Application of S-Transform for Automated Detection of Vigilance Level Using Eeg Signals

Abstract

This paper presents an S-transform-based Electroencephalogram channel optimization and feature extraction methodology for monitoring mental vigilance level of humans. Vigilance level detection methodology consists of four steps. In the first stage, two types of Electroencephalogram signals (alert and drowsy) are acquired from 30 healthy subjects and decomposed into sub-bands using the S-transform. In the second stage, permutation entropy of the S-transform coefficients is calculated and Electroencephalogram channel optimization is performed. S-transform-based statistical features are computed from the optimized Electroencephalogram channels, in the third stage. In the fourth stage, artificial intelligence techniques such as Least Square-Support Vector Machine, Artificial Neural Network and Naive Bayes Classifier are used for the classification of Electroencephalogram signals using extracted features. The performance of the feature extraction methodology is tested on the Electroencephalogram data of 30 healthy subjects. Experimental results ensured the effectiveness of proposed methodology for the estimation of mental vigilance level by using Electroencephalogram signals. It is observed that the Artificial Neural Network classifier is a good candidate for pre-emptive automatic vigilance level detection system for Brain-Computer Interface applications.

A novel machine learning‐based analytical framework for automatic detection of COVID‐19 using chest X‐ray images

“…In the present work, we selected seven classifier models to design proposed multistage COVID-19 detection framework for accurately differentiating between patients and healthy population: SVM, DT, gNB, kNN, Adaboost, XGboost, and RF. 31 SVM classifier works on the principles of max margin classification (illustrated by Equation (2)), 32,33 kNN works on the Minkowski distance between the data points (illustrated by Equation (3)), Adaboost and XGboost are based on boosting, 34 which fundamentally uses weighted set weak classifiers (wc o ) and creates a strong one (sc o ) (illustrated by Equation (4)); whereas, rest of the classification models are completely or partially based on the probabilistic distribution of data, their entropy and/or voting from base models.…”

Watershed prioritization and decision-making based on weighted sum analysis, feature ranking, and machine learning techniques

“…ML is a probabilistic model frequently applied for pattern recognition applications. It has been used for applications like Motor current signature analysis (Singh et al 2014), condition monitoring (Vakharia et al 2015), fault diagnosis (Kankar et al 2011), compressive strength 5 prediction (Sonebi et al 2016), EEG (Upadhyay et al 2016), tool wear rate prediction (Vakharia et al 2018) and many more applications, regardless of field.…”

Design of Pulse Wave Feature Vigilance Detection System Based on Computer Software Technology

“…Decreased vigilance is likely to have serious consequences, such as decreased employee productivity or even work errors, especially in medical, aerospace, and other jobs that require precise operations. It is very important to maintain a high level of vigilance [5,6]. erefore, it is very important to study the changing laws of vigilance, establish an effective vigilance detection system, and then study effective countermeasures to maintain vigilance and even increase vigilance [7,8].…”