. 2022 Apr 29;22(9):3401. doi: 10.3390/s22093401

Table 3.

Supervised Techniques results.

Dataset	Technique	Metrics				References
Dataset	Technique	Accuracy	Precision	Recall	F-Measure	References
UCI Machine Learning	Nearest Neighbor	75.7	-	-	-	[121]
	Decision Tree	76.3	-	-	-
	Random Forest	75.9	-	-	-
	Naive Bayes	76.9	-	-	-
Aras (House A)	MSA (Margin Setting Algorithm)	68.85	-	-	-	[122]
	SVM	66.90	-	-	-
	ANN	67.32	-	-	-
Aras (House B)	MSA (Margin Setting Algorithm)	96.24	-	-	-
	SVM	94.81	-	-	-
	ANN	95.42	-	-	-
CASAS Tulum	MSA (Margin Setting Algorithm)	68.00	-	-	-
	SVM	66.6	-	-	-
	ANN	67.37	-	-	-
Mhealth	K-NN	99.64	-	-	99.7	[123]
	ANN	99.55	-	-	99.6
	SVM	99.89	-	-	100
	C4.5	99.32	-	-	99.3
	CART	99.13	-	-	99.7
	Random Forest	99.89	-	-	99.89
	Rotation Forest	99.79	-	-	99.79
WISDM, SCUT_NA-A	Sliding window with variable size, S transform, and regularization based robust subspace (SRRS) for selection and SVM for Classification	96.1	-	-	-	[124]
SCUT NA-A	Sliding window with fixed samples, SVM like a classifier, cross-validation	91.21	-	-	-
PAMPA2, Mhealth	Sliding windows with fixed 2s, SVM, and Cross-validation	84.10	-	-	-
SBHAR	Sliding windows with fixed 4s, SVM, and Cross-validation	93.4	-	-	-
WISDM	MLP based on voting techniques with nb-Tree are used	96.35	-	-	-
UTD-MHAD	Feature level fusion approach& collaborative representation classifier	79.1	-	-	-
Groupware	Mark Hall’s feature selection and Decision Tree	99.4	-	-	-
Free-living	k-NN and Decision Tree	95	-	-	-
WISDM, Skoda	Hybrid Localizing learning (k-NN-LSS-VM)	81	-	-	-
UniMiB SHAR	LSTM and Deep Q-Learning	95	-	-	-
Groupware	Sliding windows Gaussian Linear Filter and NB classifier	89.5	-	-	-
Groupware	Sliding windows Gaussian Linear Filter and Decision Tree classifier	99.99	-	-	-
CSI-data	SVM	96	-	-	-	[125]
CSI-data	LSTM	89	-	-	-	[125]
Built by the authors	IBK	95	-	-	-	[126]
	Classifier based ensemble	98	-	-	-
	Bayesian network	63	-	-	-
Built by the authors	Decision Tree	91.08	-	-	89.75	[127]
	Random Forest	91.25	-	-	90.02
	Gradient Boosting	97.59	-	-	97.4
	KNN	93.76	-	-	93.21
	Naive Bayes	88.57	-	-	88.07
	SVM	92.7	-	-	91.53
	XGBoost	96.93	-	-	96.63
UK-DALE	FFNN	95.28	-	-	-	[128]
	SVM	93.84	-	-	-
	LSTM	83.07	-	-	-
UCI Machine Learning	KNN	90.74	91.15	90.28	90.45	[129]
	SVM	96.27	96.43	96.14	96.23
	HMM+SVM	96.57	96.74	96.49	96.56
	SVM+KNN	96.71	96.75	96.69	96.71
	Naive Bayes	77.03	79.25	76.91	76.72
	Logistic Reg	95.93	96.13	95.84	95.92
	Decision Tree	87.34	87.39	86.95	86.99
	Random Forest	92.3	92.4	92.03	92.14
	MLP	95.25	95.49	95.13	95.25
	DNN	96.81	96.95	96.77	96.83
	LSTM	91.08	91.38	91.24	91.13
	CNN+LSTM	93.08	93.17	93.10	93.07
	CNN+BiLSTM	95.42	96.58	95.26	95.36
	Inception+ResNet	95.76	96.06	95.63	95.75
UCI Machine Learning	NB-NB	73.68	-	-	46.9	[130]
	NB-KNN	85.58	-	-	61.08
	NB-DT	89.93	-	-	69.75
	NB-SVM	79.97	-	-	53.69
	KNN-NB	74.93	-	-	45
	KNN-KNN	79.3	-	-	49.82
	KNN-DT	87.01	-	-	60.98
	KNN-SVM	82.24	-	-	53.1
	DT-NB	84.72	-	-	60.05
	DT-KNN	91.55	-	-	73.11
	DT-DT	92.73	-	-	75.97
	DT-SVM	93.23	-	-	77.35
	SVM-NB	30.40	-	-	-
	SVM-KNN	25.23	-	-	-
	SVM-DT	92.43	-	-	75.31
	SVM-SVM	43.32	-	-	-
CASAS Tulum	Back-Propagation	88.75	-	-	-	[131]
	SVM	87.42	-	-	-
	DBM	90.23	-	-	-
CASAS Twor	Back-Propagation	76.9	-	-	-
	SVM	73.52	-	-	-
	DBM	78.49	-	-	-
WISDM	KNN	69	78	-	78	[132]
	LDA	40	34	-	34
	QDA	65	58	-	58
	RF	90	91	-	91
	DT	77	77	-	77
	CNN	66	62	-	60
DAPHNET	KNN	90	87	-	88
	LDA	91	83	-	83
	QDA	91	82	-	82
	RF	91	91	-	91
	DT	91	83	-	83
	CNN	90	87	-	87
PAPAM	KNN	65	66	-	66
	LDA	45	45	-	45
	QDA	15	19	-	19
	RF	80	83	-	83
	DT	60	60	-	60
	CNN	73	76	-	73
HHAR(Phone)	KNN	83	85	-	85
	LDA	43	45	-	45
	QDA	40	50	-	50
	RF	88	89	-	89
	DT	67	66	-	66
	CNN	84	84	-	84
HHAR(watch)	KNN	78	82	-	82
	LDA	54	52	-	52
	QDA	26	27	-	27
	RF	85	85	-	85
	DT	69	69	-	69
	CNN	83	83	-	83
Mhealth	KNN	76	81	-	81
	LDA	38	59	-	59
	QDA	91	82	-	82
	RF	85	85	-	85
	DT	77	77	-	77
	CNN	80	80	-	80
RSSI	KNN	91	91	-	91
	LDA	91	91	-	91
	QDA	91	91	-	91
	RF	91	91	-	91
	DT	91	91	-	91
	CNN	91	90	-	91
CSI	KNN	93	93	-	93
	LDA	93	93	-	93
	QDA	92	92	-	92
	RF	93	93	-	93
	DT	93	93	-	93
	CNN	92	92	-	92
Casas Aruba	DT	96.3	93.8	92.3	93	[133]
	SVM	88.2	88.3	87.8	88.1
	KNN	89.2	87.8	85.9	86.8
	AdaBoost	98	96	95.9	95.9
	DCNN	95.6	93.9	95.3	94.6
SisFall	SVM	97.77	76.17		75.6	[134]
	Random Forest	96.82	79.99		79.95
	KNN	96.71	93.99		68.36
CASAS Milan	Naive Bayes	76.65				[135]
	HMM+SVM	77.44
	CRF	61.01
	LSTM	93.42
CASAS Cairo	Naive Bayes	82.79
	HMM+SVM	82.41
	CRF	68.07
	LSTM	83.75
CASAS Kyoto 2	Naive Bayes	63.98
	HMM+SVM	65.79
	CRF	66.20
	LSTM	69.76
CASAS Kyoto 3	Naive Bayes	77.5
	HMM+SVM	81.67
	CRF	87.33
	LSTM	88.71
CASAS Kyoto 4	Naive Bayes	63.27
	HMM+SVM	60.9
	CRF	58.41
	LSTM	85.57