Table 4 Comparative study of IHDLM-CADEFST model on ToN-IoT and Edge-IIoT dataset^{20,21,22,35,36,37,38}.

Dataset	Approach	\(\:{A}{c}{c}{{u}}_{{y}}\)	\(\:{P}{r}{e}{{c}}_{{n}}\)	\(\:{R}{e}{c}{{a}}_{{l}}\)	\(\:{{F}1}_{{S}{c}{o}{r}{e}}\)
ToN-IoT dataset	dAE	87.78	90.70	87.03	85.05
	HDBSCAN	97.13	88.87	85.50	82.00
	CALR	92.74	90.41	83.65	86.42
	DNN	94.17	88.66	81.92	81.45
	CART	77.00	90.08	86.33	84.46
	XGBoost	96.50	88.32	84.94	81.23
	CNN-RNN	91.97	89.88	83.00	85.82
	RepuTE algorithm	99.18	87.34	81.10	82.77
	Neural network	97.12	87.02	81.95	83.85
	SVM	90.97	89.56	81.94	86.88
	IHDLM-CADEFST	99.45	91.01	87.61	88.51
Edge-IIoT dataset	EDLM-PSOFS	94.06	92.76	92.13	93.96
	GA-LSTM	95.39	95.61	93.48	89.79
	EfficientNetB0	91.02	90.61	91.11	93.38
	RF	93.42	92.17	91.45	93.36
	KNN	94.60	94.88	92.77	89.27
	SVM	90.28	90.01	90.54	92.66
	XGBoost	93.37	91.39	89.54	91.86
	LightGBM	93.02	89.73	90.69	92.32
	TabPFN	96.86	92.35	89.95	90.63
	Voting classifier	89.95	94.67	92.50	92.95
	IHDLM-CADEFST	99.19	95.12	95.12	95.12

Quick links

Search