التفاصيل البيبلوغرافية
| العنوان: |
A development in the approach of assessing the sensitivity of road networks to environmental hazards using functional machine learning algorithm and fractal methods. |
| المؤلفون: |
Nayyeri, Hadi1 (AUTHOR) H.nayeri@uok.ac.ir, Xu, Lei2 (AUTHOR), Ahmadi Dehrashid, Atefeh3,4 (AUTHOR), Mohammadi Khanghah, Payam1 (AUTHOR) |
| المصدر: |
Environment, Development & Sustainability. Nov2024, Vol. 26 Issue 11, p28033-28061. 29p. |
| مصطلحات موضوعية: |
*ARTIFICIAL neural networks, *CRISIS management, K-nearest neighbor classification, FRACTAL dimensions, COMPARATIVE method, CLASSIFICATION algorithms |
| مصطلحات جغرافية: |
IRAN |
| مستخلص: |
Natural hazards are considered one of the greatest challenges today. Preventing transformation processes that lead to risk and then, crisis need a structural-strategic approach. An approach that can identify the issues and challenges ahead in a systematic and comprehensive method by formulating an operational plan can provide resilience and reduce vulnerability of human settlements and urban infrastructures. The road networks as one of the most important urban elements having a crucial role in management of crisis during the occurrence of natural crises (such as earthquakes) aid in the transferring the injured and rescue forces. The main purpose of this study was to determine the vulnerability of urban road networks for earthquake risk with neural network and machines learning algorithms with a comparative and systematic approach. In order to identify the most accurate and efficient model, a comparative comparison between neural network model (ANN) and machine learning algorithms including ADTree and KNN was carried out. The results of the present study in evaluating the structural condition of the urban road network with Fractal Dimension on hazardous and vulnerable zones showed that these zones were of low fractal dimension, and the distribution and differentiation of roads were low, reducing the efficiency of the road network at times of crisis. Other results of the present research on the application of machine learning algorithms indicate that the accuracy of the ADTree algorithm was equal to 1. In addition, at the stage of measuring the efficiency of the model with the Classification metrics algorithm, the ADTree algorithm efficiency was equal to 1. However, the accuracy of the KNN algorithm (K-Nearest Neighbors) and the artificial neural network model in predicting the vulnerability of the internal road network was equal to 0.92% and 0.98%, respectively. Therefore, since the degree of accuracy of the ADTree algorithm was higher, it is the most accurate and efficient algorithm to predict the vulnerability of the road network at times of the occurrence of hazardous events, and it can be useful and effective in decision-making of policy makers and planners in pre-crisis management. [ABSTRACT FROM AUTHOR] |
|
Copyright of Environment, Development & Sustainability is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Business Source Index |