SPINN: a straightforward machine learning solution to the pulsar candidate selection problem

Abstract

We describe SPINN (Straightforward Pulsar Identification using Neural Networks), a high-performance machine learning solution developed to process increasingly large data outputs from pulsar surveys. SPINN has been cross-validated on candidates from the southern High Time Resolution Universe (HTRU) survey and shown to identify every known pulsar found in the survey data while maintaining a false positive rate of 0.64%. Furthermore, it ranks 99% of pulsars among the top 0.11% of candidates, and 95% among the top 0.01%. In conjunction with the PEASOUP pipeline (Barr et al., in prep.), it has already discovered four new pulsars in a re-processing of the intermediate Galactic latitude area of HTRU, three of which have spin periods shorter than 5 milliseconds. SPINN's ability to reduce the amount of candidates to visually inspect by up to four orders of magnitude makes it a very promising tool for future large-scale pulsar surveys. In an effort to provide a common testing ground for pulsar candidate selection tools and stimulate interest in their development, we also make publicly available the set of candidates on which SPINN was cross-validated.

Accepted for publication in MNRAS, 13 pages, 9 figures. To obtain the set of pulsar candidates we used to train SPINN see http://astronomy.swin.edu.au/~vmorello/

References in corpus (12)

• The ATNF Pulsar Catalogue
• The ATNF Pulsar Catalogue
• The Parkes Multibeam Pulsar Survey: I. Observing and Data Analysis Systems, Discovery and Timing of 100 Pulsars
• The High Time Resolution Universe Pulsar Survey I: System configuration and initial discoveries
• Pulsar searches and timing with the SKA
• The Parkes Multibeam Pulsar Survey: V. Finding binary and millisecond pulsars
• Searching for pulsars using image pattern recognition
• Selection of radio pulsar candidates using artificial neural networks
• Searches for Giant Pulses from Extragalactic Pulsars
• Discovery of 28 pulsars using new techniques for sorting pulsar candidates
• The High Time Resolution Universe Survey VI: An Artificial Neural Network and Timing of 75 Pulsars
• PEACE: Pulsar Evaluation Algorithm for Candidate Extraction -- A software package for post-analysis processing of pulsar survey candidates

Cited by in corpus (23)

• Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach
• Classifying Radio Galaxies with Convolutional Neural Network
• A Hybrid Ensemble method for Pulsar Candidate Classification
• The SUrvey for Pulsars and Extragalactic Radio Bursts I: Survey Description and Overview
• The High Time Resolution Universe survey XIV: Discovery of 23 pulsars through GPU-accelerated reprocessing
• Separation of pulsar signals from noise with supervised machine learning algorithms
• Detection of Dispersed Radio Pulses: A machine learning approach to candidate identification and classification
• FAST discovery of an extremely radio-faint millisecond pulsar from the Fermi-LAT unassociated source 3FGL J0318.1+0252
• Concat Convolutional Neural Network for Pulsar Candidate Selection
• Pulsar Candidates Classification with Deep Convolutional Neural Networks
• Discovery of 37 new pulsars through GPU-accelerated reprocessing of archival data of the Parkes Multibeam Pulsar Survey
• Pulsars Detection by Machine Learning with Very Few Features
• The SUrvey for Pulsars and Extragalactic Radio Bursts V: Recent Discoveries and Full Timing Solutions
• Pulsar Candidate Sifting Using Multi-input Convolution Neural Networks
• Vela Pulsar: Single Pulses Analysis with Machine Learning Techniques
• Machine Learning Pipeline for Pulsar Star Dataset
• Simulating high-time resolution radio-telescope observations
• Probabilistic learning for pulsar classification
• A machine learning-based approach towards the improvement of SNR of pulsar signals
• Dealing with the data imbalance problem on pulsar candidates sifting based on feature selection
• A simulation experiment of a pipeline based on machine learning for neutral hydrogen intensity mapping surveys
• Early-fusion Based Pulsar Identification with Smart Under-sampling
• A Method for Pulsar Searching: Combining a Two-dimensional Autocorrelation Profile Map and a Deep Convolutional Neural Network