As part of my work with SinBerBEST2 I worked with Dr. Pandarasamy Arjunan on electrical meter data of numerous buildings. Our work was fous mainly on the Primary-Space-Usage (PSU) labels defined by domain experts. Such labels are often unrepresentative of the modern built environment since most of current infrastructure cannot be completely classified as one category.
We propose a modular methodology for systematic validation of the man-made building classification. This methodology leverages its modularity for homogenizing power meter readings based on different temporal contexts and aggregation functions.
In collaboration with Prof. Negin Narzarian and part of the international collaboration Project coolbit, we started working on a novel form of occupant comfort data collection, using a Fitbit smartwatch. We deployed an application in the wearble in the form of a simple clock-face where the user can state their comfort preference as a binary input “comfy” or “not comfy”.
Currently, this proof of concept has been launched with a small sample set of 15 users at the National University of Singapore.
Structured surveys or interviews - on-line or off-line, in person or remote - are conventionally used to collect human comfort feedback for buildings. Though these approaches work in principle, they have a number of shortcomings:
Subjectivity: There is sufficient evidence to suggest variance in subjective well-being responses based on individual differences in respondent’s personality, geographical background and culture. Response bias & heuristics: A number of factors such as lack of knowledge (respondents do not know the answer to a question, but answer it anyway), lack of motivation (respondents may not process questions fully) and failures in communication (survey questions may be unclear or misunderstood) are often associated with increased risk of biases and respondent heuristics in survey responses.
Abstract submitted to CISBAT2019
In addition to developing FORK for the project Human-in-the-loop Sensing and Control for Commercial Building Energy Efficiency and Occupant Comfort (DOE#: DE-EE0007682), we launched a year-long, large-scale, human-in-the-loop Thermal Comfort Study (TCS). We wish to predict and evaluate the thermal comfort of 80 smart building occupants in a fully-sensed and controlled thermal chamber at Carnegie Mellon University.
This prediction, using a combination of different data-driven and thermal modelling methods, given environmental sensor data, and bio-metrics, will serve as a basis for generating subjective comfort models that will be used in autonomous HVAC system control as well as other aspects of user personalisation in the space.