Detection of Dispersed Radio Pulses: A machine learning approach to candidate identification and classification

Abstract

Searching for extraterrestrial, transient signals in astronomical data sets is an active area of current research. However, machine learning techniques are lacking in the literature concerning single-pulse detection. This paper presents a new, two-stage approach for identifying and classifying dispersed pulse groups (DPGs) in single-pulse search output. The first stage identified DPGs and extracted features to characterize them using a new peak identification algorithm which tracks sloping tendencies around local maxima in plots of signal-to-noise ratio vs. dispersion measure. The second stage used supervised machine learning to classify DPGs. We created four benchmark data sets: one unbalanced and three balanced versions using three different imbalance treatments.We empirically evaluated 48 classifiers by training and testing binary and multiclass versions of six machine learning algorithms on each of the four benchmark versions. While each classifier had advantages and disadvantages, all classifiers with imbalance treatments had higher recall values than those with unbalanced data, regardless of the machine learning algorithm used. Based on the benchmarking results, we selected a subset of classifiers to classify the full, unlabelled data set of over 1.5 million DPGs identified in 42,405 observations made by the Green Bank Telescope. Overall, the classifiers using a multiclass ensemble tree learner in combination with two oversampling imbalance treatments were the most efficient; they identified additional known pulsars not in the benchmark data set and provided six potential discoveries, with significantly less false positives than the other classifiers.

13 pages, accepted for publication in MNRAS, ref. MN-15-1713-MJ.R3

References in corpus (29)

• SMOTE: Synthetic Minority Over-sampling Technique
• The ATNF Pulsar Catalogue
• A bright millisecond radio burst of extragalactic origin
• The ATNF Pulsar Catalogue
• The Five-Hundred-Meter Aperture Spherical Radio Telescope (FAST) Project
• Birth and Evolution of Isolated Radio Pulsars
• The Parkes Multibeam Pulsar Survey: I. Observing and Data Analysis Systems, Discovery and Timing of 100 Pulsars
• Transient radio bursts from rotating neutron stars
• The High Time Resolution Universe Pulsar Survey I: System configuration and initial discoveries
• Searches for Fast Radio Transients
• Arecibo Pulsar Survey Using ALFA. I. Survey Strategy and First Discoveries
• The Parkes Multibeam Pulsar Survey: V. Finding binary and millisecond pulsars
• Searching for pulsars using image pattern recognition
• Arecibo Pulsar Survey Using ALFA: Probing Radio Pulsar Intermittency and Transients
• Selection of radio pulsar candidates using artificial neural networks
• The Green Bank Telescope 350 MHz Drift-scan Survey I: Survey Observations and the Discovery of 13 Pulsars
• Further Searches for RRATs in the Parkes Multi-Beam Pulsar Survey
• Discovery of 28 pulsars using new techniques for sorting pulsar candidates
• The High Time Resolution Universe Survey - III. Single-pulse searches and preliminary analysis
• SPINN: a straightforward machine learning solution to the pulsar candidate selection problem
• Discovery and Follow-up of Rotating Radio Transients with the Green Bank and LOFAR Telescopes
• An Interference Removal Technique for Radio Pulsar Searches
• The High Time Resolution Universe Survey VI: An Artificial Neural Network and Timing of 75 Pulsars
• MeerKAT Key Project Science, Specifications, and Proposals
• Log-Normal Distributions in Gamma-Ray Burst Time Histories
• Luminosities of recycled radio pulsars in globular clusters
• PEACE: Pulsar Evaluation Algorithm for Candidate Extraction -- A software package for post-analysis processing of pulsar survey candidates
• A search for radio pulsars and fast transients in M31 using the WSRT
• A search for dispersed radio bursts in archival Parkes Multibeam Pulsar Survey data

Cited by in corpus (19)

• FETCH: A deep-learning based classifier for fast transient classification
• Applying Deep Learning to Fast Radio Burst Classification
• Separation of pulsar signals from noise with supervised machine learning algorithms
• Single-pulse classifier for the LOFAR Tied-Array All-sky Survey
• An investigation of pulsar searching techniques with the Fast Folding Algorithm
• The FAST Galactic Plane Pulsar Snapshot Survey: II. Discovery of 76 Galactic rotating radio transients and their enigma
• Pushchino multibeam pulsar search: I. Targeted search of weak pulsars
• A novel single-pulse search approach to detection of dispersed radio pulses using clustering and supervised machine learning
• Pulsar Candidates Classification with Deep Convolutional Neural Networks
• Pulsars Detection by Machine Learning with Very Few Features
• Gaia eclipsing binary and multiple systems. Supervised classification and self-organizing maps
• Applying saliency-map analysis in searches for pulsars and fast radio bursts
• A GPU based single-pulse search pipeline (GSP) with database and its application to the commensal radio astronomy FAST survey (CRAFTS)
• Vela Pulsar: Single Pulses Analysis with Machine Learning Techniques
• Search for fast radio transients using Arecibo drift-scan observations at 1.4 GHz
• Learn from every mistake! Hierarchical information combination in astronomy
• Scalable Solutions for Automated Single Pulse Identification and Classification in Radio Astronomy
• Dealing with the data imbalance problem on pulsar candidates sifting based on feature selection
• A machine learning-based approach towards the improvement of SNR of pulsar signals