Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

Statistical Feature based Activity Classification

Print
PDF
International Journal of Computer Applications
© 2014 by IJCA Journal
Volume 96 - Number 15
Year of Publication: 2014
Authors:
Supriya Shete
Revathi Shriram
10.5120/16874-6776

Supriya Shete and Revathi Shriram. Article: Statistical Feature based Activity Classification. International Journal of Computer Applications 96(15):49-52, June 2014. Full text available. BibTeX

@article{key:article,
	author = {Supriya Shete and Revathi Shriram},
	title = {Article: Statistical Feature based Activity Classification},
	journal = {International Journal of Computer Applications},
	year = {2014},
	volume = {96},
	number = {15},
	pages = {49-52},
	month = {June},
	note = {Full text available}
}

Abstract

Activity refers two activities and in this work to classification between two activities is achieved with the help of statistical feature extraction technique. [5] The term silent activity refers to the two processes in which we are proposing a method to predict Cognitive and Non cognitive tasks performed by the human brain. Electroencephalogram (EEG) is the electrical signal of brain which contains valuable information. In this work EEG and its frequency sub-bands have been analyzed to detect silent activity signal. The electroencephogram (EEG) contains information about brain hence the sub band decomposition of EEG is used for analyzing many brain diseases. [1] The sub-band decomposition means to extract various brain waves with different frequency bands such as alpha, beta, delta, theta and gamma from EEG signal to get more information from it. The work was carried out to extract various brain waves using discrete wavelet transform. The EEG signal is decompose into five sub bands alpha, beta, gamma, theta, and delta. [2] A wavelet transform has been applied to decompose the EEG into its sub bands. Statistical features Standard deviation, Covariance is calculated for each sub-band. The effective classification of EEG used for brain computer interface and can be used for silent communication or for recognizing different mental tasks. [5]

References

  • Anatomy of Brain, Brain parts and function of each part, Encyclopedia
  • 'EEG Signal Analysis for Silent Visual Reading Classification' Oliveira, O. Grigori, and N. Guimarães. International Journal of Circuits, Systems and Signal processing
  • "Classification of EEG Signals under Different Mental Tasks Using Wavelet Transform and Neural Network with One Step Secant Algorithm", Dipti Upadhyay Department of Applied Mechanics, Motilal Nehru National Institute of Technology, Allahabad, India
  • Discriminating Mental States Using EEG Represented by Power Spectral Density, Jack Culpepper, Department of Computer Science, Harvey Mudd College, Claremont
  • Feature selection for Epilepsy Detection using EEG Mandeep Singh and Sunpreet Kaur International Journal of Information Technology and Knowledge Management December 2012
  • Chai Tong Yuen, Woo san san, Classification of Human Emotions form EEG signal using Statistical Features and Neural Network, International Journal of Integrated Engineering
  • Norizam Sulaiman, Novel Methods for Stress Features Identification using EEG Signals,Faculty of Electrical and Electronics Engineering University Malaysia Pahang , Malaysia
  • John Musson, Jiang Li, (2002) A Comparative Survey of PSD Estimation Methods for EEG Signal Analysis,IEEE Signal Processing Magazine Old Dominion University, Norfolk.
  • R. Palaniappan and P. Raveendran(2001) Cognitive Task Prediction using Parametric analysis Malaysian Journal of Computer Science.
  • Tian Lan, Andre Adami,(2006),Estimating Cognitive state using EEG signal. IEEE Trans Rehabil Eng.
  • Porbadnigk, A. (2008). EEG-based speech recognition: Impact of experimental design on performance. Institute Algorithmen und Kognitive System.
  • Wester, M. (2006). Unspoken speech speech recognition based on electroencephalography. Master's thesis, Institute Theoretische Informatik University