Step Count
Step counting, the automated measurement of steps taken, is a key metric in health research and various applications, with current research focusing on improving accuracy and robustness of step detection. This involves developing sophisticated algorithms, including attention-based LSTMs and self-attention models, to process data from diverse sources like accelerometers and even audio recordings, addressing challenges like missing data and noisy signals. Accurate step counting has significant implications for health monitoring, personalized fitness tracking, and even assistive technologies for individuals with cognitive impairments, enabling proactive interventions and improved quality of life.
Papers
Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Region
Tobias Egle, Yashuai Yan, Dongheui Lee, Christian Ott
StepCountJITAI: simulation environment for RL with application to physical activity adaptive intervention
Karine Karine, Benjamin M. Marlin