Research Article

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

Table 1

Comparative summary of state-of-the-art methods for activity recognition. All features mean no explicit features are selected.

References[15][21][31][22][27][7][41][38][40][39][23]

Feature selectionAll feature

ApproachSelected
K-means
HMM
CRF
DCNN
VSM
DBSCAN
SVM
D.S.T.o.E
LDA
AdaBoost
NBC
Itemset

DatasetsCASAS
Kasteren
SAD
UCI
HHAR
Self