采用Logistic混沌反向学习策略种群初始化，而改善蝗虫算法初始种群

Logistic chaotic reverse learning strategies employed population initialization, while improving the uniformity of hair and locust diversity algorithm initial population distribution of two phases, the first using the formula (. 7) Logistic chaotic mapping population initialization sequence. Logistic mapping is used sensitive to initial characteristics, the initial value given to the small differences in the micro-I of formula (7), i.e. to give chaotic variable y I

The population initialization is adopted by Logistic chaos reverse learning strategy, and the uniformity and diversity of the initial population distribution of locust algorithm are improved in two stages, and the first stage uses the Logistic map (7) to produce chaotic sequence for population initialization. Using the characteristics of Logistic mapping sensitivity to initial values, the initial value of the equation (7) is given to the small difference, i.e. i.e. I chaotic variable y

In the first stage, the chaos sequence generated by equation (7) is used to initialize the population. Using the sensitivity of logistic map to the initial value, we give a small difference initial value to equation (7), i.e., I chaotic variable y<br>