Investigation of a Machine learning methodology for the SKA pulsar search pipeline

Abstract

The SKA pulsar search pipeline will be used for real time detection of pulsars. Modern radio telescopes such as SKA will be generating petabytes of data in their full scale of operation. Hence experience-based and data-driven algorithms become indispensable for applications such as candidate detection. Here we describe our findings from testing a state of the art object detection algorithm called Mask R-CNN to detect candidate signatures in the SKA pulsar search pipeline. We have trained the Mask R-CNN model to detect candidate images. A custom annotation tool was developed to mark the regions of interest in large datasets efficiently. We have successfully demonstrated this algorithm by detecting candidate signatures on a simulation dataset. The paper presents details of this work with a highlight on the future prospects.

References in corpus (15)

• Deep Residual Learning for Image Recognition
• k-Nearest Neighbour Classifiers: 2nd Edition (with Python examples)
• Feature Pyramid Networks for Object Detection
• Fourier Techniques for Very Long Astrophysical Time Series Analysis
• Mask R-CNN
• The High Time Resolution Universe Pulsar Survey I: System configuration and initial discoveries
• Fast R-CNN
• Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach
• Autoencoders
• The High Time Resolution Universe Survey VI: An Artificial Neural Network and Timing of 75 Pulsars
• Pulsar Searches with the SKA
• Performance Analysis Techniques for Real-time Broadband RFI Filtering System of uGMRT
• Implementing and Characterizing Real-time Broadband RFI Excision for the GMRT Wideband Backend
• Fast Search Techniques for High Energy Pulsars
• A Processing Pipeline for High Volume Pulsar Data Streams