Arrow Research search

Author name cluster

Juan Du

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers
1 author row

Possible papers

3

JBHI Journal 2025 Journal Article

GSAHermNet: A GraphSAGE-Based Neural Network with Hermite Interpolation for Individualized Gait Pattern Generation

  • Lin Meng
  • Shaochen Xu
  • Hongtao Dong
  • Juan Du
  • Uriel Martinez-Hernandez
  • Rui Xu
  • Dong Ming

Accurate generation of gait patterns is essential for advancing robotic gait rehabilitation. This study presents GSAHermNet, a novel two-stage framework that combines a GraphSAGE-based neural network for predicting key gait events with Hermite interpolation to reconstruct full joint trajectories. Unlike conventional methods that generate the entire gait cycle directly, GSAHermNet focuses on predicting key gait events using only seven body and walking parameters, thereby reducing over fitting and enhancing generalizability across diverse walking speeds and conditions. The model was trained on a public dataset of 42 healthy subjects using 5-fold cross-validation on 40 individuals, while the remaining two subjects were reserved for independent testing. Experimental results demonstrate that GSAHermNet achieves mean absolute deviations (MAD) below 4. 58° and correlation coefficients (r) of 0. 99 for hip and knee joints, and MAD below 3. 69° with r = 0. 85 for the ankle. Comparative analyses confirm that GSAHermNet outperforms conventional statistical and machine learning approaches in both accuracy and robust ness. The proposed approach has great potential for real word applications, such as adaptive control in functional electrical stimulation systems and personalized motion planning in lower-limb exoskeletons. An online framework for real-time gait trajectory generation will be established using wearable sensor inputs in future.

AAAI Conference 2017 Conference Paper

Streaming Classification with Emerging New Class by Class Matrix Sketching

  • Xin Mu
  • Feida Zhu
  • Juan Du
  • Ee-Peng Lim
  • Zhi-Hua Zhou

Streaming classification with emerging new class is an important problem of great research challenge and practical value. In many real applications, the task often needs to handle large matrices issues such as textual data in the bag-ofwords model and large-scale image analysis. However, the methodologies and approaches adopted by the existing solutions, most of which involve massive distance calculation, have so far fallen short of successfully addressing a real-time requested task. In this paper, the proposed method dynamically maintains two low-dimensional matrix sketches to 1) detect emerging new classes; 2) classify known classes; and 3) update the model in the data stream. The update efficiency is superior to the existing methods. The empirical evaluation shows the proposed method not only receives the comparable performance but also strengthens modelling on largescale data sets.