A5050994637- Building Energy and Comfort Optimization
- Energy Load and Power Forecasting
- Air Quality Monitoring and Forecasting
- COVID-19 epidemiological studies
- Noise Effects and Management
- Infection Control and Ventilation
- COVID-19 Pandemic Impacts
- Wind and Air Flow Studies
- Sustainable Building Design and Assessment
- Phase Change Materials Research
- Multidisciplinary Science and Engineering Research
- Adsorption and Cooling Systems
- Urban Agriculture and Sustainability
- Urban Transport and Accessibility
- Electric Vehicles and Infrastructure
- Refrigeration and Air Conditioning Technologies
- Energy Harvesting in Wireless Networks
- Vehicle emissions and performance
- Social Acceptance of Renewable Energy
- Energy, Environment, and Transportation Policies
- Facilities and Workplace Management
- Health disparities and outcomes
- Energy Efficiency and Management
- Transportation Planning and Optimization
- Occupational Health and Safety Research
University of Hong Kong
2023-2024
City University of Hong Kong
2023-2024
University of Manchester
2020-2023
Occupant behaviour has significant impacts on the performance of machine learning algorithms when predicting building energy consumption. Due to a variety reasons (e.g., underperforming management systems or restrictions due privacy policies), availability occupational data long been an obstacle that hinders in Therefore, this study proposed agent-based model whereby modelling was employed generate simulated as input features for consumption prediction. Boruta feature selection also...
The transportation sector is deemed one of the primary sources energy consumption and greenhouse gases throughout world. To realise design sustainable transport, it imperative to comprehend relationships evaluate interactions among a set variables, which may influence transport CO2 emissions. Unlike recent published papers, this study strives achieve balance between machine learning (ML) model accuracy interpretability using Shapley additive explanation (SHAP) method for forecasting...
Artificial Intelligence methods (AI) have been widely applied in building energy consumption prediction. As data-intensive methods, lacking sufficient input features will significantly impede prediction performance. For some buildings where the management systems (BEMs) are underperformed, limited information can be extracted. In this study, a feature engineering framework that combines construction and selection was developed to deal with problems. Empirical mode decomposition Boruta were...
The blossoming of building related data has led to the rapid development machine learning methods in energy consumption prediction. This also allowed for strengths and brilliance over popular statistical such as seasonal autoregressive integrated moving average (SARIMA) be exposed. However, some old buildings that cannot provide sufficient data, it would intractable inefficient apply predict consumption. In this study, a hybrid method based on SARIMA support vector (SVM) was proposed...
Exposure to greenspace is protective of physical and mental health, but its role during the COVID-19 pandemic unclear. We examined cross-sectional associations residential greenness with behavioural, physical, health outcomes fifth wave in Hong Kong. A questionnaire n = 160 participants assessed frequency visits, activity from International Physical Activity Questionnaire, based on 12-item Short-Form Health Survey. Residential was measured terms number within a 400-m buffer, proximity...
The reliability of building energy prediction results is often threatened by lack comprehensive and continuous data, especially when dealing with older buildings that are not furnished management systems. In order to investigate the performance models under limited this paper utilises four distinct machine learning methods - decision tree (DT), support vector (SVM), random forest (RF) voting regression (VR) predict consumption Chemistry a prominent higher institution, based on just...
The outbreak of COVID-19 has impacted the world and society in its entirety. labour-intensive construction industry is especially disrupted by workers have a higher chance exposure to COVID-19. Despite extensiveness qualitative quantitative research around impact on industry, it observed that very limited proportion such actually investigated dynamics within specific site as well effectiveness corresponding safety control measures. Given this context, study developed an interactive...
Predicting sudden changes in energy consumption within a short time period remains challenging task for long-term building Prediction. In order to better predict during holiday periods, this paper proposes novel Prophet model adequately capture the usage patterns of classroom room Christmas periods under several data scenarios. The results showed that incorporation additional weather information as often advocated by earlier studies failed improve prediction accuracy. Although extension...
Data availability has triggered the development of implementing artificial intelligence methods on building energy consumption analysis prediction. Recent studies have also continuously proved excellent performance in this regard. However, there is a lack investigation impact types model prediction performance, especially for buildings without obvious usage patterns. In study, use long short-term memory networks (LSTMs) proposed to predicted classroom, library and student hall buildings. The...
Although the proliferation of building energy management systems (BEMS) has somewhat standardized consumption data formats, thereby enhancing their compatibility with relevant machine learning (ML)-based prediction algorithms. However, shortage still remains one most significant limiters to accurate prediction. Against this backdrop, it would seem very logical believe that a potentially viable remedy be rationalise features extracted from available data, so as guarantee better representation...
High-strength cement produces a lot of hydration heat when hydrated, it will usually lead to thermal cracks. Phase change materials (PCM) are very potential storage materials. Utilize PCM can help reduce the heat. Research shows that apply suitable amount has significant effect on improving compressive strength mortar, and also improve flexural some extent.