Back to Search
Start Over
Hybrid Computational Intelligence Algorithm for Autonomous Handling of COVID-19 Pandemic Emergency in Smart Cities.
- Source :
- Sustainable Cities & Society; Jan2022, Vol. 76, pN.PAG-N.PAG, 1p
- Publication Year :
- 2022
-
Abstract
- • A hybridization between Moth-Flame Optimization and Marine Predators Algorithms (MOMPA) is proposed • The proposed MOMPA is employed for solving the robot path planning problem with obstacle avoidance constraints. • After the validation experiment, MOMPA is applied for a case study on New Galala city in Egypt. New cities exploit the smartness of the IoT-based architecture to run their vital and organizational processes. The smart response of pandemic emergency response services needs optimizing methodologies of caring and limit infection without direct connection with patients. In this paper, a hybrid Computational Intelligence (CI) algorithm called Moth-Flame Optimization and Marine Predators Algorithms (MOMPA) is proposed for planning the COVID-19 pandemic medical robot's path without collisions. MOMPA is validated on several benchmarks and compared with many CI algorithms. The results of the Friedman Ranked Mean test indicate the proposed algorithm can find the shortest collision-free path in almost all test cases. In addition, the proposed algorithm reaches an almost %100 success ratio for solving all test cases without constraint violation of the regarded problem. After the validation experiment, the proposed algorithm is applied to smart medical emergency handling in Egypt's New Galala mountainous city. Both experimental and statistical results ensure the prosperity of the proposed algorithm. Also, it ensures that MOMPA can efficiently find the shortest path to the emergency location without any collisions. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 22106707
- Volume :
- 76
- Database :
- Supplemental Index
- Journal :
- Sustainable Cities & Society
- Publication Type :
- Academic Journal
- Accession number :
- 153961778
- Full Text :
- https://doi.org/10.1016/j.scs.2021.103430