voyeurism

the Life2Well Project to be shared during the 10th International Conference on Human Interaction & Emerging Technologies

we are very happy to share that we have been given the opportunity to share our work on Learning at the intersection of AI, physiology, EEG, our environment and well-being (the Life2Well Project) during the 10th International Conference on Human Interaction & Emerging Technologies in the track on Human-computer interaction. IHIET 2023 will be held in Nice from the 22nd till the 24th of August.

Designing for the investigation of microclimate stressors and physiological and neurological responses from the perspective of maker culture is co-authored with Nguyen Duc Minh Anh and Nguyen Thien Minh Tuan. its abstract reads:

The 2021 United Nations Climate Change Conference (COP26) resulted in the Glasgow Climate Pact. Initial work in the study reported in this paper investigated relationships between environment and physiological measurements using smartwatches, and self-designed bespoke environmental modules which are wearable around the waist. Data from this initial phase was analysed with a Random Forest regression model. The next phase of this project involves neurophysiological measurement, specifically electroencephalography (EEG). 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 phase, 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 from OpenBCI and widely available items like adhesive tapes and staples. A subsequent step involved validation of this DIY EEG headset data against research grade equipment, of which the analysis of different features of EEG data have shown to be of statistically comparable trends. For data collection, 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, the authors wore the devices for one to two hours per day to collect data. For EEG data, eight channels were recorded, basic filters (bandpass and notch) and REST re-referencing are applied. In this project, 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. The results suggest that sound level, carbon dioxide concentration, and dust concentration feature more importantly in the regression models trained on collected datasets. These factors were continually associated with high feature importance scores in the EEG data signal and in both the objective scores recorded from the electronic instruments and the more subjective self-report forms. Furthermore, it was found that visual stimulus and problem processing, in terms of information, touch, and spatial relationships, are the most influential factors affecting the participants’ physiological well-being in this research. Most recently, one aspect that is currently being investigated is electrodermal activity (EDA). EDA is marker of sympathetic network activity (Zangróniz et al., 2017). As such, it is an indication of human stress and emotion arousal, (Rahma et al., 2022). It is hoped that analyses of EDA data will further strengthen the emerging model describing the intersections between local microclimate and physiological and neurological stress. Early validation experiments comparing DIY EDA devices against research-grade Empactica E4 sets have shown promising results.

the Life2Well Project as part of the UNESCO's first online interactive learning webinar, themed on ESD-Net 2030

my team and i are thrilled to share that - by God's grace - we have been afforded the rare opportunity to share our work on Learning at the intersection of AI, physiology, EEG, our environment and well-being (the Life2Well Project) as part of UNESCO's first online interactive learning webinar, for the benefit of its global network of education stakeholders: ESD-Net 2030. The webinar will be held on the 30th of March, and our work will be shared alongside parallel sessions facilitated by the Association for Learning Design and Sustainable Development (represented by Maria Toro-Troconis and Norita Ahmad), the OPEDUCA Project (represented by Jos Eussen), and the International Association of Universities (represented by Hilligje van't Land and Isabel Toman).

ESD-Net 2030 was set up in October 2022 to take the lessons learned from the Global Action Programme and subsequently facilitate the implementation of the Education for Sustainable Development (ESD) for 2030 framework and its roadmap. To this end, the webinar series is designed with a focus on sharing and strengthening pedagogical approaches and key competencies in ESD. The inaugural March webinar will be opened by the Chief of Section of ESD, Education Sector, UNESCO - Jun Morohashi - and facilitated by Mark Manns, Sarah Margono, and Takanori Kusaka.

for our particular project, we describe the scope of our session thus:

Have you wondered how we may nurture values among our students in support of sustainable development? What about how curricula may be designed to develop climate literacy among youth and the leaders of tomorrow? In this workshop, you will hear the voices of young people themselves, as they share four examples of how they have conceptualised, designed, and enacted citizen science investigations inspired by observations from their own respective local environments. From promoting appreciations of ecological biodiversity, to understanding sleep and concentration better, to exploring the relationships between microclimatic stressors and our physiological and neurological responses - the examples all have in common that they do not rely on expensive and fragile industrial-grade equipment which cannot be taken out of the lab. Be inspired by the stories of the students as they share their ups and downs through their respective investigative journeys, and their hopes as young makers for the future.

the Life2Well Project to be shared during the FOSS Asia summit

on the 15th of April my team and i are privileged to be given the opportunity to share Learning at the intersection of AI, physiology, EEG, our environment and well-being (The Life2Well Project) at the Free and Open Source Software (FOSS) Asia summit to be held at the Lifelong Learning Institute, Singapore.

we would like to thank the hardworking team from FOSS Asia for kindly extending the invitation to us :-)

Papers on AI and well-being to be read at AHFE 2023 :-)

we are very happy to share that we have been given the opportunity to read the following papers during the 14th international conference on Applied Human Factors and Ergonomics, in the track on Cognitive Computing and the Internet of Things. AHFE 2023 will be held in San Francisco from the 20th till the 24th of July.

Development of an Automated Microclimate Adjustment System based on Concentration Levels of Students is co-authored with Jasper Koh and Prasanna Thangaraja. its abstract reads:

The microclimate of a classroom can significantly impact the students' concentration. As students ourselves, we have noticed this. For the same subject, we are concentrated in one period, then in another, we lose our attention very easily. This prompted us to investigate the relationship between students' concentration levels in relation to the microclimate. Through machine learning, specifically through facial recognition and computer vision, we aimed to investigate the students' concentration levels based on the number of blinks per minute. While researching ways to analyse concentration levels, we found multiple studies which found a correlation between blink frequency and concentration level. We found that when people are concentrated, they tend to blink less and vice versa. The relationship between microclimate climate and concentration was analysed by measuring the blinks per minute while changing the microclimate at the same time. The microclimate conditions were varied using an air conditioner where the temperature set varied from 19°C to 31°C. The microclimate was measured using the NodeMCU microcontroller board paired with SCD-30 and HM-3301 sensors from Grove. This allowed us to gather data such as temperature, relative humidity, carbon dioxide concentration, PM2.5 and PM10 readings. From this, it was found that the most significant microclimate condition that affects concentration levels is carbon dioxide concentration. As the concentration of carbon dioxide increases, the concentration of the participants decreases. The observed trend is supported by various studies as well. Simultaneously, as the microclimate conditions were being varied, we sent out a survey to find the thermal comfort level of the students, allowing us to gauge how they felt according to the environment. Thermal comfort is when a person feels comfortable with the thermal environment. Participants were tasked to do their work for a fixed duration while a sensor recorded the temperature and relative humidity of the place. For every hour, the participants were required to rank their thermal comfort by using the ASHRAE scale. This survey identified the comfort zone at an upper limit temperature of 28.9°C and relative humidity of 68.0% and a lower limit temperature of 26.2°C and relative humidity of 83.1%. With these findings, we created an automated system to alter microclimate conditions. The place will be a conducive environment for the students based on their concentration and the environmental data obtained from the sensors. The alteration of microclimate conditions was done by controlling the air conditioner using an infrared LED module connected to the NodeMCU that sent out the infrared codes according to the conditions of the room, allowing us to adjust the microclimate efficiently while fully utilising the various modes of the air conditioning system to save energy.

Exploring The Implementation of AI in a Cost-effective Device for Predicting Sleep Quality is co-authored with Jing Peng Lee and Bruce L Yu. its abstract reads:

This report presents the development and effectiveness of an Arduino-based sleep tracking device that can accurately measure various parameters of sleep, including movement, temperature, sound, light intensity, and humidity. The device was designed to be low-cost and easy to use, while not compromising on its ability to accurately measure sleep activity. The effectiveness of the device was evaluated by collecting data from test subjects and comparing it to the data collected by other sleep tracking devices. The collected data was then processed and used to train Artificial Intelligence (AI) models such as Backward Propagation Neural Network, Linear Regression Model, and Grey Relation Analysis, to predict the sleep quality rating from 0% to 100% and to identify the main cause of poor sleep. The results of the study demonstrated that the Arduino-based sleep tracking device is an effective and cost-efficient tool for measuring various parameters of sleep. However, the pressure sensor may sometimes result in inaccurate readings, which can be addressed through data cleaning and filtering. Furthermore, the use of AI models was able to predict the sleep quality rating and identify the main causes of poor sleep with high accuracy. Further research is needed to evaluate the device's performance over a longer period of time and in a larger sample of participants.

the Life2Well Project: invited to share during the NIE Innovations in Teaching and Learning seminar 2023

my team and i were thrilled to receive today an invitation to share our work on Learning at the intersection of AI, physiology, EEG, our environment and well-being (the Life2Well Project) during the Innovations in Teaching and Learning (iTL) seminar, organised by the Centre for Innovation in Learning, National Institute of Education.

the seminar will take place on the 3rd of March 2023. It provides opportunities for participants to collaborate and cross-pollinate ideas, learn about new pedagogical innovations, and share best practices across the teaching community.

iTL 2023 will be held in a so-called Design-a-thon format, facilitated by the Design Thinking Framework, enabling participants to come together and discuss problems in education collectively, which in turn, brings a variety of perspectives into the discussion. it allows participants to co-create innovative ideas that lead to enriching discussions where they can more deeply understand their learners.

concurrent with the Design-a-thon, there will be a Human Library segment, which will serve as an educational platform for participants to learn more about NIE projects related to teaching and learning. this segment allows participants to listen, relate, and ask questions about the projects shown in order to be inspired to come up with ideas for their design solutions to the design-a-thon problem statements. it is in this context that the Life2Well Project will be shared.

thanks be to God for so graciously granting us this opportunity to share and learn together.

Call for Proposals: Geographies of the here and now: inquiry of the hyperlocal as afforded by Data Science and the Internet of Things

Call for Proposals for a session to be held at the Annual Conference of the Royal Geographical Society, London, 29 August to 1 September 2023

 

Geographies of the here and now: inquiry of the hyperlocal as afforded by Data Science and the Internet of Things

 

The Internet of Things (IoT) has afforded the investigation of geographies at scales that have hitherto not been practicable. The relatively low cost of open-source hardware means that localized spaces can potentially be saturated with IoT sensors, with the resulting datasets analysed through modelling in Data Science. Examples include their use in monitoring microclimates in urban farming and to improve energy efficiencies in so-called ‘smart’ homes and workplaces. Vey and Storring (2022) have appropriated the term ‘hyperlocal’ to refer to “place governance in a fragmented world”, by which they describe the distinct geographies of places at the scale of downtowns, waterfronts, and innovation districts. Similarly, in a presentation at the 2020 Geography Teacher Educators’ Conference hosted by the Geographical Association, Witt has described the hyperlocal as referring to “a very small geographical community, such as … a local patch”. Matthews (2020) has reminded us that the pandemic has catalysed renewed interest in the hyperlocal and in personal geographies. This session aims to explore the intersections of such geographies (of the hyperlocal and personal) through the lenses afforded by Data Science and the Internet of Things. Possible topics include (but are not limited to):

 

• Methodological approaches to investigations of the hyperlocal;

• Ethical implications of the use of IoT and Data Science in such investigations;

• Empirical studies of hyperlocal and / or personal geographies;

• Personal geographies of health and well-being, particularly as seen through the lenses of IoT and Data Science; and

• Citizen science and the democratization of geographical investigation of the hyperlocal.

 

Enquiries to Kenneth Y T Lim (kenneth.lim at nie.edu.sg) are welcome.

 

Session organizer:

 

Name: Kenneth Y T Lim

Affiliation: National Institute of Education, Singapore

 

Presenters are kindly invited to submit their proposals to the session organizer by the 10th of March 2023. Proposals should minimally comprise the title of the paper, an abstract (of up to 150 words), and full contact details.

Münchner Freiheit: the enigmatic BMW iX3

It has been a month since i took ownership of a BMW iX3.

This is my first BMW, and I come to the marque after a long relationship with Citroën. This latter point is not insignificant because it speaks to what I look for in a car, and – if one were to lapse in to stereotype – the two marques have traditionally appealed to quite different clienteles.

On the face of it, my particular unit of the iX3 falls squarely in to stereotype, with its Sophisto Grey Brilliant Effect paintwork, its M Shadowline trim (including the consequent absence of chrome detailing), and its 20-inch alloy wheels. The latter are noteworthy because they are shaped for low wind resistance but are of a ride-destroying diameter.

Yet they are not.

The iX3 continues to surprise and delight me, most notably in the quality of its ride comfort. With adaptive dampers under the moniker of Adaptive M Suspension, the iX3 has a pillow-soft ride and an imperious waft. There is a hushed absence of noise, vibration and harshness, aided no doubt by its double-glazing.

The supremely serene ride quality of the iX3 is at odds with the general thrustiness of its Calvin Luk-penned proportions, and I still scratch my head at how it has been achieved without being suspended through a pneumatic medium.

Beyond the enigma of its ride quality, there are many other aspects of the car which delight.

I am not generally a fan of facelifts, but I do think the tail lamps have been particularly well interpreted. Visibility from the cabin is very good, in large part due to the proportions of the glasshouse and the properly large side mirrors. These seem mundane things to discuss, but they do contribute to the overall feeling of securité de conduite.

One cannot talk about the sense of driving security the iX3 imparts, without an extensive discussion of the degree of intelligent assistance the car affords. This manifests itself not only in the headline act of Level 2+ autonomy (through the Driving Assistant Professional suite) but also through more subtle means. Two examples to do with navigation are first the way the routings on the (properly-sized) Head Up Display dynamically orientate their position to give the driver a more holistic understanding, say, during roundabouts, and second the way the oral delivery of the estimated drive time is given not immediately upon setting off (which is a time of high cognitive load on the driver) but shortly afterwards, once the car is en route and the driver has more bandwidth to deal with the provision of secondary information.

As for autonomous driving once underway, the AI is truly well calibrated. I have not encountered false positives, unlike during my test drive of the Mercedes EQC. Autonomous driving on the iX3 can cope with vehicular traffic cutting in to one’s lane, and with motorbikes weaving in and out.

As a geographer, I love that the car is not only locationally aware, but locationally aware at different scales. At the regional scale, the car is aware of its location through GPS. Such awareness is tapped by battery management and adaptive recuperation with respect to topography and the road network. The excellence of the adaptive recuperation has helped me match the official WLTP energy consumption figures. Second, at the hyperlocal scale, the car is aware of its location with respect to other vehicular traffic, using its combination of cameras and radar. Its location awareness at this scale of operation allows the iX3 to achieve its afore-mentioned degree of autonomy, including lane-changing without driver intervention.

I use autonomous driving on the iX3 on a daily basis, and it just matches the wafty demeanour of the automobile so well.

The iX3 appeals on so many levels. The petrolhead in me loves its 43 : 57 rear-biased weight distribution and the fact that it is rear-engined, rear-wheel-driven. The physicist in me loves that its centre of gravity is lower than other X3s due to its full-electric architecture. The data scientist in me loves the excellence of calibration of its AI. The geographer in me loves that its current-excited motor contains no rare earth elements.

But most of all the philosopher in me is enthralled by the enigma the BMW iX3 represents. On the face of it, this is the most powerful, most torquey, most accelerative automobile I have owned. Yet it is also the most cosseting to drive. The sheer serenity of its passage over the vilest of road perturbations is astounding. This is an automobile which weighs 2.3 tonnes yet wafts like a cloud. There truly is some magic in this magic carpet.

[with deep gratitude to Patsy Chua, Eddie Ho, and the team at Performance Motors Ltd. thank you for going above and beyond.]

co-hosting students from CHIJ Secondary for their Work Experience Programme

my team and i are happy to be given the opportunity to co-host some students from the Convent of the Holy Infant Jesus (CHIJ) Secondary School, with a few of my colleagues from the Sustainability Learning Lab, National Institute of Education.

this opportunity comes under the auspices of the school's Work Experience Programme, and our team will be co-hosting on the afternoon of the 1st of November.

the objectives of the programme are:

- to provide an experience in which the students familiarise themselves with a variety of work situations through attachment to a workplace and they learn through direct participation and observation;

- to build life skills for the world of work; and

- to help the students make informed decisions regarding career selection.

we are happy and grateful to be part of this opportunity :-)

hosting a Senior Lecturer from the School of Infocomm, Republic Polytechnic

my team and i are very excited and happy to welcome a Senior Lecturer from the School of Infocomm, Republic Polytechnic, as she prepares to begin her year-long Industrial Attachment with us.

the polytechnic was established in July 2002 and celebrates its twentieth anniversary this year. we will host the Senior Lecturer - with expertise in Financial Technology - from November this year, till October 2023.

we look forward to a journey of learning together!

The Life2Well Project: new student-initiated investigations under its aegis

for about a year, we have been sharing our work on Learning at the intersection of AI, physiology, EEG, our environment and well-being (The Life2Well Project). 

its mandate is deliberately framed broadly to encompass student-initiated inquiry in to their own health and well-being.

this year, we are excited and happy to share that students whom we mentor are currently working on the next suite of projects; these 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.