سامانه همایش‌ها TSTA | ثبت‌نام و ارسال مقاله کنفرانس‌ها و کنگره‌های ملی

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Static and Dynamic WPLI on Stressful Scenarios: an EEG Study

Authors :

Nasrin Dehghani¹ Negin Joghataei² Zahra Ghanbari³ Mohammad Hassan Moradi⁴

1- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران) 2- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران) 3- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران) 4- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران)

Keywords :

Anxiety،stress،EEG،functional connectivity،dynamic connectivity،WPLI

Abstract :

Analyzing brain signals can provide valuable insights into the complexities of anxiety and contribute to improve mental health. In this paper, we used the DASPS dataset, which contains EEG recordings from 23 healthy individuals in a resting state with eyes closed. Participants were presented with descriptions of 6 stressful scenarios and assessed their emotional states through questionnaires. Functional connectivity was estimated using the Weighted Phase Lag Index (WPLI), and dynamic analysis was conducted through clustering methods to detect change points between different mental states. Above static and dynamic features were used for statistical analysis and classification on the 6 scenarios. Statistical tests revealed significant differences across all frequency bands between the verbal abuse scenario and the witnessing a fatal accident, while no significant difference was observed among the remaining scenarios. Classification was performed using a Support Vector Machine (SVM), and model performance was evaluated through 5-fold cross-validation. The best accuracy in the six-class classification was achieved in the gamma band, 42.02%, after applying a proposed majority voting approach. Our analysis reveals the higher performance of statistic comparing to dynamic features.