A Lifelog System for Detecting Psychological Stress with Glass-equipped Temperature Sensors

Stress is extremely harmful to one's health. It is important to know which situations or events cause us to feel stressed: if we know the factors behind the stress, we can take corrective action. However, it is hard to perceive stress in everyday life by ourselves. Automatically detecting stress from biological information is one method for dealing with this. Stress is generally detected by using a physiological index pulse, brain activity, and breathing in order to ensure universality and accuracy. This biological information reacts to sudden stressors, not chronic stressors. However, it is difficult to use measuring devices for such data in everyday life because the devices require expertise for operation and are expensive. Our goal in this study is to develop a lifelog system featuring glass-equipped sensors that can be used on a daily basis. We detect stress by examining nasal skin temperature, which is decreased by sudden stressors. In order to investigate the recognition accuracy of the proposed system, we performed experiments at the scenes of feeling stress. Results showed that the system can distinguish factors other than stress from the change in nasal skin temperature with sufficient precision. Moreover, we investigated the optimum locations to attach temperature sensors to ensure that they have both reactivity and comfort. We also implemented an application for analyzing the measured data. The application calculates the time at which a user feels stress by analyzing the measured data and extracts a stressful scene from a video recorded from the point of view of the user.

[1]  Chikamune Wada,et al.  Effects of Arithmetic Tasks on Autonomic Nervous System Activities , 2009 .

[2]  I Homma,et al.  Anxiety and respiratory patterns: their relationship during mental stress and physical load. , 1997, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[3]  Hirokazu Genno,et al.  Estimating Human Sensations Using Chaos Analysis of Nose Skin Temperature , 1996 .

[4]  Enzo Pasquale Scilingo,et al.  How the Autonomic Nervous System and Driving Style Change With Incremental Stressing Conditions During Simulated Driving , 2015, IEEE Transactions on Intelligent Transportation Systems.

[5]  Mary Czerwinski,et al.  Under pressure: sensing stress of computer users , 2014, CHI.

[6]  Jennifer Healey,et al.  Digital processing of affective signals , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[7]  T. Mizuguchi,et al.  Development and Validation of Japanese Version of State-Trait Anxiety Inventory : A study with female subjects , 1982 .

[8]  Sakamoto Kiyomi,et al.  Influence of types of video content on physiological and psychological measurements of emotional state during TV viewing , 2011 .

[9]  Ichiro Kageyama,et al.  Study on State Estimation for Drivers by using of Analysis For Vital Reaction , 2002 .

[10]  Tsutomu Terada,et al.  A smile/laughter recognition mechanism for smile-based life logging , 2013, AH.