哈尔滨师范大学自然科学学报
哈爾濱師範大學自然科學學報
합이빈사범대학자연과학학보
NATURAL SCIENCES JOURNAL OF HARBIN NORMAL UNIVERSITY
2012年
1期
46-50
,共5页
遗传算法%信息素%杂交优势%数据分类
遺傳算法%信息素%雜交優勢%數據分類
유전산법%신식소%잡교우세%수거분류
Genetic algorithm%Pheromone%Heterosis%Data classification
针对遗传算法无法利用系统中的反馈信息,求解到一定范围时出现的冗余迭代,求精确解效率低,局部搜索能力弱、易出现“早熟”现象等缺点,提出了采用蚁群信息素对均匀划分子空间进行标定,利用留存的信息素控制选择操作,采用双重选择算子、基于“杂交优势”思想的交叉算子和自适应变异算子的混合遗传算法.实验表明,采用该算法的分类系统的分类准确率、算法运行时间、算法收敛性等方面性能均有明显提高.
針對遺傳算法無法利用繫統中的反饋信息,求解到一定範圍時齣現的冗餘迭代,求精確解效率低,跼部搜索能力弱、易齣現“早熟”現象等缺點,提齣瞭採用蟻群信息素對均勻劃分子空間進行標定,利用留存的信息素控製選擇操作,採用雙重選擇算子、基于“雜交優勢”思想的交扠算子和自適應變異算子的混閤遺傳算法.實驗錶明,採用該算法的分類繫統的分類準確率、算法運行時間、算法收斂性等方麵性能均有明顯提高.
침대유전산법무법이용계통중적반궤신식,구해도일정범위시출현적용여질대,구정학해효솔저,국부수색능력약、역출현“조숙”현상등결점,제출료채용의군신식소대균균화분자공간진행표정,이용류존적신식소공제선택조작,채용쌍중선택산자、기우“잡교우세”사상적교차산자화자괄응변이산자적혼합유전산법.실험표명,채용해산법적분류계통적분류준학솔、산법운행시간、산법수렴성등방면성능균유명현제고.
n the simple genetic algorithm, it is found that the feedback information is useless. Many redundant interactions are done in later stage. The low efficiency in accurate solving, poor ability in local searching and easy emergence of premature convergence is existed. Aim at the problems above, the Hybrid Genetic Algorithm is researched in this thesis. At first, the solution space of the optimization problem is divided evenly and each subspace is marked by ant colony pheromone which controls the selection operation. Secondly, double selection operator, crossover operator based on "heterosis" and adaptive mutation operator is designed. At last, the accuracy of classification, the time of the algorithm running and the convergence of algorithm is tested through the analysis of the data of the result in experiment. It is proved that the performance of the classification based on hybrid genetic algorithm is improved on the three aspects above.