Brain and Behavior Computing

Mridu Sahu, G R Sinha, Mridu Sahu, G R Sinha

• Publisher: CRC Press
• Year: 2021
• Print ISBN: 9780367552978
• eBook ISBN: 9781000387223
• Topic: Ciencia de la computación
• Subtopic: Biotecnología en medicina

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.

1	Simulation Tools for Brain Signal Analysis

Munaza Ramzan and Suma Dawn

1.1 Introduction

The human brain contains 86 billion neurons with an average of 7,000 connections (synapses) to each other. The coordination and interaction of neurons with specific brain regions incorporate the functioning and working of the central nervous system (CNS) [1]. Therefore, it’s not possible to analyze the information transmission and compare experimental results without simulation tools. To analyze such coordination and turn them into transformative gains of various practical and clinical applications, we need ongoing processing tools and data structures. With brain simulation tools, the brain-related mathematical theory, principles, and signals are returned out into new insights and improve computational validation of input data. They can be used for both online and offline data analysis, connectivity analysis, and visualization [2]. Brain-computer interface (BCI) is an integrated system comprised of analyzed brain signals and a computer to predict and monitor a particular state of a person. The brain signals which are produced by the CNS are acquired, analyzed, and translated into desired actions in three different ways [3]. First, the active BCIs are controlled by users consciously, and the output is directly extracted from conscious brain waves. Second, the reactive BCIs are stimulus-dependent in which the user reacts to an external stimulus, and the brain waves are modulated and analyzed indirectly to control an application. Third, the passive BCIs or implicit BCIs arbitrarily derive the output from extracted brain activities without the user control, such as monitoring of user intention and interpretation of different emotional states. To predict or monitor the person’s cognitive state using brain signals, researchers and experimenters need to measure and analyze these signals in a well-defined manner. With this monitoring, different types of BCIs can be developed such as active, reactive, or passive BCIs. The basic requirement for each BCI system is the acquisition of brain signals and the commonly studied signals may include: electrical and magnetic signals [4]. The procedure for capturing such signals are EEG and MEG, respectively. To allow the processing and analysis of these signals, a collection of tools such as EEGLAB, BCILab, Fieldtrip, etc., as shown in Table 1.1, has been developed by different neuroscience communities [5]. Most of the tools are freely available for the analysis of multimodal signals with advanced signal processing techniques and methods.

Table 1.1
BSTs for EEG/MEG signals

Toolbox	Version	License	Open-source	Framework	Procedures supported	Download link
EEGLAB	14 & 2019	GNU	Yes	MATLAB®	EEG, MEG	https://sccn.ucsd.edu/eeglab/download.php
BCILAB	1.0-beta	GNU	Yes	MATLAB®, EEGLAB-Plugin	EEG, MEG	ftp://sccn.ucsd.edu/pub/bcilab
Fieldtrip	–	GNU	Yes	MATLAB®	EEG, MEG, NIRS, ECoG	http://www.fieldtriptoolbox.org/download/
BrainNet Viewer	1.7	GNU	Yes	MATLAB®	Brain Network Visualization Toolbox.	https://www.nitrc.org/projects/bnv/
SIFT	1.4.1	GNU	Yes	MATLAB®	EEG, MEG, ECoG	https://www.nitrc.org/frs/downloadlink.php/9394
PyEEG	–	GNU	Yes	Python	EEG, MEG	https://github.com/forrestbao/pyeeg

The brain is continuously involved in cognitive activities, and to identify the certain task or hypothesis-related patterns and aspects, good quality signals need to be acquired and analyzed properly. The general protocol for analysis includes brain signal acquisition (EEG, MEG), pre-processing (detection and removal of artifacts, and noise), computation of statistical features, and then apply different learning algorithms and procedures.

1.2 Toolboxes for Analysis of Brain Signal (EEG/MEG) Recordings

1.2.1 EEGLAB-Toolbox

The EEGLAB is an interactive graphical user interface (GUI) MATLAB® toolbox for the analysis of electrophysiological signals such as EEG and MEG. It runs under different operating systems such as Windows, Unix, Linux, and Mac OS X. It is developed at Swartz Center for Computational Neuroscience (SCCN) and freely available at https://sccn.ucsd.edu/eeglab/download.php. It allows importing, exporting, loading, saving, manipulating, artifact rejection, time-frequency analysis, independent component analysis (ICA), and visualization of continuous and event-related EEG/MEG signals [6]. For special analysis and modeling, different EEGLAB plug-ins are available such as EMDLAB for empirical mode decomposition analysis, ERPLAB for event-related potential (ERP), and CSP for the analysis of common spatial patterns. It is accessible via three ways: (a) EEGLAB-GUI, (b) EEGLAB data structure and command history, and (c) EEGLAB scripting [7].

The below steps need to follow for installing EEGLAB-toolbox on your machine:

• After downloading this toolbox, open MATLAB® and add EEGLAB-Toolbox path to its search path as:
MATLAB® Home -> Set Path -> Add with Subfolders -> Popup dialogue box will appear -> Select EEGLAB-Toolbox folder -> Click Ok -> Save.

• In the command window of MATLAB®, type eeglab; and hit enter as shown in Figure 1.1.

1.2.1.1 EEGLAB-GUI

The EEGLAB GUI enables users to apply various signal processing techniques and methods to EEG/MEG data without writing their own scripts. Menu shortcuts are incorporated in this t...

Table of contents

• Cover
• Half Title
• Title Page
• Copyright Page
• Dedication
• Contents
• Preface
• Acknowledgments
• Editors’ Biographies
• List of Contributors
• Chapter 1 Simulation Tools for Brain Signal Analysis
• Chapter 2 Processing Techniques and Analysis of Brain Sensor Data Using Electroencephalography
• Chapter 3 Application of Machine-Learning Techniques in Electroencephalography Signals
• Chapter 4 Revolution of Brain Computer Interface: An Introduction
• Chapter 5 Signal Modeling Using Spatial Filtering and Matching Wavelet Feature Extraction for Classification of Brain Activity Pattern
• Chapter 6 Study and Analysis of the Visual P300 Speller on Neurotypical Subjects
• Chapter 7 Effective Brain Computer Interface Based on the Adaptive-Rate Processing and Classification of Motor Imagery Tasks
• Chapter 8 EEG-Based BCI Systems for Neurorehabilitation Applications
• Chapter 9 Scalp EEG Classification Using TQWT-Entropy Features for Epileptic Seizure Detection
• Chapter 10 An Efficient Single-Trial Classification Approach for Devanagari Script-Based Visual P300 Speller Using Knowledge Distillation and Transfer Learning
• Chapter 11 Deep Learning Algorithms for Brain Image Analysis
• Chapter 12 Evolutionary Optimization-Based Two-Dimensional Elliptical FIR Filters for Skull Stripping in Brain Imaging and Disorder Detection
• Chapter 13 EEG-Based Neurofeedback Game for Focus Level Enhancement
• Chapter 14 Detecting K-Complexes in Brain Signals Using WSST2-DETOKS
• Chapter 15 Directed Functional Brain Networks: Characterization of Information Flow Direction during Cognitive Function Using Non-Linear Granger Causality
• Chapter 16 Student Behavior Modeling and Context Acquisition: A Ubiquitous Learning Framework
• Index