Segmenting human activities based on HMMs using smartphone inertial sensors

• Human Activity Recognition and Segmentation using Hidden Markov Models.
• Hidden Markov Models configuration analysis.
• Activity sequence modeling.

This paper describes the development of a Human Activity Recognition and Segmentation (HARS) system based on Hidden Markov Models (HMMs). This system uses inertial signals from a smartphone to recognize and segment six different physical activities: walking, walking-upstairs, walking-downstairs, sitting, standing and lying down. All the experiments have been done using a publicly available dataset called UCI Human Activity Recognition Using Smartphones. The developed system improves the results obtained on this dataset in previous works. The main contribution of this paper is the incorporation of an Activity Sequence Model. The best results show an Activity Segmentation Error Rate of 2.1%.