Explaining resilience model of historical bazaars using artificial neural network

Abstract

Purpose

Historical bazaars, a huge treasure of Iranian culture, art and economy, are places for social capital development. Un-supervised management in past decades has led to the demolition and change of historical bazaars and negligence of its different aspects. The present research aims to investigate the resilience of historical bazaars preserving their identity and different developments.

Design/methodology/approach

The artificial neural network (ANN) has been applied to investigate the resilience of historical bazaars. This model consists of three main networks for evaluating the resilience of historical networks in terms of adaptability, variability and reactivity.

Findings

The ANN proposed to evaluate the resilience of historic bazaars based on the mentioned factors is efficient. By calculating mean squared error (MSE), the model accuracy for evaluating adaptability, variability and reactivity were obtained at 7.62e-25, 2.91e-24 and 1.51e-24. The correlation coefficient was obtained at a significance level of 99%. This indicates the considerable effectiveness of the artificial intelligence model in modeling and predicting the qualitative properties of historical bazaars resilience.

Originality/value

This paper clarifies indexes and components of resilience in terms of adaptability, variability and reactivity. Then, the ANN model is obtained with the least error and very high accuracy that predict the resilience of historical bazaars.

Citation

Heydari Torkamani, M., Shahbazi, Y. and Belali Oskoyi, A. (2023), "Explaining resilience model of historical bazaars using artificial neural network", Smart and Sustainable Built Environment, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/SASBE-06-2022-0123