Windowed State-Space Filters for Signal Detection and Separation

Wildhaber, Reto A.; Zalmai, Nour; Jacomet, Marcel; Loeliger, Hans-Andrea (2018). Windowed State-Space Filters for Signal Detection and Separation IEEE Transactions on Signal Processing, 66(14), pp. 3768-3783. 10.1109/TSP.2018.2833804

[img] Text
WindowedStateSpace.pdf - Supplemental Material
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (155kB) | Request a copy
[img] Text
stamp.jsp_tp=&arnumber=8355586&tag=1 - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (2kB) | Request a copy

This paper introduces a toolbox for model-based detection, separation, and reconstruction of signals that is especially suited for biomedical signals, such as electrocardiograms (ECGs) or electromyograms (EMGs). The modeling is based on autonomous linear state space models (LSSMs), which are localized with flexible windows. The models are fit to observations by minimizing the squared error while the use of LSSMs leads to efficient recursive error computations and minimizations. Multisection windows enable complex models, and per-sample weights enable multistage processing or adaptive smoothing. This paper is motivated by, and intended for, practical applications, for which several examples and tabulated cost computations are given.

Item Type:

Journal Article (Original Article)

Division/Institute:

Engineering and Information Technology > Institute for Human Centered Engineering (HUCE)
Engineering and Information Technology
BFH Centres > BFH Centre for Technologies in Sports and Medicine

Name:

Wildhaber, Reto A.;
Zalmai, Nour;
Jacomet, Marcel and
Loeliger, Hans-Andrea

Subjects:

R Medicine > R Medicine (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering

ISSN:

1053-587X

Language:

English

Submitter:

Marcel Jacomet

Date Deposited:

12 Feb 2020 09:00

Last Modified:

12 Feb 2020 09:00

Publisher DOI:

10.1109/TSP.2018.2833804

ARBOR DOI:

10.24451/arbor.8539

URI:

https://arbor.bfh.ch/id/eprint/8539

Actions (login required)

View Item View Item
Provide Feedback