QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series
Nonstationary time series are ubiquitous in almost all natural and engineering systems. Capturing the time-varying signatures from nonstationary time series is still a challenging problem for data mining. Quadratic Time-Frequency Distribution (TFD) provides a powerful tool to analyze these data. How...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020031 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544399834218496 |
|---|---|
| author | Tao Chen Yang Jiao Lei Xie Hongye Su |
| author_facet | Tao Chen Yang Jiao Lei Xie Hongye Su |
| author_sort | Tao Chen |
| collection | DOAJ |
| description | Nonstationary time series are ubiquitous in almost all natural and engineering systems. Capturing the time-varying signatures from nonstationary time series is still a challenging problem for data mining. Quadratic Time-Frequency Distribution (TFD) provides a powerful tool to analyze these data. However, they suffer from Cross-Term (CT) issues that impair the readability of TFDs. Therefore, to achieve high-resolution and CT-free TFDs, an end-to-end architecture termed Quadratic TF-Net (QTFN) is proposed in this paper. Guided by classic TFD theory, the design of this deep learning architecture is heuristic, which firstly generates various basis functions through data-driven. Thus, more comprehensive TF features can be extracted by these basis functions. Then, to balance the results of various basis functions adaptively, the Efficient Channel Attention (ECA) block is also embedded into QTFN. Moreover, a new structure called Muti-scale Residual Encoder-Decoder (MRED) is also proposed to improve the learning ability of the model by highly integrating the multi-scale learning and encoder-decoder architecture. Finally, although the model is only trained by synthetic signals, both synthetic and real-world signals are tested to validate the generalization capability and superiority of the proposed QTFN. |
| format | Article |
| id | doaj-art-4d5ba1f5935f489d8f39ed8a92de5f6e |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-4d5ba1f5935f489d8f39ed8a92de5f6e2025-02-03T10:19:58ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017390591910.26599/BDMA.2024.9020031QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time SeriesTao Chen0Yang Jiao1Lei Xie2Hongye Su3State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, ChinaShenzhen Key Laboratory of Intelligent Bioinformatics, and College of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaState Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, ChinaNonstationary time series are ubiquitous in almost all natural and engineering systems. Capturing the time-varying signatures from nonstationary time series is still a challenging problem for data mining. Quadratic Time-Frequency Distribution (TFD) provides a powerful tool to analyze these data. However, they suffer from Cross-Term (CT) issues that impair the readability of TFDs. Therefore, to achieve high-resolution and CT-free TFDs, an end-to-end architecture termed Quadratic TF-Net (QTFN) is proposed in this paper. Guided by classic TFD theory, the design of this deep learning architecture is heuristic, which firstly generates various basis functions through data-driven. Thus, more comprehensive TF features can be extracted by these basis functions. Then, to balance the results of various basis functions adaptively, the Efficient Channel Attention (ECA) block is also embedded into QTFN. Moreover, a new structure called Muti-scale Residual Encoder-Decoder (MRED) is also proposed to improve the learning ability of the model by highly integrating the multi-scale learning and encoder-decoder architecture. Finally, although the model is only trained by synthetic signals, both synthetic and real-world signals are tested to validate the generalization capability and superiority of the proposed QTFN.https://www.sciopen.com/article/10.26599/BDMA.2024.9020031time-frequency analysis (tfa)multi-scale residual encoder-decoder (mred)quadratic time-frequency distribution (tfd) |
| spellingShingle | Tao Chen Yang Jiao Lei Xie Hongye Su QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series Big Data Mining and Analytics time-frequency analysis (tfa) multi-scale residual encoder-decoder (mred) quadratic time-frequency distribution (tfd) |
| title | QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series |
| title_full | QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series |
| title_fullStr | QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series |
| title_full_unstemmed | QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series |
| title_short | QTFN: A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series |
| title_sort | qtfn a general end to end time frequency network to reveal the time varying signatures of the time series |
| topic | time-frequency analysis (tfa) multi-scale residual encoder-decoder (mred) quadratic time-frequency distribution (tfd) |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020031 |
| work_keys_str_mv | AT taochen qtfnageneralendtoendtimefrequencynetworktorevealthetimevaryingsignaturesofthetimeseries AT yangjiao qtfnageneralendtoendtimefrequencynetworktorevealthetimevaryingsignaturesofthetimeseries AT leixie qtfnageneralendtoendtimefrequencynetworktorevealthetimevaryingsignaturesofthetimeseries AT hongyesu qtfnageneralendtoendtimefrequencynetworktorevealthetimevaryingsignaturesofthetimeseries |