NeuroMood Insights

In the wake of the transformative shift to online activities prompted by the 2020 COVID-19 pandemic, our project emerges as a proactive response to the undeniable impact on mental health. Recognizing the significance of this issue, we have delved into the realm of mental and emotional well-being in the context of virtual learning environments.

Our project employs a seamless integration of OpenCV and CNN machine learning algorithms to delve into the intricate landscape of students' emotional states during online learning. The OpenCV analyzes facial expressions and non-verbal cues, capturing nuanced visual data. Complementing this, the CNN algorithm, trained on diverse datasets, interprets these visual cues, discerning subtle patterns associated with different emotional states. This cohesive marriage of OpenCV's visual intelligence and deep learning capabilities enables real-time and nuanced assessments of students' emotional well-being. Our project addresses the complex challenges in understanding and supporting the emotional aspects of virtual education, contributing to a more empathetic and effective online learning experience.

The Muse S, placed on the frontal and temporal cortices, facilitates the collection of raw EEG data. This data, rich in insights about executive functioning and sensory processing, undergoes real-time Fast Fourier Transform. This process effectively decomposes raw waveforms into their five fundamental frequency bands, and subsequently, the amplitude values of each band are averaged across the five channels.

The processed EEG data is then fed into another AI model, meticulously trained to convert this complex neural information into easily interpretable text. This transformative step not only enhances accessibility to the data but also opens avenues for practical applications in understanding and addressing mental and emotional states.

To provide a user-friendly interface and make our insights accessible, we employ Streamlit as the frontend. This integration seamlessly blends OpenCV, responsible for computer vision applications, with the processed EEG data. The result is a powerful tool capable of dynamically determining the mental and emotional states of students engaged in online learning. Ultimately, our project aspires to contribute significantly to the well-being of individuals in the digital learning landscape, offering timely insights and fostering a supportive environment for mental health in online education.