This paper presents a pattern classification method based on sparse representation. This new method bypasses the need for feature extraction and selection that are typically presented in the conventional classification methods, and performs classification using raw sensor signals directly. The performance of this new method is evaluated in the context of human physical activity assessment. Experimental results obtained from 105 human subjects demonstrate higher discriminative power than using the conventional k-nearest neighbor algorithm, verifying the effectiveness of the sparse representation method.
- Dynamic Systems and Control Division
Pattern Classification Based on Sparse Representation
Liu, S, Gao, RX, John, D, Staudenmayer, J, & Freedson, PS. "Pattern Classification Based on Sparse Representation." Proceedings of the ASME 2012 5th Annual Dynamic Systems and Control Conference joint with the JSME 2012 11th Motion and Vibration Conference. Volume 2: Legged Locomotion; Mechatronic Systems; Mechatronics; Mechatronics for Aquatic Environments; MEMS Control; Model Predictive Control; Modeling and Model-Based Control of Advanced IC Engines; Modeling and Simulation; Multi-Agent and Cooperative Systems; Musculoskeletal Dynamic Systems; Nano Systems; Nonlinear Systems; Nonlinear Systems and Control; Optimal Control; Pattern Recognition and Intelligent Systems; Power and Renewable Energy Systems; Powertrain Systems. Fort Lauderdale, Florida, USA. October 17–19, 2012. pp. 737-742. ASME. https://doi.org/10.1115/DSCC2012-MOVIC2012-8678
Download citation file: