根据文本集的中心和初始簇的中心,选择一组具有良好区分度的方向构建IMIC坐标系,在该坐标系下构造出各坐标轴的重新标度函数用于提高聚类决策的有效性.算法IMIC经过多次迭代,收敛到最终解.IMIC算法的时间复杂度与K-means保持在同一量级上.实验结果表明,IMIC算法有较好的聚类质量.%According to the text set center and initial cluster center,in the text clustering process, this paper chose a set of discriminative directions to construct the IMIC coordinate, and constructed each axis to re-scaling function in order to improve the effectiveness of cluster policy, according to the distribution characteristics of the initial clusters. IMIC iterative algorithm ways converged to the final solution. The time complexity of IMIC remained the same as K-means by using a K-means-like iteration strategy. Experimental results show that IMIC algorithm has better clustering quality.
展开▼
