Research
AI-Based Music Intervention for Alzheimer's Disease and Related Dementias (ADRD)
Abstract
Alzheimer's Disease and Related Dementias affect over 6 million Americans, leading to cognitive decline, emotional dysregulation, and caregiver burden. Music therapy has shown great potential in alleviating neuropsychiatric symptoms in ADRD, yet its scalability is hindered by the shortage of certified therapists and lack of objective treatment outcome measures.
Our project proposes an AI-driven system that analyzes facial expressions, head and body movements, and physiological signals (e.g., heart rate, skin conductance) to assess emotional responses of older adults during music listening. Using a uniquely collected dataset of music intervention sessions, we are developing a multimodal deep learning model capable of interpreting subtle affective cues in real-world environments. This tool empowers caregivers and therapists with real-time feedback and long-term psychological profiling, supporting more accessible, adaptive, and evidence-based music interventions.
Team
Engineering
- Dr. Yu Sun, Professor, Computer Science and Engineering, USF
- Dr. Dmitry Goldgof, Professor, Computer Science and Engineering, USF
- Dr. Shaun Canavan, Associate professor, Computer Science and Engineering, USF
- Dr. John Templeton, Associate professor, Computer Science and Engineering, USF
- Jiayi Wang, PhD Student, Computer Science and Engineering, USF
- Phong Lu, Undergraduate Student, Computer Science and Engineering, USF
- Jianing Su, Undergraduate Student, Computer Scinece, University of Washington
Music Therapy & Behavioral Science
- Dr. Hongdao Meng, Professor, Behavioral and Community Sciences, USF
- Ashley Tabachnick, Master Student, Behavioral and Community Sciences, USF
- Guanqing Guo, Neurologic Music Therapist, Berklee College of Music
- Victoria Figueroa, Undergraduate Student, Behavioral and Community Sciences, USF