{"id":22589124,"url":"https://github.com/vidhi1290/deep-learning-for-eeg-emotion-classification","last_synced_at":"2025-04-10T03:05:20.431Z","repository":{"id":192548854,"uuid":"686968320","full_name":"Vidhi1290/Deep-Learning-for-EEG-Emotion-Classification","owner":"Vidhi1290","description":"This repository contains a Python code script for performing emotion classification using EEG (Electroencephalogram) data. Emotion classification from EEG signals is an important application in neuroscience and human-computer interaction. The code leverages deep learning techniques to analyze EEG data and predict emotional states.","archived":false,"fork":false,"pushed_at":"2023-09-04T10:33:22.000Z","size":1880,"stargazers_count":14,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-12-08T08:12:54.782Z","etag":null,"topics":["coorelation","data-exploration","data-preprocessing","data-science","data-visualization","deep-learning","deep-learning-algorithms","eeg-emotion-recognition","egg-signals","emotion-distribution","emotion-prediction","feature-analysis","heatmap","human-emotions","machine-learning","machine-learning-algorithms","pie-chart","spectral-analysis","time-series-visualization"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Vidhi1290.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-09-04T10:28:35.000Z","updated_at":"2024-11-24T09:05:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"7913a4a5-3ee1-41d3-a3ff-bf8d2e60c939","html_url":"https://github.com/Vidhi1290/Deep-Learning-for-EEG-Emotion-Classification","commit_stats":null,"previous_names":["vidhi1290/deep-learning-for-eeg-emotion-classification"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vidhi1290%2FDeep-Learning-for-EEG-Emotion-Classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vidhi1290%2FDeep-Learning-for-EEG-Emotion-Classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vidhi1290%2FDeep-Learning-for-EEG-Emotion-Classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vidhi1290%2FDeep-Learning-for-EEG-Emotion-Classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vidhi1290","download_url":"https://codeload.github.com/Vidhi1290/Deep-Learning-for-EEG-Emotion-Classification/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236835147,"owners_count":19212424,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["coorelation","data-exploration","data-preprocessing","data-science","data-visualization","deep-learning","deep-learning-algorithms","eeg-emotion-recognition","egg-signals","emotion-distribution","emotion-prediction","feature-analysis","heatmap","human-emotions","machine-learning","machine-learning-algorithms","pie-chart","spectral-analysis","time-series-visualization"],"created_at":"2024-12-08T08:12:21.617Z","updated_at":"2025-02-02T18:28:46.510Z","avatar_url":"https://github.com/Vidhi1290.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EEG Emotion Classification with Deep Learning\n\n## Overview\n\nThis repository contains Python code for performing emotion classification using EEG (Electroencephalogram) data. Emotion classification from EEG signals is an important application in neuroscience and human-computer interaction. The code leverages deep learning techniques to analyze EEG data and predict emotional states.\n\n## Key Features\n\n1. **Data Loading and Preprocessing:**\n   - Loads EEG data from a CSV file containing features extracted from EEG signals.\n   - Converts emotion labels (e.g., 'NEGATIVE', 'NEUTRAL', 'POSITIVE') to numerical values (0, 1, 2) for classification.\n\n2. **Data Visualization:**\n   - Utilizes various visualization techniques to gain insights into the EEG data:\n     - Pie chart to display the distribution of emotions in the dataset.\n     - Time-series plot to visualize EEG signals over time.\n     - Power Spectral Density (PSD) plot for spectral analysis.\n     - Correlation heatmap to understand feature correlations.\n     - t-SNE (t-Distributed Stochastic Neighbor Embedding) visualization for dimensionality reduction.\n\n3. **Feature Significance Analysis:**\n   - Conducts statistical tests (t-tests) to identify significant and non-significant features for each emotion category.\n   - Presents results through bar charts, making it easy to understand which features contribute most to emotion prediction.\n\n4. **Advanced Preprocessing:**\n   - Normalizes feature data using z-score normalization.\n   - Splits the dataset into training and testing sets.\n\n5. **Deep Learning Model:**\n   - Builds a deep neural network model for emotion classification.\n   - The model architecture consists of multiple dense layers with ReLU activation functions and dropout layers.\n   - Compiles the model using the Adam optimizer and sparse categorical cross-entropy loss.\n   - Trains the model on the training data with validation, tracking accuracy during training.\n\n6. **Model Evaluation:**\n   - Evaluates the trained model on the testing dataset, reporting the accuracy of emotion classification.\n   - Generates a confusion matrix and a classification report for a comprehensive performance assessment.\n\n7. **Random Sample Visualization:**\n   - Selects a random EEG sample from the testing dataset and predicts its emotion label.\n   - Plots EEG signals from the selected sample for visualization.\n\n## Getting Started\n\nFor detailed usage instructions and explanations, please refer to the code comments and accompanying documentation in the repository.\n\n## Customization\n\nFeel free to customize and extend this code for your specific EEG emotion classification projects.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidhi1290%2Fdeep-learning-for-eeg-emotion-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvidhi1290%2Fdeep-learning-for-eeg-emotion-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidhi1290%2Fdeep-learning-for-eeg-emotion-classification/lists"}