This project focused on developing a cross-cultural Convolutional Neural Network (CNN) confusion model, aimed at detecting and alerting instructors of their students’ confusion (Submitted, International Learning Analytics & Knowledge Conference).
This project involved automating the assessment of student engagement in STEM classrooms using eye-tracking data, clustering attention motifs with unsupervised learning methods (Presented, Undergraduate Research Symposium Meeting of the Minds).
Developed a real-time, multimodal, and multi-language emotion recognition app using DeepFace, SpeechRecognition, and revChatGPT as part of a course project at Carnegie Mellon University. The application was deployed on Streamlit Cloud, enabling emotion recognition through facial expressions and speech analysis in multiple languages.