Bipolar bozukluğun fNIRS ölçümleri kullanılarak derin öğrenme ile sınıflandırılması

Functional Near-Infrared Spectroscopy (fNIRS) is a neural imaging method that is proved to be prominent in the classification of psychiatric disorders, and assertive accuracy results are being obtained using fNIRS. High temporal resolution, feasibility, and partial endurance to head movements are the traits that are highlighting fNIRS among other imaging methods. fNIRS data is a one dimensional multi-channeled time series. In this thesis, bipolar disorder is classified using some state of the art deep learning methods that are specialized for time series classification. Multilayer Perceptrons, one dimensional Convolutional Neural Networks (CNN), one dimensional Residual Neural Networks (ResNet) and one dimensional Encoder networks are trained, evaluated and compared on the fNIRS data where there are 33 control and 28 bipolar subjects. Although the number of subjects is not high enough, promising accuracies are obtained using different test methods. The best classification accuracy of 75.32% is obtained by using the ResNet classifier.