Intrusion Detection in Industrial Internet of Things Network-Based on Deep Learning Model with Rule-Based Feature Selection

Table 5

For the NSL-KDD dataset, the results of the proposed model have been compared with nine other classifiers.

Technique	Detection rate	FPR
F-SVM [95]	92.2%	8.7%
CVT [96]	95.3%	5.6%
DMM [91]	97.2%	2.4%
TANN [97]	91.1%	9.4%
DBN [98]	95.1%	4.5%
RNN [52]	73%	3.6%
DNN [81]	76%	15%
Ensemble-DNN [99]	98%	14.7%
ADS-DL [11]	99%	1.8%
Proposed model	98.9	1.1%