Table A4.

Summary of reviewed articles.

Art	Year	Est	AP	rPoint	fMap	fmRoom	mAlg	sAlg	mError	oError	sType
[129]	2018	pMap	$N/A$	$N/A$	UJI Library	Y	RNN		2.48 $\mathrm{m}$	99.6% floor level	RSSI
		pMap	$N/A$	$N/A$	UJI Library	Y	LSTM		2.6 $\mathrm{m}$	99.5% floor level	RSSI
[85]	2018	pMap	520	993	UJIIndoorLoc	Y	RDF		6.72 $\mathrm{m}$	std = 4.82 m	RSSI
[130]	2018	exp	7	101	404.5 ${\mathrm{m}}^2$	Y	FF-DNN			RMSE = 0.32 m, 53.123% in 0.5 m	RSSI
[43]	2018	exp	4	25	80 ${\mathrm{m}}^2$	N	RF		0.40 $\mathrm{m}$		CSI
[131]	2018	exp	4	67	1664 ${\mathrm{m}}^2$	Y	SVM		1.34 $\mathrm{m}$		RSSI
[86]	2018	pMap	520	993	UJIIndoorLoc	Y	CNN		2.77 $\mathrm{m}$	100% for floor prediction	RSSI
[132]	2018	exp	$N/A$	$N/A$	NULL	NULL	SVR	RBF Kernel		95% in 1.81 m	RSSI
[133]	2018	exp	40	180	1209 ${\mathrm{m}}^2$	Y	RF			95% accuracy 1.5 × 1.5 m	RSSI
[134]	2018	exp	8	40	580 ${\mathrm{m}}^2$	Y	RVFL		0.43 $\mathrm{m}$	RMSE = 0.5830 m	RSSI
[69]	2018	sim	4	36	441 ${\mathrm{m}}^2$	N	RVM	PLS	0.84 $\mathrm{m}$		RSSI
		exp	6	25	156 ${\mathrm{m}}^2$	Y	RVM	PLS		41% in 1 m and 91% in 2 m	RSSI
[135]	2017	exp	3	110	109.25 ${\mathrm{m}}^2$	N	FF-DNN			RMSE = 0.6782 m	RSSI
[136]	2017	exp	4	$N/A$	NULL	N	ANN			RMSE = 1.1045 m	RSSI
		exp	6	$N/A$	NULL	N	ANN			RMSE = 1.2288 m	RSSI
[137]	2017	exp	16	126	304 ${\mathrm{m}}^2$	Y	SVM		1.43 $\mathrm{m}$		RSSI
[138]	2017	sim	6	441	100 ${\mathrm{m}}^2$	N	LS-SVM		2.56 $\mathrm{m}$		RSSI
[139]	2017	exp	38	411	600 ${\mathrm{m}}^2$	Y	ELM		1.91 $\mathrm{m}$		RSSI
[140]	2017	exp	28	67	30 ${\mathrm{m}}^2$	N	ANN		2.2 $\mathrm{m}$		RSSI
[141]	2017	exp	185	480	NULL	Y	SVM			100% shop level	RSSI
[142]	2017	pMap	520	993	UJIIndoorLoc	Y	DNN			92% floor recognition	RSSI
[143]	2017	exp	8	48	53.35 ${\mathrm{m}}^2$	N	SVR			86.2% in 1.5 m and 90.4% in 2 m	RSSI
[144]	2017	exp	$N/A$	$N/A$	NULL	Y	SVM			97.31% flat and 88.38% floor	RSSI
[145]	2016	exp	22	84	387.75 ${\mathrm{m}}^2$	Y	BPNN		0.98 $\mathrm{m}$		RSSI
[146]	2016	sim	4	25	400 ${\mathrm{m}}^2$	N	MLP-ANN		0.27 $\mathrm{m}$	std = 0.36 m	RSSI
[147]	2016	sim	$N/A$	$N/A$	NULL	NULL	EB-ANN			RMSE = 0.4991 m	RSSI
[148]	2016	exp	5	54	150 ${\mathrm{m}}^2$	Y	SVR			70% in 5 m	RSSI
[149]	2016	exp	16	188	1125 ${\mathrm{m}}^2$	Y	ANN		1.89 $\mathrm{m}$	90% in 2.971 m	RSSI
[70]	2016	sim	12	1600	1600 ${\mathrm{m}}^2$	N	SVR			RMSE = 1.42 m	RSSI
		exp	13	116	1000 ${\mathrm{m}}^2$	Y	SVR			RMSE = 1.8 m, 74% in 2 m	RSSI
[150]	2016	exp	$N/A$	112	460 ${\mathrm{m}}^2$	Y	SVM		1.2 $\mathrm{m}$		RSSI

art: Article; mAlg: Main algorithm used; est: Experimental or pMapulated study; sAlg: Other algorithms used in the study; AP: APs used; mError: Mean Error; rPoint: Reference Points used in offline phase; oError: Other metrics reported in the study; fMap: Size of experimental room or radio-map used; sType: Signal type used; fmRoom: Rooms used in exp/pMap.