Foot2hip: A deep neural network model for predicting lower limb
kinematics from foot measurements
Objective: This study aims to develop a neural network (foot2hip) for
long-term recording of gait kinematics with improved user comfort.
Methods: Foot2hip predicts ankle, knee, and hip joint angle profiles in
the sagittal plane using foot kinematics and kinetics during walking.
Foot2hip consists of three convolution, two max-pooling, two LSTM and
three dense layers. An indigenously developed insole and an outsole were
used to measure the kinetics and kinematics of the foot, respectively.
Seven healthy participants were recruited to follow an experimental
protocol consisting of six walking conditions: slow, medium, fast
walking speed, rearfoot, flatfoot, and forefoot landing pattern.
Results: When tested for leave-one-out and nested cross-validation,
foot2hip obtained 3.04° ±0.20 RMSE and 0.97±0.01 correlation coefficient
for knee joint, 1.7°± 0.09 RMSE and 0.95±0.01 correlation coefficient
for hip joint, and 1.32°±0.08 RMSE and 0.91±0.02 correlation coefficient
for ankle joint (averaged across all folds). Conclusion: The prediction
performance of foot2hip is encouraging and shows its applicability in
accurately predicting lower limb kinematics with minimal wearables.
Significance: The hardware used along with foot2hip is low cost ($268 +
N× $35, N is the number of different foot sizes), comfortable, and easy
to use. Therefore, it is suitable for most clinical and personal