Multisource Heterogeneous Data Fusion Analysis of Regional Digital Construction Based on Machine Learning

Table 2

Basic information of the data set.

Data set	Training data set	Test data set
Total number of samples	494317	335287
Number of normal samples	95632	57482
Number of abnormal samples	245632	258037
Number of DoS samples	380334	218742
R2L sample number	1015	15078
Number of U2R samples	41	217
Probe sample number	4096	4055
Unknown number of samples	—	17601