[Retracted] Improving Recognition of Overlapping Activities with Less Interclass Variations in Smart Homes through Clustering-Based Classification

Table 4

Performance evaluation metrics on Milan dataset without activities balancing using threefold cross-validation.

Dataset	Cross-validation	Clustering method	Classification method	Precision (%)	Recall (%)	F score [0, 1]	Accuracy (%)
Milan	Threefolds	Fuzzy C-means [35]	ANN [45]	82.23	83.04	0.83	83.04
			ET-KNN [47]	79.61	80.25	0.80	80.25
			KNN [48]	78.41	78.51	0.79	78.25
			SMO [46]	74.37	74.54	0.75	75.37
		Hierarchical [42]	ANN	80.01	81.01	0.81	81.01
			ET-KNN	77.51	77.91	0.78	78.01
			KNN	75.41	75.41	0.76	75.41
			SMO	73.23	72.22	0.72	73.23
		K-mean [36]	ANN	77.51	80.01	0.79	80.01
			ET-KNN	76.41	76.71	0.77	76.51
			KNN	74.71	75.41	0.76	75.41
			SMO	72.41	72.22	0.73	72.23
		DBSCAN [37]	ANN	78.41	78.51	0.79	78.71
			ET-KNN	76.51	77.01	0.77	77.01
			KNN	74.61	73.41	0.74	74.61
			SMO	72.31	73.41	0.73	73.51

The precision, recall, and accuracy are in percentages (%), while the range of F score is between [0-1], with 1 being the highest. The highest values are in bold.