Assessing the perception of overall indoor environmental quality: Model validation and interpretation

Associations of Indoor Environmental Quality Parameters with Students’ Perceptions in Undergraduate Dormitories: A Field Study in Beijing during a Transition Season

“…The results were consistent with the call of Wei et al [ 18 ] to prioritize the IAQ for the proper characterization of the IEQ in buildings, followed by thermal, lighting and acoustic conditions. Moreover, Tang et al [ 19 ] compared different models to evaluate the overall IEQ satisfaction. They found that unsatisfactory factors often had a dominant negative impact on occupants’ perceptions, which cannot be counteracted by higher satisfaction with other factors.…”

Comparison of edge computing methods in Internet of Things architectures for efficient estimation of indoor environmental parameters with Machine Learning

“…The World Health Organization (WHO) has made frequent efforts to improve and refine air quality standards from the definition of air quality guidelines on pollutants in 2005 (WHO, 2006). Lack of model comparison is a major obstacle to assessing the accuracy and robustness of existing models (Tang et al, 2022), as some approaches that are widely used in predicting IEQ and building energy assumption, such as Machine Learning (ML) due to the ability to identify and learn underlying patterns in massive data with almost no human intervention (Tian et al, 2021). However, they could have validation gaps on separate data not used in the model development to ensure that the model does not overfit and then fail to fit the new data (Wei et al, 2019).…”

“…At present, the use of ML has spread in the field of energy efficiency and indoor environment analysis in buildings (Copiaco et al, 2023), and although there are numerous algorithms to carry out the learning process, the most widely used are the ANNs of type Multilayer Perceptron (MLP) for their ability to model nonlinear functions between inputs and outputs with accuracy, fault tolerance, and flexibility, due to its extensive interconnectivity (Martínez-Comesaña et al, 2021). Other ML algorithms are also used in the context of indoors, such as Random Forest (RF) that is based on individual regression trees not pruned (Tang et al, 2022;Yu et al, 2021), Support Vector Machine (SVM) which attempts to minimise an upper limit on the generalisation error rather than minimising the prediction error (Leong et al, 2020;Zhong et al, 2019), and decision trees based on Gradient Boost (GBDT) (Almalawi et al, 2022;Moursi et al, 2021).…”

“…Some AI approaches can assist edge-IoT computing to reduce network latencies or congestion (Veeramanikandan et al, 2020) and therefore improve energy efficiency, where the software programming platform can also play a very relevant role. Although there is a great variety in programming languages and software toolkits, it is worth mentioning some of the most used to implement ML models on processing devices, such as Python and R languages with many open-source libraries (Kadiyala and Kumar, 2017;Tang et al, 2022), toolkits such as Mathworks Statistics and Machine Learning toolbox and Deep Learning toolbox for Matlab (Cho and Moon, 2022), and software environments such as Mathworks ThingSpeak (Scislo and Szczepanik-Scislo, 2021).…”

Indoor Thermal and Ventilation Indicator on University Students’ Overall Comfort

“…However, though most studies investigated all IEQ aspects, they just discussed the relationship between overall comfort and individual aspect and didn't elaborate on their interferences among different IEQ aspects [9,21,22]. Moreover, it has been found that most relevant studies considering the interactions among various IEQ aspects select only offices as research targets [23][24][25][26]. Few studies have been conducted on university classrooms with unique traits compared to other rooms [27].…”