first submission

Author: Tian-A-Tan

README.md

@@ -9,21 +9,25 @@ external forces from kinematics, ii) predicting the influence of gait modificati
 experiments, and iii) predicting comprehensive kinematics and kinetic changes that occur with increasing running 
 speeds.
 
-## Corresponding Publication
-This repository includes the code and models for an [abstract](./figures/readme_fig/Tan_ASB2024.pdf).
-Full-length preprint is coming soon.
-
 ## Environment
 Our code is developed under the following environment. Versions different from ours may still work.
 
 Python 3.9.16; Pytorch 1.13.1; Cuda 11.6; Cudnn 8.3.2; numpy 1.23.5;
 
-## Dataset
-[AddBiomechanics Dataset](https://addbiomechanics.org/download_data.html)
+## Trained model
+GaitDynamics has [a diffusion model](/example_usage/GaitDynamicsDiffusion.pt) and 
+[a force refinement model](/example_usage/GaitDynamicsRefinement.pt).
+Downstream task 1 uses both models, while downstream task 2 and 3 use only the diffusion model.
 
-## Example code
+## Force estimation with GaitDynamics
 [A Google Colab notebook](https://colab.research.google.com/drive/1n6kH3gnwLdQ2DH5krigbkiO06NjDtyxI?usp=sharing)
 is provided for the downstream tasks 1 – force estimation using flexible combinations of kinematic inputs.
-By executing the code, and example .mot file with joint angles of an OpenSim skeletal model will be imported from GitHub.
+By executing the code, the GaitDynamics models, and example .mot file with joint angles of an OpenSim skeletal model will be imported from GitHub.
 Users can upload their own .mot files to the Colab notebook to obtain force predictions.
 To use a reduced kinematic input combinations, simply delete the corresponding columns in the .mot file.
+
+## Dataset
+[AddBiomechanics Dataset](https://addbiomechanics.org/download_data.html)
+
+## Publication
+This repository includes the code and models for a [preprint]() and an [abstract](./figures/readme_fig/Tan_ASB2024.pdf).

example_usage/GaitDynamicsDiffusion.pt

@@ -279,10 +279,10 @@ def format_ticks(ax):
     metric_sugainet = get_all_the_metrics(model_key=f'/{folder}/sugainet_none_diffusion_filling')
 
     params_name_formal_name_pairs = {
-        'calcn_l_force_vy': 'Vertical\nForce - Profile',
-        'calcn_l_force_vx': 'Anterior-Posterior\nForce - Profile',
-        'calcn_l_force_vz': 'Medial-Lateral\nForce - Profile',
-        'calcn_l_force_vy_max': 'Vertical\nForce - Peak'}
+        'calcn_l_force_vy': 'Vertical\nForce—Profile',
+        'calcn_l_force_vx': 'Anterior-Posterior\nForce—Profile',
+        'calcn_l_force_vz': 'Medial-Lateral\nForce\u2014Profile',
+        'calcn_l_force_vy_max': 'Vertical\nForce\u2014Peak'}
     params_of_interest = list(params_name_formal_name_pairs.keys())
 
     rc('text', usetex=True)
@@ -310,23 +310,23 @@ def format_ticks(ax):
 
     # From "Comparison of different machine learning models to enhance sacral acceleration-based estimations of running stride temporal variables and peak vertical ground reaction force"
     line0, = plt.plot([2.8, 3.7], [13, 13], '--', linewidth=2, color=[0.0, 0.0, 0.0], alpha=0.5)
-    plt.text(4.1, 14, 'Running MDC - Healthy [25]', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
+    plt.text(4.1, 14, 'Running MDC - Healthy$^{\ 31}$', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
     plt.annotate('', xytext=(4.05, 14), xycoords='data', xy=(3.75, 13), arrowprops=dict(arrowstyle="->"))
 
     # From "Intra-rater repeatability of gait parameters in healthy adults during self-paced treadmill-based virtual reality walking"
     line1, = plt.plot([2.8, 3.7], [10.18, 10.18], '--', linewidth=2, color=[0.0, 0.0, 0.0], alpha=0.5)
-    plt.text(4.1, 11.18, 'Walking MDC - Healthy [26]', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
+    plt.text(4.1, 11.18, 'Walking MDC - Healthy$^{\ 32}$', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
     plt.annotate('', xytext=(4.05, 11.18), xycoords='data', xy=(3.75, 10.18), arrowprops=dict(arrowstyle="->"))
 
     # and "Minimal detectable change for gait variables collected during treadmill walking in individuals post-stroke"
     line2, = plt.plot([2.8, 3.7], [4.65, 4.65], '--', linewidth=2, color=[0.0, 0.0, 0.0], alpha=0.5)
-    plt.text(4.1, 5.65, 'Walking MDC - Stroke [27]', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
+    plt.text(4.1, 5.65, 'Walking MDC - Stroke$^{\ 33}$', fontdict=FONT_DICT_SMALL, color=[0.0, 0.0, 0.0], va='center')
     plt.annotate('', xytext=(4.05, 5.65), xycoords='data', xy=(3.75, 4.65), arrowprops=dict(arrowstyle="->"))
 
     format_axis(plt.gca())
     format_ticks(plt.gca())
     plt.tight_layout(rect=[-0.03, 0., 1.03, 0.88])
-    plt.legend(list(bars), ['GaitDynamics', 'Convolutional Neural Network [19]', 'Recurrent Neural Network [20]'],
+    plt.legend(list(bars), ['GaitDynamics', 'Convolutional Neural Network$^{\ 21}$', 'Recurrent Neural Network$^{\ 22}$'],
                frameon=False, fontsize=FONT_SIZE_SMALL, bbox_to_anchor=(0.7, 1.2), ncols=1)
     plt.savefig(f'exports/da_grf.png', dpi=300, bbox_inches='tight')
     plt.show()
@@ -384,7 +384,7 @@ def format_ticks(ax_plt):
     format_axis(plt.gca())
     format_ticks(ax_plt)
     ax_plt.legend(list(bars) + [line_1], [
-        'Partial-Body Kinematics with Inpainting Filling (GaitDynamics)', 'Partial-Body Kinematics with Median Filling', 'Full-Body Kinematics (GaitDynamics)'],
+        'Partial-Body Kinematics with Inpainting (GaitDynamics)', 'Partial-Body Kinematics with Median Filling', 'Full-Body Kinematics (GaitDynamics)'],
                   frameon=False, fontsize=FONT_SIZE_SMALL, bbox_to_anchor=(0., 0.88), loc='lower left')
     plt.savefig(f'exports/da_segment_filling.png', dpi=300, bbox_inches='tight')
     plt.show()

example_usage/GaitDynamicsRefinement.pt

@@ -59,7 +59,7 @@ def draw_fig():
     ax_angles = fig.add_subplot(gs[1, 0])
     for i, (ax, scale) in enumerate(zip([ax_kam, ax_angles], [1, - 180/np.pi])):
         for i_condition, condition in enumerate(condition_list):
-            condition_val = condition.split('_')[-1]
+            condition_val = float(condition.split('_')[-1])
             true_averaged, pred_averaged, ts_averaged, true_std, pred_std, ts_std = [scale * ele for ele in get_average_and_std(
                 bl_true, bl_pred, ts_true, condition, params_of_interest_col_loc)]
 
@@ -68,12 +68,12 @@ def draw_fig():
                 print('Pred 2st peak diff {:.1f}'.format(true_averaged[51:, i].max() - pred_averaged[51:, i].max()))
             elif i == 1:
                 print('Pred 1st peak value {:.1f}'.format(pred_averaged[:, i].max()))
-            ax.plot(pred_averaged[:, i], '--', color=colors[i_condition], linewidth=LINE_WIDTH_THICK, label=f'{condition_val} x Normal Trunk Sway - Synthetic         ')
+            ax.plot(pred_averaged[:, i], '--', color=colors[i_condition], linewidth=LINE_WIDTH_THICK, label='{:.1f} x Normal Trunk Sway - Synthetic         '.format(condition_val))
             # ax.grid(True, linewidth=1, alpha=0.5)
             if i_condition == len(condition_list) - 1:
-                ax.plot(true_averaged[:, i], '-', color=[0.4, 0.4, 0.4], label='Normal Walking - Experimental [38]')
+                ax.plot(true_averaged[:, i], '-', color=[0.4, 0.4, 0.4], label='Normal Walking - Experimental')
                 ax.fill_between(range(len(true_averaged)), true_averaged[:, i] - true_std[:, i], true_averaged[:, i] + true_std[:, i], color='gray', alpha=0.3)
-                ax.plot(ts_averaged[:, i], '-', color=colors[3], label='Large Trunk Sway - Experimental [38]')
+                ax.plot(ts_averaged[:, i], '-', color=colors[3], label='Large Trunk Sway - Experimental')
                 ax.fill_between(range(len(ts_averaged)), ts_averaged[:, i] - ts_std[:, i], ts_averaged[:, i] + ts_std[:, i], color=colors[-1], alpha=0.3)
                 if i == 0:
                     print('Exp 1st peak diff {:.1f}'.format(true_averaged[:, i].max() - ts_averaged[:, i].max()))

figures/da_grf_test_set_1.py

@@ -157,7 +157,7 @@ def draw_speed_only_fig():
 
         if i_param == 1:
             ax.legend([ebar1, ebar0, ebar2],
-                      ['Experimental Measurement[xxxx]', 'GaitDynamics Generation', 'OmniControl Generation [36]'],
+                      ['Experimental Measurement', 'GaitDynamics Generation', 'OmniControl Generation'],
                       frameon=False, bbox_to_anchor=(0.8, 1.25), ncol=3, handlelength=4)
     plt.subplots_adjust(.08, .08, .98, .92)
     plt.savefig(f'exports/da_run_faster_1.png', dpi=300)