Istvan Gergely Czibula

Istvan Gergely Czibula

Auto-generated profile, based on publicly available information

Istvan Gergely Czibula

Department of Computer Science, Babes-Bolyai University, Cluj-Napoca, Romania

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2014 in Information Sciences
Verified
Journal Article
Closed access
Gabriela CzibulaGabriela Czibula
Gabriela Czibula
ZOZsuzsanna Oneț-Marian
Zsuzsanna Oneț-Marian
ICIstvan Gergely Czibula
Istvan Gergely Czibula

10 January 2014 in Knowledge and Information Systems
Verified
Journal Article
Closed access
PDF file
GCGabriela Czibula
Gabriela Czibula
ZOZsuzsanna Oneț-Marian
Zsuzsanna Oneț-Marian
ICIstvan Gergely Czibula
Istvan Gergely Czibula

1 July 2019 in Expert Systems with Applications
Verified
Journal Article
Closed access
Gabriela CzibulaGabriela Czibula
Gabriela Czibula
ICIstvan Gergely Czibula
Istvan Gergely Czibula
DMDiana-Lucia Miholca
Diana-Lucia Miholca
LCLiana Maria Crivei
Liana Maria Crivei

1 September 2011
Verified
Conference Paper
Closed access
MBMaria-Iuliana Bocicor
Maria-Iuliana Bocicor
Gabriela CzibulaGabriela Czibula
Gabriela Czibula
ICIstvan-Gergely Czibula
Istvan-Gergely Czibula
The DNA fragment assembly is a very complex optimization problem important within many fields including bioinformatics and computational biology. The problem is NP-hard, that is why many computational techniques including computational intelligence algorithms were designed for finding good solutions for this problem. Since DNA fragment assembly is a crucial part of any sequencing project, researchers are still focusing on developing better assemblers. In this paper we aim at proposing a new reinforcement learning based model for solving the fragment assembly problem. We are particularly focusing on the DNA fragment assembly problem. Our model is based on a Q-learning agent-based approach. The experimental evaluation confirms a good performance of the proposed model and indicates the potential of our proposal.

11 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
AAAlexandra-Ioana Albu
Alexandra-Ioana Albu
Gabriela CzibulaGabriela Czibula
Gabriela Czibula
AMAndrei Mihai
Andrei Mihai
ICIstvan Gergely Czibula
Istvan Gergely Czibula
SBSorin Burcea
Sorin Burcea
AMAbdelkader Mezghani
Abdelkader Mezghani
With the recent increase in the occurrence of severe weather phenomena, the development of accurate weather nowcasting is of paramount importance. Among the computational methods that are used to predict the evolution of weather, deep learning techniques offer a particularly appealing solution due to their capability for learning patterns from large amounts of data and their fast inference times. In this paper, we propose a convolutional network for weather forecasting that is based on radar product prediction. Our model (NeXtNow) adapts the ResNeXt architecture that has been proposed in the computer vision literature to solve the spatiotemporal prediction problem. NeXtNow consists of an encoder–decoder convolutional architecture, which maps radar measurements from the past onto radar measurements that are recorded in the future. The ResNeXt architecture was chosen as the basis for our network due to its flexibility, which allows for the design of models that can be customized for specific tasks by stacking multiple blocks of the same type. We validated our approach using radar data that were collected from the Romanian National Meteorological Administration (NMA) and the Norwegian Meteorological Institute (MET) and we empirically showed that the inclusion of multiple past radar measurements led to more accurate predictions further in the future. We also showed that NeXtNow could outperform XNow, which is a convolutional architecture that has previously been proposed for short-term radar data prediction and has a performance that is comparable to those of other similar approaches in the nowcasting literature. Compared to XNow, NeXtNow provided improvements to the critical success index that ranged from 1% to 17% and improvements to the root mean square error that ranged from 5% to 6%.

14 July 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
Gabriela CzibulaGabriela Czibula
Gabriela Czibula
AMAndrei Mihai
Andrei Mihai
AAAlexandra-Ioana Albu
Alexandra-Ioana Albu
ICIstvan-Gergely Czibula
Istvan-Gergely Czibula
SBSorin Burcea
Sorin Burcea
AMAbdelkader Mezghani
Abdelkader Mezghani
Short-term quantitative precipitation forecast is a challenging topic in meteorology, as the number of severe meteorological phenomena is increasing in most regions of the world. Weather radar data is of utmost importance to meteorologists for issuing short-term weather forecast and warnings of severe weather phenomena. We are proposing AutoNowP, a binary classification model intended for precipitation nowcasting based on weather radar reflectivity prediction. Specifically, AutoNowP uses two convolutional autoencoders, being trained on radar data collected on both stratiform and convective weather conditions for learning to predict whether the radar reflectivity values will be above or below a certain threshold. AutoNowP is intended to be a proof of concept that autoencoders are useful in distinguishing between convective and stratiform precipitation. Real radar data provided by the Romanian National Meteorological Administration and the Norwegian Meteorological Institute is used for evaluating the effectiveness of AutoNowP. Results showed that AutoNowP surpassed other binary classifiers used in the supervised learning literature in terms of probability of detection and negative predictive value, highlighting its predictive performance.