针对Isomap采用Floyd-Warshall算法求最短路径时运算速度慢的问题,考虑到邻域图的稀疏性,提出了Isomap的改进算法.通过采用基于Fibonacci堆的Dijkstra算法,减少了求最短路径的时间,从而提高了Isomap的速度.在多个数据集上的实验结果表明,改进后的算法较原Isomap算法的运算速度快.
For the slow operational speed problem of the Isomap algorithm in which the Floyd-Warshall algorithm is applied to finding shortest paths, an improved Isomap algorithm is proposed based on the sparseness of the adjacency graph. In the improved algorithm, the runtime for shortest paths is reduced by using Dijkstra' s algorithm based on a Fibonacci heap, thus speeding up the Isomap operation. The experimental results on several data sets show that the improved version of Isomap is faster than the original one.