Instinct-Based Mating in Genetic Algorithms Applied to the Tuning of 1-NN Classifiers

Abstract

The behavior of the genetic algorithm (GA), a popular approach to search and optimization problems, is known to depend, among other factors, on the fitness function formula, the recombination operator, and the mutation operator. What has received less attention is the impact of the mating strategy that selects the chromosomes to be paired for recombination. Existing GA implementations mostly choose them probabilistically, according to their fitness function values, but we show that more sophisticated mating strategies can not only accelerate the search, but perhaps even improve the quality of the GA-generated solution. In our implementation, we took inspiration from the "opposites-attract" principle that is so common in nature. As a testbed, we chose the problem of 1-NN classifier tuning where genetic solutions have been employed before, and are thus well-understood by the research community. We propose three "instinct-based" mating strategies and experimentally investigate their behaviors.

Camera identification for very low bit rate time varying quantization noise videos

“…It can be seen that the overall correct identification rate of our proposed method is 100%. On the other hand, the overall correct identification rates of the conventional correlation method [8] and the conventional 1-nearest neighbor rule approach [9] are only 30% and 40%, respectively, which are unacceptably low for practical uses.…”

“…The first 180 frames of each video are used for the camera identification. Table 1, Table 2 and Table 3 show the identification results based on our proposed method, the conventional correlation method [8] and the conventional 1-nearest neighbor rule approach [9], respectively. It can be seen that the overall correct identification rate of our proposed method is 100%.…”

“…Another common method is to assign the unknown camera to the one with the nearest neighbor of the PRNU [9]. However, if mobile devices are employed to capture the videos, then these videos are compressed at very low bit rates [10].…”

“…Hence, the camera identification results based on different frames of the videos are different. Since it is assumed in existing camera identification algorithms [8], [9] that the videos are not compressed and the overall noise pattern statistics are stationary, very poor identification performances will be resulted if existing algorithms [8], [9] are applied to the camera identification based on very low bit rate videos with time varying quantization noises.…”

A clustering based mate selection for evolutionary optimization

“…In EAs, a proper mate selection can also control the population convergence and diversity efficiently [6,12,13]. In the last decades some mating strategies have been proposed [16], including random mating, roulette wheel selection, truncate selection, tournament selection, gender based selection [7,15,19], niche based selection [2], dissociative selection [3,4], and some other methods [5,14,18]. Although these mating strategies have been proposed, it has not attracted much attention in the community of evolutionary computation [16].…”