Classification of EEG data for human mental state analysis using Random Forest Classifier

Edla, Damodar Reddy; Mangalorekar, Kunal; Dhavalikar, Gauri; Dodia, Shubham

doi:10.1016/j.procs.2018.05.116

Cited by 84 publications

(34 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…RF uses multiple learning methods to achieve better prediction ability. It establishes a multitude of decision trees and classifies the data into a certain class by voting or averaging the outputs of the forests of decision trees [ 29 ]. An ensemble aggregation method with random subspace was used for the RF model.…”

Section: Methodsmentioning

confidence: 99%

EEG-Based Prediction of the Recovery of Carotid Blood Flow during Cardiopulmonary Resuscitation in a Swine Model

Kim

Hong

et al. 2021

Sensors

View full text Add to dashboard Cite

The recovery of cerebral circulation during cardiopulmonary resuscitation (CPR) is important to improve the neurologic outcomes of cardiac arrest patients. To evaluate the feasibility of an electroencephalogram (EEG)-based prediction model as a CPR feedback indicator of high- or low-CBF carotid blood flow (CBF), the frontal EEG and hemodynamic data including CBF were measured during animal experiments with a ventricular fibrillation (VF) swine model. The most significant 10 EEG parameters in the time, frequency and entropy domains were determined by neighborhood component analysis and Student’s t-test for discriminating high- or low-CBF recovery with a division criterion of 30%. As a binary CBF classifier, the performances of logistic regression, support vector machine (SVM), k-nearest neighbor, random forest and multilayer perceptron algorithms were compared with eight-fold cross-validation. The three-order polynomial kernel-based SVM model showed the best accuracy of 0.853. The sensitivity, specificity, F1 score and area under the curve of the SVM model were 0.807, 0.906, 0.853 and 0.909, respectively. An automated CBF classifier derived from non-invasive EEG is feasible as a potential indicator of the CBF recovery during CPR in a VF swine model.

show abstract

Section: Methodsmentioning

confidence: 99%

EEG-Based Prediction of the Recovery of Carotid Blood Flow during Cardiopulmonary Resuscitation in a Swine Model

Kim

Hong

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Edla et al [11] have proposed a framework for human mental state detection. In this work, the authors used a random forest classifier to classify the mental states viz.…”

Section: Literature Reviewmentioning

confidence: 99%

Brain–computer interface for assessment of mental efforts in e‐learning using the nonmarkovian queueing model

Balamurugan

Mullai

Soundararajan³

et al. 2020

Comp Applic In Engineering

View full text Add to dashboard Cite

The rapid advancement in information and communication technology has made e‐learning an alternative learning method for many learners. In the last few years, a huge number of learners around the world have registered in massive open online courses (MOOCs) provided by various online learning platforms. However, MOOC platforms have a vital task for the online course provider to provide enhanced students' learning experiences and satisfaction. In this work, we developed a brain–computer interface for gathering data and detecting a learner's mental situation by observing MOOC videos and electroencephalogram (EEG) devices based on John Sweller's Cognitive Load Theory. The acquired EEG signals are preprocessed with two different normalization methods to scale signals. To validate the introduced framework, the system adopted three machine learning algorithms (random forest using non‐Markovian model, support vector machine, and k‐nearest neighbors) to develop a model with preprocessed training data and test the classifiers to validate their ensemble classifiers' performance. Finally, experimental analysis showed that the random forest classifier with the non‐Markovian approach achieved more than the other two techniques in the form of overall accuracy (99.15%) and F‐measures (99.21%).

show abstract

“…Ni et al used EEG data and bidirectional LSTM recurrent neural network to check whether a student is 'confused' or 'not confused' while watching online course videos [13]. Edla et al lead an investigation to gather EEG data from 40 human brains and used techniques to extract features with random forest classifier for the classification of mental state of human into two classes those were concentration and meditation [14]. For emotion detection, Mangalagowri and Raj used EEG data and extract features using 'db4' wavelet using multilevel decomposition and used Feed Forward Backpropogation algorithm [15].…”

Section: Related Workmentioning

confidence: 99%

Classification of Student's Confusion Level in E-Learning using Machine Learning

2019

IJITEE

View full text Add to dashboard Cite

With the advancement of technology, the traditional mode of teaching-learning pedagogy has evolved into online education system as it is easily accessible. But, it is very difficult to detect whether the students are ‘confused’ or ‘not confused’ while watching online videos. Getting confused while watching online videos is one of the root causes of less performance of the students. Keeping in mind the above statements, we would like to investigate whether the students are ‘confused’ or ‘not confused’ while watching Massive Open Online Course (MOOC) videos. There are a lot of studies that prove electroencephalogram (EEG) signals behave differently as we are in different conditions such as happy, sad, angry, etc. So, in this paper, we have applied several supervised learning algorithms to detect if the students are ‘confused’ or ‘not confused’ while watching MOOC videos using EEG data. The results of this paper show that machine learning is a potential technique, for the analysis of EEG data that can detect the confusion level of the students which is comparable to human observation for predicting the confusion level of the students that can improve the quality of online education system.

show abstract

Classification of EEG data for human mental state analysis using Random Forest Classifier

Cited by 84 publications

References 16 publications

EEG-Based Prediction of the Recovery of Carotid Blood Flow during Cardiopulmonary Resuscitation in a Swine Model

EEG-Based Prediction of the Recovery of Carotid Blood Flow during Cardiopulmonary Resuscitation in a Swine Model

Brain–computer interface for assessment of mental efforts in e‐learning using the nonmarkovian queueing model

Classification of Student's Confusion Level in E-Learning using Machine Learning

Contact Info

Product

Resources

About