摘要
蚁群算法是优化领域中新出现的一种仿生进化算法,广泛应用于求解复杂组合优化问题,并已在通信网络、机器人等许多应用领域得以具体应用。聚类问题作为一种无监督的学习,能根据数据间的相似程度自动地进行分类。基于蚁群算法的聚类算法已经在当前的数据挖掘研究中得到应用。文中针对早期蚁群聚类算法的缺点,提出一种改进的启发式蚁群聚类算法(IHAC),将蚁群在多维空间中移动的启发式知识存储在称之为"记忆银行"的设备当中,来指导蚁群后边的移动行为,降低蚁群移动的随意性,避免产生未分配的数据对象。并用一些数据做了一些实验,结果证明改进的蚁群聚类算法在误分类错误率和运行时间上优于早期的蚁群聚类算法。
Ant colony algorithm is a novel category of bionic algorithm for optimization problems which has various applications to different COPS, e g. communication networks,robotics. As an unsupervised learning technique, dustering is a division of data into groups of similar objects. The ant- based clustering algorithm has currently applications in the data mining community.Based the disadvantage of the classical algorithm, this paper presents an improved heuristic ant- clustering algorithm（IHAC） .A device of memory bank is proposed, which can bring forth heuristic guiding ant to move in the bi - dimension space. The device lowers the randomness of ant＇ s moving and avoids the producing of un- assigned data object. Results on real data sets are given to show that lilAC has superiority in rnisclassification error rate and runtime over the classical algorithm.
出处
《计算机技术与发展》
2007年第8期37-39,共3页
Computer Technology and Development
基金
山东自然科学基金重大项目(Z2004G01)
山东省教育厅计划项目(J05G01)
"泰山学者"建设工程专项经费资助
关键词
蚁群算法
聚类
蚁群聚类算法
记忆银行
ant colony algorithm
clustering
ant - clustering algorithm
memory bank
