Multimodal Sensing for Enhanced User Experience and Well-being

Explores a machine learning approach for emotion detection and music recommendation. The system leverages facial expressions to infer a user's emotional state and recommends music tailored to that emotion.The project involves:Data Acquisition and Preprocessing: Collecting and preparing a dataset of facial expressions with corresponding emotional labels.Convolutional Neural Network (CNN) Development: Training a CNN model to identify emotions from facial expressions captured through a webcam or video feed.Music Recommendation Model Development: Creating and training a model using music features (tempo, rhythm, melody) and corresponding emotional labels to recommend suitable music.Integration and Deployment: Deploying the emotion detection and music recommendation models into a software application. The application captures the user's facial expressions, detects emotions, and recommends music based on the detected emotion.Evaluation and Maintenance: Continuously monitoring the system's performance and retraining the models for improved accuracy over time.This work contributes to the development of affective computing applications by demonstrating the use of machine learning for emotion detection and personalized music recommendations.