Can Mental Stress Data Feed the Design and Operation of Indoor Environment?
06/30/2023
Buildings are moving from passive assets to active environments by becoming “smart.”
1. BIM data
Building Information Modeling (BIM) is a rapidly evolving collaboration tool that facilitates integrated design and construction management. BIM enables multidimensional models to be created and even allows the support for information-based real-time collaboration. This information can be used to drive technologies such as city-sized models, augmented reality equipment, radio-frequency identification (RFID) tagging, and even the use of 3D printers. (Lester, 2014).
2. IoT in architecture design
2.1 What is IoT
The Internet of Things (IoT) is a network of physical devices, vehicles, home appliances, and other items embedded with electronics, software, sensors, actuators, and connectivity, enabling these objects to connect and exchange data. (Shafiq et al., 2022)
The IoT creates endless streams of data, and the possibilities for harnessing that data are endless. However, it does not come without its problems. There are three major challenges concerning the IoT that we cannot ignore: (Hendricks, 2015)
Ubiquitous data collection.
Potential for unexpected uses of consumer data.
Heightened security risks.
2.2 How does IoT affect indoor environmental quality
Smart buildings are the most promising field of application for IoT. This concept integrates buildings with environmental sensors to measure temperature, airflow, humidity, CO2, occupancy, and occupant density (Desogus et al., 2021).
3. Data on mental stress
Mental stress levels were previously studied by questionnaires and surveys (Mauss & Robinson, 2009). To inform indoor environment design and operation, mental stress data need to be collected in a real-time and statistical way.
3.1 Bio-signals of mental stress
Bio-signals are time-dependent measures of biological processes occurring in the human body and can be utilized to infer a person’s state of health. Bio-signals are efficient indicators of stress. (Mitro et al., 2023). Various detectable bio-signals of the human body have been utilized throughout the years: the ones that have been proven to be more reliable and widely used to extract health state indicators, such as stress, are described below:
Electrocardiogram (ECG): an ECG measures the electrical activity generated by the heart as it contracts. The ECG is one of the most extensively used signals in stress detection research (Keshan et al., 2015) because it directly reflects the activity of the heart, which in turn is affected by Autonomic Nervous System (ANS) changes.
Photoplethysmography (PPG): PPG is a simple optical technique used to detect volumetric changes in blood in the peripheral circulation (Shelley & Shelley, 2001). PPG is a low-cost and noninvasive method that makes measurements at the surface of the skin. From PPG signals, various measures can be extracted, such as pulse rate (PR), pulse rate variability (PRV), blood volume pulse (BVP), blood oxygen saturation level (SpO2), and blood pressure (BP).
Electromyogram (EMG): an EMG signal is a biomedical signal that measures electrical currents generated in muscles during their contraction. Stress impacts muscle contraction, which is why EMG can be exploited to identify stress. (Karthikeyan et al., 2012)
Electrodermal Activity (EDA): EDA, also called Galvanic Skin Response (GSR) or skin conductance (SC) is a measure of changes in the electrical conductance of skin, based on the production of sweat. It is widely used in psychological stress detection. (Setz et al., 2010)
Heart rate variability (HRV) reflects the distribution of heartbeats over a given time interval. HRV can be obtained by computing the time difference corresponding to each pair of successive peaks, and it represents one of the most promising markers of the ANS [41]. HRV-extracted metrics are commonly used as features in stress detection tasks, as they are considered reliable indicators of stress. (Li et al., 2018)
3.2 Device used to collect mental stress data
In the field of wearable-based stress detection, it is often the case that off-the-shelf, commercial solutions are utilized to acquire biometric data and that the collected datasets are subsequently used for tackling the stress detection task. For instance, one research used four physiological signals—electrodermal activity (EDA), premature ventricular beats (PVB), interbeat intervals (IBI), and skin temperature (ST)—provided by a wrist-worn device, to develop a stress detection model for the elderly (Nath & Thapliyal, 2021). Others tried to predict the stress levels experienced by travelers over a long journey, by proposing a personalized regressive model based on several bio-signals (Vila et al., 2019). Specifically, accelerometer measurements, EDA, blood volume pulse (BVP), and ST signals, recorded by wristband device, were used as inputs. Mitro et al (Mitro et al., 2023) developed a low-cost, easy-to-use, and fully customized smart wristband, implementing a lightweight machine learning pipeline for stress detection, and an algorithm based on five-time domain features and one extra heart-rate-related feature, to provide a “stress” or “no stress” output.
4. Proposal
Mental stress data is one part of the IoT data that can be collected and monitored through sensors, and personal devices. There is a substantial body of research showing that indoor environmental quality could significantly affect occupants’ cognitive functions and therefore their learning and work performance. (Cui et al., 2013, Jahncke et al., 2011). In return, how could mental stress data influence indoor environmental quality? As buildings get more intelligent, the dynamic interaction between humans and buildings should be a continued feedback loop.
This research proposes integrating the mental stress data collected by IoT devices into the BIM system used in the design and operation of an Indoor environment. Four potential aspects of indoor environment quality can be monitored through the indoor space users’ mental stress levels:
Temperature
Lighting
Soundscape
Human building interfaces
After collecting the mental status data, machine learning would be applied to evaluate the stress level and compared it with the data owner’s goal for monitoring the mental stress. The results would be conveyed to BIM to inform the building system to make responsive design decisions and operational adjustments to the indoor environment.
5. Potential challenges
We expect the following challenges:
Privacy: IoT data collected at the individual level contains private information, like age, gender, geolocation, physical health data, etc. It can be easily abused.
Accuracy of mental stress: mental stress has positive and negative effects on personal performance. It is not accurate to only rely on statistics to make design or operation decisions for the indoor environment.
Individual vs group mental stress status: Indoor environments always have a group of users; individual mental stress data need to be evaluated and compared with the group’s data to make balanced decisions.
Reference:
Desogus, G., Quaquero, E., Rubiu, G., Gatto, G., & Perra, C. (2021). BIM and IoT Sensors Integration: A Framework for Consumption and Indoor Conditions Data Monitoring of Existing Buildings. Sustainability, 13(8), 4496. https://doi.org/10.3390/su13084496
H. Jahncke, S. Hygge, N. Halin, A.M. Green, K. Dimberg. (2011). Open-plan office noise: cognitive performance and restoration, J. Environ. Psychol. 31, 373–382. https://doi.org/10.1016/j.jenvp.2011.07.002.
Hendricks, D. (2015). The Trouble with the Internet of Things. London Datastore. Greater London Authority.
Karthikeyan, P., Murugappan, M., Yaacob., Sazali. EMG Signal Based Human Stress Level Classification Using Wavelet Packet Transform. In Trends in Intelligent Robotics, Automation, and Manufacturing, Proceedings of the First International Conference, Iram, Kuala Lumpur, Malaysia, 28–30 November 2012; Ponnambalam, S.G., Parkkinen, J., Ramanathan, K.C., Eds.; Springer: Berlin/Heidelberg, Germany, 2012.
Keshan, N., Parimi, P.V., Bichindaritz, I. Machine learning for stress detection from ECG signals in automobile drivers. In Proceedings of the 2015 IEEE International Conference on Big Data (Big Data), Santa Clara, CA, USA, 29 October–1 November 2015; pp. 2661–2669.
Lester, A. (2014), BIM. In Lester, A. (Ed.), Project Management, Planning and Control (6th ed., pp. 503-521). Elsevier.
Li, F., Xu, P., Zheng, S., Chen, W., Yan, Y., Lu, S., Liu, Z. (2018). Photoplethysmography-based psychological stress detection with pulse rate variability feature differences and elastic net. International Journal of Distributed Sensor Networks.,14(9). 10.1177/1550147718803298
Mitro, N., Argyri, K., Pavlopoulos, L., Kosyvas, D., Karagiannidis, L., Kostovasili, M., Misichroni, F., Ouzounoglou, E., & Amditis, A. (2023). AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring. Sensors, 23(5), 2821. https://doi.org/10.3390/s23052821
Mauss, I. B., & Robinson, M. D. (2009). Measures of emotion: A review. Cognition & Emotion, 23(2), 209–237. 10.1080/02699930802204677
Nath, R., & Thapliyal, H. (2021). Smart Wristband-Based Stress Detection Framework for Older Adults With Cortisol as Stress Biomarker. IEEE Trans. Consum. Electron. 67, 30–39.
Setz, C., Arnrich, B., Schumm, J., La Marca, R., Troster, G., Ehlert, U. (2010). Discriminating Stress From Cognitive Load Using a Wearable EDA Device. IEEE Trans. Inf. Technol. Biomed. 14, 410–417.
Shafiq, M., Gu, Z., Cheikhrouhou, O., Alhakami, W. & Hamam, H. (2022). The Rise of “Internet of Things” Review and Open Research Issues Related to Detection and Prevention of IoT-Based Security Attacks. Wireless Communications and Mobile Computing.12. 10.1155/2022/8669348
Shelley, K., Shelley, S. (2001). Pulse oximeter waveform: Photoelectric plethysmography. Clin. Monit. 2, 420–428.
Vila, G., Godin, C., Sakri, O., Labyt, E., Vidal, A., Charbonnier, S., Ollander, S., Campagne, A. (2019). Real-Time Monitoring of Passenger’s Psychological Stress. Future Internet. 11, 102.
Cui. W., Cao G., Park, J.H., Ouyang, Q., Zhu, Y. (2013). Influence of indoor air temperature on human thermal comfort, motivation, and performance, Build. Environ. 68, 114–122, https://doi.org/10.1016/j.buildenv.2013.06.012