Design and Implementation of an Improved K-Means Clustering Algorithm

Table 1

UCI dataset with optimal k value.

UCI data set	Records	Number of attributes	Best value of k
Iris	150	4	3
Wine	178	13	3
Glass	214	9	6
TAE	151	5	3
Soybean-(small)	47	35	4
Blood	748	4	2
Diabetes	768	8	2
Seeds	210	7	3
Waveform	5000	40	3
E. coli	336	8	8