Official pytorch implementation of "Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition". (Ubicomp 2022)
Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition (accepted at Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2022) aims to solve the intra-class variability challenge in Human activity recognition community. The proposed Behaviour Pattern Disentanglement (BPD) framework can disentangle the behavior patterns from the irrelevant noises such as personal styles or environmental noises, etc.
This code provides an implementation for BPD. This repository is implemented using PyTorch and it includes code for running experiments on GOTOV, Pamap2, DSADS, MHEALTH datasets.