Computer-aided diagnosis Application by using Nonlinear Dynamics of EEG Signals to detect Depression State

In neurophysiology, nonlinear dynamics has been utilised to decode the intricate EEG brainwave patterns. In order to better understand the nonlinear nature of EEG data, numerous nonlinear approaches have been suggested and implemented recently. Nonlinear dynamics, a key mathematical subject that characterises the complex real-world phenomena characterised by nonlinear dynamics, has attracted significant interest in a wide range of scientific disciplines, including physics, chemistry, economics, electronics, and biomedical engineering, to name just a few. In this study, the authors explored how EEG waves may be detected using a computer to help in the diagnosis of depression. Depression is a mental illness that interferes with a person's ability to carry out normal, daily tasks. To lessen the burden on the sufferer and their loved ones, an accurate diagnosis of depression is crucial. Psychiatric disorders can be detected by the EEG's signal changes. As an objective, non-invasive method, the EEG has found widespread application in the study of numerous neurological conditions. But a CAD system is built to identify and analyse the subtle alterations in the signals. EEG signals, both normal and depressed, can be broken down into their component frequencies using the discrete cosine transform (DCT). DCT coefficients are used to assess the efficacy of nonlinear techniques such sample entropy, correlation dimension, fractal dimension, greatest Lyapunov exponent, Hurst exponent, and detrended fluctuation analysis. The t-value is used to rank the extracted characteristics. Classifiers are fed these relevant features. Accuracy achieved is 94.2 percent in classification together with 93.4 percent sensitivity and 95.6 percent specificity.