Fig 1.
Definition of sagittal plane movements as well as the (X,Y) coordinates.
Sagittal plane movements included the rotation around the X-axis (i.e., AV) and the translation along the Y-axis (i.e., LA).
Fig 2.
Foot, shank and thigh sagittal plane AV and LA.
Those were selected as the model’s independent variables predominantly because primary motions of the human movement are flexion and extension in the sagittal plane (6). (a) Foot (X1), shank (X2) and thigh (X3) AV. (b) Foot (Y1), shank (Y2) and thigh (Y3) LA.
Table 1.
Train-test split datasets.
Fig 3.
Sliding window demonstration on 1 feature.
The graph shows the sliding window operation on the foot angular velocity (X1). In this paper, the input/output window comprises of 6 features.
Table 2.
Models’ configuration for inter-subject leave-one-out cross validation test.
Fig 4.
LSTM models prediction performance based on the inter-subject test for each feature vector at PWS only.
Models were tested with 75 time-steps and the same participant was tested across LSTM models. Black is the actual trajectory. Brown is the Vanilla LSTM predicted trajectory. Red is the Stacked LSTM predicted trajectory. Green is the Bi-LSTM predicted trajectory. Blue is the ED-LSTM predicted trajectory. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Fig 5.
Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector.
Red is the RMSE (Left Y-axis). Black is the CC (Right Y-axis). Wider gaps between the two error lines (CC and RMSE) means better prediction quality for the related feature vector. The Stacked and ED LSTM maintained the gap for all feature vectors. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Fig 6.
Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector.
Green is the RMSE (Left Y-axis). Blue is the NRMSE (Right Y-axis). Lower error points for the MAE and NRMSE means a better predictive model for the related feature vector. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Table 3.
Leave-one-out cross validation test error based on the MAE, MSE and the RMSE at the PWS and 5km.h-1 combined.
Table 4.
Leave-one-out cross validation test error based on the NRMSE (%) at the PWS and 5km.h-1 combined.
Table 5.
Leave-one-out cross validation test evaluation based on the CC at the PWS and 5km.h-1 combined.