Hybrid ANFIS Model For Depression Recognition Consuming Three-Channel EEG Data

The goal of this effort is to make it more widely used by detecting depression with fewer EEG modes, namely Fp1, Fp2, and Fz. Band power (delta, theta, alpha, and beta) and sub-bands obtained through the selected channels are then used in the research. It also assesses the use of Hybrid ANFIS as well as its variants as classification systems, including GA-ANFIS, PSO-ANFIS, and FA-ANFIS. Filtering and re-referencing to CAR, ICA, and visually are some of the methods used to reduce artifacts and noise in fMRI information. A publicly available information is used in the process, which is then partitioned into a set for training and a testing set. Using ANFIS-GA, this research achieved a high classification accuracy of ${8 5 . 5 9 \%}$, indicating that the suggested framework might be helpful for physicians when detecting depressive disorders. Potentially beneficial uses are demonstrated by the findings, which indicate that depressive disorders may be effectively and easily identified using a minimal number of channels and characteristics. Consequently, the project’s methodology and the implementation of the enhanced hybrid ANFIS systems provide useful data about the use of EEG for depressive disorders diagnosis. Given these findings, it’s reasonable to assume that the suggested technique has the potential to contribute to the enhancement of depressive disorders testing methods.