Grega Vrbančič

Grega Vrbančič
Assistant Professor , Intelligent Systems Laboratory
Title:Assistant Professor, PhD. of Computer Science
E-mail:grega.vrbancic@um.si
Telephone:0038622204711
Room:G2‐1N.07 Laboratorij Newton
Contact hours:Link
Book your timeslot
LinkedIn profile:LinkedIn

Main research interests

  • Machine Learning
  • Deep Learning
  • Data Science

Publications

The full report can be found on COBISS.

Selected papers:

  • Vrbančič, G. and Podgorelec, V., 2021. Efficient ensemble for image-based identification of Pneumonia utilizing deep CNN and SGD with warm restarts. Expert Systems with Applications, p.115834. DOI: 10.1016/j.eswa.2021.115834
  • Podgorelec, V., Pečnik, Š. and Vrbančič, G., 2020. Classification of Similar Sports Images Using Convolutional Neural Network with Hyper-Parameter Optimization. Applied Sciences, 10(23), p.8494. DOI: 10.3390/app10238494
  • Vrbančič, G. and Podgorelec, V., 2020. Transfer Learning With Adaptive Fine-Tuning. IEEE Access, 8, pp.196197-196211. DOI: 10.1109/ACCESS.2020.3034343
  • Vrbančič, G., Fister Jr, I. and Podgorelec, V., 2019. Parameter setting for deep neural networks using swarm intelligence on phishing websites classification. International Journal on Artificial Intelligence Tools, 28(06), p.1960008. DOI: 10.1142/S021821301960008X
  • Vrbancic, G. and Podgorelec, V., 2019. Automatic Detection of Heartbeats in Heart Sound Signals Using Deep Convolutional Neural Networks. Elektronika ir Elektrotechnika, 25(3), pp.71-76. DOI: 10.5755/j01.eie.25.3.23680
  • Vrbancic, G. and Podgorelec, V., 2018. Automatic classification of motor impairment neural disorders from EEG signals using deep convolutional neural networks. Elektronika ir Elektrotechnika, 24(4), pp.3-7. DOI: 10.5755/j01.eie.24.4.21469

Reviewer

  • IEEE Access
  • Expert Systems with Applications
  • Plos One
  • Scientific Reports
  • International Journal of Bio-Inspired Computation
  • Data in Brief

The full list of reviews can be found on Publons.

Bookmark the permalink.

Comments are closed.