论文信息 - Some statistical properties of the minimum spanning forest

Some statistical properties of the minimum spanning forest

Abstract A minimum spanning forest method is described which finds cluster patterns in a random graph of points. A relation between the main number of clusters and a defined fixed thresholding value is obtained. Then, using the number of clusters as a parameter, a uniformity test suitable for low statistics data sets is proposed. Finally, some effective applications on simulated and real data are also discussed.

V. Di Gesù | B. Sacco | B. Sacco | V. Gesù

[1] Chin-Liang Chang,et al. Finding Prototypes For Nearest Neighbor Classifiers , 1974, IEEE Transactions on Computers.

[2] R. Prim. Shortest connection networks and some generalizations , 1957 .

[3] G. Estabrook. A mathematical model in graph theory for biological classification. , 1966, Journal of theoretical biology.

[4] Ming-Kuei Hu,et al. Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[5] H. Nieuwenhuijzen,et al. Image processing techniques in astronomy , 1975 .

[6] J. Kruskal. On the shortest spanning subtree of a graph and the traveling salesman problem , 1956 .

[7] F. Lebrun,et al. COS‐B OBSERVATION OF THE MILKY WAY IN HIGH‐ENERGY GAMMA RAYS , 1980 .

[8] Geoffrey H. Ball,et al. Data analysis in the social sciences: what about the details? , 1965, AFIPS '65 (Fall, part I).

[9] Giselher G. Lichti,et al. Second Cos $B$ Catalog of High-energy gamma-ray Sources , 1981 .

[10] Charles T. Zahn,et al. and Describing GestaltClusters , 1971 .