Viktoras Chadysas

Dr. Viktoras Chadysas

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
16 November 2018 in Sustainability
Verified
Journal Article
Open access
PDF file
MVMarina Valentukeviciene
Marina Valentukeviciene
LBLina Bagdžiūnaitė-Litvinaitienė
Lina Bagdžiūnaitė-Litvinaitienė
VCViktoras Chadysas
Viktoras Chadysas
ALAndrius Litvinaitis
Andrius Litvinaitis
The trans-boundary area between the Europe Union and other countries is highly susceptible to changes in water quality and variations in the potential pollution load that could influence its eco-systems significantly. The Neris (Viliya) River is one of the biggest surface water bodies in Lithuania and Belarus with an ecologically important area protected by international legislation. The study was aimed at evaluating the impacts of integrated pollution on water quality of the Neris River taking into account different storm-water flows and ecological scenarios. For this purpose, qualitative and quantitative statistical evaluation was set up and calculation was done; different integrated pollution loads of the catchment area were estimated. The evaluation considered a decrease in river discharge due to changes in the regional storm-water flow and technological development that should lead to the growing covered surface and a reduction in the untreated storm-water flows. The obtained results indicated that, in the case of storm-water treatment, the total nitrate and phosphate concentrations will decrease, while in the cases of changes in combined suspended solid, the concentration of nutrients will decrease. Thus, a trans-boundary storm-water treatment plant of the Viliya River is required as it should eliminate pollution accumulation and restore its acceptable environmental status. A coordinated international project for the entire catchment of the Neris (Viliya) River based on the specifications and requirements of the EU Water Framework Directive (EU 2000) should be developed and implemented. Subsequently, ecological river-use policies should be established at the international level, which should offer considerable perspectives for the sustainable development of the area.

17 May 2022 in Informatica
Verified
Journal Article
Open access
PDF file
ABAndrej Bugajev
Andrej Bugajev
RKRima Kriauzienė
Rima Kriauzienė
OVOlegas Vasilecas
Olegas Vasilecas
VCViktoras Chadysas
Viktoras Chadysas
One of the biggest difficulties in telecommunication industry is to retain the customers and prevent the churn. In this article, we overview the most recent researches related to churn detection for telecommunication companies. The selected machine learning methods are applied to the publicly available datasets, partially reproducing the results of other authors and then it is applied to the private Moremins company dataset. Next, we extend the analysis to cover the exiting research gaps: the differences of churn definitions are analysed, it is shown that the accuracy in other researches is better due to some false assumptions, i.e. labelling rules derived from definition lead to very good classification accuracy, however, it does not imply the usefulness for such churn detection in the context of further customer retention. The main outcome of the research is the detailed analysis of the impact of the differences in churn definitions to a final result, it was shown that the impact of labelling rules derived from definitions can be large. The data in this study consist of call detail records (CDRs) and other user aggregated daily data, 11000 user entries over 275 days of data was analysed. 6 different classification methods were applied, all of them giving similar results, one of the best results was achieved using Gradient Boosting Classifier with accuracy rate 0.832, F-measure 0.646, recall 0.769.

1 June 2020 in Entrepreneurship and Sustainability Issues
Verified
Journal Article
Open access
Rita Remeikien4Rita Remeikien4
Rita Remeikien4
LGLigita Gaspareniene
Ligita Gaspareniene
VCViktoras Chadysas
Viktoras Chadysas
EREvaldas Raistenskis
Evaldas Raistenskis
Entrepreneurship and Sustainability Issues is a peer-reviewed journal which publishes original research papers and case studies

12 July 2023 in Molecules
Verified
Journal Article
Open access
PDF file
MVMarina Valentukeviciene
Marina Valentukeviciene
Ieva AndriulaityteIeva Andriulaityte
Ieva Andriulaityte
VCViktoras Chadysas
Viktoras Chadysas
One consequence of intensive outdoor disinfection using chlorinated compounds is environmental pollution. It has been found that disinfectants are the most effective tool to avoid the spread of infections and viruses. Studies have shown that the use of chlorine-based disinfectants (sodium hypochlorite) leaves residual chlorine and other disinfection byproducts in the environment. They also have harmful effects on, inter alia, water quality, ecosystems, as well as exacerbating the corrosion of surfaces. To meet regulatory standards, monitoring of the presence of residual chlorine in the environment is vitally important. The aim of this study is to analyse the occurrence of residual chlorine in stormwater after outdoor disinfection using sodium hypochlorite and to investigate its interaction with different microelements as well their possible impacts. Stormwater samples collected at permanently disinfected locations were analysed via X-ray absorption spectroscopy. The concentrations of Cl and the following elements Na, Si, K, Ca, Cr, Fe, Ni, Cu, Zn were detected and their relationship with chlorine was determined using the Python programming language. The research presents Cl concentration values (%) that vary from 0.02 to 0.04. The results of the modelling revealed strong correlations between Cl and Fe (value 0.65) and Ca (value −0.61) and the occurrence of CaCl2 and FeCl3. The strong relationship between Cl and Fe explains the significant increase in surface corrosion after disinfection with chlorine-based substances.

27 June 2022
Verified
Book Chapter
Closed access
PDF file
VCViktoras Chadysas
Viktoras Chadysas
ABAndrej Bugajev
Andrej Bugajev
RKRima Kriauzienė
Rima Kriauzienė
OVOlegas Vasilecas
Olegas Vasilecas

5 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ABAndrej Bugajev
Andrej Bugajev
RKRima Kriauzienė
Rima Kriauzienė
VCViktoras Chadysas
Viktoras Chadysas
Predicting customer churn is essential for telecommunications companies to maintain profitability. However, training models on historical models leads to performance degradation when they are applied to future conditions—a phenomenon known as concept drift. We employ a sliding-window approach that separates the training and testing time windows, creating a future-based “true test”. Using unique real data, we show that a CatBoost classifier model trained on older data can remain relevant when new, unseen intervals are used. A key innovation of our work is the use of 40-day “partial churn” labels; a model trained on these labels accurately predicts 90-day churn by simply adjusting the decision threshold. Out of the six modeled scenarios, in the main realistic scenario, CatBoost retained an accuracy above 0.798 and an F1 of near 0.704, reflecting its robustness even under real-world delays and potential drift. Overall, our findings emphasize that models do not necessarily “expire” with time; rather, their performance varies according to when they are tested. This research underscores the importance of a truly future-based evaluation (instead of artificial splits) and offers practical guidance for earlier churn detection when facing real-world data delays.