SPECIALLY COLLECTED PAPERS
Shimadzu Review 78[3・4] (2021)
Abstract
Technologies for estimating the internal state of humans based on physiological signals are being tried for a wide range of applications. Using such technologies for service applications requires human metrics tied to user experience. An integrated data analysis of various data would benefit the development of such metrics. Therefore, we developed the HuME (Human Metrics Explorer)™ multi-device biometric system, for assisting in developing human metrics with physiological signals applicable to each service. The HuME system reduces the time and burden spent measuring and recording data from multiple physiological signals or video images. It uses a technique based on recorded marker signals included in data from multiple measuring devices to adjust timestamps of data from respective devices. This article describes the concept of the HuME system processes physiological signals from multiple devices, an overview of the specific system used to achieve that concept, and an example of a verification experiment conducted for application development purposes. For applications of emotion estimation, we developed a wearable device that causes minimal burden on the subject and identifies transitions in facial expression based on an integrated analysis of physiological signals and video images acquired while the subject experiences a product or service. Similarly, for sleep monitoring applications we demonstrated a system that can be used to obtain a detailed understanding of events that occur during sleep.
1Brain and Five Senses Technology Unit, Technology Research Laboratory, Shimadzu Corporation, Kyoto, Japan
2Department of Robotics, Faculty of Science and Engineering, Ritsumeikan University, Shiga, Japan
3Psychological Process Research Team, Guardian Robot Project, RIKEN, Kyoto, Japan
*The information contained in Shimadzu Review has not been modified since the original publication date. Please be aware that in some cases, products mentioned within the articles are no longer available.