IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 9 - Issue 3, March 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Epileptic Seizure Detection Using Eeg Signals And Multilayer Perceptron Learning Algorithm

[Full Text]

 

AUTHOR(S)

Fluvia Antoney, B.Ramamurthy

 

KEYWORDS

Epileptic Seizure,Electroencephalogram,Feature extraction,Multi-LayerPerceptron Learning Algorithm, Support Vector Machine, Wavelet.

 

ABSTRACT

Purpose: Epileptic is a neurological chronic disorder that causes unprovoked, recurrent seizure. A seizure is a sudden rush of electrical activity in the brain. The central nervous system characterized by the loss of consciousness and convulsions. Epileptic is caused by abnormal electrical discharge that lead to uncountable movements, loss of consciousness and convulsions. 50-80 million people in the world are affected by this disorder. Now a days children and adults are affected the most and it has been medically treated. Sometimes it may lead to death and serious injuries. In this technology world the computerized detection is an enhanced solution to protect epileptic patients from dangers at the time of this seizure. Method: Perceptron learning algorithm is a supervised learning of binary classifiers and also it is a simple prototype of a biological neuron in artificial neural network. EEG is extensively documented for the diagnosing and assessing brain activates and related disorders. In this paper EEG signals are taken as dataset for epilepsy detection. The data is been represented based on three domains namely frequency, time and time-frequency applied by the chebysev filter for processing the signals. Result: Help the patients from dangers at the time of the seizure. Conclusion: The neurological diseases can be divided into two loss of consciousness and convulsions. In this technology world the seizure can be detected by computerized way like EEG and so on. This paper proposes an epileptic seizure detection using EEG (Electroencephalogram) and perceptron learning algorithm.

 

REFERENCES

[1]. Zakareya Lasefr, et-al “Epilepsy Seizure Detection Using EEG signals”, IEEE, pp.162167, 78-1-5386-1104-3/17. ©2017.
[2]. Mrs. Varsha K. Harpale, Dr. Vinayak K. Bairagi”Time and Frequency Domain Analysis of EEG Signals for Seizure Detection: A Review”978-1-4673-6621-2/16. © 2016 IEEE”.
[3]. Shirish D. Kalbhor1, Varsha K. Harpale” The Review of Detection and Classification of Epilectic Seizures Using WaveletTransform”IEEE.
[4]. AmjedS.Al-Fahoum1 andAusilahA.Al-Fraihat2” Methods of EEG Signal Features Extraction Using Linear Analysis in Frequency and Time-Frequency Domains” ISRNNeuroscience, Volume 2014, Article ID 730218, 7 pages.
[5]. Alexandros T. Tzallas, Member, IEEE, Markos G.” Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis”, IEEE transaction on information technology in biomedicine, VOL. 13, NO. 5, 2009.
[6]. Sharanreddy, P.K. Kulkarni” EEG signal classification for Epilepsy Seizure Detection using Improved Approximate Entropy” International Journal of Public Health Science (IJPHS) Vol. 2, No. 1, March 2013, pp. 23~32.
[7]. Debdeep Sikdar etal “Epilepsy and seizure characterisation by multifractal analysis of EEGsubbands” Biomedical Signal Processing and Control 41 (2018) 264–270 Volume 41, March 2018, Pages 264-270.
[8]. Jelena Djuris etal” Design Space Approach in Optimization of Fluid Bed Granulation and Tablets Compression Process” The Scientific World Journal Volume 2012, Article ID 185085, 10 pages
[9]. K. A. I. Aboalayo , et al "Sleep stage classification using EEG signal analysis: a comprehensive survey and new investigation," Entropy, vol. 18, p. 272, 2016.