In April 2021, we began a mentoring relationship with two high school students who chose to work with us on a project at the intersection of Data Science, the Internet of Things, wearables, and the United Nations Sustainable Development Goals (SDGs).

Neuroergonomics is a relatively nascent field within the broader landscape of neuroscience (Parasuraman & Rizzo, 2006). My students approach this intersection from the perspective of peer-based learning and maker-culture, as opposed to relying on industry-grade and laboratory-based high-cost equipment. Consultation with faculty who are academically independent from our team and who work in the field of neuroscience has helped to validate the statistical viability of their work. 

We call the project Life2Well, where the acronym stands for Learning at the intersection of AI, physiology, EEG, our environment and well-being.

If you would like to learn about this project through podcast-style audio, please go ahead :-)

In the photos in the documents embedded below, you can see that in the initial stages, students would wear their wearable around their waists. As the project has evolved, we have latterly used Electrodermal Activity (EDA) wristbands.

Many of the parts are made from common household items.

What is more, our students are using the data obtained from these sensors and applying sophisticated statistical analyses to them to determine the best-fit relationships which they have accurately used to predict physiological stress levels (obtained by the wearable FitBits they wear around their wrists) according to ambient microclimate variables.

Our students conceptualised, designed, coded, and built a wearable suite of local microclimate sensors using common household items as much as possible in order to use regression analysis to devise a predictive model for health and well-being in low-resource contexts vulnerable to the effects of climate change.

Subsequently, neurophysiological measurement - specifically electroencephalography (EEG) - was introduced to the model to explore how the changes in environmental or biometric measurements correlate with changes in neurophysiological measurements. In this latter study, EEG data is viewed as an independent data type that is distinct from environmental and other physiological data. The headset model used to record EEG data is again a bespoke hand-made design, comprising a combination of biosensing board and electrodes and widely available items like adhesive tapes and staples. All data recorded is stored in Google Drive; Python is used to synchronize, pre-process data and train regression models. The first headset prototype was assembled in mid-October 2021, and was tested and developed in early November. From mid-November to late January 2022, we wore the devices for one to two hours per day to collect data. EEG time-series are used as input in regression models with other data types as output. Two regression models were trained then compared, the first being convolutional neural network with pre-built architecture and the other being a Random Forest model with features extracted from EEG time-series. Inferences are made from the models using open-source interpreters, with an eventual aim to infer how one’s local environment might impact one’s emotions and health.

We feel this work is so very relevant to the SDGs and to human health and well-being, and to climate change, and may be of particular value in low-resource contexts vulnerable to the effects of climate change.

In 2023, we conceptualised how Generative AI might be used to complement Life2Well.

In 2023 / 2024, other student-initiated projects under the Life2Well aegis include:

• Integration of Deep Learning in digital Clock Drawing Tests onto consumer platforms for enhanced detection of mild cognitive impairment;

• An exploration of Machine Learning and Reinforcement Learning for emotional well-being;

• Investigating the relationship between microclimate factors and human exercise performance; and

• Optimizing Learning Environments: A Microclimate Study of a School Campus in Singapore using the Integrated Environment Modeller Simulation Tool (IEMsim).

In 2022 / 2023, other student-initiated projects under the Life2Well aegis include:

• Implementing Artificial Intelligence in Sleep Analysis systems;

• An investigation on the effects of different types of fragrance on stress level of junior college students;

• Design and prototyping of an AI-based real-time detector for the calisthenic push up exercise;

• Investigation of the effects of microclimate on concentration levels; and

• Mitigating anxiety and stress: Investigating features of Lo-fi Music as attributed to its calming effects.

Life2Well was identified by UNESCO to be featured as part of the organisation's first online interactive learning webinar, themed on Education for Sustainable Development (ESD-Net) 2030 on 30 March 2023. Of the registered participants, 21 % were from African nations, 20 % were from Central and South Asia, 16 % were from the UK and Europe, 10 % were from East Asia, 10 % were from the Middle East, 9 % were from Central and South America, 9 % were from North America, and the remainder from Southeast Asia.

The following year, Life2Well was shared during UNESCO's second annual flagship event Digital Learning Week, in the session on 'Leveraging AI for personalised learning and assessment', Paris, 4 September 2024.

Life2Well has been published in:

Nguyễn Duc, M. A., M. T. Nguyễn Thien, K. Y. T. Lim, and A. H. Hilmy, “The Life2Well Project: Investigating the relationship between physiological stress and environmental factors through data science, the Internet of Things and Do-It-Yourself wearables” in Dias, D., & Araujo, C. M. (Eds.) Creativity and innovation for a better world, Intech Open, 2022.

Lim, K. Y. T., M. A. Nguyễn Duc, M. T. Nguyễn Thien, R. Yuvaraj, and J. S. Fogarty, “Investigating the effects of microclimate on physiological stress and brain function with data science and wearables” Sustainability, special issue on “Aspirations within Interdisciplinary STEM / STEAM Education under the Education for Sustainable Development (ESD)”, 14 (17): 2022.

Nguyen Thien, M. T., M. A. Nguyen Duc, and K. Y. T. Lim, “Designing for the investigation of microclimate stressors and physiological and neurological responses from the perspective of maker culture” in Ahram, T., & Taiar, R. (eds.) Artificial Intelligence & Future Applications, Proceedings of the 10th International Conference on Human Interaction & Emerging Technologies in the track on Human-computer interaction, AHFE Open Access, Vol. 111, Nice, France, 23 August 2023; pp. 356-365.

Lim, K. Y. T., M. T. Nguyen Thien, M. A. Nguyen Duc, and H. F. Posada-Quintero, (2024) “Application of DIY Electrodermal Activity wristband in detecting stress and affective responses of students” in Bioengineering Vol. 11 No. 3, in the section on Biosignal Processing, in the special issue on Electronic Wearable Solutions for Sport and Health.

Quek, Y. M., N. A. Dinh, K. Y. T. Lim, M. A. Nguyễn Đức, and M. T. Nguyễn Thiên, “Investigating the relationship between microclimate factors and human exercise performance from the perspective of citizen science” in Kalra, J. (Ed.) Proceedings of the 15th International Conference on Applied Human Factors and Ergonomics, in the track on Human Factors in Sports, Injury Prevention and Outdoor Recreation, in the session on Performance, Risk, and Wellness in Sports, Nice, France, 27 July 2024.

Nguyễn Đức, M. A., M. T. Nguyễn Thiên, K. Y. T. Lim, and H. Posada-Quintero, “The use of bespoke wearables to investigate neurological and physiological responses to microclimate stressors in quasi-formal academic contexts” in Yemelyanov, A. M., & Elliott, L. J. (Eds.) Proceedings of the 15th International Conference on Applied Human Factors and Ergonomics, in the track on Neuroergonomics and Cognitive Engineering, in the session on Neuroergonomics: Neural Feature Extraction and Use, Nice, France, 27 July 2024.

Lim, K. Y. T., Y. H. Wong, D. N. Tran, E. K. X. Lee, M. T. Nguyen Thien, and M. A. Nguyen Duc, “Exploratory investigation of electrodermal activity in learning from a large language model versus from curated texts” in Degen, H. & Ntoa, S. (Eds.) Artificial Intelligence in HCI – Part I, Proceedings of the 27th international conference on Human-Computer Interaction, Gothenburg, 22 June 2025.

Nguyen Duc, M. A., M. T. Nguyen Thien, K. Y. T. Lim, and H. F. Posada-Quintero, “Investigating Effects of Microclimate on Stress and Affect using Low-cost Wearables in Quasi-formal Academic Contexts” AI, Brain and Child, 1: 2025.

and

Lim, K. Y. T., M. A. Nguyễn Đức, and M. T. Nguyễn Thien, “Exploring the potential of AI in nurturing learner empathy, pro-social values and environmental stewardship” in Wang, T., & Keane, T. (Eds.) Artificial Intelligence for advancing education quality and inclusion: Practices across educational settings, Dordrecht, The Netherlands: Springer (in press, 2025).

In addition:

Life2Well was featured in the 14 February 2022 issue of the Singapore Press Holdings schools' newspaper IN.