Improving EEG Electrode Sensitivity with Graphene Nano Powder and Neural Network for Schizophrenia Diagnosis

Hallucinations and delusions are symptoms of schizophrenia. Due to persistent auditory and visual hallucinations, a person with schizophrenia cannot process reality clearly. Abnormal brain activity results from delusion and hallucination. During the capture of EEG signals, aberrant behavior is detec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Tikrit journal of engineering sciences 2023-03, Vol.30 (1), p.84-93
Hauptverfasser: V. Divya, Dr. S. Sendil Kumar, S. Usha, S. Hemamalini, Krishnan, Gokula
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Hallucinations and delusions are symptoms of schizophrenia. Due to persistent auditory and visual hallucinations, a person with schizophrenia cannot process reality clearly. Abnormal brain activity results from delusion and hallucination. During the capture of EEG signals, aberrant behavior is detected. The EEG electrodes do not well detect the brain's current distribution. Schizophrenia causes the EEG signal to be warped and less sensitive, which results in incorrect interpretation of brain activity. In this paper, an EEG electrode constructed of graphene nanopowder is suggested that is sensitive to the brain's weak electrical activity. The cold spray approach created graphene EEG electrodes, improving the material bonding and chemical characteristics. By obtaining EEG readings from schizophrenic patients, the sensitivity of the graphene electrode was assessed. The EEG signal was collected from the subject when taking part in cognitive tests like question sessions and numerical problems. Several neural networks (NN) algorithms can be used to identify hallucination and delusion aspects in EEG recordings. Further details regarding the hallucination and delusion aspects in the EEG signal were provided by the NN, showing a Graphene electrode. As compared to other NN models, the comparative study of several NN models revealed that the BFGS quasi-Newtonian backpropagation algorithm accurately recognized hallucination and delusion features.
ISSN:1813-162X
2312-7589
DOI:10.25130/tjes.30.1.8