RoC: Robust and Low-Complexity Wireless Indoor Positioning Systems for Multifloor Buildings Using Location Fingerprinting Techniques

Table 2

Different indoor positioning systems considering robustness and complexity.

Category	Scheme	Focus on	Location results	Localization algorithm	Robustness	Complexity	Additional sensor
—	[18]	Robustness	Floor	ML	The algorithm provides robustness in terms of the movement of objects across the floors	Low	Pressure sensor
—	[19]	Robustness	Floor	Particle filter	The algorithm provides robust tracking of floor changing when the robots moved in the staircase	High	Gyroscopes
Scene analysis	[20]	Robustness	x, y	HED	The system can provide the robustness of systems under the environment dynamics	Medium	—
	[21]	Robustness	x, y	MCA	The algorithm is can tolerate against changes in the environment	Medium	—
	[22]	Robustness	x, y	Ensemble learning	The system can handle the problems of the Wi-fi positioning caused by the unstable infrastructure	High	—
	[23]	Robustness	x, y	Probabilistic based	The algorithm can reduce the influence of symmetry RSS signal	Low	—
	[24]	Complexity	x, y	k-means	—	Medium	—
	[25]	Complexity	x, y	FCM	The algorithm can classify the data into clusters which are robust to the multipath effect	Medium	—
	[26]	Complexity	x, y	SVM-C	—	High	—
	[27]	Complexity	x, y	Hierarchical clustering	The strategy is more robust in highly fluctuating RSS measurements	High	—
	Proposed algorithm	Robustness and complexity	x, y, floor	RMoS floor + Active Fusion	The algorithm can overcome the problem of RN failures	Low	Temp. and humid. sensor