Abstract
We propose a resource-efficient, real-time human activity recognition framework, transforming the multi-class classification problem into a hierarchical model based on the Metabolic Equivalent of Task (MET), creating a personalized structure for each individual.
Publication
In the proceedings of Activity Recognition and Prediction for Smart IoT Environments, Springer
![Mahdi Pedram](/authors/mahdi-pedram/avatar_hu64f3de493ecef862cc07c07e21adee27_102649_270x270_fill_q75_box_center.jpg)
Graduate Alumni
I am a fourth year PhD student at Washington State University. I work as a research assistant with Professor Hassan Ghasemzadeh. My research topics include embedded systems, health monitoring systems, wearable sensor development, sensor data mining, power optimization, and machine learning. I received my B.S. degree in Computer Cngineering from Amirkabir University of Technology, Tehran, Iran in 2014.
![Ramesh Kumar Sah](/authors/ramesh-sah/avatar_hu9a3e28a84a284510e109dc8e324db071_279305_270x270_fill_q75_box_center.jpg)
Research Assistant
I am a Computer Science PhD student in the Embedded Machine Intelligence Laboratory (EMIL) at Washington State University, Pullman.
![Hassan Ghasemzadeh](/authors/hassan-ghasemzadeh/avatar_hu7b978ab76ad90ca51f18f381de7a3965_6873_270x270_fill_q75_box_center.jpg)
Director
Hassan Ghasemzadeh is an Associate Professor of Biomedical Informatics at Arizona State University (ASU) and a Computer Science Adjunct Faculty at Washington State University (WSU).