This study presents building energy forecasting methodology for cooling load for three institutional buildings. These buildings belong to a university campus in Singapore. The daily energy consumption for cooling load is obtained for a period of two years and the daily variation is analysed. The energy consumption is initially divided into five classes and the class numbers are used as inputs to develop a forecasting model. The model is developed using two machine learning tools. The tools used are Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Interface System (ANFIS). The division of data for training and testing the model is nearly 60% and 40% respectively. The results show that both ANN and ANFIS forecast the cooling load energy consumption of the three buildings with good accuracy. The correlation coefficient between measured and predicted consumption for training data are well above 0.98. The same is well above 0.96 for testing data. It is noted that such a methodology can be positively extended to other institutional buildings in the campus

We conducted a prospective environmental surveillance study to investigate the air, surface, dust, and water contamination of a room occupied by a patient infected with mpox virus (MPXV) at various stages of the illness. The patient tested positive for MPXV from a throat swab and skin lesions. Environmental sampling was conducted in a negative pressure room with 12 unidirectional high efficiency particulate air filter (HEPA) air changes per hour and daily cleaning of the surfaces. A total of 179 environmental samples were collected on days 7, 8, 13, and 21 of illness. Among the days of sampling, air, surface, and dust contamination showed the highest contamination rates on day 7 and 8 of illness, with a gradual decline to the lowest contamination level by day 21. Viable MPXV was isolated from surfaces and dust samples and no viable virus was isolated from the air and water samples.

This study presents an investigation and discussion on the energy performance of three tertiary institutional buildings in Singapore. Building information, energy consumption data of the air-conditioning system, and energy consumption data of the plug loads were collected separately. MATLAB identification models are developed to simulate the real daily energy consumption data:. Three functions are introduced to represent the function of daily occupancy, function of additional occupancy due to visitors and the function of outdoor air temperature. The results show that the predicted value follows the trend of real energy consumption value very well and can predict the daily variations. The newly developed methodology is able to simulate the daily variations of energy consumption. R² of 0.54, 0.66 and 0.63 can be achieved for the three buildings respectively

Within the multi-functionality of educational buildings, the energy conservation potential can be very different. In addition, among different retrofitting solutions investigated involving interventions on the building envelope, ventilation strategies, artificial lighting systems as well as equipment upgrading, different saving potential would come from different aspects. The opportunities for energy saving potential from the overall point of view and from the detailed aspect view of different retrofitting solutions would be very useful and important for building renovation decision making. This study presents a detailed retrofitting study of two different educational buildings. One represents a building with average occupancy variation and containing mainly offices and labs. The other one represents a building with high occupancy variation and containing mainly lecture rooms and studios. This comparison of the results gives an idea of the different energy saving potential for different types of educational buildings. Principal component analysis is also adopted to investigate the detailed performance of one of the buildings which is influenced stronger by these retrofitting solutions.