@misc{WitulskaZaleskaKremzerOsiadaczetal., author = {Witulska, Justyna and Zaleska, Anna and Kremzer-Osiadacz, Natalia and Wyłomańska, Agnieszka and Jabłoński, Ireneusz}, title = {Robust variance estimators in application to segmentation of measurement data distorted by impulsive and non-Gaussian noise}, series = {Measurement}, volume = {239}, journal = {Measurement}, publisher = {Elsevier BV}, issn = {0263-2241}, doi = {10.1016/j.measurement.2024.115472}, pages = {21}, language = {en} } @misc{DulasWitulskaWyłomańskaetal., author = {Dulas, Dominik and Witulska, Justyna and Wyłomańska, Agnieszka and Jabłoński, Ireneusz and Walkowiak, Krzysztof}, title = {Data-driven model for sliced 5G network dimensioning and planning, featured with forecast and "what-if" analysis}, series = {IEEE Access}, volume = {12}, journal = {IEEE Access}, number = {5_Supplement}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, address = {M{\"u}nchen}, isbn = {9783446425606}, issn = {2169-3536}, doi = {10.1109/ACCESS.2024.3383324}, pages = {50067 -- 50082}, language = {en} } @misc{WitulskaHendlerKasprowiczetal., author = {Witulska, Justyna and Hendler, Marta and Kasprowicz, Magdalena and Czosnyka, Marek and Wyłomańnska, Agnieszka and Jabłoński, Ireneusz}, title = {Framework for unveiling change points in multivariate signals with non-Gaussian patterns}, series = {2025 33rd European Signal Processing Conference (EUSIPCO)}, journal = {2025 33rd European Signal Processing Conference (EUSIPCO)}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-9-4645-9362-4}, issn = {1230-3496}, doi = {10.23919/EUSIPCO63237.2025.11226194}, pages = {2582 -- 2586}, abstract = {This study focuses on the challenge of monitoring and managing complex systems by distinguishing sequential states while observing multiple variables. We introduce a methodology for change point detection in multivariate data with nonGaussian distribution based on fusion techniques, underpinned by multivariate statistical test based on the Cramer-von-Mises approach. To evaluate the performance of our method, we conducted a comparative analysis with established baseline techniques, namely e-Divisive and Kernel Change Point Analysis methods, using a multivariate sub-Gaussian distribution. Finally, we demonstrate the practical applicability of our approach by showing its ability to reduce invasiveness in detecting intracranial hypertension events during neurointensive monitoring of traumatic brain injury patient by identifying the temporal distribution structure in multivariate data.}, language = {en} } @misc{WitulskaHendlerKasprowiczetal., author = {Witulska, Justyna and Hendler, Marta and Kasprowicz, Magdalena and Czosnyka, Marek and Jabłoński, Ireneusz and Wyłomańska, Agnieszka}, title = {Identifying the temporal distribution structure in multivariate data for time-series segmentation based on two-sample test}, series = {Information fusion}, volume = {125}, journal = {Information fusion}, publisher = {Elsevier BV}, address = {Amsterdam}, issn = {1566-2535}, doi = {10.1016/j.inffus.2025.103445}, pages = {1 -- 21}, abstract = {The research tackles the challenge of monitoring and managing a complex system by distinguishing consecutive states while observing multiple variables, especially in non-Gaussian environment. We introduce a novel methodology - MIDAST - aimed at fusion-based multivariate data segmentation and grounded in multivariate statistical tests, including the Kolmogorov-Smirnov test, a Maximum Mean Discrepancy-based test, and a kernel-based test. The performance of the method is evaluated through a comparative analysis against selected baseline techniques, specifically e-Divisive and Kernel Change Point Analysis methods, with a focus on segmentation accuracy. Additionally, the computational complexity of the proposed methodology is assessed. Computer simulation experiments, conducted across two distinct data models: (a) multivariate sub-Gaussian and (b) multivariate Student's t distributions, has been performed to evaluate the efficiency of designed methodology. Various scenarios have been examined, with different change factors considered, such as strength of the correlation between components, number of degrees of freedom (for the Student's t distribution), and the stability index (for the sub-Gaussian distribution). Finally, to depict a practical meaning of the proposed approach we successfully demonstrated invasiveness minimization of intracranial hypertension events detection by identifying the temporal distribution structure in multivariate data. MIDAST supplemented with a windowing mechanism enables screening temporal changes in one or many statistical parameters describing multivariate distribution of measured time series, uncovering single or multiple data change points marking the boundaries within which the homogeneous laws governing the evolution of the physical system and/or process apply.}, language = {en} }