Table 3. Performance comparison of Stacked Discriminant Feature Learning (SDFL) with alternative approaches.

Method	Accuracy (%)
Multiclass Support Vector Machine 7	96
Dynamic Time Warping 18	89.00
Hierarchical Continuous Hidden Markov Model 19	93.18
Deep Belief Network (as reported in 9 )	95.80
Group-based Context-aware method for human activity recognition (GCHAR) 3	94.16
Handcrafted Cascade Ensemble Learning model (CELearning) 16	96.88
Automated Cascade Ensemble Learning model (CELearning) 16	95.93
Convolutional Neural Network (CNN) 10	95.75
Artificial Neural Network (ANN) (as reported in 10 )	91.08
Stacked Discriminant Feature Learning (SDFL)	96.27