一种利用多主体领域系统进行数据聚类的新方法

摘要

A new data clustering method MATS was proposed, which was inspired by Ant Colony Algorithm, In addition,there are some existence technique was also utilized in our method,such as the density concept and cluster validity index ( DB-index ) . MATS can automatically find clusters, depending on a few parameters that are not directly related to the data set. The experiment results verified that MATS is able to discover cluster with varying shapes and it is effective when applied to image segmentation.%提出一种数据聚类方法：MATS,该方法受蚁群算法启发,同时应用存在性技术,例如密度概念和聚类有效性指数( DB-指数)。 MATS可以自动根据一些与数据集不直接相关的参数找到簇。实验结果证明了MATS可以识别不规则簇并能有效应用于图像分割,在图像分割速度和效果方面比传统聚类算法(如FCM算法)有明显提高。