Maintaining a comfortable temperature in large buildings can often be a challenge, as heating, ventilation, and air conditioning (HVAC) systems struggle to balance the needs of occupants and energy efficiency. However, researchers from Carnegie Mellon University have proposed a novel method that utilizes machine learning (ML) models to predict and address biases in human responses to temperature, ultimately improving the accuracy of thermal comfort predictions.
In a study featured in Building and Environment, the researchers developed a technique known as Multidimensional Association Rule Mining (M-ARM). The M-ARM method utilizes data and models to identify and correct biases in human perceptions of temperature. By analyzing conflicting responses from building occupants regarding their thermal comfort, the researchers were able to determine the real comfort zone for the majority of individuals in the building.
The study evaluated seven ML models and found that the incorporation of the M-ARM method significantly enhanced the accuracy of thermal comfort predictions. This breakthrough research addresses the limitations of current methods and highlights the potential instances of subjective data biases. By accounting for factors such as humidity, temperature, and clothing, the researchers aim to provide a more comprehensive understanding of occupants’ thermal preferences.
Lead researcher, Pingbo Tang, emphasizes the importance of addressing defective data sets that contribute to excess energy consumption in large buildings. Tang states, “This work is about using the question-answering behavior of the person when they are facing a few related thermal comfort questions to adjust self-conflicts and estimate reality.” By considering various impact factors, such as dataset size, classifier types, and calibration methods, the researchers were able to improve the reliability of thermal perception predictions and reduce errors in the current model.
The findings of this study have significant implications for the advancement of ML-based strategies in building temperature regulation. By improving the accuracy of thermal comfort predictions, this research aims to create better strategies for controlling temperature in buildings. The ultimate goal is to enhance occupant comfort while simultaneously reducing energy consumption.
This innovative approach to temperature regulation in large buildings has the potential to revolutionize the HVAC industry. By leveraging ML models and incorporating the M-ARM method, building managers can optimize energy efficiency and ensure occupants’ comfort. This research not only addresses the complexities of the physical environment and subjective perceptions but also emphasizes the importance of data accuracy in achieving energy-saving solutions.
As the development of ML-based strategies continues, we can expect to see significant progress in the field of building temperature regulation. By harnessing the power of machine learning and data analysis, buildings can become more energy-efficient and occupants can enjoy a comfortable environment. The combination of technological advancements and research efforts, such as the M-ARM method proposed by the Carnegie Mellon University team, holds great promise for a sustainable and comfortable future.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
Money Singh is a seasoned content writer with over four years of experience in the market research sector. Her expertise spans various industries, including food and beverages, biotechnology, chemical and materials, defense and aerospace, consumer goods, etc.