Thesis
Using interpretable machine learning for indoor CO₂ level prediction and occupancy estimation
- Creator
- Rights statement
- Awarding institution
- University of Strathclyde
- Date of award
- 2021
- Thesis identifier
- T16101
- Person Identifier (Local)
- 201652026
- Qualification Level
- Qualification Name
- Department, School or Faculty
- Abstract
- Management and monitoring of rooms’ environmental conditions is a good step towardsachieving energy efficiency and a healthy indoor environment. However, studies indicatethat some of the current methods used in environmental room monitoring are faced withsome challenges such as high cost and lack of privacy. As a result, there is need to use amethod that is simpler, reliable, affordable and without any privacy issues. Therefore, theaims of this thesis were: (i) to predict future CO₂ levels using environmental sensor data,(ii) to determine room occupancy using environmental sensor data and (iii) to create aprototype dashboard for possible future room management based on the modelsdeveloped for room occupancy and CO₂ prediction. Machine learning methods were usedand these included: Gradient Boosting ensemble model (GB), Long Short-Term Memoryrecurrent neural network model (LSTM) and Facebook Prophet model for time series(Prophet). The sensor data were recorded from three different office locations (two testsites at a university and a real-world commercial office in Glasgow, Scotland, UK). Theresults of the analysis show that with LSTM method, a Root Mean Square Error (RMSE)(absolute fit of the model results to the observed data) of 0.0682 could be achieved fortwo-hour time interval CO₂ prediction and with GB, of 82% accuracy could be achievedfor proposed room occupancy estimation. Furthermore, as the model understanding wasraised as a key issue, interpretable machine learning methods (SHapley AdditiveexPlanation. (SHAP) and Local Model-agnostic explanations. (LIME)) were used tointerpret room occupancy results obtained by GB model. In addition a dashboard wasdesigned and prototyped to show room environmental data, predicted CO₂ levels andestimated room occupancy based on what the sensor data and models might provide forpeople managing rooms in different settings. The proposed dashboard that was designedin this research was evaluated by interested participants and their responses show that theproposed dashboard could potentially offer inputs to building management towards thecontrol of heating, ventilation and air-conditioning systems. This in turn could lead toimproved energy efficiency, better planning of shared spaces in buildings, potentiallyreducing energy and operational costs, improved environmental conditions for roomoccupants; potentially leading to improved health, reduced risks, enhanced comfort andimproved productivity. It is advised that further studies should be conducted at multiplelocations to demonstrate generalisation of the results of the proposed model. In addition,the end benefits of the model could be assessed through applying its outputs to enhancethe control of HVAC systems, room management systems and safety systems. The healthand productivity of the occupants could be monitored in detail to identify whetherresulting environmental improvements deliver improvements in health and productivity.The findings of this research contribute new knowledge that could be used to achievereliable results in room occupancy estimation using machine learning approach.
- Advisor / supervisor
- Bellingham, Richard
- Lennon, Marilyn
- Resource Type
- DOI
- Funder
Beziehungen
Objekte
| Miniaturansicht | Titel | Hochladedatum | Sichtbarkeit | Aktionen |
|---|---|---|---|---|
|
|
PDF of thesis T16101 | 2021-12-13 | Öffentlich | Herunterladen |