Using a Fuzzy Genetic Algorithm for Solving Transportation Logistics Problems

Transportation Logistics BI AI FGA Fuzzy Genetic Algorithm Triangular fuzzy logic Genetic Algorithm Fuzzy logic

Authors

  • Osama Emam Faculty of Computers and Artificial Intelligence, Information Systems Department, Helwan University, Cairo, Egypt
  • Riham Mohamed Younis Haggag Faculty of Commerce and Business Administration, Business Information Systems Department, Helwan University, Cairo, Egypt
  • Nanees Nabil
    nanis_nabil@yahoo.com
    Faculty of Commerce and Business Administration, Business Information Systems Department, Helwan University, Cairo, Egypt
November 10, 2022

Downloads

Recently, Science defined transportation as the most potent component of logistics. In addition, it has an interdependent relationship with business logistics. Also, AI is intervened in transportation logistics to solve transportation issues. Also, it is used for optimizing and obtaining possible solutions for critical and complex problems. This paper aims to optimize costs and profit to get satisfaction for individuals and organizations using AI techniques. A proposed methodology consisted of two phases. The first phase discusses data collection, and the second involves applying FGA Artificial Intelligence techniques. A proposed Transportation Logistics model was used to determine boundary profit for each Product, and a Fuzzy Genetic Algorithm FGA for transportation logistics was done to solve transportation issues. According to that, outcomes were detected by optimizing the transportation cost by detecting the parent's and the child's chromosomes, and it took the number of iterations =2000. Also, between 100 loops, the best of 5 loops took 1.53 Millie seconds per loop Using GA. Similarly, GA was used for optimizing the minimum total cost of the Product also by determining parents and child chromosomes, which took the Number of iterations= 2000, and among 100 loops, the best five loops took 1.40 ms per loop. Moreover, determining the profit boundary of each predicted Product using triangular fuzzy logic shows that the minimum profit is considered between (20 million and 23.9 million), while the moderate profit is (24 million), and the maximum profit is more than (24.1 million).