Comparative study between incremental and ensemble learning on data streams: Case study

Journal of Big Data

Table 3 The mean of the accuracy on data stream Hyperplane2

	Data-chunk size	500	1000	2000
Classifier number	Algorithm
10	SEA	77.06_±0.97	87.91_±1.97	87.36_±0.78
	AWE	84.94_±3.87	85.72_±0.53	89.09_±.012
20	SEA	86.32_±1.21	87.17_±0.99	91.15_±0.29
	AWE	87.96_±0.52	89.27_±0.96	91.42_±0.26
30	SEA	89.22_±1.56	88.49_±0.5	90.44_±0.08
	AWE	90.36_±0.43	89.44_±0.46	90.39_±0.04

SEA get the optimal accuracy at a 2,000 data chunk size and 20 base classifiers, while AWE algorithm get optimal accuracy at a 2,000 data chunk size and 20 base classifiers.