CoSMoS : Collaborative Sensing & Managing on Stress


For a long time, many of all ages have suffered from mental stress because of various reasons such as job, family, relationship, and finance. Chronic stress has been well-known to harm people in negative way by increasing risk of cardiovascular disease, diabetes, mental disorders etc. [1]. In the era of well-being, people have been paying more and more attention on their stress in everyday life. Accordingly, identifying the stress and further managing it just in time has become definitely challenging.

In order to estimate whether a person gets stressed or not, various sensors can be utilized including heart rate and electrodermal activity. For example, heart rate increases because of getting stressed because of presentation in front of large audience. Through in-depth study on existing works, we have investigated interesting sensor data to estimate mental stress. Thanks to the popularity of the wearable devices, we can easily collect those sensor data from individuals. Utilizing wearable sensor devices, we have designed a framework strEsstimate as the first phase of our project CoSMoS.


strEsstimate (i) monitors and collects various sensor data in real-time, (ii) organizes and improves multimodal sensor database, and (iii) analyzes and extracts interesting patterns of various sensor data under stressful episodes. In strEsstimate, we designed a scenario including two stressors (Stressor 1 : cognitive task and Stressor 2 : socio-evaluative task) based on conventional works as shown in Figure 1.

Figure 1 : Stress inducing scenario in laboratory utilizing two stressors

strEsstimate exploits three wearable devices Zephyr “Bioharness”[2], LG “Watch Style”[3], and Empatica “E4″[4] and additionally monitors a person using VSTARCAM “100E”[5] that is an IP camera. A person under our experimental scenario wears “Bioharness” on his/her chest and “Watch Style” and “E4” on both wrists (“E4” on non-dominant side) as shown in Figure 2. Embedded sensors and detailed information about them are described in Table 1.

Figure 2 : Real-time monitoring with the implemented application on Microsoft Surface for a person wearing three data-collection devices

Table 1 : Embedded sensor specifications of three data-collection devices

Our experimental study was approved by Yonsei University Institutional Review Board (7001988-201706-HR-201-03). We gathered 100 subjects of 40 females and 60 males of 20s and 30s. Entire experiments were conducted in the laboratories in Yonsei University. Based on strEsstimate, we are preparing open access to our database and analysis tool for comprehensive understanding of the data.


  • [1]
  • [2]
  • [3]
  • [4] Garbarino, M., Lai, M., Bender, D., Picard, R. W., & Tognetti, S. (2014). Empatica E3 – A wearable wireless multi-sensor device for real-time computerized biofeedback and data acquisition. In 2014 EAI 4th International Conference on Wireless Mobile Communication and Healthcare (Mobihealth) 39-42.
  • [5]

Relavant Publications

Research funding

  • 정부부처: Institute for Information & Communications Technology Promotion(IITP) grant funded by the Korea government(MSIP)
  • 과제번호: R0124-16-0002
  • 과제명: Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly
  • 과제기간: 2016~2021년
  • 총 액수: 약 159억