Detecting one's stress state is essential to prevent severe health problems. However, most of the existing stress detection techniques require direct contact between the user and the sensor devices, leading to user inconvenience. Further, it is difficult to provide reliable stress detection because of loosened wearing of sensor devices and the limited battery life of the devices. In this paper, we present i) a non-contact stress detection technique based on the user movement patterns using an impulse-radio ultra-wideband (IR-UWB) radar without estimating vital signals and ii) an attention-based neural network. We design novel radar signal features to accurately represent user movements that are related to the stress state. For the demonstration, we collect a multi-modal dataset from 50 subjects under stress-inducing experiments using both contact and non-contact sensor devices. Consequently, we achieve a binary stress detection accuracy of 76.22% which outperforms the wearable-based approach with movement data by up to 11.57%.
|Title of host publication||Proceedings of the 36th Annual ACM Symposium on Applied Computing, SAC 2021|
|Publisher||Association for Computing Machinery|
|Number of pages||4|
|Publication status||Published - 2021 Mar 22|
|Event||36th Annual ACM Symposium on Applied Computing, SAC 2021 - Virtual, Online, Korea, Republic of|
Duration: 2021 Mar 22 → 2021 Mar 26
|Name||Proceedings of the ACM Symposium on Applied Computing|
|Conference||36th Annual ACM Symposium on Applied Computing, SAC 2021|
|Country/Territory||Korea, Republic of|
|Period||21/3/22 → 21/3/26|
Bibliographical noteFunding Information:
This work was supported by Institute of Information & Communications Technology Planning Evaluation (IITP) grant funded by the Korea government(MSIT) [2016-0-00562(R0124-16-0002), Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly].
© 2021 Owner/Author.
All Science Journal Classification (ASJC) codes