Achieving Single-Sensor Complex Activity Recognition from Multi-Sensor Training Data
This addresses the challenge of high-accuracy activity recognition for users with limited sensor availability, such as smartphone users, though it is incremental in leveraging multi-sensor training data.
The paper tackles the problem of recognizing complex activities using only a single sensor in real-world scenarios, where multi-sensor setups are impractical, and achieves up to a 17% improvement in F1-score compared to training with the same sensor data in new user scenarios.
In this study, we propose a method for single sensor-based activity recognition, trained with data from multiple sensors. There is no doubt that the performance of complex activity recognition systems increases when we use enough sensors with sufficient quality, however using such rich sensors may not be feasible in real-life situations for various reasons such as user comfort, privacy, battery-preservation, and/or costs. In many cases, only one device such as a smartphone is available, and it is challenging to achieve high accuracy with a single sensor, more so for complex activities. Our method combines representation learning with feature mapping to leverage multiple sensor information made available during training while using a single sensor during testing or in real usage. Our results show that the proposed approach can improve the F1-score of the complex activity recognition by up to 17\% compared to that in training while utilizing the same sensor data in a new user scenario.