Skip to main content

A mobile ontology-based Platform for sharing and reuse of deep learning models

Primary supervisor

Pari Delir Haghighi

Co-supervisors

  • Dr Yuxin Zhang (Monash Engineering)
  • A/Prof Prem Jayaraman (Swinburne University)

In recent years, the use of deep learning (DL) models has attracted significant attention in healthcare domain
due to its ability to provide far accurate insights than other machine learning-based techniques. Although DL models have different architectures, the underlying concepts that describe the properties and relations are similar and could benefit from an ontology-based representation to enable sharing and reuse.

Student cohort

Single Semester
Double Semester

Aim/outline

This project aims to extend an existing ontology-based platform for sharing and reuse of existing deep learning models to enable novice researchers to download and run DL models on their mobile phones using real-time sensor data, e.g. the mobile phone's accelerometer data. 

URLs/references

  1. J. Wang, Y. Chen, S. Hao, X. Peng, and L. Hu, “Deep learning for sensor-based activity recognition: A survey,” Pattern Recognition Letters, vol. 119, pp. 3–11, Mar. 2019. 
  2. V. Jindal, J. Birjandtalab, M. B. Pouyan, and M. Nourani, “An adaptive deep learning approach for PPG-based identification,” in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Aug. 2016, pp. 6401–6404, iSSN: 1558-4615.

Required knowledge

  • Strong programming experience 
  • Mobile app development 
  • Deep learning