Sayyedjavad Ziaratnia

Papers

Total Citations

H-Index

About

Sayyedjavad Ziaratnia is a rising researcher at the intersection of affective computing and multimodal deep learning, with a primary focus on remote physiological sensing and human stress estimation. His most-cited work introduces a novel architecture called CCT-LSTM, which fuses video-based facial and physiological cues to estimate stress levels remotely—a critical capability for applications in driver safety monitoring, early health intervention, and adaptive human–robot interaction. By enabling non-contact stress detection, Ziaratnia’s research addresses the growing need for scalable, privacy-sensitive mental health tools. With 6 citations since 2024, his work is gaining traction among engineers and clinicians alike. Beyond stress estimation, his broader interests span deep learning architectures, computer vision, and real-time affective state inference. Ziaratnia’s contributions are particularly notable for their practical orientation: they bridge the gap between laboratory-grade sensing and real-world deployment, offering a pathway toward systems that can proactively respond to human emotional and cognitive states. As the field of remote health monitoring accelerates, his multimodal approach positions him as a promising voice in next-generation human-centered AI.