Multiscale activity recognition algorithms to improve cross-subjects performance resilience in rehabilitation monitoring systems.

Journal: Computer methods and programs in biomedicine
Published Date: Apr 23, 2025

Abstract

BACKGROUND AND OBJECTIVE: This study introduces multiscale feature learning to develop more robust and resilient activity recognition algorithms, aimed at accurately tracking and quantifying rehabilitation exercises while minimizing performance disparities across subjects with varying motion-related characteristics.

Authors

  • Ciro Mennella
    Institute for High-Performance Computing and Networking (ICAR) - Research National Council of Italy (CNR), Italy. Electronic address: ciro.mennella@icar.cnr.it.
  • Massimo Esposito
    National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR), Via P. Castellino 111, 80131 Naples, Italy.
  • Giuseppe De Pietro
    Institute for High-Performance Computing and Networking (ICAR) - Research National Council of Italy (CNR), Italy.
  • Umberto Maniscalco
    Institute for High-Performance Computing and Networking (ICAR) - Research National Council of Italy (CNR), Italy. Electronic address: umberto.maniscalco@icar.cnr.it.

Keywords

External Resources

Popular Topics
Recent Journals