Brain and Behavior Computing
- Length: 400 pages
- Edition: 1
- Language: English
- Publisher: CRC Press
- Publication Date: 2021-06-24
- ISBN-10: 0367552973
- ISBN-13: 9780367552978
- Sales Rank: #0 (See Top 100 Books)
Brain and Behavior Computing offers insights into the functions of the human brain. This book provides an emphasis on brain and behavior computing with different modalities available such as signal processing, image processing, data sciences, statistics further it includes fundamental, mathematical model, algorithms, case studies, and future research scopes. It further illustrates brain signal sources and how the brain signal can process, manipulate, and transform in different domains allowing researchers and professionals to extract information about the physiological condition of the brain.
Emphasizes real challenges in brain signal processing for a variety of applications for analysis, classification, and clustering.
Discusses data sciences and its applications in brain computing visualization. Covers all the most recent tools for analysing the brain and it’s working.
Describes brain modeling and all possible machine learning methods and their uses.
Augments the use of data mining and machine learning to brain computer interface (BCI) devices.
Includes case studies and actual simulation examples. This book is aimed at researchers, professionals, and graduate students in image processing and computer vision, biomedical engineering, signal processing, and brain and behavior computing.
Cover Half Title Title Page Copyright Page Dedication Contents Preface Acknowledgments Editors' Biographies Contributors 1. Simulation Tools for Brain Signal Analysis 1.1. Introduction 1.2. Toolboxes for Analysis of Brain Signal (EEG/MEG) Recordings 1.2.1. EEGLAB-Toolbox 1.2.1.1. EEGLAB-GUI 1.2.1.2. Data Importing 1.2.1.2.1. Load Data as MATLABĀ® Array 1.2.1.3. EEGLAB Data-Structure 1.2.2. Brain Computer Interface Lab Toolbox (BCILab) 1.2.2.1. Installation 1.2.2.2. BCILab-GUI 1.2.2.3. BCILab Scripting 1.2.2.3.1. Example 1.2.3. PyEEG 1.2.3.1. Example 1.2.4. Fieldtrip Toolbox 1.2.4.1. Installation 1.2.4.2. Reading the MEG/EEG Recording Using Fieldtrip 1.2.4.3. Reading Event Information 1.2.4.4. Re-Referencing EEG Recordings 1.2.4.5. Visualize Electrode Locations 1.2.4.6. Example 1.2.5. BrainNet Viewer 1.2.5.1. Installation 1.2.5.2. File Menu 1.2.5.2.1. Load Surface File 1.2.5.2.2. Load Node File 1.2.5.2.3. Load Edge File 1.2.5.3. Option Menu 1.2.5.3.1. Layout Option Panel 1.2.5.3.2. Global Option Panel 1.2.5.3.3. Surface Option Panel 1.2.5.3.4. Node Option Panel 1.2.5.3.5. Edge Option Panel 1.2.5.3.6. Volume Option Panel 1.2.5.3.7. Image Option Panel 1.2.5.4. Visualize Menu 1.2.5.5. Tools Menu 1.3. Conclusion References 2. Processing Techniques and Analysis of Brain Sensor Data Using Electroencephalography 2.1. Introduction 2.2. Building Blocks of the Human Brain 2.3. Brain Signal Acquisition Techniques 2.3.1. Local Field Potential (LFP) 2.3.2. Positron Emission Tomography (PET) 2.3.3. Electroencephalography (EEG) 2.3.4. Functional Near-Infrared Spectroscopy (fNIRS) 2.4. Electroencephalogram (EEG) 2.4.1. EEG Sensor Data Collection 2.4.2. Applications of EEG Signals 2.4.3. EEG Signal Preprocessing 2.4.3.1. ICA Algorithm 2.5. Statistical Analysis of Brain Sensor Data 2.5.1. Parametric Test 2.5.2. Nonparametric Test 2.6. EEG Sensor Data Analysis 2.6.1. Time-Domain Analysis 2.6.2. Frequency Domain Analysis 2.6.2.1. Fast Fourier Transform 2.6.3. Time-Frequency Domain Analysis 2.6.3.1. Complex Morlet Wavelet 2.7. Extreme Learning Machine (ELM) 2.7.1. ELM Algorithm 2.7.2. Dataset Description 2.7.3. Results 2.8. Conclusion References 3. Application of Machine-Learning Techniques in Electroencephalography Signals 3.1. Introduction 3.2. Brain and Electroencephalography (EEG) 3.2.1. Human Brain 3.2.2. Fundamentals of Brain Activities and Their Electrical Nature 3.2.3. Principles of EEG and What They Measure 3.2.4. Importance of EEG and Its Signal Processing Features 3.3. Introduction to Machine Learning Techniques 3.3.1. Conventional Machine Learning Algorithms for Classification 3.3.2. Deep Learning Algorithms for Classification 3.3.2.1. Convolution Layer 3.3.2.2. Activation Function 3.3.2.3. Pooling Layer 3.3.2.4. Post Processing of Predicted Label 3.3.3. Deciding on a Classification Algorithm 3.4. Neuroscience Application of Machine Learning Using EEG Signals 3.4.1. Seizure Detection 3.4.1.1. Background: What Are Seizures? 3.4.1.2. Application: How Can ML Help Predict Seizure From EEG? 3.4.2. Sleep Stage Detection 3.4.2.1. Background: What Is Sleep? 3.4.2.2. Application: How Can ML Help Classify Sleep Stages From EEG? 3.5. Summary References 4. Revolution of Brain Computer Interface: An Introduction 4.1. Introduction 4.2. Neuroimaging Approaches in BCIs 4.3. Types of BCIs 4.4. Neurophysiologic Signals 4.4.1. Event-Related Potential (ERP) 4.4.2. Neuronal Ensemble Activity (NEA) 4.4.3. Oscillatory Brain Activity (OBA) 4.4.4. Visual Evoked Potential (VEP) 4.4.5. P300 Evoked Potential 4.4.6. Slow Cortical Potential (SCP) 4.4.7. Sensorimotor Rhythm 4.5. Signal Processing and Machine Learning 4.5.1. Frequency Domain Feature (FDF) 4.5.2. Time Domain Feature (TDF) 4.5.3. Machine Learning Feature (MLF) 4.5.4. Spatial Domain Feature (SDF) 4.6. The Challenges in The Brain Computer Interface: 4.6.1. Information Transfer Rate ("ITR") 4.6.2. High Error Rate ("HER") 4.6.3. Autonomy 4.6.4. Cognitive Burden 4.6.5. Training Process 4.7. The Development of Biosensing Techniques for BCI Applications 4.7.1. Wet Sensor 4.7.2. Dry Biosensor 4.7.3. Nano- and Microtechnology Sensors 4.7.4. Multimodality Sensors 4.8. Integration of Sensing Devices and Biosensors Into BCI Systems 4.8.1. Present Developments in Biosensing Device Technologies 4.8.1.1. Essential System Design 4.8.1.2. Simple Front-End 4.8.1.3. Transmission Medium 4.8.2. Advances of Future Bio-sensing Technique in BCI 4.8.2.1. Scaling Down of Power Sources 4.8.2.2. Real Life Applications of Human Brain Imaging 4.9. BCI Technology 4.9.1. Functional Near Infrared Technology (fNIR) 4.9.2. Functional Near Infrared (fNIR) Device 4.9.3. Shut Circled, Input Managed, fNIR Based Brain Computer Interface 4.10. Applications 4.10.1. Communications 4.10.2. Entertainments 4.10.3. Educational and Self-Regulation 4.10.4. Medical Applications 4.10.4.1. Detection and Diagnosis 4.10.4.2. Prevention 4.10.4.3. Restoration and Rehabilitation 4.10.5. Other BCI Applications 4.11. Future Scope 4.11.1. The Future of BCI Technologies 4.11.1.1. Direct Control (DC) 4.11.1.2. Circuitous Control or Indirect Control (CC or IC) 4.11.1.3. Communications 4.11.1.4. Brain-Process Modification (BPM) 4.11.1.5. Mental State Detection (MSD) 4.11.1.6. Opportunistic State-Based Detection (OSBD) 4.11.2. Future BCI Applications Based on Advanced Biosensing Technology 4.12. Conclusions References 5. Signal Modeling Using Spatial Filtering and Matching Wavelet Feature Extraction for Classification of Brain Activity Patterns 5.1. Introduction 5.1.1. Sensorimotor Rhythms (SMR): An Efficient Input to BCI 5.2. Signal Processing Strategies for BCI 5.2.1. Signal Modelling Methods 5.2.1.1. Surface Laplacian (SL) Counteracting the Volume Conduction 5.2.2. Feature Extraction Strategies 5.2.2.1. Wavelet Transform 5.2.2.2. Methods for Wavelet Function Selection 5.2.3. Feature Formation 5.2.4. Feature Selection Strategies 5.2.5. Classifier 5.2.5.1. Support Vector Machine for Classification 5.2.5.2. Discriminant Analysis for Classification 5.2.5.3. K-Nearest Neighbor (k-NN) 5.3. Dataset Used 5.4. Implementation Methodology 5.4.1. Implementation of Surface Laplacian 5.4.2. Wavelet Function Selection Methodology 5.4.2.1. Level of Wavelet Decomposition 5.4.2.2. Wavelet Function Selection 5.4.2.3. Optimized Feature Extraction and Classification 5.5. Results 5.6. Concluding Remarks References 6. Study and Analysis of the Visual P300 Speller on Neurotypical Subjects 6.1. Introduction 6.1.1. Goals and Objectives 6.2. Literature Review 6.3. Dataset Description 6.4. Electroencephalography 6.4.1. Event Related Potential 6.5. P300 Speller 6.6. Manual Feature Extraction 6.7. Classification Techniques 6.8. Model Fitting (Support Vector Machine) 6.9. Proposed Methodology 6.9.1. Manual Approach 6.9.1.1. Feature Extraction 6.9.1.2. Feature Selection 6.9.1.3. Classification 6.9.2. Semi-Automated Approach 6.10. Result and Analysis 6.10.1. Results through Manual Approach 6.10.2. Results through the Semi-Automated Approach 6.10.3. Comparison of the Two Techniques 6.11. Conclusion Acknowledgments References 7. Effective Brain Computer Interface Based on the Adaptive-Rate Processing and Classification of Motor Imagery Tasks 7.1. Introduction and Background 7.2. Motivation and Contribution 7.3. Electroencephalography in Healthcare and BCI 7.4. The Proposed Approach 7.4.1. Dataset 7.4.2. Reconstruction 7.4.3. The Event-Driven A/D Converter (EDADC) 7.4.4. The Event-Driven Segmentation 7.4.5. Extraction of Features 7.4.5.1. Extraction of Time Domain Features 7.4.5.2. Extraction of Frequency Domain Features 7.4.6. Machine Learning Algorithms 7.4.6.1. Support Vector Machine (SVM) k-Nearest Neighbors (k-NN) 7.5. The Performance Evaluation Measures 7.5.1. Compression Ratio 7.5.2. Computational Complexity 7.5.3. Classification Accuracy 7.5.3.1. Accuracy (Acc) 7.5.3.2 Specificity (Sp) 7.6. Experimental Results 7.7. Discussion 7.8. Conclusion Acknowledgments References 8. EEG-Based BCI Systems for Neurorehabilitation Applications 8.1. Introduction 8.1.1. Classification of BCI Systems 8.1.1.1. Invasive, Semi-Invasive and Non-Invasive BCI Systems 8.1.1.2. Exogenous and Endogenous BCI Systems 8.1.1.3. Synchronous and Asynchronous BCI Systems 8.1.1.4. Dependent and Independent BCI Systems 8.2. EEG Based BCI System Architecture for Neurorehabilitation 8.2.1. Pre-Rehabilitation Phase 8.2.2. Rehabilitation Phase 8.2.3. Post-rehabilitation Phase 8.3. Types of BCI Paradigms 8.3.1. Steady-State Visual Evoked Potential (SSVEP) 8.3.1.1. Introduction 8.3.1.2. Case Study for SSVEP-BCI Implementation in Neurorehabilitation: BCI Based 3D Virtual Playground for the Attention Deficit Hyperactivity Disorder (ADHD) Patients 8.3.1.2.1. Methodology and Experimental Setup 8.3.1.2.2. Experimental Results 8.3.1.2.3. Case Study Conclusion 8.3.2. P300 8.3.2.1. Introduction 8.3.2.2. Case Study for P300-BCI Implementation in Neurorehabilitation: Adaptive Filtering for Detection of User-Independent Event Related Potentials in BCIs 8.3.2.2.1. Methodology and Experimental Setup 8.3.2.2.2. Experimental Results 8.3.2.2.3. Case Study Conclusion 8.3.3. Motor Imagery (MI) 8.3.3.1. Introduction 8.3.3.2. Case Study for MI-BCI Implementation in Neurorehabilitation: Brain Computer Interface in Cognitive Neurorehabilitation 8.3.3.2.1. Methodology and Experimental Setup 8.3.3.2.2. Experimental Results 8.3.3.2.3. Case Study Conclusion 8.4. Types of BCI Controlled Motion Functioning Units 8.4.1. Functional Electric Stimulation (FES) 8.4.2. Robotics Assistance 8.4.3. VR Based Hybrid Unit 8.5. Neurorehabilitation Applications of BCI Systems 8.6. Conclusion References 9. Scalp EEG Classification Using TQWT-Entropy Features for Epileptic Seizure Detection 9.1. Introduction 9.2. Material and Methods 9.2.1. EEG Data 9.2.2. TQWT-Based EEG Decomposition 9.3. Feature Extraction Methodology 9.3.1. Approximate Entropy (AE) Estimation 9.3.2. Sample Entropy (SE) Estimation 9.3.3. Renyi's Entropy (RE) Estimation 9.3.4. Permutation Entropy (PE) Estimation 9.4. Soft Computing Techniques 9.5. Results and Discussion 9.6. Conclusion References 10. An Efficient Single-Trial Classification Approach for Devanagari Script-Based Visual P300 Speller Using Knowledge Distillation and Transfer Learning 10.1. Introduction 10.2. Methodology 10.2.1. The Dataset 10.2.2. Details of the Proposed Architecture 10.2.2.1. Block-1 (L0): Input 10.2.2.2. Block-2 (L1-L2): Temporal Information 10.2.2.3. Block-3 (L3-L5): Spatial Information 10.2.2.4. Block-4 (L6-L7): Class Prediction 10.2.3. Knowledge Distillation (Teacher-Student Network) 10.3. Experimental Setup 10.3.1. Transfer Learning 10.3.1.1. Inter-Subject Transfer Learning 10.3.1.2. Inter-Trial Transfer Learning 10.3.2. Training Settings 10.4. Results 10.4.1. ShallowCNN 10.4.1.1. Cross-Subject Analysis 10.4.1.2. Within-Subject Analysis 10.4.2. EEGNet 10.4.2.1. Cross-Subject Analysis 10.4.2.2. Within-Subject Analysis 10.4.3. Proposed Channel-Wise EEGNet 10.4.3.1. Cross-Subject Analysis 10.4.3.2. Within-Subject Analysis 10.5. Discussion 10.5.1. Hypothesis 1: Channel-Mix Versus Channel-Wise Convolution 10.5.2. Hypothesis 2: Effect of Knowledge Distillation 10.5.3. Hypothesis 3: Data Balancing Approaches 10.5.4. Hypotheses 4 & 5: Effect of Transfer Learning 10.6. Conclusion Acknowledgment References 11. Deep Learning Algorithms for Brain Image Analysis 11.1. Introduction 11.2. Brain Image Data and Strategies 11.3. Deep Neural Networks 11.3.1. Perceptron 11.3.2. FeedForward Neural Networks 11.3.3. Convolutional Neural Networks 11.4. Image Registration 11.4.1. Rigid Registration 11.4.2. Deformable Registration 11.4.3. Experiments 11.4.3.1. Impact of Loss Function 11.4.4. Multimodal Registration 11.4.5. Atlas Construction 11.5. Image Segmentation 11.5.1. Ischemic Stroke Lesion Segmentation 11.5.2. Brain Tumor Segmentation 11.5.3. Multiple Sclerosis Lesion Segmentation 11.5.4. Hippocampus Segmentation 11.5.5. Experiments 11.6. Image Classification 11.6.1. Schizophrenia Diagnosis 11.6.2. Diagnosis of Alzheimer Disease 11.7. Conclusion Notes References 12. Evolutionary Optimization-Based Two-Dimensional Elliptical FIR Filters for Skull Stripping in Brain Imaging and Disorder Detection 12.1. Introduction 12.2. Pre-Processing 12.2.1. Image Enhancement 12.2.2. Image Denoise 12.2.3. Skull Stripping 12.3. Filter Design for Image Enhancement (Formulation of Objectives) 12.4. Filter Design for Image Denoising (Formulation of Objectives) 12.5. Filter Design for Skull Stripping (Formulation of Objectives) 12.6. ABC Algorithm 12.7. QABC Algorithm 12.8. Skull Stripping and Brain Tumor Localization Architecture 12.9. Results and Discussion 12.9.1. Examples of Skull Stripping 12.9.2. Examples of Tumor Segmentation 12.9.3. Tumor Localization 12.10. Conclusion References 13. EEG-Based Neurofeedback Game for Focus Level Enhancement 13.1. Introduction 13.1.1. Brain Computer Interface and Neurofeedback 13.1.2. Types of NF and Brain Rhythms 13.1.3. EEG-Based Games 13.2. Neurofeedback Game Design 13.2.1. System Framework 13.2.2. EEG Data Acquisition Module 13.2.3. EEG Game Design with Unity 3D 13.2.4. The Car Driving Game 13.2.4.1. The EEG Headset Panel 13.2.4.2. The Stages 13.2.4.3. The Controls 13.2.5. Computation of FL and Scores 13.2.5.1. Computation of FL 13.2.5.2. Computation of Scores 13.3. Neurofeedback Session 13.3.1. Subjects 13.3.2. Mental Command Training 13.3.3. Neurofeedback Sessions through Game Playing 13.4. Results and Discussion 13.4.1. Effect of Age of the Participants 13.4.2. Effect of Gender of the Participants 13.4.3. Effect of Game Elements 13.5. Conclusion and Future Recommendations Acknowledgment References 14. Detecting K-Complexes in Brain Signals Using WSST2-DETOKS 14.1. Introduction 14.2. Synchro-Squeezed Wavelet Transform 14.3. Second-Order Wavelet-Based SST 14.3.1. Numerical Implementation of WSST2 14.3.2. Computing WSST2 14.4. Detection of Sleep Spindles and K-Complexes (DETOKS) 14.4.1. Sparse Optimization 14.5. WSST2-DETOKS for K-Complex Detection 14.5.1. Problem Formulation 14.5.2. Algorithm 14.6. Data Description 14.6.1. Proposed Scoring Method 14.7. Results 14.7.1. Statistical Analysis 14.8. Conclusion Acknowledgment References 15. Directed Functional Brain Networks: Characterization of Information Flow Direction during Cognitive Function Using Non-Linear Granger Causality 15.1. Introduction 15.2. Directed Functional Brain Network Construction 15.3. Granger Causality 15.4. Directed FBNs ANALYSIS 15.4.1. Connectivity Density 15.4.2. Clustering Coefficient 15.4.3. Local Information Measure 15.5. Methods 15.5.1. Participants in the Cognitive Experiments 15.5.2. EEG Data Collection 15.5.2.1. Baseline - Eyes Open (EOP) 15.5.2.2. Cognitive Task Relating to Visual Search (VS) 15.5.2.3. Web Search Cognitive Task (Around 5-10 Minutes) 15.5.3. EEG Signal Pre-processing 15.5.4. A Framework for the Computation and Analysis of Information Flow Direction Patterns 15.5.5. Information Flow Direction Patterns (IFDP) for Weighted Directed Network 15.6. Results and Discussion 15.6.1. Binary Directed Functional Brain Network 15.6.1.1. Connectivity Density 15.6.1.2. Clustering Coefficient 15.6.2. Weighted Directed Functional Brain Network 15.6.2.1. Weighted IFDP Analysis 15.6.2.2. Local Information Measure 15.7. Conclusion References 16. Student Behavior Modeling and Context Acquisition: A Ubiquitous Learning Framework 16.1. Introduction 16.2. A Survey on Context Modeling Frameworks 16.2.1. Context Modeling Approaches 16.2.1.1. Various Context Modeling Approaches in Ubiquitous Learning Environments 16.2.2. Context Acquisition, Reasoning, and Dissemination in Ubiquitous Learning Environments 16.2.2.1. Student Learning Behavioral Model 16.2.2.2. Subject Domain 16.2.2.3. Context Acquisition and Dissemination 16.3. Proposed Modeling of Student Learning Behavior, Subject Domain, and Context Acquisition in Ubiquitous Learning Environments 16.3.1. Student Context Information Representation 16.3.2. Supporting Structure of Context Acquisition 16.3.3. Student Modeling 16.3.4. Learning Behavior Goal Elements of a Student 16.3.5. Subject Domain Modeling 16.3.6. Context Information Modeling in Ubiquitous Learning Systems 16.3.7. Context Information Modeling for Specific Student's Accessing the System 16.4. Evaluation of Proposed Model in Various Learning Scenarios 16.4.1. Professional Student Accessing the System 16.4.2. Novice Student to Check on Negative Emotions 16.5. Conclusion References Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.