DocumentCode :
3715248
Title :
Non invasive EEG signal processing framework for real time depression analysis
Author :
Shamla Mantri;Dipti Patil;Pankaj Agrawal;Vijay Wadhai
Author_Institution :
Electronics Engineering Dept., GHRCE, Nagpur, India
fYear :
2015
Firstpage :
518
Lastpage :
521
Abstract :
There is a long list of words that describe depression; sadness, unhappiness, sorrow, dejection, low spirit, despondency, woe, gloom, pessimism, desolation, despair, hopelessness, moodiness, and a host of others. This study throws light upon the contribution EEG signal for depression analysis. In this paper, classification of depressed patients from normal subjects are identified by using EEG signal. Experimental results are carried out with the help of 13 depressed patients and 12 normal subjects. This paper tries to classify person´s mental state either normal or depressed with the help of EEG signal using signal processing technique FFT and machine learning technique SVM. These noninvasive signal techniques are useful for detection of depression disorders through EEG signals. The proposed work is compared with the other methods. The diagnosis is done and appropriate remedies are taken according to scale of the depression in the patient. This work shows that linear analysis of EEG can be an efficient method for identifying depressed patients from normal subjects. It is recommended that this analysis may be a supporting aid for psychiatrists to identify severity level of depressed patients.
Keywords :
"Electroencephalography","Feature extraction","Artificial neural networks","Training","Testing","Yttrium","Support vector machines"
Publisher :
ieee
Conference_Titel :
SAI Intelligent Systems Conference (IntelliSys), 2015
Type :
conf
DOI :
10.1109/IntelliSys.2015.7361188
Filename :
7361188
Link To Document :
بازگشت