Quality of Solution

The quality of a GA string is calculated using a fitness function (also known as an objective function), which yields a quantitative measure, known as the fitness of the string. The fitness function must reward the better strings with higher fitness than their poorer competitors, but the exact function that is 

Using Artificial Intelligence in Chemistry and Biology A Practical Guide 

The surface defined by an arbitrary fitness function, across which the genetic algorithm (GA) searches for a maximum or minimum. The surface may be complex and contain numerous minima and maxima. 

The algorithm works to find the solution of maximum fitness, so the fitness of each solution must be related in some way to the interaction energy this latter term is readily calculated. The energy between point charges q1 and q2, a distance r apart, is 

Distances used in the calculation of the interaction energy of two dipoles. 

---

Verification techniques which verify and evaluate the quality of solutions in relation to the specification q. 

In view of the importance of choosing appropriate values for EA variables, it is common for these to be selected through a combination of past experience with similar problems and some testing of the dependence of the quality of solution reached with different population sizes, mutation rates and so on. Since the population size in different methods varies considerably (in a GA it is typically in the range 30-100, while genetic programming (GP) populations may... 

The general properties of these components are discussed in short in the following sections. It is also shown how they determine the quality of solutions of analytical problems. 

Each element a i, y] measures the quality of solution i relative to solution j in terms of the n objective functions. An element o i, y] close to 0 indicates that solution j outranks solution i. If the value is... 

Section 4 describes the recent advancements in terms of schema mapping rewriting techniques that were introduced to improve the quality of solutions ... 

Heuristic Rule of thumb employed in an algorithm to improve its performance (time and space requirements or quality of solution produced). This rule may be very effective in certain instances and ineffective in others. 

Performance of two different algorithms namely simulated annealing and tabu search for solving MDVRP with inventory transfer between depots in a three-echelon supply chain was studied by Fard and Setak (2011). Three-echelon supply chain composed of a single plant, multiple distribution centers and a set of retailers with deterministic demands. The results depicted that the tabu search approach outperformed the simulated annealing approach in terms of quality of solution. 

Thus, the maintained temperature of ultrafiltration was in the range of 60 °C. Temperature above 60 °C may be unsuitable for the quality of solutions, that is the reason why during our practical work we use temperature range of 4-60 °C. 

For instance, in Tewolde and Weihua (2008), two solutions are proposed for path planning the first is based on GA and the second is based on ACO. A comparison study of the techniques was performed in a real-world deployment of multiple robotic manipulators using specific spraying tools in an industrial environment. Results of this study show that both solutions provide very comparable results for small problem sizes, but when the size and the complexity of the problem increase, the ACO-based algorithm achieves a better quality of solution, but with a higher execution time, as compared to the GA-based algorithm. 

The GA Phase it consists in appl dng a modified crossover operator on the set of optimal paths generated by the ACO algorithm after N iterations in order to improve the quality of solution found by the ants. The key idea of our proposed erossover operator consists in selecting two common nodes M and N1 from two parent paths PI and P2 and comparing the three sub-parts of PI and P2 existing (7) before Al, (2) between the two selected nodes A1 and 7V2, and (i) after the second node N2. The best parts are selected to form the new path. 

The good performance of the ACO-GA algorithm in terms of quality of solution is due to the marriage ofthese two approaches. Indeed, the GA algorithm is a kind of post optimization or local search that improves the quality of solution found by the ACO algorithm, which can easily sink into a local optimum if the size of the problem is large. 

---