Tue, Aug 5, 2025
[Archive]
Director Research, Karnavati University, Gandhinagar-382422, Gujarat, India
Abstract: (37 Views)
We utilized the most applicable artificial intelligence systems for the challenge of cooling load (CL) in housing units. We fine-tuned them in 2 stages using an innovative evolutionary algorithm called Biogeography-Based Optimization (BBO). The abovementioned procedure is then applied to establish a connection between the system's input and output characteristics. The vital output of the system was the measure of CL. In contrast, the input attributes included surface area, relative compactness, roof area, wall area, glazing area distribution, overall height, and orientation. Two well-known statistical indices, the correlation coefficient ( 
) and root mean squared error (RMSE) were used to assess the BBO approach’s expected outcome for data sets. According to the findings of the BBO network's initial stage, the 
and RMSE, the testing data set, and suggested BBO-MLP forecasting network models acquired amounts of 0.96007 and 0.06946, respectively. In the second stage, data for ten distinct alpha values are achieved. These data suggest that an alpha of 1.1 provides excellent efficiency. In addition, the amounts of
) and root mean squared error (RMSE) were used to assess the BBO approach’s expected outcome for data sets. According to the findings of the BBO network's initial stage, the and RMSE amounts for the training and testing data sets were 0.965281 and 0.06773, respectively. Per the and RMSE, the testing data set, and suggested BBO-MLP forecasting network models acquired amounts of 0.96007 and 0.06946, respectively. In the second stage, data for ten distinct alpha values are achieved. These data suggest that an alpha of 1.1 provides excellent efficiency. In addition, the amounts of and RMSE for the testing data set is (0.95113 and 0.07667) and (0.95574 and 0.07628) for the training data set, respectively.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
