scispace - formally typeset
Search or ask a question
Author

P. Bhuvaneswari

Bio: P. Bhuvaneswari is an academic researcher from Bharathiar University. The author has contributed to research in topics: Electroencephalography & Support vector machine. The author has an hindex of 5, co-authored 6 publications receiving 176 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: Electroencephalography signals and its characterization with respect to various states of human body and experimental setup used in EEG analysis are focused on.

201 citations

Journal ArticleDOI
TL;DR: An overview of classification techniques available in Support Vector Machine is given and role of SVM on EEG signal analysis is focused on.
Abstract: Support Vector Machine (SVM) is one of the popular Machine Learning techniques for classifying the Electroencephalography (EEG) signals based on the neuronal activity of the brain. EEG signals are represented into high dimensional feature space for analyzing the brain activity. Kernel functions are helpful for efficient implementation of non linear mapping. This paper gives an overview of classification techniques available in Support Vector Machine. This paper also focus role of SVM on EEG signal analysis. General Terms EEG Signal Processing.

48 citations

Journal ArticleDOI
TL;DR: This paper discusses statistical based linear feature extraction methods such as Root Mean Square, Variance and Linear Prediction Coefficient and influence of decision rules such as consensus and majority rule in the classification of epilepsy data set.

18 citations

Journal ArticleDOI
TL;DR: A new transformation based wavelet decomposition method is proposed in this work to categorize normal EMG signals from abnormal neuropathy disorder signals to detect abnormal EMG signal from normal patterns which helps radiologist for better prediction of various disorders based on EMg signals.
Abstract: Background/Objectives: Neuropathy is a disorder which will be detected using Electromyography (EMG) signals. A new transformation based wavelet decomposition method is proposed in this work to categorize normal EMG signals from abnormal neuropathy disorder signals. Methods/Statistical Analysis: Transformation technique is applied to convert the signals into frequency map. Wavelet decomposition method decomposes transformed signal into set of various levels of coefficients. Cepstral feature have been applied to extract meaningful properties and Minimum Redundancy Maximum Relevance (MRMR) method has been applied to reduce dimensionality of cepstral features. Findings: The KNN classifier is used to discriminate neuropathy disorder from healthy Electromyography signals. The results shows better classification accuracy using cepstral feature set. Entire signal has been subdivided into 20 and 40 sub segments for better features. Coefficients for five levels have been extracted where 40 sub segment features shows better classification accuracy than 20 sub segments. In some cases, 3rd and 5th level coefficients of 20 sub segments shows better classification. Application/Improvements: This study helps to detect abnormal EMG signal from normal patterns which helps radiologist for better prediction of various disorders based on EMG signals.

7 citations

Proceedings ArticleDOI
01 Dec 2014
TL;DR: Results shows that first level and third level coefficient shows better classification accuracy than other components and Spectral entropy has good classification results than Shannon and approximate entropy.
Abstract: Understanding cognitive responses of human brain is one of the significant research fields where electroencephalography plays vital role in analyzing brain functionality with respect to brain signals. Electromyography is another modality to understand cognitive responses with respect to muscle activation. In this research work, a data set consists of healthy and myopathy has been considered from physionet data repository. Signal has been decomposed using wavelet transformation. Features such as Shannon, spectral and approximate entropy have been extracted from decomposed signal. Support vector machine has been used for classification. Result shows that first level and third level coefficient shows better classification accuracy than other components. Spectral entropy has good classification results than Shannon and approximate entropy.

5 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: The study presents a brief comparison of various functional neuroimaging techniques, revealing the excellent Neuroimaging capabilities of EEG signals such as high temporal resolution, inexpensiveness, portability, and non-invasiveness as compared to the other techniques such as positron emission tomography, magnetoencephalogram, functional magnetic resonance imaging, and transcranial magnetic stimulation.

113 citations

Journal ArticleDOI
TL;DR: An efficient, parametric, general, and completely automatic real time classification method of electroencephalography signals obtained from self-induced emotions, aiming at a multi-class classification and may be considered in the framework of machine learning.

85 citations

Journal ArticleDOI
31 Jul 2020
TL;DR: PAA for compressing massive volumes of EEG data for reliable analysis and permutation entropy (PE) and auto-regressive (AR) model features are investigated to explore whether the changes in EEG signals can effectively distinguish MCI patients from healthy control subjects.
Abstract: Mild cognitive impairment (MCI) can be an indicator representing the early stage of Alzheimier’s disease (AD). AD, which is the most common form of dementia, is a major public health problem worldwide. Efficient detection of MCI is essential to identify the risks of AD and dementia. Currently Electroencephalography (EEG) is the most popular tool to investigate the presenence of MCI biomarkers. This study aims to develop a new framework that can use EEG data to automatically distinguish MCI patients from healthy control subjects. The proposed framework consists of noise removal (baseline drift and power line interference noises), segmentation, data compression, feature extraction, classification, and performance evaluation. This study introduces Piecewise Aggregate Approximation (PAA) for compressing massive volumes of EEG data for reliable analysis. Permutation entropy (PE) and auto-regressive (AR) model features are investigated to explore whether the changes in EEG signals can effectively distinguish MCI from healthy control subjects. Finally, three models are developed based on three modern machine learning techniques: Extreme Learning Machine (ELM); Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) for the obtained feature sets. Our developed models are tested on a publicly available MCI EEG database and the robustness of our models is evaluated by using a 10-fold cross validation method. The results show that the proposed ELM based method achieves the highest classification accuracy (98.78%) with lower execution time (0.281 seconds) and also outperforms the existing methods. The experimental results suggest that our proposed framework could provide a robust biomarker for efficient detection of MCI patients.

63 citations

Journal ArticleDOI
TL;DR: Generalizes a methodology for building machine learning pipelines for multimodal educational data, using a modularized approach, namely the "grey‐box" approach and demonstrates that fusion of eye‐tracking, facial expressions and arousal data provide the best prediction of effort and performance in adaptive learning settings.
Abstract: Students' on‐task engagement during adaptive learning activities has a significant effect on their performance, and at the same time, how these activities influence students' behavior is reflected in their effort exertion. Capturing and explaining effortful (or effortless) behavior and aligning it with learning performance within contemporary adaptive learning environments, holds the promise to timely provide proactive and actionable feedback to students. Using sophisticated machine learning (ML) algorithms and rich learner data, facilitates inference‐making about several behavioral aspects (including effortful behavior) and about predicting learning performance, in any learning context. Researchers have been using ML methods in a "black‐box" approach, ie, as a tool where the input data is the learner data and the output is a given class from the chosen construct. This work proposes a methodological shift from the "black‐box" approach to a "grey‐box" approach that bridges the hypothesis/literature‐driven (feature extraction) "white‐box" approach with the computation/data‐driven (feature fusion) "black‐box" approach. This will allow us to utilize data features that are educationally and contextually meaningful. This paper aims to extend current methodological paradigms, and puts into practice the proposed approach in an adaptive self‐assessment case study taking advantage of new, cutting‐edge, interdisciplinary work on building pipelines for educational data, using innovative tools and techniques. Practitioner NotesWhat is already known about this topic Capturing and measuring learners' engagement and behavior using physiological data has been explored during the last years and exhibits great potential.Effortless behavioral patterns commonly exhibited by learners, such as "cheating," "guessing" or "gaming the system" counterfeit the learning outcome.Multimodal data can accurately predict learning engagement, performance and processes.What this paper adds Generalizes a methodology for building machine learning pipelines for multimodal educational data, using a modularized approach, namely the "grey‐box" approach.Showcases that fusion of eye‐tracking, facial expressions and arousal data provide the best prediction of effort and performance in adaptive learning settings.Highlights the importance of fusing data from different channels to obtain the most suited combinations from the different multimodal data streams, to predict and explain effort and performance in terms of pervasiveness, mobility and ubiquity.Implications for practice and/or policy Learning analytics researchers shall be able to use an innovative methodological approach, namely the "grey‐box," to build machine learning pipelines from multimodal data, taking advantage of artificial intelligence capabilities in any educational context.Learning design professionals shall have the opportunity to fuse specific features of the multimodal data to drive the interpretation of learning outcomes in terms of physiological learner states.The constraints from the educational contexts (eg, ubiquity, low‐cost) shall be catered using the modularized gray‐box approach, which can also be used with standalone data sources. [ABSTRACT FROM AUTHOR]

62 citations

Journal ArticleDOI
TL;DR: In this article, a new approach for extension of univariate iterative filtering (IF) for decomposing a signal into intrinsic mode functions (IMFs) or oscillatory modes is proposed for multivariate multi-component signals.

59 citations