Przemysław Juszczuk

Dr. Przemysław Juszczuk

Systems Research Institute, Polish Academy of Sciences, Warsaw, MA, Poland

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 October 2021 in International Journal of Information Management
Verified
Journal Article
Closed access
Jan KozakJan Kozak
Jan Kozak
KKKrzysztof Kania
Krzysztof Kania
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
MMMaciej Mitręga
Maciej Mitręga

1 December 2021 in Entropy
Verified
Journal Article
Open access
PDF file
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
Jan KozakJan Kozak
Jan Kozak
GDGrzegorz Dziczkowski
Grzegorz Dziczkowski
Szymon GłowaniaSzymon Głowania
Szymon Głowania
TJTomasz Jach
Tomasz Jach
Barbara ProbierzBarbara Probierz
Barbara Probierz
In the era of the Internet of Things and big data, we are faced with the management of a flood of information. The complexity and amount of data presented to the decision-maker are enormous, and existing methods often fail to derive nonredundant information quickly. Thus, the selection of the most satisfactory set of solutions is often a struggle. This article investigates the possibilities of using the entropy measure as an indicator of data difficulty. To do so, we focus on real-world data covering various fields related to markets (the real estate market and financial markets), sports data, fake news data, and more. The problem is twofold: First, since we deal with unprocessed, inconsistent data, it is necessary to perform additional preprocessing. Therefore, the second step of our research is using the entropy-based measure to capture the nonredundant, noncorrelated core information from the data. Research is conducted using well-known algorithms from the classification domain to investigate the quality of solutions derived based on initial preprocessing and the information indicated by the entropy measure. Eventually, the best 25% (in the sense of entropy measure) attributes are selected to perform the whole classification procedure once again, and the results are compared.

13 March 2020 in Entropy
Verified
Journal Article
Open access
PDF file
Jan KozakJan Kozak
Jan Kozak
KKKrzysztof Kania
Krzysztof Kania
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
Financial markets give a large number of trading opportunities. However, over-complicated systems make it very difficult to be effectively used by decision-makers. Volatility and noise present in the markets evoke a need to simplify the market picture derived for the decision-makers. Symbolic representation fits in this concept and greatly reduces data complexity. However, at the same time, some information from the market is lost. Our motivation is to answer the question: What is the impact of introducing different data representation on the overall amount of information derived for the decision-maker? We concentrate on the possibility of using entropy as a measure of the information gain/loss for the financial data, and as a basic form, we assume permutation entropy with later modifications. We investigate different symbolic representations and compare them with classical data representation in terms of entropy. The real-world data covering the time span of 10 years are used in the experiments. The results and the statistical verification show that extending the symbolic description of the time series does not affect the permutation entropy values.

1 November 2020 in Applied Soft Computing
Verified
Journal Article
Closed access
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
LKLech Kruś
Lech Kruś

10 April 2022 in Entropy
Verified
Journal Article
Open access
PDF file
Jan KozakJan Kozak
Jan Kozak
Barbara ProbierzBarbara Probierz
Barbara Probierz
KKKrzysztof Kania
Krzysztof Kania
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
Classification is one of the main problems of machine learning, and assessing the quality of classification is one of the most topical tasks, all the more difficult as it depends on many factors. Many different measures have been proposed to assess the quality of the classification, often depending on the application of a specific classifier. However, in most cases, these measures are focused on binary classification, and for the problem of many decision classes, they are significantly simplified. Due to the increasing scope of classification applications, there is a growing need to select a classifier appropriate to the situation, including more complex data sets with multiple decision classes. This paper aims to propose a new measure of classifier quality assessment (called the preference-driven measure, abbreviated p-d), regardless of the number of classes, with the possibility of establishing the relative importance of each class. Furthermore, we propose a solution in which the classifier’s assessment can be adapted to the analyzed problem using a vector of preferences. To visualize the operation of the proposed measure, we present it first on an example involving two decision classes and then test its operation on real, multi-class data sets. Additionally, in this case, we demonstrate how to adjust the assessment to the user’s preferences. The results obtained allow us to confirm that the use of a preference-driven measure indicates that other classifiers are better to use according to preferences, particularly as opposed to the classical measures of classification quality assessment.

17 June 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Szymon GłowaniaSzymon Głowania
Szymon Głowania
Jan KozakJan Kozak
Jan Kozak
Przemysław JuszczukPrzemysław Juszczuk
Przemysław Juszczuk
The analysis of sports data and the possibility of using machine learning in the prediction of sports results is an increasingly popular topic of research and application. The main problem, apart from choosing the right algorithm, is to obtain data that allow for effective prediction. The article presents a comprehensive KDD (Knowledge Discovery in Databases) approach that allows for the appropriate preparation of data for sports prediction on sports data. The first part of the article covers the subject of KDD and sports data. The next section presents an approach to developing a dataset on top football leagues. The developed datasets are the main purpose of the article and have been made publicly available to the research community. In the latter part of the article, an experiment with the results based on heterogeneous groups of classifiers and the developed datasets is presented.