Non-Invasive Bio-Signal Data Classification Of Psychiatric Mood Disorders Using Modified CNN and VGG16

Authors : Ali Berkan URAL

Pages : 323-332

Doi:10.29137/umagd.1232222

View : 10 | Download : 5

Publication Date : 2023-01-31

Article Type : Research Paper

Abstract :In this study, the aim is to develop an ensemble machine learning insert ignore into journalissuearticles values(ML); based deep learning insert ignore into journalissuearticles values(DL); model classifiers to detect and compare one type of major psychiatric disorders of mood disorders insert ignore into journalissuearticles values(Depressive and Bipolar disorders); using Electroencephalography insert ignore into journalissuearticles values(EEG);. The diverse and multiple non-invasive biosignals were collected retrospectively according to the granted ethical permission. The experimental part is consisted from three main parts. First part is the data collection&development, the second part is data transformation and augmentation via Spectrogram image conversion process and online Keras data augmentation part, respectively. The third and final part is to fed these image dataset into modified Convolutional Neural Network insert ignore into journalissuearticles values(CNN); and VGG16 models for training and testing parts to detect, compare and discriminate mood disorders types in detail with a specific healthy group. As the performance evaluation background of the mood disorder classification models, confusion matrices and receiver operating characteristics insert ignore into journalissuearticles values(ROC); curves were used and finally, the accuracy achieved by CNN model was 88% and VGG16 model was %90, which is an improvement of 10% compared to the previous studies in literature. Therefore, our system can help clinicians and researchers to manage, diagnose and prognosis of the mental health of people.
Keywords : Psychiatric disorders, Mood disorder, Depressive disorder, Bipolar Disorder, Deep Learning, Pretrained model classification