Solving the Traveling Salesman Problem Using New Operators in Genetic Algorithms

Abstract

Problem statement: Genetic Algorithms (GAs) have been used as search algorithms to find near-optimal solutions for many NP problems. GAs require effective chromosome representations as well as carefully designed crossover and mutation operators to achieve an efficient search. The Traveling Salesman Problem (TSP), as an NP search problem, involves finding the shortest Hamiltonian Path or Cycle in a graph of N cities. The main objective of this study was to propose a new representation method of chromosomes using upper triangle binary matrices and a new crossover operator to be used as a heuristic method to find near-optimum solutions for the TSP. Approach: A proposed genetic algorithm, that employed these new methods of representation and crossover operator, had been implemented using DELPHI programming language on a personal computer. Also, for the purpose of comparisons, the genetic algorithm of Sneiw had been implemented using the same programming language on the same computer. Results: The outcomes obtained from running the proposed genetic algorithm on several TSP instances taken from the TSPLIB had showed that proposed methods found optimum solution of many TSP benchmark problems and near optimum of the others. Conclusion: Proposed chromosome representation minimized the memory space requirements and proposed genetic crossover operator improved the quality of the solutions in significantly less time in comparison with Sneiw's genetic algorithm.

Multi-Robot Task Scheduling with Ant Colony Optimization in Antarctic Environments

“…This has the advantage of being easy to implement and fast to calculate, but it does not guarantee minimum distance. The genetic algorithm (GA) [ 8 , 9 , 10 , 11 ], one of the heuristic algorithms, guarantees distance and time according to the setting of the user parameter. If the user parameter is properly set, the distance can be calculated with a reasonable calculation time.…”

Educational data modelling using curve fitting and average uniform algorithm

“…Metaheuristic algorithms are typically efficient in calculating near-optimum solutions of problems that cannot be solved easily or at all using other techniques, which constitute the great majority of problems (YoLee and Geem, 2005). Some of the metaheuristic algorithms are inspired by natural process, such as the Genetic Algorithm (GA) (Al Rahedi and Atoum, 2009;Freisleben and Merz, 2016), the Ant Colony Optimisation (ACO) (Dorigo et al, 1996), the Honey-Bee Mating Optimisation (HBMO) (Bozorg-Haddad et al, 2017), and so on. In contrast, there are other types of algorithms such as Tabu Search (TS) which don't originate in natural processes.…”

Object Recognition Based on Image Segmentation and Clustering

“…Its basic notion is to integrate all the priors in to unified framework. In this works the segmentation task only needs the probability of Super Pixels, because the Object Parts cannot be waived, as it carries shape Priors (Al Rahedi and Atoum, 2009;AL-Salami, 2010;Harishchander et al, 2010;Maalla et al, 2009).…”