A Probabilistic Model of Activity Recognition with Loose Clothing

This file contains source code and dataset of paper "A Probabilistic Model of Activity Recognition with Loose Clothing". This paper proposes a probabilistic model and verifies it in a physical realisation and a real human activity recognition task. The experiment result shows that this model can be used to predict the performance of activity reignition in different situations. This study is also the first to suggest that fabric movement can be beneficial to activity recognition in a real human task. With this finding, textile-based sensors could be used for activity recognition in real-world applications. It also has many advantages, such as being able to ensure the wearer’s comfort by unobtrusive sensing and allowing the capture of natural behaviour. For the description of code and data, please see the readme file in the dataset.