A Novel Approach for Enhancing Joint Moment Prediction in Complex Gait Patterns Using Pretrained Weights in Time-Series Models

Accurately predicting joint moments is crucial for assessing human motor function; however, obtaining such data directly from individuals remains challenging. While the gait data for common activities like walking (WAK) and running can be easily acquired through accelerometers, gyroscopes, and electromyography (EMG) sensors, the sensor data for less common or irregular gait patterns are relatively scarce. This scarcity limits the generalization ability of existing time-series models in predicting joint moments during complex gait patterns. To address this issue, this article proposes a novel method to improve the performance of time-series models in predicting joint moments during complex gait scenarios by utilizing pretrained weights. These pretrained weights are derived from the gait data collected from a large sample of healthy individuals, capturing key information that represents various muscle activity characteristics. The pretrained weights are then applied to time-series models, significantly enhancing their prediction accuracy in complex gait conditions. Experimental results show notable improvements in metrics, such as variance accounted for (VAF), root mean square error (RMSE), and the coefficient of determination ( ${R}^{{2}}$ ), confirming that the pretrained weights improve the generalization capability of joint moment prediction models.