Thermal comfort assessment for the built environment has become more available to analysts and researchers due to the proliferation of sensors and subjective feedback methods. These data can be used for modeling comfort behavior to support design and operations towards energy efficiency and well-being. By nature, occupant subjective feedback is imbalanced as indoor conditions are designed for comfort, and responses indicating otherwise are less common. This situation creates a scenario for the machine learning workflow where class balancing as a pre-processing step might be valuable for developing predictive thermal comfort classification models with high-performance. This paper investigates the various thermal comfort dataset class balancing techniques from the literature and proposes a modified conditional Generative Adversarial Network (GAN), comfortGAN, to address this imbalance scenario. These approaches are applied to three publicly available datasets, ranging from 30 and 67 participants to a global collection of thermal comfort datasets, with 1,474; 2,067; and 66,397 data points, respectively. This work finds that a classification model trained on a balanced dataset, comprised of real and generated samples from comfortGAN, has higher performance (increase between 4% and 17% in classification accuracy) than other augmentation methods tested. However, when classes representing discomfort are merged and reduced to three, better imbalanced performance is expected, and the additional increase in performance by comfortGAN shrinks to 1 - 2%. These results illustrate that class balancing for thermal comfort modeling is beneficial using advanced techniques such as GANs, but its value is diminished in certain scenarios. A discussion is provided to assist potential users in determining which scenarios this process is useful and which method works best.

Understanding occupants’ satisfaction with their environment is an important step to improve indoor environmental quality (IEQ). These satisfaction data are limited to Singaporean commercial buildings. We surveyed (N = 666) occupant satisfaction with 18 IEQ parameters in seven Green Mark certified air-conditioned commercial buildings in Singapore. About 78 % of the participants expressed satisfaction with their overall workspace environment. Occupants were most satisfied with flexibility of dress code (86 % satisfaction), electrical lighting (84 %) and cleanliness (82 %), and most dissatisfied with sound privacy (42 % dissatisfaction), personal control (32 %) and temperature (30 %). We found that satisfaction with cleanliness has the highest impact to overall workspace environment satisfaction. Our results suggest achieving high occupant satisfaction for some IEQ factors is harder than others, which suggests the premise of singular satisfaction rating (e.g., 80 %) that applies to all IEQ parameters may not be reliable and representative. We determined that the major contributors to thermal dissatisfaction were insufficient air movement and overcooled workspaces. Occupants in open plan office were unhappy with the noise produced by their nearby colleagues. We also found that several IEQ variables (odors, air movement, available space, overall privacy, sound privacy and temperature) which are not statistically significant to the overall workspace satisfaction on their own, but their impacts becomes substantial when these IEQ variables are merged into larger environmental factors (i.e., Perceived Air Quality, Acoustics, Layout and Thermal). These results can support the development of an IEQ benchmarks for commercial buildings in Singapore.

In a business as usual scenario, atmospheric carbon dioxide concentration (CO₂) could reach 950 parts per million (ppm) by 2100. Indoor CO₂ concentrations will rise consequently, given its dependence on atmospheric CO₂ levels. If buildings are ventilated following current standards in 2100, indoor CO₂ concentration could be over 1300 ppm, depending on specific ventilation codes. Such exposure to CO₂ could have physiological and psychological effects on building occupants. We conducted a randomized, within-subject study, examining the physiological effects on the respiratory functions of 15 persons. We examined three exposures, each 150 min long, with CO₂ of: 900 ppm (reference), 1450 ppm (decreased ventilation), and 1450 ppm (reference condition with added pure CO₂). We measured respiratory parameters with capnometry and forced vital capacity (FVC) tests. End-tidal CO₂ and respiration rates did not significantly differ across the three exposures. Parameters measured using FVC decreased significantly from the start to the end of exposure only at the reduced ventilation condition (p < 0.04, large effect size). Hence, poor ventilation likely affects respiratory parameters. This effect is probably not caused by increased CO₂ alone and rather by other pollutants—predominantly human bioeffluents in this work—whose concentrations increased as a result.

Air conditioning and mechanical ventilation systems may be oversized in commercial buildings in the Tropics. Oversized cooling coils may lead to reduced dehumidifying performance, indoor air quality and thermal comfort and increased energy consumption. In this paper, an adaptable cooling coil design is assessed with a general-purpose coil selection software tool, in which the number of active rows changes as a function of the load. For a 100% oversized coil, it is shown that the adaptable cooling coil is able to provide small but relevant improved humidity control down to 25% of the design load. This was obtained without affecting energy performance in typical variable air volume design and control. For specific applications, where variable air volume systems mainly control space humidity, there are also energy savings. The adaptable cooling coil could be seen as providing additional flexibility in the operation of HVAC systems, particularly in the tropics.

We evaluated diurnal trends of size-resolved indoor and outdoor fluorescent biological airborne particles (FBAPs) and their contributions to particulate matter (PM) within 0.5-20 μm. After a ten-week continuous sampling via two identical wideband integrated bioaerosol sensors, we found that both indoor and outdoor diurnal trends of PM were driven by its bioaerosol component. Outdoors, the median [interquartile range] FBAP mass concentration peaked at 8.2 [5.8-9.9] μg/m³ around sunrise and showed a downtrend from 6:00 to 18:00 during the daytime and an uptrend during the night. The nighttime FBAP level was 1.8 [1.4-2.2] times higher than that during the daytime, and FBAPs accounted for 45 % and 56 % of PM during daytime and nighttime, respectively. Indoors, the rise in concentrations of FBAPs smaller than 1 μm coincided with the starting operation of the heating, ventilation, and air conditioning (HVAC) system at 6:00, and the concentration peaked at 8:00 and dropped to the daily average by noontime. This indicated that the starting operation of the HVAC system dislodged the overnight settled and accumulated fine bioaerosols into the indoor environment. For particles larger than 1 μm, the variation of mass concentration was driven by occupancy. Based on regression modeling, the contributions of indoor PM, non-FBAP, and FBAP sources to indoor mass concentrations were estimated to be 93 %, 67 %, and 97 % during the occupied period.

In warm environments, isothermal cooling by deliberately enhanced air movement can maintain thermal comfort using less energy than compressor-based air conditioning. To evaluate the performance of a brushless direct current (DC) stand fan, the cooling fan efficiency (CFE) index was measured in a climatic chamber under four dry-bulb temperatures (24, 26, 28, and 30 °C), six speed settings (corresponding to centreline speeds in the range 0.6-2.5 m/s at 1 m distance), two fan-manikin distances (1 and 2 m) and two orientations (front, side). The CFE index is defined as the ratio of the whole-body cooling effect generated by non-uniform airflow from the fan to its power consumption (°C/W). The CFE index overcomes the limitations of assessing the cooling effect based just on a few air speed measurements. The results show that the CFE index is influenced by dry-bulb temperature, fan speed setting, and fan-manikin distance, but not by fan-manikin orientation. The lower the temperature and the closer the fan, the higher is the CFE index. Increasing fan speed setting simultaneously enhances whole-body cooling and increases power use. Consequently, the CFE has a non-monotonic relationship with fan speed setting and the peak value is reached for an intermediate speed. As compared with previous testing results using an alternating current stand fan, the CFE index of the DC fan we tested is three times higher. As a complement to air-conditioning, the tested stand fan is a suitable energy-efficient technology for providing thermal comfort in warm environments.

In warm environments, isothermal cooling by deliberately enhanced air movement can maintain thermal comfort using less energy than compressor-based air conditioning. To evaluate the performance of a brushless direct current (DC) stand fan, the cooling fan efficiency (CFE) index was measured in a climatic chamber under four dry-bulb temperatures (24, 26, 28, and 30 °C), six speed In warm environments, isothermal cooling by deliberately enhanced air movement can maintain thermal comfort using less energy than compressor-based air conditioning. To evaluate the performance of a brushless direct current (DC) stand fan, the cooling fan efficiency (CFE) index was measured in a climatic chamber under four dry-bulb temperatures (24, 26, 28, and 30 °C), six speed settings (corresponding to centreline speeds in the range 0.6-2.5 m/s at 1 m distance), two fan-manikin distances (1 and 2 m) and two orientations (front, side). The CFE index is defined as the ratio of the whole-body cooling effect generated by non-uniform airflow from the fan to its power consumption (°C/W). The CFE index overcomes the limitations of assessing the cooling effect based just on a few air speed measurements. The results show that the CFE index is influenced by dry-bulb temperature, fan speed setting, and fan-manikin distance, but not by fan-manikin orientation. The lower the temperature and the closer the fan, the higher is the CFE index. Increasing fan speed setting simultaneously enhances whole-body cooling and increases power use. Consequently, the CFE has a non-monotonic relationship with fan speed setting and the peak value is reached for an intermediate speed. As compared with previous testing results using an alternating current stand fan, the CFE index of the DC fan we tested is three times higher. As a complement to air-conditioning, the tested stand fan is a suitable energy-efficient technology for providing thermal comfort in warm environments.

In warm environments, isothermal cooling by deliberately enhanced air movement can maintain thermal comfort using less energy than compressor-based air conditioning. To evaluate the performance of a brushless direct current (DC) stand fan, the cooling fan efficiency (CFE) index was measured in a climatic chamber under four dry-bulb temperatures (24, 26, 28, and 30 °C), six speed settings (corresponding to centreline speeds in the range 0.6-2.5 m/s at 1 m distance), two fan-manikin distances (1 and 2 m) and two orientations (front, side). The CFE index is defined as the ratio of the whole-body cooling effect generated by non-uniform airflow from the fan to its power consumption (°C/W). The CFE index overcomes the limitations of assessing the cooling effect based just on a few air speed measurements. The results show that the CFE index is influenced by dry-bulb temperature, fan speed setting, and fan-manikin distance, but not by fan-manikin orientation. The lower the temperature and the closer the fan, the higher is the CFE index. Increasing fan speed setting simultaneously enhances whole-body cooling and increases power use. Consequently, the CFE has a non-monotonic relationship with fan speed setting and the peak value is reached for an intermediate speed. As compared with previous testing results using an alternating current stand fan, the CFE index of the DC fan we tested is three times higher. As a complement to air-conditioning, the tested stand fan is a suitable energy-efficient technology for providing thermal comfort in warm environments.