Skip to main content

Table 2 Comparison of linear regression and neural network energy expenditure estimates made per gait cycle for different use cases during inclined loaded walking

From: Rapid energy expenditure estimation for ankle assisted and inclined loaded walking

Model Metric Novel Condition Novel Subject Both-Novel Subject Vertical Forcea Raw Subjectb
Linear Regression RMSEc\(\left (\frac {\mathrm {W}}{\text {kg}}\right)\) 0.62 0.94 0.95 0.98 1.39
  Error 6.7% 12.1% 13.7% 12.3% 16.5%
Neural Network RMSE \(\left (\frac {\mathrm {W}}{\text {kg}}\right)\) 0.56 0.83 0.78 0.86 0.88
  Error 6.1% 9.7% 11.7% 10.0% 11.2%
  1. aThe subject vertical force use case was the novel subject use case with inputs restricted to vertical ground reaction forces and EMG signals
  2. bThe raw subject use case was the novel subject use case without any data preprocessing other than rectifying the EMG signals
  3. cRMSE is the root mean squared error normalized by the average subject mass