K-SVD based Periodicity Dictionary Learning
- Creators
- Kulkarni, Pranav
- Vaidyanathan, P. P.
Abstract
It has recently been shown that periodicity in discrete-time data can be analyzed using Ramanujan sums and associated dictionaries. This paper explores the role of dictionary learning methods in the context of period estimation and periodic signal representation using dictionaries. It is shown that a well-known dictionary learning algorithm, namely K-SVD, is able to learn Ramanujan and Farey periodicity dictionaries from the noisy, sparse coefficient data generated from them without imposing any periodicity structure in the learning stage. This similarity between the learned dictionary and the underlying original periodicity dictionary reaffirms the power of the K-SVD in predicting the right dictionary from data without explicit application-specific constraints. The paper also examines how the choice of different parameter values affect the similarity of the learned dictionary to the underlying dictionary. Two versions of K-SVD along with different initializations are analyzed for their effect on representation and denoising error for the data.
Additional Information
© 2020 IEEE. This work was supported in parts by the ONR grant N00014-18-1-2390, the NSF grant CCF-1712633, and the California Institute of Technology.Attached Files
Published - 09443567.pdf
Files
Name | Size | Download all |
---|---|---|
md5:203946b09d70322d843c44008a409336
|
3.0 MB | Preview Download |
Additional details
- Eprint ID
- 109537
- Resolver ID
- CaltechAUTHORS:20210622-213746336
- N00014-18-1-2390
- Office of Naval Research (ONR)
- CCF-1712633
- NSF
- Caltech
- Created
-
2021-06-23Created from EPrint's datestamp field
- Updated
-
2021-06-23Created from EPrint's last_modified field