Title :
Neural network estimation of LAL/VPC resions of silkmoth using Genetic Algorithm
Author :
Chiba, Ryosuke ; Hashimoto, Sunao ; Kazawa, Tomoki ; Kanzaki, Ryohei ; Ota, Jun
Author_Institution :
Fac. of Syst. Design, Tokyo Metropolitan Univ., Hino, Japan
Abstract :
When a male silk moth senses sexual pheromone of a female partner by using its antenna, it repeats certain series of walking pattern and arrives to the partner. This walking pattern is generated in Lateral Accessory Lobe (LAL) and the ventral protocerebrum (VPC) domain which controls physical exercise. Therefore, in this study, we elucidate the process of this behavior by constructing a neural network model of the LAL domain. Concretely, we build a model that treats some numbers of neurons as one neuron and estimate strength of each connection between 10 neuron representatives of neuron groups with Genetic Algorithm. The estimated network is verified and consided from engineering and biology.
Keywords :
biology; brain; gait analysis; genetic algorithms; neural nets; LAL-VPC resion; genetic algorithm; lateral accessory lobe; neural network estimation; physical exercise control; sexual pheromone sensing; silkmoth; ventral protocerebrum domain; walking pattern;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-6674-0
DOI :
10.1109/IROS.2010.5652262