089.2.1.2 With Surgery 2089.2.2 Mental Strategies 2099.2.2.1 Ssvep 2109.2.2.2 Neural Motor Imagery 2109.3 Data Collection 2119.3.1 Overview of the Data 2119.3.2 EEG Headset 2139.3.3 EEG Signal Collection 2149.4 Data Pre-Processing 2159.4.1 Artifact Removal 2169.4.2 Signal Processing and Dimensionality Reduction 2179.4.3 Feature Extraction 2179.5 Classification 2189.5.1 Deep Learning (DL) Model Pipeline 2199.5.2 Architecture of the DL Model 2209.5.3 Output Metrics of the Classifier 2219.5.4 Deployment of DL Model 2219.5.5 Control System 2239.5.6 Control Flow Overview 2239.6 Control Modes 2239.6.1 Speech Mode 2239.6.2 Blink Stimulus Mapping 2239.6.3 Text Interface 2259.6.4 Motion Mode 2259.6.5 Motor Arrangement 2259.6.6 Imagined Motion Mapping 2269.7 Compilation of All Systems 2269.8 Conclusion 226References 22710 Identification of Imagined Bengali Vowels from EEG Signals Using Activity Map and Convolutional Neural Network 231Rajdeep Ghosh, Nidul Sinha and Souvik Phadikar10.1 Introduction 23210.1.1 Electroencephalography (EEG) 23310.1.2 Imagined Speech or Silent Speech 23310.2 Literature Survey 23410.3 Theoretical Background 23810.3.1 Convolutional Neural Network 23810.3.2 Activity Map 24010.4 Methodology 24210.4.1 Data Collection 24310.4.2 Pre-Processing 24410.4.3 Feature Extraction 24510.4.4 Classification 24710.5 Results 24910.6 Conclusion 252Acknowledgment 252References 25211 Optimized Feature Selection Techniques for Classifying Electrocorticography Signals 255B. Paulchamy, R. Uma Maheshwari, D. Sudarvizhi AP(Sr. G), R. Anandkumar AP(Sr. G) and Ravi G.11.1 Introduction 25611.1.1 Brain–Computer Interface 25611.2 Literature Study 25811.3 Proposed Methodology 26011.3.1 Dataset 26111.3.2 Feature Extraction Using Auto-Regressive (AR) Model and Wavelet Transform 26111.3.2.1 Auto-Regressive Features 26111.3.2.2 Wavelet Features 26211.3.2.3 Feature Selection Methods 26211.3.2.4 Information Gain (IG) 26311.3.2.5 Clonal Selection 26311.3.2.6 An Overview of the Steps of the Clonalg 26411.3.3 Hybrid CLONALG 26511.4 Experimental Results 26811.4.1 Results of Feature Selection Using IG with Various Classifiers 27211.4.2 Results of Optimizing Support Vector Machine Using CLONALG Selection 27411.5 Conclusion 276References 27712 BCI – Challenges, Applications, and Advancements 279R. Remya and Sumithra, M.G.12.1 Introduction 27912.1.1 BCI Structure 28012.2 Related Works 28112.3 Applications 28212.4 Challenges and Advancements 29712.5 Conclusion 299References 299Index 303