Publication result detail

In-Bed Posture Classification Based on Sparse Representation in Redundant Dictionaries

MIHÁLIK, O.; SÝKORA, T.; HUSÁK, M.; FIEDLER, P.

Original Title

In-Bed Posture Classification Based on Sparse Representation in Redundant Dictionaries

English Title

In-Bed Posture Classification Based on Sparse Representation in Redundant Dictionaries

Type

Paper in proceedings (conference paper)

Original Abstract

Non-orthogonal signal representation using redundant dictionaries gradually gained popularity over the last decades. Sparse methods find major application in signal denoising, audio declipping, time-frequency analysis, and classification, to name a few. This paper is inspired by the exceptional results of sparse representation classification originally suggested for face recognition. We compare the method to other common classifiers using simulated as well as real datasets. In the latter the proposed method is tested with real pressure data from a bed equipped with a matrix of 30×11 pressure sensors. Here the method outperforms standard classification methods (surpassing 91 % accuracy) without need of parameter selection or special user’s skills. Furthermore it offers a means of dealing with occlusions, whose results are presented as well.

English abstract

Non-orthogonal signal representation using redundant dictionaries gradually gained popularity over the last decades. Sparse methods find major application in signal denoising, audio declipping, time-frequency analysis, and classification, to name a few. This paper is inspired by the exceptional results of sparse representation classification originally suggested for face recognition. We compare the method to other common classifiers using simulated as well as real datasets. In the latter the proposed method is tested with real pressure data from a bed equipped with a matrix of 30×11 pressure sensors. Here the method outperforms standard classification methods (surpassing 91 % accuracy) without need of parameter selection or special user’s skills. Furthermore it offers a means of dealing with occlusions, whose results are presented as well.

Keywords

sparse representation, redundant dictionary, SRC, posture classification, denoising

Key words in English

sparse representation, redundant dictionary, SRC, posture classification, denoising

Authors

MIHÁLIK, O.; SÝKORA, T.; HUSÁK, M.; FIEDLER, P.

RIV year

2023

Released

20.05.2022

Publisher

Elsevier

Book

17th IFAC Conference on Programmable Devices and Embedded Systems – PDeS 2022.

ISBN

2405-8963

Periodical

IFAC-PapersOnLine

Volume

55

Number

4

State

United Kingdom of Great Britain and Northern Ireland

Pages from

374

Pages to

379

Pages count

6

URL

https://doi.org/10.1016/j.ifacol.2022.06.062

Full text in the Digital Library

http://hdl.handle.net/11012/208166

BibTex

@inproceedings{BUT177806,
  author="Ondrej {Mihálik} and Tomáš {Sýkora} and Michal {Husák} and Petr {Fiedler}",
  title="In-Bed Posture Classification Based on Sparse Representation in Redundant Dictionaries",
  booktitle="17th IFAC Conference on Programmable Devices and Embedded Systems – PDeS 2022.",
  year="2022",
  journal="IFAC-PapersOnLine",
  volume="55",
  number="4",
  pages="374--379",
  publisher="Elsevier",
  doi="10.1016/j.ifacol.2022.06.062",
  issn="2405-8971",
  url="https://doi.org/10.1016/j.ifacol.2022.06.062"
}

Documents

Mihalik_PDeS_2022