Sung‐Hyun Yang

About

Sung-Hyun Yang is a leading researcher in pervasive computing and human activity recognition (HAR), with a particular focus on recognizing complex, concurrent, and interleaved activities—a significant challenge beyond simple, single-task recognition. His major contributions include pioneering the application of deep learning architectures to this problem. Notably, he developed a deep machine learning method for concurrent HAR (2020, 39 citations), which has become a foundational reference in the field for applications in ambient assistive living, robotics, and healthcare monitoring. Yang also advanced probabilistic modeling with the Log-Viterbi algorithm for second-order hidden Markov models (2018, 11 citations), improving the accuracy of sequential activity recognition. More recently, he adapted Long Short-Term Memory (LSTM) networks specifically for concurrent activity recognition (2021, 9 citations), demonstrating how deep learning can outperform traditional methods. His work directly addresses the real-world complexity of human behavior, enabling more intelligent and responsive systems for elderly care, health monitoring, and human-robot interaction. With a cumulative impact of nearly 60 citations across his most influential papers, Yang’s research is essential reading for anyone working at the intersection of machine learning and context-aware computing.

Research Focus

Key Achievements

Top Papers

1. 1
   A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition

   39 citations · 2020
2. 2
   Log-Viterbi algorithm applied on second-order hidden Markov model for human activity recognition

   11 citations · 2018
3. 3
   Adapted Long Short-Term Memory (LSTM) for Concurrent\\ Human Activity Recognition

   9 citations · 2021

Key Collaborators

Contact & Links