Using Wearable Sensors to Estimate Vertical Ground Reaction Force Based on a Transformer

In this paper, we present a new method to estimate ground reaction forces (GRF) from wearable sensors for a variety of real-world situations. We address the drawbacks of using force plates with limited activity range and high cost in previous work. We use a transformer encoder as a feature extractor to extract temporal and spatial features from wearable sensors more efficiently. Using the Mean Absolute Percentage Error (MAPE) as the evaluation criterion, the experimental results show that the average error of the predicted values using the transformer as a feature extractor improved by 32% compared to the RNN architecture and by 25% compared to the LSTM architecture. Finally, we use Gate_MSE to solve the problem of a large peak error in GRF prediction. Meanwhile, this paper explores the effect of the number of wearable sensors or wearable modes on GRF prediction.

Automated summary

In this paper, a new method is proposed to estimate ground reaction forces (GRF) using wearable sensors for various real-world situations. The drawbacks of using force plates, such as limited activity range and high cost, are addressed. A transformer encoder is used as a feature extractor to efficiently extract temporal and spatial features from the wearable sensors. Experimental results show that using the transformer as a feature extractor improves the average error of predicted values by 32% compared to the RNN architecture and by 25% compared to the LSTM architecture. Additionally, Gate_MSE is employed to solve the problem of large peak errors in GRF prediction, and the effect of the number of wearable sensors or modes on GRF prediction is explored.