Data-driven approach to develop prediction model for outdoor thermal comfort using optimized tree-type algorithms

Jeong, Jaemin; Jeong, Jaewook; Lee, Minsu; Lee, Jaehyun; Chang, Soo Chul

doi:10.1016/j.buildenv.2022.109663

Cited by 12 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PMV and PPD [50], which are drawn using binary votes of large mixed-gender groups of individuals, are useful in designing ventilation, air conditioning, and other systems in buildings and homes as well as in establishing construction standards for large scale use; however, they are not meant to measure a specific individuals' perceptions of comfort. Proper quantification of the actual comfort sensation felt by either individual occupants or families living in home units requires individual real-time monitoring of the occupants' instantaneous physiological responses [54,55]. Because such invasive procedures are impractical for daily use, imitation learning more suitable for smart home automation than reinforcement learning [7].…”

Section: Discussionmentioning

confidence: 99%

Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home

Al-Ani

Das

2023

Energies

View full text Add to dashboard Cite

Automated indoor environmental control is a research topic that is beginning to receive much attention in smart home automation. All machine learning models proposed to date for this purpose have relied on reinforcement learning using simple metrics of comfort as reward signals. Unfortunately, such indicators do not take into account individual preferences and other elements of human perception. This research explores an alternative (albeit closely related) paradigm called imitation learning. In the proposed architecture, machine learning models are trained with tabular data pertaining to environmental control activities of the real occupants of a residential unit. This eliminates the need for metrics that explicitly quantify human perception of comfort. Moreover, this article introduces the recently proposed deep attentive tabular neural network (TabNet) into smart home research by incorporating TabNet-based components within its overall framework. TabNet has consistently outperformed all other popular machine learning models in a variety of other application domains, including gradient boosting, which was previously considered ideal for learning from tabular data. The results obtained herein strongly suggest that TabNet is the best choice for smart home applications. Simulations conducted using the proposed architecture demonstrate its effectiveness in reproducing the activity patterns of the home unit’s actual occupants.

show abstract

Section: Discussionmentioning

confidence: 99%

Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home

Al-Ani

Das

2023

Energies

View full text Add to dashboard Cite

show abstract

“…Other studies used a hybrid method, i.e., combining machine learning techniques such as Ada Boost, Bayesian bridge, and random forest to improve PET results. It was found that the hybrid model increased the prediction accuracy to 95% [21]. Simulation methods were employed as an alternative to the traditional method for evaluating outdoor thermal comfort, outdoor space usage, and to test the influence of any demographic and social factors using fuzzy logic [91], a multi-agent system [18], or ENVI-met [71,76,85,89,92].…”

Section: Methodology For Estimation Of Otcismentioning

confidence: 99%

“…Machine learning techniques like ANN, GA, and ELM were employed for the improved predictive accuracy of PET [20]. Jeong et al (2022) applied Bayesian hyperparameter tuning to machine learning models and found that random forest could increase prediction accuracy to 90-95% [21].…”

Section: Predictive Ability Of Otcismentioning

confidence: 99%

“…Studies also noted that UTCI often predicted a neutral thermal range better than PET or PMV [74]. To overcome this shortcoming, a few researchers also evaluated neutral thermal range from modified PET or PMV by logistic or probit analysis [62] or machine learning techniques like ANN [20,21]. It was found that the thermal neutral range was also a function of seasonal variation [45,70] and the existing climatic zone [81].…”

Section: Thermal Neutral Stress Rangementioning

confidence: 99%

“…Other studies employing non-traditional approaches include multi-sensory design with walkability and outdoor thermal comfort [19], estimating real-time OTCI and Physiological Equivalent Temperature (PET) using IoT devices, and applying digital twins and Geographic Information Systems (GIS) to predict OTCI [12]. Overall, the studies that use an OTCI still need to be more accurate, while most studies that use Machine learning (ML) or Internet of Things (IoT) mostly try only to improve the existing OTCI [20,21] thereby making the two approaches fragmented. This incongruence forms the rationale behind this review paper that aims to assess factors, besides meteorological, in influencing the prediction accuracy of OTCIs so that both traditional paradigms and Industry 4.0 [22] can be combined to create a notable and reliable region-specific OTCI using 'Knowledge Translation'.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Review on Gaps and Challenges in Prediction Outdoor Thermal Comfort Indices: Leveraging Industry 4.0 and ‘Knowledge Translation’

Elnabawi,

Hamza

2024

Buildings

View full text Add to dashboard Cite

The current outdoor thermal comfort index assessment is either based on thermal sensation votes collected through field surveys/questionnaires or using equations fundamentally backed by thermodynamics, such as the widely used UTCI and PET indices. The predictive ability of all methods suffers from discrepancies as multi-sensory attributes, cultural, emotional, and psychological cognition factors are ignored. These factors are proven to influence the thermal sensation and duration people spend outdoors, and are equally prominent factors as air temperature, solar radiation, and relative humidity. The studies that adopted machine learning models, such as Artificial Neural Networks (ANNs), concentrated on improving the predictive capability of PET, thereby making the field of Artificial Intelligence (AI) domain underexplored. Furthermore, universally adopted outdoor thermal comfort indices under-predict a neutral thermal range, for a reason that is linked to the fact that all indices were validated on European/American subjects living in temperate, cold regions. The review highlighted gaps and challenges in outdoor thermal comfort prediction accuracy by comparing traditional methods and Industry 4.0. Additionally, a further recommendation to improve prediction accuracy by exploiting Industry 4.0 (machine learning, artificial reality, brain–computer interface, geo-spatial digital twin) is examined through Knowledge Translation.

show abstract

Assessment and prediction of pedestrian thermal comfort through machine learning modelling in tropical urban climate of Nagpur City

Mohite,

Surawar

2024

Theor Appl Climatol

View full text Add to dashboard Cite

Data-driven approach to develop prediction model for outdoor thermal comfort using optimized tree-type algorithms

Cited by 12 publications

References 33 publications

Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home

Imitation Learning with Deep Attentive Tabular Neural Networks for Environmental Prediction and Control in Smart Home

Review on Gaps and Challenges in Prediction Outdoor Thermal Comfort Indices: Leveraging Industry 4.0 and ‘Knowledge Translation’

Assessment and prediction of pedestrian thermal comfort through machine learning modelling in tropical urban climate of Nagpur City

Contact Info

Product

Resources

About