Classifier Implementation for Spontaneous EEG Activity during Schizophrenic Psychosis

Authors

  • Rekha Sahu KIIT University, School of Computer Engineering
  • Satya Ranjan Dash KIIT University, School of Computer Application
  • Lleuvelyn A. Cacha Universiti Sultan Zainal Abidin, Faculty of Health Science
  • R. R. Poznanski Universiti Sultan Zainal Abidin, Faculty of Informatics and Computing
  • Shantipriya Parida Idiap Research Institute

DOI:

https://doi.org/10.13053/cys-25-3-3874

Keywords:

EEG, spiking neural network, long short-term memory, temporal contrast, Poisson probability distribution, schizophrenia, probabilistic spiking neuron model, electroencephalography spikes

Abstract

The mental illness or abnormal brainis recorded with EEG, and it records corollarydischarge, which helps to identify schizophreniaspontaneous situation of a patient.The recordings arein a time interval that shows the brain’s differentnodes normal and abnormal activities.The spiking neuralnetwork procedure can be applied here to detect theabnormalities of patients. The abnormal spikes aredetected using temporal contrast method, and Poissonprobability has been used to find the probability ofabnormality discharge of each channel.Then recurrentneural network advance version long short-term memorytrained with nine channels of probability values togenerate the probability of spontaneous EEG activityduring schizophrenia. On learning of long short-termmemory trainer, Adam gradient optimization techniqueis implemented.Finally, using decoded temporalcontrast method schizophrenia patients predicted bythe above procedure accuracy using cross-validationmethod predicted as 97% whereas actual positiverate showing computes the area under the receiveroperating characteristic curve as 100% area.Again,after a threshold implement of the temporal contrastmethod, it is predicted 100% accuracy with the testingdataset.The novelty and robotic of a spiking neuralnetwork model called probabilistic spiking neuron modelare shown after the mathematical formulation of inputdata set to generate the spikes carefully and intelligentlylike Hz value of EEG should be fixed accurately forthe schizophrenia patients and selection of suitablerecurrent supervised classifier.

Downloads

Published

2021-08-18

Issue

Vol. 25 No. 3 (2021): 25(3) 2021

Section

Articles

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.