Multi-sensor human activity recognition using CNN and GRU

In the current era of rapid technological innovation, human activity recognition (HAR) has emerged as a principal research area in the field of multimedia information retrieval. The capacity to monitor people remotely is a main determinant of HAR’s central role. Multiple gyroscope and accelerometer sensors can be used to aggregate data which can be used to recognise human activities—one of the key research objectives of this study. Optimal results are attained through the use of deep learning models to carry out HAR in the collected data. We propose the use of a hierarchical multi-resolution convolutional neural networks in combination with gated recurrent uni. We conducted an experiment on the mHealth and UCI data sets, the results of which demonstrate the efficiency of the proposed model, as it achieved acceptable accuracies: 99.35% in the mHealth data set and 94.50% in the UCI data set.