Fusion Approaches of Heterogeneous Multichannel CNN and LSTM Models for Human Activity Recognition using Wearable Sensors
Phurich Saengthong, Seksan Laitrakun · 2021
Human activity recognition (HAR) is an emerging filed to classify daily activities and is applicable to many applications including healthcare. Several machine learning models and approaches have been investigated to improve the classification performances. In this paper, we investigate several fusion approaches of heterogeneous multichannel models where the channels use different kinds of deep learning (DL) algorithms to better the HAR performances. The DL algorithms exploited in those channels are convolutional neural networks (CNNs), long short-term memory networks (LSTMs), CNN-LSTMs, and convolutional LSTMs. Six different fusion approaches based on feature fusion and decision fusion are applied to combine the outputs of the channels. Their classification performances are evaluated and compared. The best fusion approaches achieve 98.96% and 96.35% of accuracy when using the PAMAP2 and DaLiAc datasets, respectively.