Please note this advert is for a Summer Internship as part of a collaboration between FIT, Arts and MADA. It is not an advertisement for an honours or masters thesis project at present. Please note you can ONLY apply for the internship via the Monash internship page.
Honours and Minor Thesis projects
In many branches of science (e.g., Artificial Intelligence, Engineering etc.), the modelling of the problem is done through the use of functions (e.g., f(x) = y). On a very high-level, we can think of Machine Learning as the problem of approximating function f from the pair of measurements (x,y), and Optimization as the problem of finding the value of input x that maximizes the output y given function f.
(This is *not* a minor thesis or honours project, but a summer scholarship project advert only available to existing Monash taught students).
This project provides an opportunity to build on an existing funded project that focussed on document annotation using a web platform. The idea of this project is to build systems that can help humans add labels to documents more rapidly.
Android is a mobile operating system that occupies 72.11% market share globally. As the most popular mobile operating system, the android mobile app industry has been active for over a decade, generating billions of dollars in revenue for Google and thousands of mobile app developers. Several third-party Android app stores in China are estimated to generate over $8 billion in yearly revenue. Meanwhile, the number of bugs and vulnerabilities in mobile apps is growing. In 2016, 24.7% of mobile apps contained at least one high-risk security flaw.
For most engineering applications we use metals and alloys (mixture of metals) for components that need to carry significant loads. These materials have an elastic limit beyond which they start to deform irreversibly. Such irreversible deformation, called plasticity, is generally of very discrete nature and the development of such discrete strain patterns, particularly during the early stage of plasticity, is very poorly understood.
The existing deep learning-based time series classification (TSC) algorithms have some success in multivariate time series, their accuracy is not high when we apply them to brain EEG time series (65-70%). This is because there is a large variation between EEG data of different subjects, so a TSC model cannot generalise on unseen subjects well. In this research project, we investigate self-supervised contrastive learning to encode the EEG data. This way we can better model the distribution of our EEG data before classifying it into different mental statuses. See recent work here .
Feedback is crucial to learning success; yet, higher education continues to struggle with effective feedback processes. It is important to recognise that feedback as a process requires both teachers and students to take active roles and work as ‘partners’. This project seeks to enhance effective feedback processes by 1) exploring the alignment between current feedback practice with student-centred feedback principles and 2) investigating into student experience with feedback. The overall project will adopt mixed methods explained as follows:
Turning Point’s National Ambulance Surveillance System is a surveillance database comprising enriched ambulance clinical data relating to alcohol and other substance use, suicidal and self-injurious thoughts and behaviours, and mental health-related harms in the Australian population. These data are used to inform policy and intervention design and are the subject of ever-increasing demand from academic professionals and units, government departments, and non-government organisations.
The number of kidney cancer patients is increasing each year. Computed Tomography (CT) scans of the kidneys are useful to assess tumors and study tumor morphology. Semantic segmentation techniques enable the identification of kidney and surrounding anatomy on the pixel level. This allows clinicians to provide accurate treatment plans and improve efficiency. The large size of CT volumes poses challenges for deep segmentation methods as it cannot be accommodated on a single GPU in its original resolution. Downsampling CT scans influences the segmentation performance.
Develop, implement, and test deep learning techniques for automatic classification of epileptic seizures using video data of seizures