A Deep Learning-Based Framework for Human Activity Recognition in Smart Homes

Table 1

Human activity recognition models.

Traditional approaches	Deep learning approaches
Support vector machines [5, 29]	Deep belief network [36]
Naïve Bayes [30]	RNN [37]
Random forests [23, 31]	CNN, LSTM [38, 39]
Ensemble approaches [32]	CNN-LSTM [40]
Hidden Markov models [33–35]	CNN–Bi-LSTM [41]