An Exploration of Deep Learning Solutions in Diverse Application Domains
Prof. Richard Sinnott1
1The University Of Melbourne, Melbourne, Australia
The Melbourne eResearch Group (www.eresearch.unimelb.edu.au) are involved in a multitude of projects, many of which are focused on big data and data analytics. Many research communities have much to benefit from artificial intelligence and especially from the application of deep learning to real worlld problems. This talk will cover diverse areas where practical solutions have been delivered to customers by the Melbourne eResearch Group including:
• Projects on real time traffic classification and vehicle types on the road network of Victoria;
• Counting of large scale crowds;
• Feral (individual) cat recognition and the unique challenges of disambiguating a given feral cat from many other feral cats in low resource settings, i.e. with only a few images;
• Detecting lameness in horses without the need for sensors to detect limb and/or head motion;
• Detection of chainsaw sounds to detect illegal harvesting of timber for Government organisations in Vicoria;
• Applying deep learning technology to identify and classify video content as a deepfake, and
•The classification of dog/cat species and their emotion.
The talk will cover a (very) brief background to deep learning and focus on the results that are now possible, with specific focus on projects requiring image detection and classification and the use of mobile applications. Demonstrations of the result of the case studies will be provided.
Professor Richard O. Sinnott is Professor of Applied Computing Systems and Director of the Melbourne eResearch Group at the University of Melbourne. He has been lead software engineer/architect on an extensive portfolio of national and international projects, with specific focus on those research domains requiring finer-grained access control (security) and those dealing with big data challenges. He has over 400 peer reviewed publications across a range of applied computing research areas.