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

Table 14

Confusion matrix on the Milan dataset with activities balancing using threefold in the combination of fuzzy C-means and ANN.

Acts	Slp	Tlt	Dsk	Dnr	Gbr	Kch	Mbr	Lh	Mr	Red	Tv	Mmd	Chr	Emd	Med
Slp	96.2								3.8
Tlt		86.5			4.0		7.5
Dsk			94.0	2.8							1.2		2.0
Dnr				95.0		3.0					2.0
Gbr		4.2			93.0		2.6
Kch				1.9		94.5			1.1			2.5	1.0
Mbr		7.0					90.0		2.9
Lh								100.0
Mr							5.8		93.2				1.0
Red						1.0				95.9	3.1
Tv									3.7	4.0	92.3
Mmd						6.0						85.8		8.2
Chr						9.6			3.8				86.6
Emd						2.0						10.2		87.8
Med						2.1						4.0		3.9	90.0

The columns represent the predicted activities, while the rows represent the actual activities. The performance of overlapping activities is highlighted in bold. Key. acts: activities, Slp: sleeping, Tlt: bed to toilet, Dsk: desk activity, Dnr: dining room activity, Gbr: guest bathroom, Kch: kitchen activity, Mbr: master bathroom, LH: leave home, Mr: master bedroom, Red: read, Tv: watch Tv, Mmd: morning medicine, Chr: chores, Emd: evening medicine, and Med: mediate.