Research & Publications
Advancing the frontiers of AI and machine learning through innovative research and practical applications
Research Projects
Emotion Detection via EEG Brainwaves
High-accuracy emotion recognition using EEG signals and advanced RNN architecture
Developed a sophisticated RNN model with GRU architecture for emotion recognition using EEG brainwave data. The research achieved state-of-the-art accuracy in emotion classification and was presented at an international conference.
Key Achievements
- 97.34% emotion recognition accuracy achieved
- Novel GRU-based architecture for EEG signal processing
- Real-time emotion classification capabilities
Publications
LSTM-based Cryogen Control for Superconducting Accelerators
Advanced neural network system for precise cryogen level control in particle accelerators
Developed an LSTM-based neural network for autonomous control of cryogen levels in superconducting accelerators. The system maintains precise temperature control critical for accelerator operations with minimal human intervention.
Key Achievements
- ±1% error margin maintained over extended periods
- Successfully deployed for accelerator operations at IUAC Delhi
- Reduced manual intervention by 85%
Research Interests
Multimodal AI Systems
Exploring the integration of multiple AI modalities for enhanced understanding and interaction
Neural Architecture Search
Automated discovery of optimal neural network architectures for specific tasks
Real-time AI Applications
Developing AI systems that can operate in real-time environments with strict latency requirements
Human-AI Interaction
Designing intuitive interfaces and interaction paradigms between humans and AI systems