Dr Mangalam Sankupellay ~ Adjunct Lecturer

Dr. Mangalam Sankupellay (BCompSc (Hons), MCompSc-Res., Ph.D) is a researcher and lecturer in the Discipline of Information Technology. Her areas of expertise lie in machine learning, signal processing, image processing and artificial intelligence. 

Mangalam's research focuses on developing software tools for automating long-term environmental monitoring.  These tools analyse acoustics data (e.g. forest sounds) to automatically extract relevant ecological events (e.g. the number and types of birds present).  They use machine-learning techniques such as deep learning, neural networks, and clustering algorithms.

Mangalam also investigates how the acoustics data for such environmental monitoring can be captured using Internet of Things (IoT) devices.

 

 

Current Research Projects:

• Recognising Animal Calls in Environmental Acoustic Recordings using Small Number of Labelled Calls: A Semi-Supervised Deep-Learning Approach. Funded by College of Science and Engineering ECR/MCR Research Support Scheme, Jul – Dec 18, AUD 11,956.90
• Ecological studies on cetaceans with a focus on the Irrawaddy dolphin (Orcaella brevirostris) around Penang Island (MM01_1819), in collaboration with University Science Malaysia. Funded by Ocean Park Conservation Foundation Hong Kong (OPCFHK), Jul 18 – Jun 20, ~AUD 44,500 (HK$ 259, 250)
• Programming Auto-marking Tool. Funded by JCU Learning and Teaching Grants (E-Assessment), May - Dec 18, AUD 9,990

 

Recently Completed Projects:

• AB3 - Australian Backyard Bird Box: Connecting People to the Environment. Funded by Research Infrastructure Block Grant,  James Cook University, Oct – Dec 16, AUD 26,000
• Persona Association of Students in a Peer-Facilitated Support for Learning Program. Funded by Learning and Teaching Grant, Queensland University of Technology,  Jan 16 – Jun 17, AUD 14,906.90

 

Mangalam's Patent: Process to design and fabricate a custom-fit implant

A process for the design, development and fabrication of a custom-made reconstruction and a custom-fit implant for medical applications.

 

Mangalam’s Publications is indexed: 

• dblp - Computer Science Biblography

• Semantic Scholar

• Scinapse

 

Community Engagement

• Townsville children using the latest technology to help scientists monitor birds

• With the Discipline of IT team, host the Young ICT Explorers Event in collaboration with SAP and CSIRO. YICTE is a non-profit “Technology Fair” competition, which has been created by SAP to encourage school students from grades 4 to 12 to create their best Information and Communication Technology (ICT) related projects.

Interests

Research

• Mangalam is interested in application of machine learning and deep learning techniques to analyse environmental acoustics recordings for long term environmental monitoring. Mangalam also investigates how Internet of Things (IoT) devices can be used for recording the acoustics data that can then be used for such environmental monitoring.
• Mangalam currently supervises one full time PhD candidate. If you are interested in studying for a Master or PhD with Mangalam, she specialises in the following areas: Machine Learning Deep Learning Artificial Intelligence Internet of Things Human Computer Interaction Visual Analytics Eco-Acoustics Please do contact Mangalam (mangalam.sankupellay@jcu.edu.au) or the Graduate Research School for further information. Research (Honours, Masters and PhD) students can start in either February or July.

Teaching

• Mangalam’s teaching interest lie in the areas of management and analysis of data for decision making. She utilizes project-based learning with real world examples and projects to increase student engagement

Experience

• 2014 to 2016 - Postdoctoral Research Associate, Queensland University of Technology (Brisbane, Australia)
• 2014 to 2016 - Associate Lecturer, Queensland University of Technology (Brisbane, Australia)
• 2003 to 2007 - Lecturer, University of Malaya (Kuala Lumpur, Malaysia)

Research Disciplines

• Computer vision and multimedia computation (4603)
• Data management and data science (4605)
• Machine learning (4611)

Socio-Economic Objectives

• Microeconomics (1505)

Awards

• 2017 - 1st prize winner, 3 Minute Thesis, Early Career Researcher, College of Business, Law and Governance
• 2016 - 1st prize winner, 3 Minute Thesis, Early Career Researcher, College of Business, Law and Governance
• 2008 to 2010 - International Postgraduate Research Scholarship
• 2007 to 2008 - Envedour Australia-Malaysia Award

Fellowships

• 2016 - Visiting Fellow, Queensland University of Technology

Memberships

• 2015 - Member - Women in Technology (WiT)
• 2015 - Member, Association for Computing Machinery

These are the most recent publications associated with this author. To see a detailed profile of all publications stored at JCU, visit ResearchOnline@JCU. Hover over Altmetrics badges to see social impact.

Journal Articles

• Andersen T, Belward S, Sankupellay M, Myers T and Chen C (in press) Reoptimisation strategies for dynamic vehicle routing problems with proximity-dependent nodes. TOP,
• Li X, Ghodosi H, Chen C, Sankupellay M and Lee I (2022) Improving Network-Based Anomaly Detection in Smart Home Environment. Sensors, 22 (15).
• Carroll J, Sankupellay M, Newcomb M, Rodgers J and Cook R (2018) GoSoapBox in public health tertiary education: a student response system for improving learning experiences and outcomes. Australasian Journal of Educational Technology, 34 (5). pp. 58-71

Book Chapters

• Carroll J, Sankupellay M, Cornford M and Bahir N (2016) 'Women on a Wiki': social constructivist analysis of the effectiveness of online collaborative spaces for reflective learning in women's health studies. In: Virtual Learning. InTechOpen, Rijeka, Croatia, pp. 87-99

Conference Papers

• Madanayake A, Sankupellay M and Lee I (2020) Profiling the natural environment using acoustics: long-term environment monitoring through cluster structure. Proceedings of the 3rd International Conference on Software Engineering and Information Management. In: ICSIM'20: 3rd International Conference on Software Engineering and Information Management, 12-15 January 2020, Sydney, NSW, Australia
• Efremova D, Sankupellay M and Konovalov D (2019) Data-efficient classification of birdcall through Convolutional Neural Networks transfer learning. Proceedings of the International Conference on Digital Image Computing. In: DICTA 2019: International Conference on Digital Image Computing: Techniques and Applications, 2-4 December 2019, Perth, WA, Australia
• Konovalov D, Saleh A, Bradley M, Sankupellay M, Marini S and Sheaves M (2019) Underwater fish detection with weak multi-domain supervision. Proceedings of the International Joint Conference on Neural Networks. In: 2019 IJCNN: International Joint Conference on Neural Networks, 14-19 July 2019, Budapest, Hungary
• Lapico A, Sankupellay M, Cianciullo L, Myers T, Konovalov D, Jerry D, Toole P, Jones D and Zenger K (2019) Using image processing to automatically measure pearl oyster size for selective breeding. Proceedings of the International Conference on Digital Image Computing. In: DICTA 2019: International Conference on Digital Image Computing: Techniques and Applications, 2-4 December 2019, Perth, WA, Australia
• Wang J, Sankupellay M, Konovalov D, Towsey M and Roe P (2019) Social network analysis of an acoustic environment: the use of visualised data to characterise natural habitats. Proceedings of the International Conference on Digital Image Computing. In: DICTA 2019: International Conference on Digital Image Computing: Techniques and Applications, 2-4 December 2019, Perth, WA, Australia
• Hardy D, Myers T and Sankupellay M (2018) Cohorts and cultures: developing future design thinkers. Proceedings of the 20th Australasian Computing Education Conference. In: ACE2018: 20th Australasian Computing Education Conference, 30 January - 2 February 2018, Brisbane, QLD, Australia
• Sankupellay M and Konovalov D (2018) Bird call recognition using deep convolutional neural network, ResNet-50. Proceedings of the Australian Acoustical Society Conference. In: AAS2018: Acoustics 2018: hear to listen, 6-9 November 2018, Adelaide, SA, Australia
• Sankupellay M, Kalma A, Magin S, Cappadonna J, Roe P and Brereton M (2017) BirdSound: enticing urban dwellers to engage with local birds around their home. Procedings of the 29th Australian Conference on Computer-Human Interaction (OzCHI 2017). In: OzCHI 2017: Human Nature, 28 November - 01 December 2017, Brisbane, QLD, Australia

More

ResearchOnline@JCU stores 21+ research outputs authored by Dr Mangalam Sankupellay from 2011 onwards.

Advisory Accreditation: I can be on your Advisory Panel as a Primary or Secondary Advisor.

These Higher Degree Research projects are either current or by students who have completed their studies within the past 5 years at JCU. Linked titles show theses available within ResearchOnline@JCU.

Current

• Dynamic and stochastic vehicle routing for autonomous weed control. (PhD , Secondary Advisor)
• Contact mining from spatio-temporal trajectories (PhD , Secondary Advisor)