CEnsLoc: Infrastructure-Less Indoor Localization Methodology Using GMM Clustering-Based Classification Ensembles

Table 1

A comparison of performance measures of various classification algorithms for Wi-Fi-based position estimation.

Algorithm	Time to build model (sec)	Accuracy	Kappa statistic	RMSE	Precision	Recall	F1	MCC	ROC area
K	0	99.52	0.98	0.02	0.99	0.99	0.99	0.99	1
k-NN	0	99.06	0.99	0.03	0.99	0.99	0.99	0.98	0.99
RFE	1.11	98.76	0.98	0.04	0.98	0.98	0.98	0.98	1
FURIA	5.92	97.26	0.96	0.05	0.97	0.97	0.97	0.96	0.99
Multilayer perceptron	25.84	97.05	0.96	0.06	0.97	0.97	0.97	0.96	0.99
J48	0.1	95.91	0.95	0.08	0.95	0.95	0.95	0.95	0.98
Dl4jMlp classifier	26.31	94	0.93	0.08	0.94	0.94	0.94	0.93	0.99
SVM	5.82	90.6	0.89	0.12	0.93	0.90	0.90	0.9	0.94
Naive Bayes	0.02	89.79	0.88	0.12	0.91	0.89	0.89	0.89	0.99
AdaBoost with decision stump	0.1	36.81	0.22	0.25	0.15	0.36	0.21	0.18	0.76