One of the most significant problems the Australian Sheep and Lamb industry faces today is Grass Seed Infestation (GSI), which occurs when seeds accumulate in the sheep's fleece and penetrate the skin, causing infection. Meat & Livestock Australia estimates that the yearly losses caused due to GSI are around AUD$47.5M (in Australia alone). Recently, we have demonstrated that terahertz spectroscopy and imaging can be utilised for early detection of GSI. This is possible because terahertz waves can penetrate through sheep wool and have the appropriate wavelength for identifying the seed. Moreover, terahertz waves have non-invasive and non-ionizing properties and are ideal for non-contact and standoff detection. To implement the technology, it is necessary to have a fast raster scan and enhance the signal quality. In this project, we aim to implement an image processing technique (e.g., background subtraction) to reduce the average time required for raster scans and enhance the signal-to-noise ratio. We will develop low-cost machine learning-enabled terahertz signal-processing solutions for a sheep auto drafter.

School

Electrical Engineering and Telecommunications

Research Area

Electrical engineering | Terahertz communications | Wireless communications | Signal processing | Photonics | Machine learning | Optimisation | Antenna and propagation | Computer simulations

The student on this multidisciplinary project will work with TELE group academic staff, Dr Shaghik Atakaramians (expert in terahertz) and Dr Deepak Mishra (expert in signal processing). The students will be part of Electrical Engineering and Telecommunications (EET) cutting-edge research groups: Terahertz Innovation Group and Cyber-Physical System Group.

The interested student needs to be good in computer programming along with having basic knowledge of photonics, wireless communications, machine learning and image processing. We will be providing lectures on advanced concepts as a part of the training for this project.

The project contains developing MATLAB codes for the post-processing of Terahertz images from raster scans with the following expected outcomes:

Outcome 1: identifying signal processing technique for enhancing the signal quality and identification of GSI.

Outcome 2: Implantation of technique in MATLAB.

Outcome 3: co-authorship in journal publication if successfully developed and implemented and mentoring and support for PhD application.

Other outcomes: A poster presentation and a brief video highlighting the main findings.

Senior Research Associate  Deepak Mishra
Senior Research Associate
  • C. Chaccour, M. N. Soorki, W. Saad, M. Bennis, P. Popovski and M. Debbah, "Seven Defining Features of Terahertz (THz) Wireless Systems: A Fellowship of Communication and Sensing," in IEEE Communications Surveys & Tutorials, vol. 24, no. 2, pp. 967-993, Secondquarter 2022, doi: 10.1109/COMST.2022.3143454.
  • "Winning against seeds, management tools for your sheep enterprise", Meat & Livestock Australia Ltd, 2013 [Online]. Available: http://www.mla.com.au