ANN for gait estimations: a review on current trends and future applications

In recent years, gait analysis through estimations has gained significant interest. Through a critical evaluation of recent gait estimations based on Artificial Neural Networks (ANNs), this paper reviews the potential of these methods. It is found that three layer Feed Forward Neural Networks (FFNNs) are widely employed in gait parameter estimations. Traditional kinetic sensors are generally expensive and requires a laboratory environment for data collection. Due to this reason, previous research mainly performed estimations of kinetic parameters from kinematic data thus eliminating the need of traditional kinetic sensors. In comparison to kinematic data, kinetic data are less complex. Moreover, the advancement of wearable kinetic foot sensors offers the advantage of data recording outside laboratory, and are comparatively cost effective. Therefore, estimating kinematics from wearable kinetic sensor data may present to be a better alternative, which has not yet been investigated, thus providing space for future research.