Lee Hee-Chan
Papers
1
Total Citations
11
H-Index
1
About
Lee Hee-Chan is a researcher focused on advancing human activity recognition (HAR) through sophisticated probabilistic modeling and algorithmic innovation. His major contribution lies in adapting and optimizing hidden Markov models (HMMs) for real-world, sensor-based activity detection. His most cited work, "Log-Viterbi algorithm applied on second-order hidden Markov model for human activity recognition" (2018, 11 citations), introduces a computationally efficient variant of the Viterbi algorithm that enhances the accuracy of second-order HMMs—a model class better suited to capturing temporal dependencies in complex activities. This work directly addresses challenges in pervasive computing, ambient intelligence, and healthcare monitoring, including assistive living and elderly care. While his citation count reflects a focused, emerging impact, Lee’s technical refinement of core machine learning algorithms for HAR positions him as a contributor to practical, deployable systems that interpret human behavior from sensor streams. His work is particularly relevant for researchers building robust, real-time activity recognition pipelines in resource-constrained environments.
Research Focus
Key Achievements
Top Papers
- 1