基于自适应遗传算法FIR数字滤波器优化设计

FIR数字滤波器优化设计的目标是对滤波器理想性能的逼近。遗传算法是一种模仿生物进化过程的全局优化概率搜索算法,它提出了一种求解复杂系统优化问题的通用框架,且不依赖于问题的领域和种类,在此将自适应的遗传算法应用于FIR数字滤波器的优化设计,通过评价种群的"早熟度"来自适应调整交叉率和变异率,提高了遗传算法的搜索效率。计算机仿真结果证明,该算法能够获得满意的滤波器性能。

自适应遗传算法在电器产品优化设计中的研究

传统的基于人工神经网络的电器产品优化方法,在对电器产品优化设计后花费的材料成本仍然较高,因此设计一种基于自适应遗传算法的电器产品优化方法。首先,依据电器产品设计基本性能需求,建立电器产品优化目标函数,包括电器产品材料成本和最小变电损耗;然后,引入一个新的函数作为种群是否早熟的判断依据,以降低计算时间,在此基础上对电器产品优化点编码;最后,利用自适应遗传算法实现电器产品优化设计。通过实验对比结果可知,此次设计的基于自适应遗传算法的电器产品优化方法比传统方法的电器产品设计成本低,证明了此次设计方法的有效性。

基于改进遗传算法的模糊神经网络控制器的设计

为了充分利用遗传算法的全局搜索能力和BP算法的局部搜索能力,提出了1种基于改进遗传算法的模糊神经网络控制器的设计,并通过对二阶系统模型的仿真,证明基于改进遗传算法的模糊神经网络控制器比常规的模糊神经网络控制器具有更好的控制性,具有更大的实用性。

Effects of Mulching Material on the Early Fruit Yield of Tomato （Lycopersicon esculentum Mill.） Varieties under Polyhouse Growing Condition

Tomato is one of the most widely produced and consumed vegetable crops in Ethiopia. It is not produced during the rainy season, mainly due to high disease pressure and low soil temperature. Therefore, an experiment was conducted to study the effect of different types of mulch （black and white plastic mulch as well as grass mulch） on early yield of tomato varieties （Miya ＆ Cochoro） under polyhouse growing condition at Bahir Dar during the rainy season in 2012. Treatments were arranged in 4 - 2 factorial combinations in randomized complete block design with three replications. One month old seedlings were transplanted on 8.4 m2 gross plots size （3 m x 2.8 m） at a spacing of 70 cm x 40 cm between rows and plants, respectively. Data recorded from plants found in the two middle rows of each plot. Di-ammonium phosphate （DAP） and Urea fertilizers were applied at the rate of 200 kg and 100 kg/ha, respectively. Sixteen plants were considered for data collection in each plot. White plastic mulch resulted in significantly （P 〈 0.05） earlier flowering, fruit setting and fruit maturity compared to other mulching materials. Varieties were also significantly different in days required to flowering, fruit setting and fruit maturity. Miya took significantly short period to flower, fruit set and fruit maturity compared to Cochoro variety. The effect of different mulch types on early fruit yield was found statistically significant. The highest early marketable fruit yield of 10.99 ton/ha and 10.54 ton/ha were recorded when Miya variety was grown with white and black plastic mulch, respectively. Therefore, use of white and black plastic mulches recommended for early tomato fruit yield.

Integrating Tabu Search in Particle Swarm Optimization for the Frequency Assignment Problem

In this paper, we address one of the issues in the frequency assignment problem for cellular mobile networks in which we intend to minimize the interference levels when assigning frequencies from a limited frequency spectrum. In order to satisfy the increasing demand in such cellular mobile networks, we use a hybrid approach consisting of a Particle Swarm Optimization(PSO) combined with a Tabu Search(TS) algorithm. This approach takes both advantages of PSO efficiency in global optimization and TS in avoiding the premature convergence that would lead PSO to stagnate in a local minimum. Moreover, we propose a new efficient, simple, and inexpensive model for storing and evaluating solution's assignment. The purpose of this model reduces the solution's storage volume as well as the computations required to evaluate thesesolutions in comparison with the classical model. Our simulation results on the most known benchmarking instances prove the effectiveness of our proposed algorithm in comparison with previous related works in terms of convergence rate, the number of iterations, the solution storage volume and the running time required to converge to the optimal solution.