Research on multivariate time series prediction method for upper motion intention perception

To address the limitations of relying on a single information source and the low accuracy in upper limb motion intention perception during exoskeleton-based rehabilitation training, a multivariate time-series prediction method that integrates a cross-graph convolution module with a stochastic synthetic attention mechanism is proposed. Specifically, a cross-graph convolution module based on Spatial Node Encoding (SNE) is developed to fuse data from the Inertial Measurement Unit (IMU) and visual signals, thereby capturing spatial relationships among variables. A multi - view topology mapping network with a stochastic synthetic attention mechanism is introduced to extract temporal features, and a Graph Convolutional Network - Long Short - Term Memory (GCN - LSTM) model is constructed. The proposed GCN - LSTM model is compared with the 1 - Dimensional Convolution - Long Short - Term Memory (1DConv - LSTM) and Bidirectional Long Short - Term Memory (Bi - LSTM) models through experiments. The results show that the GCN - LSTM achieves a joint trajectory fitting degree, R2, of 0. 9417. It represents an approximate 9 % improvement over 1DConv–LSTM and a 10 % improvement over Bi–LSTM, effectively enhancing the accuracy of upper limb motion intention perception and contributing to the improvement of rehabilitation training effects.

Authors

• Yang Meng
• Shuhao Liang
• Jinda Wang
• Fei Niu
• Wendong Wang Beijing University of Posts and Telecommunications
• Zelin Ci

Keywords

• Motion intention perception
• Multivariate time series forecasting
• Multimodal information fusion
• Upper limb rehabilitation
• Graph convolution network