Add BrightSurf on Google Email

IEEE Chinese Association of Automation


A novel deep learning architecture for multi-source data fusion

A team of researchers proposes a deep learning architecture called CCDNN to learn correlated representations for multi-source data fusion. The method demonstrates promising performance, surpassing existing methods in reconstruction tasks and achieving better results in industrial fault diagnosis and remaining useful life cases.

SourceIEEE Chinese Association of Automation·JournalIEEE/CAA Journal of Automatica Sinica·TypeComputational simulation/modeling·DateMay 15, 2026

CASIA-EXO: A novel exoskeleton for adaptive motor learning in post-stroke rehabilitation

Researchers developed a novel exoskeleton CASIA-EXO with subject-adaptive control, enabling efficient motor relearning and enhancing neural plasticity. The system uses intention-based trajectory planning and performance-based intervention adaptation to individualize training trajectories and intervention levels.

SourceIEEE Chinese Association of Automation·JournalIEEE/CAA Journal of Automatica Sinica·TypeExperimental study·DateNov 11, 2025