Veljko Pejovic
I am an assistant professor at the Faculty of Computer and Information Science (FRI), University of Ljubljana, Slovenia. My research deals with mobile computing. Lately I have been focused on mobile sensing and machine learning, approximate mobile computing, and the security in the IoT domain.
Contact:
- email: Veljko.Pejovic [at] fri.uni-lj.si
- post: Room 3.15 Faculty of Computing and Information Science University of Ljubljana, Vecna pot 113, Ljubljana, Slovenia
Fully-funded PhD studies in Distributed Machine Learning in collaboration with KAUST!
KAUST (Saudi Arabia) and the University of Ljubljana are jointly working towards a new distributed deep learning paradigm that will ensure further proliferation of intelligent ubiquitous computing applications. Within this line of research, we are calling for applications for a fully-funded PhD fellowship in the area of distributed machine learning. More info!
Researcher positions (internship and PhD) in Approximate Mobile Computing!
I am looking for researchers passionate about making mobile devices more resource efficient to join us at the University of Ljubljana. More info!
Academic history:
- Postdoctoral Research Fellow, University of Birmingham, UK, 2012-2014
- PhD Computer Science, University of California Santa Barbara, USA, 2012
- BS Computer Science and Engineering, University of Belgrade, Serbia, 2006
News
- May 2022: Honoured that our paper Toward Cognitive Load Inference for Attention Management in Ubiquitous Systems was awarded the Best Paper Runner-up Award from IEEE Pervasive Computing!
- April 2022: Alina's paper on a novel compressive sensing - deep learning pipeline for mobile and IoT devices is accepted for presentation at ACM Computing Frontiers. Congratulations!
- March 2022: Octavian's poster on low-energy keyword spotting using slimmable convolutional neural networks was presented at TinyML summit.
- Feb 2022: Presented our group's research at KAUST
- Nov 2021: Our group visited Koper for the Slovenian HCI conference with Andraž, Amadej, and Anže presenting their work there.
- Sep 2021: Martin Gjoreski (USI, Lugano) and myself held an online workshop on Cognitive load Inference from Physiological Signals at Neuroergonomics Conference 2021 (video)
- June 2021: Two years ago we conducted research on the use of social roles for interruptibility management. We haven't had luck with publishing this, however, folks from Apple have shown interest in our work on a few occasions. Recently announced iOS 15 brings social role-driven notification managment to mobile devices. A coincidence? To offer a chance to learn more about our approach we put our pre-print on arXiv.
Recent publications
- We examine how contextual factors and a user's personality impact the perception of video playback in our latest preprint.
- Recently we started exploring the interplay of compressive sensing and deep learning. Alina's survey of this exciting domain is now on arXiv.
- Lessons learnt from the cognitive load inference ML challenge we organised last year are now summarised in our IEEE Access paper.
- Wi-Mind system for wireless cognitive load inference is presented in our latest Internation Journal of Human-Computer Interaction (IJHCI) paper.
- Our recent work on context-aware mobile neural network approximations is going to be presented at the EuroMLSys workshop with EuroSys 2021 in April 2021 [free registration].