Denoising Method of Pulsar Photon Signal Based on Recurrent Neural Network

Yu, Jiguo; Jin, Jing; Yu, Yuelong; Hu, Shengyi; Wang, Longqi; Zhao, Hongyang

doi:10.1109/icus48101.2019.8996040

Cited by 2 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If we already have pulsars with high SNRs before sending those profiles to the folding algorithm, then it is imperative that a lesser number of periods would be required for pulsar folding, which also implies that the observing telescope would need to observe the pulsars for a shorter duration of time to generate the same SNR after folding, and thus, we can generate high quality single pulse profiles using a combination of Machine Learning and Folding techniques in a more effective manner. Some head-start has already been made in this, where deep Recurrent neural networks have been used to denoise the pulsar profiles [13], but the initial SNR which was sent to the RNN algorithm was hovering around 6 in their work which is on the higher side as compared to our work.…”

Section: Discussionmentioning

confidence: 94%

“…In [10], a new, two-stage approach for identifying and classifying dispersed pulse groups (DPGs) in single-pulse search output is presented, and [11] has reduced the amount of pulsar candidates to be visually inspected by several orders of magnitude. In [12], a strategy to classify a big set of unbalanced pulsar data has been proposed, and [13] works on improving the SNR of a pulsar candidate through recurrent neural networks(RNN). Recent studies like [14] and [15] present a holistic review of machine learning based pulsar search algorithms [13] has focused on a similar problem, while working on the data from the Vela pulsar from the RXTE mission, where they have proposed a different (deep learning based) approach to boost the SNR of pulsars.…”

Section: Introductionmentioning

confidence: 99%

“…In [12], a strategy to classify a big set of unbalanced pulsar data has been proposed, and [13] works on improving the SNR of a pulsar candidate through recurrent neural networks(RNN). Recent studies like [14] and [15] present a holistic review of machine learning based pulsar search algorithms [13] has focused on a similar problem, while working on the data from the Vela pulsar from the RXTE mission, where they have proposed a different (deep learning based) approach to boost the SNR of pulsars. But their work improves the SNR of pulsars upto to 15-16 only, which may not be sufficient to study these pulsars efficiently and extract the pulse shape information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A machine learning-based approach towards the improvement of SNR of pulsar signals

Singh,

Pathak

2020

Preprint

View full text Add to dashboard Cite

Many pulsar folding algorithms are currently deployed to generate strong SNRs for the total intensity profiles. But they require large observation times to effectively improve the SNR. Over the years, new approaches to de-noise the pulsar total intensity data have sprung up, powered by Machine learning and Deep learning algorithms. Efforts are made to implement the currently proposed supervised machine learning models, such as ensembling techniques like Decision Tree Regressor, Random Forest Regressor,Adaboost Regressor, Gradient Boosting Regressor (GBR), K-Nearest Neighbours(KNN) and Support Vector Regressor (SVR) to find out the best possible algorithm which can work over a variety of pulsars from the EPN database of pulsars. All the data used in this work is extracted from the European Pulsar Network (EPN) database of pulsar profiles. The training dataset is obtained by post-processing of pulsar profile data from the EPN database and testing is performed on a preselected portion of the original data. The results are obtained by testing the above algorithms for 10 different pulsars including some historically significant ones, and the predicted profiles are plotted. We find that Gradient boosting regressor works the best in denoising pulsar data.. Through this work, we will try to emphasize that there is a reduction in number of periods of folding by 35-40% when a combination of machine learning models with the existing pulsar folding techniques like Fast Folding Algorithm(FFA) is employed, which can further reduce the pulsar observation times for the telescopes hunting for pulsars today.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A machine learning-based approach towards the improvement of SNR of pulsar signals

Singh,

Pathak

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…It has also been shown in [ 21 ] that the wavelet denoising methodology heavily relies on expertise and experience and is not compatible with an average processor. New approaches to increase the SNR of X-ray pulsar signals can be found in [ 25 ] with a machine learning method and in [ 26 ] with a recurrent neural network method, respectively. These two kinds of denoising strategies actually require high computational costs too.…”

Section: Introductionmentioning

confidence: 99%

X-ray Pulsar Signal Denoising Based on Variational Mode Decomposition

Chen

Zhao

Yan

2021

Entropy

View full text Add to dashboard Cite

Pulsars, especially X-ray pulsars detectable for small-size detectors, are highly accurate natural clocks suggesting potential applications such as interplanetary navigation control. Due to various complex cosmic background noise, the original pulsar signals, namely photon sequences, observed by detectors have low signal-to-noise ratios (SNRs) that obstruct the practical uses. This paper presents the pulsar denoising strategy developed based on the variational mode decomposition (VMD) approach. It is actually the initial work of our interplanetary navigation control research. The original pulsar signals are decomposed into intrinsic mode functions (IMFs) via VMD, by which the Gaussian noise contaminating the pulsar signals can be attenuated because of the filtering effect during signal decomposition and reconstruction. Comparison experiments based on both simulation and HEASARC-archived X-ray pulsar signals are carried out to validate the effectiveness of the proposed pulsar denoising strategy.

show abstract

Denoising Method of Pulsar Photon Signal Based on Recurrent Neural Network

Cited by 2 publications

References 10 publications

A machine learning-based approach towards the improvement of SNR of pulsar signals

A machine learning-based approach towards the improvement of SNR of pulsar signals

X-ray Pulsar Signal Denoising Based on Variational Mode Decomposition

Contact Info

Product

Resources

About