Petar S.
Machine Learning Engineer
Petar is a passionate researcher with 4 years of working experience. He is a very responsible and hardworking person with good organizational skills. Petar has worked on a wide variety of use cases as a Machine Learning engineer including Deep Learning algorithms for Optical Character Recognition (OCR) and Intelligent Word Recognition (IWR) for signature recognition, and recurrent neural network approach to improve the air quality index prediction.
Some of the scientific publications of Petar:
[1] P. Sekulić, M. Bajčeta, and S. Djukanović, “Retinal blood vessels segmentation using support vector machine and modified line detector,” in Informacione tehnologije 2017 -sadašnjost i budućnost, pp. 185–188, 2017.[2] P. Sekulić, S. Djukanović, and I. Djurović, “Detection of downy mildew in grapevine leaves using support vector
machine,” in Zbornik radova: Informacione tehnologije 2016, pp. 169–172, 2016.
[3] M. Bajčeta, P. Sekulić, S. Djukanović, T. Popovic, and V. Popović-Bugarin, “Retinal blood vessels segmentation
using ant colony optimization,” in 2016 13th Symposium on Neural Networks and Applications (NEUREL), pp. 1–6,
IEEE, 2016.
[4] F. Cassano, A. Casale, P. Regina, L. Spadafina, and P. Sekulić, “A recurrent neural network approach to improve
the air quality index prediction,” in International Symposium on Ambient Intelligence, pp. 36–44, Springer, 2019.
[5] M. Bajčeta, P. Sekulić, B. Krstajić, S. Djukanović, and T. Popović, “A private iot cloud platform for precision agriculture and ecological monitoring,” in International Conference on Electrical, Electronic and Computing Engineering (IcETRAN), 2016.
[6] E. Hot and P. Sekulić, “Compressed sensing mri using masked dct and dft measurements,” in 2015 4th Mediterranean Conference on Embedded Computing (MECO), pp. 323–326, IEEE, 2015.
Main expertise
Other skills
Python 3 years
PHP 2 years
TensorFlow 2 years
Selected experience
Employment
Machine Learning Scientist
Fleka - 1 year 1 month
- Working on a machine-learning algorithm to create a smart image database.
- Working on the implementation of Elasticsearch for the newspaper portals ”Pobjeda” and ”Analitika” and the official website of the Government of Montenegro.
Technologies:
- Technologies:
ElasticSearch
Software Developer
Robot Code - 8 months
- Worked on developing two information systems. One is for ordering and delivering food, while the other is for scheduling in beauty salons in Montenegro.
Technologies:
- Technologies:
Python
Machine Learning Engineer
Omnitech MNE - 1 year 5 months
- Worked on a Machine Learning system on the SeVaRA project. SeVaRA integrates an R&D project aimed at defining an innovative system for the calculation of an aggregated environmental risk index derived from multiple parameters summarized in:
- risk of consequences of very short-term weather events;
- risk of the geo-location according to historical data;
- risk associated with instability of soil or manufactured goods.
Machine Learning Engineer
Datum Solutions - 11 months
- Developing a Machine Learning system about signature recognition;
- Creating Deep Learning algorithms for Optical Character Recognition (OCR) and Intelligent Word Recognition (IWR).
Full-stack Developer
Fleka - 3 months
- Developing web applications for a bank.
Technologies:
- Technologies:
PHP
JavaScript
Laravel
Angular.js
Machine Learning Researcher
Faculty of Electrical Engineering - 1 year 6 months
- Worked on various Machine learning systems. Some of his projects were Retinal blood vessel segmentation and Detection of Downy Mildew in Grapevine Leaves.
Technologies:
- Technologies:
Python
TensorFlow
Education
MSc.Machine Learning
Faculty of Electrical Engineering in Podgorica · 2011 - 2017
Find your next developer within days, not months
We can help you deliver your product faster with an experienced remote developer. All from €31.90/hour. Only pay if you’re happy with your first week.
In a short 25-minute call, we would like to:
- Understand your development needs
- Explain our process to match you with qualified, vetted developers from our network
- Share next steps to finding the right match, often within less than a week
First developer starts within days. No aggressive sales pitch.