EEG-Driven-Emotion-Detection-and-Classification

Github Link : https://github.com/MohammedAfthab18/EEG-Driven-Emotion-Detection-and-Classification

Website :https://colab.research.google.com/github/MohammedAfthab18/validation/blob/master/EEG_Final_Project.ipynb

A project that uses EEG data to classify human emotions using machine learning techniques.
In this study, we aim to leverage the power of deep learning in analyzing the sentiment of financial news articles. We employ three distinct deep learning architectures and evaluate their performance rigorously:

Long Short-Term Memory (LSTM): A well-known recurrent neural network (RNN) variant, LSTM, is designed to capture long-range dependencies in sequences. We train an LSTM-based model to comprehend the sequential nature of financial news data and determine its sentiment.

Gated Recurrent Unit (GRU): Another RNN variant, the Gated Recurrent Unit (GRU), has shown promise in handling sequential data. We employ GRU to compare its performance with LSTM in sentiment analysis.

Deep Neural Network (DNN): In addition to recurrent architectures, we explore the capabilities of a Deep Neural Network, which is not inherently sequential. By designing a multi-layer DNN, we aim to assess whether it can yield competitive results in sentiment classification