This repository provides the codes and data used in our paper "DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors",where we implement and evaluate several state-of-the-art approaches, ranging from handcrafted-based methods to convolutional neural networks. Also, we standardize a large number of datasets, which vary in terms of sampling rate, number of sensors, activities, and subjects.
The various datasets are to large to upload, which we used in our experiments. If you need these datasets, please contact us by email (leizhang@njnu.edu.cn or gaowenbin1018@gmail.com).
● Python3
● PyTorch (Recommended version 1.2.0+cu92)
● Scikit-learn
● Numpy