Abstract
Peak detection and localization in a noisy signal with an unknown baseline is a fundamental task in signal processing applications such as spectroscopy. A current trend in signal processing is to reformulate traditional processing pipelines as (deep) neural networks that can be trained end-to-end. A trainable algorithm for baseline removal and peak localization can serve as an important module in such a processing pipeline. In practical applications, one of the most successful approaches to joint baseline suppression and peak localization is based on the continuous wavelet transform: We re-formulate this as a convolutional neural network (CNN) followed by a non-linear readout layer. On a synthetic benchmark we demonstrate that with sufficient training data, the CNN approach consistently outperforms the optimized continuous wavelet method by means of adapting to the spectral peak shape, noise level, and characteristics of the baseline. The CNN approach to peak localization shows great promise, as it can more efficiently leverage data to outperform the current state of the art, and can readily be extended and incorporated as a module in a larger neural network architecture.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 |
| Publisher | IEEE |
| Publication date | 1 May 2019 |
| Pages | 2757-2761 |
| Article number | 8682311 |
| ISBN (Electronic) | 9781479981311 |
| DOIs | |
| Publication status | Published - 1 May 2019 |
| Event | 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom Duration: 12 May 2019 → 17 May 2019 |
Conference
| Conference | 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 |
|---|---|
| Country | United Kingdom |
| City | Brighton |
| Period | 12/05/2019 → 17/05/2019 |
| Sponsor | IEEE |
Keywords
- Convolution Neural Network
- Peak detection
- Peak localization
- Spectroscopy
- Wavelet
Cite this
}
Peak Detection and Baseline Correction Using a Convolutional Neural Network. / Schmidt, Mikkel N.; Alstrom, Tommy S.; Svendstorp, Marcus; Larsen, Jan.
Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 . IEEE, 2019. p. 2757-2761 8682311.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
TY - GEN
T1 - Peak Detection and Baseline Correction Using a Convolutional Neural Network
AU - Schmidt, Mikkel N.
AU - Alstrom, Tommy S.
AU - Svendstorp, Marcus
AU - Larsen, Jan
PY - 2019/5/1
Y1 - 2019/5/1
N2 - Peak detection and localization in a noisy signal with an unknown baseline is a fundamental task in signal processing applications such as spectroscopy. A current trend in signal processing is to reformulate traditional processing pipelines as (deep) neural networks that can be trained end-to-end. A trainable algorithm for baseline removal and peak localization can serve as an important module in such a processing pipeline. In practical applications, one of the most successful approaches to joint baseline suppression and peak localization is based on the continuous wavelet transform: We re-formulate this as a convolutional neural network (CNN) followed by a non-linear readout layer. On a synthetic benchmark we demonstrate that with sufficient training data, the CNN approach consistently outperforms the optimized continuous wavelet method by means of adapting to the spectral peak shape, noise level, and characteristics of the baseline. The CNN approach to peak localization shows great promise, as it can more efficiently leverage data to outperform the current state of the art, and can readily be extended and incorporated as a module in a larger neural network architecture.
AB - Peak detection and localization in a noisy signal with an unknown baseline is a fundamental task in signal processing applications such as spectroscopy. A current trend in signal processing is to reformulate traditional processing pipelines as (deep) neural networks that can be trained end-to-end. A trainable algorithm for baseline removal and peak localization can serve as an important module in such a processing pipeline. In practical applications, one of the most successful approaches to joint baseline suppression and peak localization is based on the continuous wavelet transform: We re-formulate this as a convolutional neural network (CNN) followed by a non-linear readout layer. On a synthetic benchmark we demonstrate that with sufficient training data, the CNN approach consistently outperforms the optimized continuous wavelet method by means of adapting to the spectral peak shape, noise level, and characteristics of the baseline. The CNN approach to peak localization shows great promise, as it can more efficiently leverage data to outperform the current state of the art, and can readily be extended and incorporated as a module in a larger neural network architecture.
KW - Convolution Neural Network
KW - Peak detection
KW - Peak localization
KW - Spectroscopy
KW - Wavelet
U2 - 10.1109/ICASSP.2019.8682311
DO - 10.1109/ICASSP.2019.8682311
M3 - Article in proceedings
AN - SCOPUS:85068989965
SP - 2757
EP - 2761
BT - Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
PB - IEEE
ER -