Fractional fourier transform in time series prediction
buir.contributor.author | Koç, Emirhan | |
buir.contributor.author | Koç, Koç, Aykut | |
buir.contributor.orcid | Koç, Emirhan|0000-0002-7275-1570 | |
buir.contributor.orcid | Koç, Aykut|0000-0002-6348-2663 | |
dc.citation.epage | 2546 | en_US |
dc.citation.spage | 2542 | en_US |
dc.citation.volumeNumber | 29 | en_US |
dc.contributor.author | Koç, Emirhan | |
dc.contributor.author | Koç, Aykut | |
dc.date.accessioned | 2023-02-13T11:41:24Z | |
dc.date.available | 2023-02-13T11:41:24Z | |
dc.date.issued | 2022-12-09 | |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.description.abstract | Several signal processing tools are integrated into machine learning models for performance and computational cost improvements. Fourier transform (FT) and its variants, which are powerful tools for spectral analysis, are employed in the prediction of univariate time series by converting them to sequences in the spectral domain to be processed further by recurrent neural networks (RNNs). This approach increases the prediction performance and reduces training time compared to conventional methods. In this letter, we introduce fractional Fourier transform (FrFT) to time series prediction by RNNs. As a parametric transformation, FrFT allows us to seek and select better-performing transformation domains by providing access to a continuum of domains between time and frequency. This flexibility yields significant improvements in the prediction power of the underlying models without sacrificing computational efficiency. We evaluated our FrFT-based time series prediction approach on synthetic and real-world datasets. Our results show that FrFT gives rise to performance improvements over ordinary FT. | en_US |
dc.description.provenance | Submitted by Betül Özen (ozen@bilkent.edu.tr) on 2023-02-13T11:41:24Z No. of bitstreams: 1 Fractional_Fourier_Transform_in_Time_Series_Prediction.pdf: 930176 bytes, checksum: d047ef195d665287f0753a20306ec163 (MD5) | en |
dc.description.provenance | Made available in DSpace on 2023-02-13T11:41:24Z (GMT). No. of bitstreams: 1 Fractional_Fourier_Transform_in_Time_Series_Prediction.pdf: 930176 bytes, checksum: d047ef195d665287f0753a20306ec163 (MD5) Previous issue date: 202-12-09 | en |
dc.identifier.doi | 10.1109/LSP.2022.3228131 | en_US |
dc.identifier.eissn | 1558-2361 | |
dc.identifier.issn | 1070-9908 | |
dc.identifier.uri | http://hdl.handle.net/11693/111214 | |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | https://www.doi.org/10.1109/LSP.2022.3228131 | en_US |
dc.source.title | IEEE Signal Processing Letters | en_US |
dc.subject | Time series analysis | en_US |
dc.subject | Feature extraction | en_US |
dc.subject | Decoding | en_US |
dc.subject | Fourier transforms | en_US |
dc.subject | Training | en_US |
dc.subject | Wavelet transforms | en_US |
dc.subject | Recurrent neural networks | en_US |
dc.title | Fractional fourier transform in time series prediction | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Fractional_Fourier_Transform_in_Time_Series_Prediction.pdf
- Size:
- 908.38 KB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.69 KB
- Format:
- Item-specific license agreed upon to submission
- Description: