Elevator Pitch
What might the collision of maker culture, data science, electroencephalograms, the Internet of Things, and climate science look like? In this session, we share a student-initiated project which explores this very intersection. Come join us and BYOCM (bring your own craft materials)!
Description
We share an ongoing independent research project that is being conducted by a pair of high school students under the mentorship of a Research Scientist from the National Institute of Education, Singapore. DIY EEG headsets were designed and built from a citizen science approach to collect brainwave data daily for a 2-hour session each. From July 2021 to June 2022, data from these sensors was complemented by that obtained from smartwatches (namely blood oxygen saturation, heart rate and its variability, body temperature, respiration rate and sleep score). Identical units of a wearable device containing environmental sensors (such as ambient temperature, air pressure, infrared radiation and relative humidity) were designed and worn respectively by five adolescents over the same period. Thus far, more than 100,000 data points have been processed through Deep Learning models such as Random Forest regression and Convolutional Neural Networks (CNN).
Background
Climate change has been one of the most urgent problems to confront in the 21st century. The fifth report of the Intergovernmental Panel on Climate Change (IPCC) confirms that human influence on the climate system is clear and growing, with impacts observed across all continents and oceans (IPCC, 2014). Climate change has been degrading the quality of life for every creature on Earth. Glaciers have shrunk, ice on rivers and lakes is breaking up earlier, plant and animal ranges have shifted and trees are flowering sooner (NASA, 2021). From the United Nations World Urbanisation Prospects in 2017, 4.1 billion people live in urban areas (Ritchie & Roser, 2018). This means over half of the world (56% in 2020) live in urban settings. Urbanization continues apace and it also accounts for global climate change. The rapid and large-scale urbanization leads to severe land-use conversion and impacts ecosystem services (Wang et al., 2019). The latter refer to the direct and indirect contributions of ecosystems to human well-being. With ecosystems being damaged, human well-being is also affected. In the context of this pressing problem, urban microclimate studies have been gaining prominence due to rapid urbanization (Toparlar et al., 2017). Concurrently with the rapid changes in microclimate, a technological revolution has also brought about fresh wind to the field of neuroscience. Collecting electroencephalography (EEG) data has been made progressively more accessible and that has paved the way for many researchers to delve into the activities of the brain. For example, EEG is used in photic stimulation, a common procedure performed in the EEG laboratory in children and adults to detect abnormal epileptogenic sensitivity to flickering light (i.e., photosensitivity) (Kasteleijn-Nolst Trenité et al., 2012). In another instance, sound level can have an impact on the functioning of the brain, which can be observed through EEG data (Brockmeyer & D’Angiulli, 2016). In research, EEG is used as a means to identify human stress level since it is already proved that there is significant correlation between levels of psychological stress and EEG power (Hou et al., 2015). In other cases, EEG data are also strongly related to the change in human physiological health, for example, heart rate variability (Dziembowska et al., 2016). That is the reason why the authors felt compelled to explore the relationships between microclimate and our brain activities. It is self-evident that climate change has various effects on the well-being of a person. As human beings we are conscious and aware of our surroundings, and our responses to changes in microclimate may affect our emotions and health. To elaborate, climate change might precipitate changes to microclimates to the extent that for those inhabiting these biomes, the changes might be detrimental to physical and mental well-being. For instance, a study by Liu et al. in 2019 concluded that “the increasing research interest in thermal comfort and health has heightened the need to figure out how the human body responds, both psychologically and physiologically, to different microclimates”. Therefore, investigating EEG data may unveil hidden relationships as to how microclimate is related to our perception of well-being at a granular level.
Scope of presentation
This session will focus less on the literature scan and the significance of the findings, and instead more on the maker-ly aspects of the DIY EEG headsets, and on the processing of the environmental and encephalographic datasets through Deep Learning models.
Your potential takeaways
The audience will come away with a basic understanding of the collection of environmental and EEG data from the perspective of citizen science, and also how the resulting datasets might be analysed and interpreted in a preliminary manner.
No specialist prior knowledge will be assumed, except perhaps a rudimentary understanding of how Deep Learning models work.
Notes
Data from this project has been presented as Learning at the intersection of Artificial Intelligence (AI), physiology, EEG data, our environment and well-being (the Life2Well Project) at: - the Symposium on Human Dynamics Research: Mining Human Dynamics with Big Data (sponsored by the Spatial Analysis and Modeling specialty group, the Geographic Information Science and Systems specialty group, and the Cyberinfrastructure specialty group), 8th Symposium on Human Dynamics Research, annual conference of the American Association of Geographers 2022; and - the 13th International Conference on Applied Human Factors and Ergonomics 2022 in the track on Cognitive Computing and the Internet of Things. The project has also been showcased to Senior Minister and Coordinating Minister for National Security Teo Chee Hean on 13 May 2022 during his visit to the Science of Learning in Education Centre at the National Institute of Education; and also at the official launch of the AI@NIE Blueprint on 25 May 2022.