Journals
Publish with us
Publishing partnerships
About us
Blog
Mathematical Problems in Engineering
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
Mathematical Problems in Engineering
/
2018
/
Article
/
Tab 1
/
Research Article
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
Table 1
Accuracy and F1 score for each algorithm with the public domain UCI dataset. The best result in each column is highlighted in bold.
Algorithm
Accuracy
F1 score
MC-HF-SVM
89.3%
-
Baseline LSTM
90.8%
90.8%
Bidir-LSTM
91.1%
91.1%
Res-LSTM
91.6%
91.5%
Res-Bidir-LSTM
93.6
93.5