Improved Performance of a Cooperative Genetic Algorithm When Solutions Were Presented as Cartoon Faces
- 1.5k Downloads
Genetic algorithms are often able to identify solutions within a multidimensional problem space that elude human detection. Humans sometimes have difficulty retrospectively identifying the features or feature combinations that lead to the success of an individual solution. However, humans are adept at identifying configural patterns within faces. We hypothesized that mapping the features of a problem space onto a cartoon face space would help humans visualize patterns and contribute to the operation of a genetic algorithm.
In this study, human participants viewed foragers in a virtual environment. The genetic code of each forager was presented either as a list of features or as a cartoon face. Participants selected either one or both parents for mating at each generation. Foraging improved significantly when forager attributes were presented as a face, compared to trials in which attributes were presented as a list. This improvement was found for both human-directed and cooperative genetic algorithms.
Keywordsevolutionary human-computer interaction perception decisionmaking
Unable to display preview. Download preview PDF.
- 1.Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)Google Scholar
- 6.Noda, E., Freitas, A.A., Lopes, H.S.: Discovering interesting prediction rules with a genetic algorithm. In: Proceedings of the 1998 Congress on Evolutionary Computation, vol. 2 (1999)Google Scholar
- 8.Domas, C.: The 1s and 0s behind cyber warfare (2013), http://www.ted.com/talks/chris_domas_the_1s_and_0s_behind_cyber_warfare
- 10.Qian, Z.Q., Teng, H.F., Xiong, D.L., Sun, Z.G.: Human-computer cooperation genetic algorithm and its application to layout design. In: Proceeding of the 4th Asia-Pacific Conference on Simulated Evolution and Learning, Singapore, pp. 299–302 (2002)Google Scholar
- 11.Kosorukoff, A.: Human based genetic algorithm. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 5, pp. 3464–3469 (2001)Google Scholar
- 12.Takagi, H.: Interactive evolutionary computation: system optimization based on human subjective evaluation. In: IEEE International Conference on Intelligent Engineering Systems (INES 1998), pp. 17–19 (1998)Google Scholar
- 13.Boschetti, F., Takagi, H.: Visualization of EC landscape to accelerate EC conversion and evaluation of its effect. In: Proceedings of the 2001 Congress on Evolutionary Computation, vol. 2, pp. 880–886 (2001)Google Scholar
- 15.Bao, J., Sakamoto, G., Nickerson, J.V.: Evaluating design solutions using crowds. In: Proceedings of the Seventeenth Americas Conference on Information Systems, Detroit, Michigan (2011)Google Scholar
- 16.Guo, Y.-.N., Cheng, J.: Adaptive evaluation strategy based on surrogate models. In: Maurtua, I. (ed.) Human Computer Interaction, pp. 259–277. InTech (2007)Google Scholar
- 17.Caldwell, C., Johnston, V.S.: Tracking a criminal suspect through face space with a genetic algorithm. In: Proceedings of the Fourth International Conference on Genetic Algorithm, pp. 416–421 (1991)Google Scholar
- 18.Secretan, J., Beato, N., D’Ambrosio, D.B., Rodriguez, A., Campbell, A., Stanley, K.O.: Picbreeder: evolving pictures collaboratively online. In: Proceedings of the Computer Human Interaction Conference, pp. 1759–1768 (2008)Google Scholar
- 19.Stump, C.: Project PANOPTES: crowdsourcing the search for exoplanets. In: American Astronomical Society Meeting Abstracts 22,Google Scholar
- 22.Barry, S.: Fixing my Gaze, p. 272. Basic Books (2009)Google Scholar