Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition
This work addresses sensor-based activity recognition for applications in smart devices and IoT, but it is incremental as it compares existing methods rather than introducing new ones.
The paper investigated various deep learning architectures, training mechanisms like contrastive learning, and feature representations for sensor-based human activity recognition, finding that deep methods outperform traditional approaches on two datasets.
The extensive ubiquitous availability of sensors in smart devices and the Internet of Things (IoT) has opened up the possibilities for implementing sensor-based activity recognition. As opposed to traditional sensor time-series processing and hand-engineered feature extraction, in light of deep learning's proven effectiveness across various domains, numerous deep methods have been explored to tackle the challenges in activity recognition, outperforming the traditional signal processing and traditional machine learning approaches. In this work, by performing extensive experimental studies on two human activity recognition datasets, we investigate the performance of common deep learning and machine learning approaches as well as different training mechanisms (such as contrastive learning), and various feature representations extracted from the sensor time-series data and measure their effectiveness for the human activity recognition task.