Human Activity Recognition Based on Multichannel Convolutional Neural Network With Data Augmentation

Abstract

In view of the excellent portability and privacy protection of wearable sensor devices, human activity recognition (HAR) of wearable devices has increased applications in human-computer interaction, health care, etc. Therefore, it is necessary to recognize various human activities accurately and efficiently. In this paper, we propose a multi-channel convolutional neural network with data augmentation for HAR, denoted AMC-CNN. First, the sliding windows in time series are used to construct the feature window, and then the feature window is augmented by data transformation and data addition. Through the horizontal connection of the augmented feature windows, the reconstructed feature samples are obtained. Second, a relatively lightweight multi-channel convolutional neural network is designed. In order to mine deep correlations between sensor data more efficiently, we use reasonable convolution kernel settings to compute multi-channel convolutions and extract parallel multi-scale features, and then train the model to recognize human activities. Finally, experiments are carried out on WISDM and MHEALTH datasets to verify the effectiveness of the data augmentation. Moreover, the other three models are adopted for comparative experiments. The evaluation indexes show that the method proposed in this paper has a better recognition effect, which verifies that the AMC-CNN model is effective in both single-sensor and multi-sensor HAR.INDEX TERMS Multi-channel convolutional neural network, data augmentation, human activity recognition, wearable devices.

Detection of Road Potholes by Applying Convolutional Neural Network Method Based on Road Vibration Data

“…In the former, both ML techniques and CNNs, DL methods, are commonly employed, while the latter predominantly relies on thresholding and machine learning methods. Furthermore, when examining studies related to HAR based on vibration-based approaches, it is observed that CNN techniques are extensively utilized in these studies as well [47][48][49][50][51][52].…”

“…A unique shallow CNN with a C3 block was suggested for sensor-based HAR, where all channels in the same layer have extensive interaction to capture distinctive features in raw sensor data [50]. An augmented multichannel convolutional neural network (AMC-CNN) model was proposed to better explore feature patterns in time series and enhance the capability of HAR [51]. To improve the accuracy of human activity recognition (HAR), a novel approach called convolution ternary (HAR-CT) was proposed, which enhances a CNN using the trained ternary quantization (TTQ) approach [52].…”