Research Article
CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks
Table 8
Performance comparison of classification models applied to PAMAP2 and RealDisp Datasets.
| | Dataset | Study | Year | (%) |
| | RealDisp | CNN
CNN with block-wise smoothing [28] | 2017 | 90.1
92.8 | | Wavelet transform and pooling operator [57] | 2019 | 81.7 | | SMART [58] | 2020 | 80 | | ETGP [59] | 2021 | 91 | | CNN-LSTM-LF (proposed) | | 92.15 | | PAMAP2 | 2L-CNN
3L-CNN [20] | 2017 | 86
85 | | Attention model [32] | 2018 | 87.5 | | ETGP [59] | 2021 | 91 | | 3-layer CNN + C3 [60] | 2021 | 91.93 | | iSPLInception [22] | 2021 | 89 | | CNN-LSTM-LF (proposed) | | 93.78 |
|
|
