Employing a Machine Learning Approach to Detect Combined Internet of Things Attacks against Two Objective Functions Using a Novel Dataset

Table 3

Raw dataset.

Node	Received	Dups	Lost	Hops	RtMetric	ETX	Churn	Beacon interval	Reboots	CPU power	On-time	Listen duty cycle	Max interpacket time	Simulation t	Malicious/benign	Objective function
1.1	0	0	0	0.000	0.000	0.000	0	0	0	0.000	0	0.000	0	40	m-rankandversion	MRHOF
2.2	60	0	1	3.017	1040.183	48.771	1	1645266	0	0.3859	7756254	0.8725	138000	40	m-rankandversion	MRHOF
3.3	62	0	1	1.000	512.000	16.000	0	1643451	0	0.4022	790122	0.8768	113000	40	m-rankandversion	MRHOF
4.4	59	0	0	2.000	773.051	32.000	0	1723711	0	0.3543	717160	0.7488	113000	40	m-rankandversion	MRHOF
5.5	63	0	0	1.143	573.127	19.048	4	1605000	0	0.4258	787136	0.9806	118000	40	m-rankandversion	MRHOF
6.6	61	0	2	1.098	537.180	17.574	2	1667459	0	0.4715	797966	1.0172	204000	40	m-rankandversion	MRHOF
7.7	59	0	1	2.000	770.237	32.000	1	1668305	0	0.4091	722396	0.9103	116000	40	m-rankandversion	MRHOF
8.8	59	0	0	2.000	771.576	32.059	0	1724813	0	0.3958	723483	0.7992	116000	40	m-rankandversion	MRHOF
9.9	58	0	0	2.000	770.603	32.000	0	1728568	0	0.4448	713151	0.8766	117000	40	m-rankandversion	MRHOF
10.1	59	0	0	2.000	774.186	32.000	0	1690525	0	0.3749	663158	0.7730	83000	40	m-rankandversion	MRHOF
11.1	59	0	0	3.000	1036.542	48.167	0	1701491	0	0.3573	736572	0.7743	115000	40	m-rankandversion	MRHOF
1.1	0	0	0	0.000	0.000	0.000	0	0	0	0.0000	0	0.0000	0	10	b-rankandblackhole	OF0
2.2	23	0	0	3.000	1024.000	48.000	0	1167913	0	0.3794	282283	0.7976	104000	10	b-rankandblackhole	OF0
3.3	23	0	0	1.000	512.000	16.000	0	1099521	0	0.3870	277460	0.7298	111000	10	b-rankandblackhole	OF0