Machine Learning, Statistical Methods and Simulations for Signal-Sorting

Location: Sydney, NSW

Duration: 5 months

Please note: Due to the sensitivity and security of this project, students must have Australian Citizenship to apply. Students also need to be enrolled in one of the following universities; Macquarie University, The University of Newcastle, The University of New South Wales, The University of Sydney, University of Technology Sydney, University of Wollongong or Western Sydney University. Any applicants not meeting this requirement will automatically be deemed ineligible for this project.

This research internship is funded in partnership with New South Wales Defence Innovation Network.

Project Background

JEDS is exploring the application of machine-learning and statistical approaches to clustering problems. In particular, they are looking to explore innovative ways of sorting time-interleaved pulse train signals. It is intended that the outputs of the research performed during this internship will form the basis for a sophisticated signal-sorting process, that will be further developed in a larger project.

Research to be Conducted

Building off JEDS’ current work in simulating Radio Frequency (RF) environments and generating labelled data sets, the candidate will contribute by generalising the existing framework. From the labelled data sets, the distribution of the problem-space may be represented. The research will aim to identify and extract various features to assist in the clustering tasks utilising statistical heuristics and machine learning architectures.

Skills Required

We are looking for a PhD student with the following:


  • Expertise in un/supervised machine learning and statistical methods.
  • Experience implementing at least one or more of the following: Autoencoders; Self-Organising Maps; Bayesian statistics; Gaussian processes; Recurrent Neural-Networks; DBScan; k-means.
  • Experience implementing at least one or more of the following: Artificial Neural-Networks; Deep-learning; Random Forests.
  • Proficient in coding in at least one or more of the following (Python/C++/ MATLAB).
  • Ability to simulate (in software) complex physical models.


  • Experience using machine learning frameworks. (Tensor Flow, Theano, Caffe, mxnet, Pytorch, etc)
  • Exposure to coding in CUDA.
  • Ability to work in a team environment
  • Excellent English language communication skills.

Expected Outcomes

The interns will gain valuable exposure to the defence industry and expand their portfolio by applying their expertise to solving problems in industry. The expected project outcomes will include the following:

  • A review of the current state-of-the-art in un/supervised machine learning and statistical methods, and how they can be applied to the sorting of time-interleaved pulse train signals.
  • A general framework for simulating complex RF environments, with the ability to produce labelled data sets.
  • An ensemble of algorithms able to perform the sorting of time-interleaved signals.

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner.  The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

Applications Close

30 October 2019


APR – 1073