01668nas a2200109   4500000000100000000000100001008004100002260005500043100002000098245008900118520135100207       2013                            d  bInstytut Informatyki Teoretycznej i Stosowanej PAN1 aMichał Cholewa00aCzołowe funkcje kuliste jako baza do aproksymacji sygnałów o ograniczonym paśmie3 aTematem pracy jest analiza algorytmu aproksymującego sygnały o ograniczonym pasmie opartego na czołowych funkcjach kulistych. Obecny stan wiedzy zawiera analizę błędu pesymistycznego dla zawężonego przypadku funkcji o ograniczonej energii oraz oszacowanie błędu w przypadku średnim, jednakże bez uwzględnienia błędu wynikającego z błędu pomiaru i kwantyzacji oraz jittera. Ponieważ oba te czynniki występują w praktycznym zastosowaniu wszelkich algorytmów aproksymacyjnych, gruntowna analiza ich wpływu jest istotna z punktu badania efektywności algorytmu. Szczególnie jitter jest wielkością o znaczącym wpływie na wynik działania algorytmu, jako, że nawet niewielki jitter sprawia, że problem wymyka się spod założeń Lematu Smolyaka, który mówi o istnieniu optymalnego algorytmu liniowego. W pracy przedstawione jest oszacowanie błędu średniego dla rodziny zadanych miar Gaussa i wykazuje, że błąd średni algorytmu można dobrze ograniczyć. To prowadzi do wniosku, że algorytm aproksymacji sygnałów o ograniczonym pasmie oparty o czołowe funkcje kuliste jest algorytmem odpornym na działanie czynników zakłócających takich jak błąd pomiaru i kwantyzacji oraz jitter. Praca zawiera również implementację algorytmu numerycznego wyliczania wartości zadanych czołowych funkcji kulistych.00355nas a2200109   4500000000100000000000100001008004100002100002000043700002300063245014500086022001400231       2012                            d1 aMichał Cholewa1 aPrzemysław Głomb00aEstimation of the number of states for gesture recognition with Hidden Markov Models based on the number of critical points in time sequence  a0167-865500313nas a2200121   4500000000100000000000100001008004100002100002000043700002300063245008400086300001400170490000700184       2011                            d1 aMichał Cholewa1 aPrzemysław Głomb00aGesture data modeling and classification based on critical points approximation  a365–3730 v9500607nas a2200241   4500000000100000000000100001008004100002260002600043100002000069700002300089700002100112700002400133700002100157700001900178700001800197700001400215700001500229700001800244700002400262700001800286245003900304020002200343       2013                            d  bOficyna Wydawnicza PW1 aMichał Cholewa1 aPrzemysław Głomb1 aSebastian Opozda1 aMichał Romaszewski1 aArkadiusz Sochan1 aM. Kosiedowski1 aE. Kuśmierek1 aA. Bęben1 aP. Krawiec1 aA. Stroiński1 aWojciech Burakowski1 aPiotr Krawiec00aAplikacje Sieci Świadomej Treści  a978-83-7814-099-301429nas a2200241   4500000000100000000000100001000000100002008004100003100001900044700001800063700001800081700002000099700002300119700002100142700002400163700002100187700001400208700001500222245003900237300001600276520088100292022001401173       2012                            d1 aM. Kosiedowski1 aE. Kuśmierek1 aA. Stroiński1 aMichał Cholewa1 aPrzemysław Głomb1 aSebastian Opozda1 aMichał Romaszewski1 aArkadiusz Sochan1 aA. Bęben1 aP. Krawiec00aAplikacje sieci świadomej treści  a1491–15023 aArtykuł przedstawia aplikacje korzystające z sieci świadomej treści PI CAN opracowanej w ramach projektu Inżynieria Internetu Przyszłości (IIP)1. Są to trzy aplikacje oferujące dostęp do treści multimedialnych: HomeNetMedia dla celów rozrywki, Rozproszone Wirtualne Muzeum dla edukacji oraz Biblioteka Cyfrowa Pacjenta dla przekazywania informacji medycznej. Scharakteryzowana została funkcjonalność sieci PI CAN z punktu widzenia aplikacji wraz z zasadami współpracy z użytkownikami, tj. dostawcami i konsumentami treści. Poszczególne aplikacje omówione zostały ze wskazaniem sposobu wykorzystania sieci świadomej treści oraz implementacji usług zewnętrznych powiązanych z siecią PI CAN specyficznych dla aplikacji. Przedstawione zostały również wyniki integracji poszczególnych aplikacji z siecią PI CAN oraz wyniki przeprowadzonych testów.  a1230-349600592nas a2200217   4500000000100000000000100001008004100002260003800043100002300081700002000104700002100124700002300145700001800168700002500186700001600211700001700227245008700244300001200331490000900343020002200352       2015                            d  bSpringer International Publishing1 aPrzemysław Głomb1 aMichał Cholewa1 aLeszek Rutkowski1 aMarcin Korytkowski1 aRafal Scherer1 aRyszard Tadeusiewicz1 aLotfi Zadeh1 aJacek Zurada00aExperimental Evaluation of Selected Approaches to Covariance Matrix Regularization  a391-4010 v9120  a978-3-319-19368-701556nam a2200169   4500000000100000000000100001008004100002260002300043100001700066700002000083700001900103245007300122856004900195300000800244520111600252022001801368       2016                            d  bIITiS PANaGliwice1 aPiotr Gawron1 aMichał Cholewa1 aKatarzyna Kara00aRewolucja stanu - fantastyczne wprowadzenie do informatyki kwantowej  uhttps://depot.ceon.pl/handle/123456789/16807  a1283 a<p>Świat, jaki znamy – świat wolnych sieci informacyjnych, świat swobodnej wymiany wiedzy i doświadczeń – skończył się nieodwołalnie. Wolny dostęp do wiedzy okazał się szkodliwą ideą, a najbardziej skorzystali na nim zbrodniarze, twórcy broni biologicznej, która nieomal zmiotła cywilizację z powierzchni ziemi. Zdziesiątkowana przez terror, wojny i epidemię ludzkość powoli odradza się pod czujnym okiem Cerbera. Jego agenci mają jeden cel: nie dopuścić, aby wiedza stała się znów powszechnie dostępna.</p>

<p>Jednak wszechobecna cenzura rodzi bunt.</p>

<p>Niektórzy są nawet gotowi ginąć – i zabijać – za wolny dostęp do informacji. I najwyraźniej czują się dość pewnie, by rzucić Cerberowi wyzwanie – bo czym innym może być zamach na wysokiego dygnitarza organizacji w jej głównej kwaterze? Teraz Cerber musi użyć wszystkich dostępnych środków, by znaleźć zleceniodawców napastnika. Niestety, jego as atutowy, kwantowa hakerka Eve, właśnie zasiada na ławie oskarżonych pod zarzutem zdrady na rzecz grupy terrorystycznej ALICE...</p>
  a978839260541600491nas a2200157   4500000000100000000000100001008004100002100002400043700002300067700002000090245011800110856007100228300001200299490000800311022001400319       2016                            d1 aMichał Romaszewski1 aPrzemysław Głomb1 aMichał Cholewa00aSemi-supervised hyperspectral classification from a small number of training samples using a co-training approach  uhttp://www.sciencedirect.com/science/article/pii/S0924271616303446  a60 - 760 v121  a0924-271600274nas a2200109   4500000000100000000000100001008004100002100002000043700002300063245005600086020002200142       2016                            d1 aMichał Cholewa1 aPrzemysław Głomb00aTwo Stage SVM Classification for Hyperspectral Data  a978-989-758-173-100288nas a2200109   4500000000100000000000100001008004100002100002300043700002000066245007000086020002200156       2016                            d1 aPrzemysław Głomb1 aMichał Cholewa00aPerformance of Interest Point Descriptors on Hyperspectral Images  a978-989-758-175-501088nas a2200181   4500000000100000000000100001008004100002100002000043700001700063700002300080700001900103245007200122856004800194300000800242490000700250520063500257022001400892       2017                            d1 aMichał Cholewa1 aPiotr Gawron1 aPrzemysław Głomb1 aDariusz Kurzyk00aQuantum hidden Markov models based on transition operation matrices  uhttp://dx.doi.org/10.1007/s11128-017-1544-8  a1010 v163 a<p>In this work, we extend the idea of quantum Markov chains (Gudder in J Math Phys 49(7):072105 [3]) in order to propose quantum hidden Markov models (QHMMs). For that, we use the notions of transition operation matrices and vector states, which are an extension of classical stochastic matrices and probability distributions. Our main result is the Mealy QHMM formulation and proofs of algorithms needed for application of this model: Forward for general case and Vitterbi for a restricted class of QHMMs. We show the relations of the proposed model to other quantum HMM propositions and present an example of application.</p>
  a1573-133200522nas a2200169   4500000000100000000000100001008004100002260001200043100002300055700002400078700002000102700002100122245011600143856007100259490000800330022001400338       2018                            d  c07/20181 aPrzemysław Głomb1 aMichał Romaszewski1 aMichał Cholewa1 aKrzysztof Domino00aApplication of hyperspectral imaging and Machine Learning methods for the detection of gunshot residue patterns  uhttp://www.sciencedirect.com/science/article/pii/S03790738183036570 v290  a0379-073801191nas a2200145   4500000000100000000000100001008004100002260003800043100002400081700002300105700002000128245009700148520077800245020002201023       2018                            d  bSpringer International Publishing1 aMichał Romaszewski1 aPrzemysław Głomb1 aMichał Cholewa00aAdaptive, Hubness-Aware Nearest Neighbour Classifier with Application to Hyperspectral Data3 a<p>We present an extension of the Nearest Neighbour classifier that can adapt to sample imbalances in local regions of the dataset. Our approach uses the hubness statistic as a measure of a relation between new samples and the existing training set. This allows to estimate the upper limit of neighbours that vote for the label of the new instance. This estimation improves the classifier performance in situations where some classes are locally under-represented. The main focus of our method is to solve the problem of local undersampling that exists in hyperspectral data classification. Using several well-known Machine Learning and hyperspectral datasets, we show that our approach outperforms standard and distance-weighted kNN, especially for high values of k.</p>
  a978-3-030-00840-600427nas a2200157   4500000000100000000000100001008004100002260001000043100002000053700002300073700002400096245011600120300001200236490000700248022001400255       2019                            d  cMarch1 aMichał Cholewa1 aPrzemysław Głomb1 aMichał Romaszewski00aA Spatial-Spectral Disagreement-Based Sample Selection With an Application to Hyperspectral Data Classification  a467-4710 v16  a1545-598X00555nas a2200169   4500000000100000000000100001008004100002260007300043100002300116700002100139700002400160700002000184245011100204856003700315300001100352020002200363       2019                            d  c2019bWroclaw University of Science and TechnologyaWrocław, Poland1 aPrzemysław Głomb1 aKrzysztof Domino1 aMichał Romaszewski1 aMichał Cholewa00aBand selection with Higher Order Multivariate Cumulants for small target detection in hyperspectral images  uhttps://arxiv.org/abs/1808.03513  ap. 121  a978-83-943803-2-800293nas a2200097   4500000000100000000000100001008004100002100002000043700002100063245011100084       2016                            d1 aMichał Cholewa1 aArkadiusz Sochan00aMulti-sensor dataset for testing merge of Hyperspectral, HD and 3D cloud information for image recognition03407nas a2200193   4500000000100000000000100001008004100002260001200043100002000055700002400075700002300099700002200122700002000144245008300164856004600247490000700293520289900300022001403199       2020                            d  c11/20201 aKamil Książek1 aMichał Romaszewski1 aPrzemysław Głomb1 aBartosz Grabowski1 aMichał Cholewa00aBlood Stain Classification with Hyperspectral Imaging and Deep Neural Networks  uhttps://www.mdpi.com/1424-8220/20/22/66660 v203 a<p>In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.</p>
  a1424-822001424nas a2200145   4500000000100000000000100001008004100002100002400043700002300067700002100090700002000111245008000131856004300211520102400254       2020                            d1 aMichał Romaszewski1 aPrzemysław Głomb1 aArkadiusz Sochan1 aMichał Cholewa00aA Dataset for Evaluating Blood Detection in Hyperspectral Images [Data set]  uhttps://doi.org/10.5281/zenodo.39849053 a<p>The sensitivity of hyperspectral imaging (imaging spectroscopy) to haemoglobin derivatives makes it a promising tool for detection and classification of blood. However, due to complexity and high dimensionality of hyperspectral images, the development of hyperspectral blood detection algorithms is challenging. To facilitate their development, we present a new hyperspectral blood detection dataset. This dataset consists of 14 hyperspectral images (ENVI format) of a mock-up scene containing blood and visually similar substances (e.g. artificial blood or tomato concentrate). Images were taken over a period of three weeks and differ in terms of background composition and lighting intensity. To facilitate the use of data, the dataset includes an annotation of classes: pixels where blood and similar substances are visible have been marked by the authors. The main intention behind the dataset is to serve as testing data for Machine Learning methods for hyperspectral target detection and classification.</p>
01436nas a2200169   4500000000100000000000100001008004100002100002400043700002300067700002100090700002000111245006900131856003700200490000800237520100700245022001401252       2021                            d1 aMichał Romaszewski1 aPrzemysław Głomb1 aArkadiusz Sochan1 aMichał Cholewa00aA dataset for evaluating blood detection in hyperspectral images  uhttps://arxiv.org/abs/2008.102540 v3203 a<p>The sensitivity of imaging spectroscopy to haemoglobin derivatives makes it a promising tool for detecting blood. However, due to complexity and high dimensionality of hyperspectral images, the development of hyperspectral blood detection algorithms is challenging. To facilitate their development, we present a new hyperspectral blood detection dataset. This dataset, published under an open access license, consists of multiple detection scenarios with varying levels of complexity. It allows to test the performance of Machine Learning methods in relation to different acquisition environments, types of background, age of blood and presence of other blood-like substances. We have explored the dataset with blood detection experiments, for which we have used a hyperspectral target detection algorithm based on the well-known Matched Filter detector. Our results and their discussion highlight the challenges of blood detection in hyperspectral data and form a reference for further works.</p>
  a0379-073801481nas a2200205   4500000000100000000000100001008004100002260004200043100002000085700002300105700002400128700002000152700002200172700001900194245010400213856003700317490001000354520088900364022002201253       2022                            d  c05/2022bSpringer, ChamaLecce, Italy1 aKamil Książek1 aPrzemysław Głomb1 aMichał Romaszewski1 aMichał Cholewa1 aBartosz Grabowski1 aKrisztian Buza00aImproving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation  uhttps://arxiv.org/abs/2109.137480 v132313 a<p>Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fractions (abundances), which is needed for effective hyperspectral analysis and classification. However, as we show in this paper, the training of autoencoders for unmixing is highly dependent on weights initialisation; some sets of weights lead to degenerate or low-performance solutions, introducing negative bias in the expected performance. In this work, we experimentally investigate autoencoders stability as well as network reinitialisation methods based on coefficients of neurons’ dead activations. We demonstrate that the proposed techniques have a positive effect on autoencoder training in terms of reconstruction, abundances and endmembers errors.</p>
  a978-3-031-06427-201389nas a2200193   4500000000100000000000100001008004100002260001200043100002300055700002000078700001900098700001800117700002400135245006600159856004000225490000700265520090900272022001401181       2023                            d  c05/20231 aPrzemysław Głomb1 aMichał Cholewa1 aWojciech Koral1 aAndrzej Madej1 aMichał Romaszewski00aDetection of emergent leaks using machine learning approaches  uhttps://doi.org/10.2166/ws.2023.1180 v233 a<p>In this work, we focus on the detection of leaks occurring in district metered areas (DMAs). Those leaks are observable as a number of time-related deviations from zone patterns over days or weeks. While they are detectable given enough time, due to the huge cost of water loss resulting from an undetected leak, the main challenge is to find them as soon as possible, when the deviation from the zone pattern is small. Using our collected observational data, we investigate the appearance of leaks and discuss the performance of several machine learning (ML) anomaly detectors in detecting them. We test a diverse set of six anomaly detectors, each based on a different ML algorithm, on nine scenarios containing leaks and anomalies of various kinds. The proposed approach is very effective at quickly (within hours) identifying the presence of a leak, with a limited number of false positives.</p>
  a1606-974900544nas a2200181   4500000000100000000000100001008004100002100002300043700002000066700001900086700001700105700001700122700002100139700002100160700001900181245012300200856003900323       2023                            d1 aPrzemysław Głomb1 aMichał Cholewa1 aPaweł Foszner1 aJakub Bularz1 aMaria Ganzha1 aLeszek Maciaszek1 aMarcin Paprzycki1 aDominik Slezak00aContinual learning of a time series model using a mixture of HMMs with application to the IoT fuel sensor verification  uhttps://doi.org/10.15439/2023F185600457nas a2200157   4500000000100000000000100001008004100002260001200043100002400055700002400079700002300103700002000126700002500146245009100171856003700262       2024                            d  c06/20241 aMichał Romaszewski1 aPrzemysław Sekuła1 aPrzemysław Głomb1 aMichał Cholewa1 aKatarzyna Kołodziej00aThrough the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models  uhttps://arxiv.org/abs/2406.0492600578nas a2200193   4500000000100000000000100001008004100002260001200043100002000055700002400075700002300099700002500122700002100147700001600168700001900184700001800203700002000221245014300241       2024                            d  c06/20241 aMichał Cholewa1 aMichał Romaszewski1 aPrzemysław Głomb1 aKatarzyna Kołodziej1 aMichał Gorawski1 aJakub Koral1 aWojciech Koral1 aAndrzej Madej1 aKryspin Musioł00a‘Just One More Sensor is Enough’ – Iterative Water Leak Localization with Physical Simulation and a Small Number of Pressure Sensors00456nas a2200157   4500000000100000000000100001008004100002260001200043100002500055700002000080700002300100700001900123700002400142245009500166856003700261       2024                            d  c09/20241 aKatarzyna Kołodziej1 aMichał Cholewa1 aPrzemysław Głomb1 aWojciech Koral1 aMichał Romaszewski00aEfficient Numerical Calibration of Water Delivery Network Using Short-Burst Hydrant Trials  uhttps://arxiv.org/abs/2410.0277200409nas a2200145   4500000000100000000000100001008004100002100002500043700002000068700002400088700002300112700001900135700002400154245008500178       2024                            d1 aKatarzyna Kołodziej1 aMichał Cholewa1 aMichał Romaszewski1 aPrzemysław Głomb1 aWojciech Koral1 aPrzemysław Sekuła00aCalibration of Water Demand Network Through a Machine Learned Digital Twin Model00427nas a2200157   4500000000100000000000100001008004100002260001200043100002400055700002400079700002300103700002000126700002500146245009100171490000700262       2025                            d  c03/20251 aMichał Romaszewski1 aPrzemysław Sekuła1 aPrzemysław Głomb1 aMichał Cholewa1 aKatarzyna Kołodziej00aThrough the Thicket: A Study of Number-Oriented LLMS Derived from Random Forest Models0 v1501940nas a2200157   4500000000100000000000100001008004100002100002400043700002400067700002300091700002000114700001900134245006100153856006700214520150100281       2025                            d1 aPrzemysław Sekuła1 aMichał Romaszewski1 aPrzemysław Głomb1 aMichał Cholewa1 aŁukasz Pawela00aQuantum-aware Transformer model for state classification  uhttps://link.springer.com/chapter/10.1007/978-3-031-97570-7_153 a<p>Entanglement is a fundamental feature of quantum mechanics, playing a crucial role in quantum information processing. However, classifying entangled states, particularly in the mixed-state regime, remains a challenging problem, especially as system dimensions increase. In this work, we focus on bipartite quantum states and present a data-driven approach to entanglement classification using transformer-based neural networks. Our dataset consists of a diverse set of bipartite states, including pure separable states, Werner entangled states, general entangled states, and maximally entangled states. We pretrain the transformer in an unsupervised fashion by masking elements of vectorized Hermitian matrix representations of quantum states, allowing the model to learn structural properties of quantum density matrices. This approach enables the model to generalize entanglement characteristics across different classes of states. Once trained, our method achieves near-perfect classification accuracy, effectively distinguishing between separable and entangled states. Compared to previous Machine Learning, our method successfully adapts transformers for quantum state analysis, demonstrating their ability to systematically identify entanglement in bipartite systems. These results highlight the potential of modern machine learning techniques in automating entanglement detection and classification, bridging the gap between quantum information theory and artificial intelligence.</p>
00474nas a2200169   4500000000100000000000100001008004100002100002400043700002100067700001600088700001800104700002100122700002000143245008900163856004500252490000700297       2025                            d1 aPrzemysław Sekuła1 aNarjes Shayesteh1 aQinglian He1 aSara Zahedian1 aRodrigo Moscosso1 aMichał Cholewa00aMove Over Law Compliance Analysis Utilizing a Deep Learning Computer Vision Approach  uhttps://www.mdpi.com/2076-3417/15/4/20110 v1501834nas a2200217   4500000000100000000000100001008004100002260001200043100002400055700001600079700001900095700002100114700001800135700001700153700001500170700002000185245007100205856004600276490000700322520128700329       2025                            d  c09/20251 aPrzemysław Sekuła1 aQinglian He1 aKaveh Sadabadi1 aRodrigo Moscosso1 aThomas Jacobs1 aZachary Laan1 aMark Franz1 aMichał Cholewa00aVehicle-to-Infrastructure System Prototype for Intersection Safety  uhttps://www.mdpi.com/2076-3417/15/17/97540 v153 a<p>This study investigates the use of Autonomous Sensing Infrastructure and Connected and Autonomous Vehicles (CAV) technologies to support infrastructure-to-vehicle (I2V) and infrastructure-to-everything (I2X) communications, including the alerting of drivers and pedestrians. It describes research findings in the following CAV functionalities: (1) Intersection-based object detection and tracking; (2) Basic Safety Message (BSM) generation and transmission; and (3) In-Vehicle BSM receipt and display, including handheld (smartphone) application BSM receipt and user presentation. The study summarizes the various software and hardware components used to create the I2V and I2X prototype solutions, which include open-source and commercial software as well as industry-standard transportation infrastructure hardware, e.g., Signal Controllers. Results from in-lab testing demonstrate effective object detection (e.g., pedestrians, bicycles) based on sample traffic camera video feeds as well as successful BSM message generation and receipt using the leveraged software and hardware components. The I2V and I2X solutions created as part of this research are scheduled to be deployed in a real-world intersection in coordination with state and local transportation agencies.</p>
02630nas a2200241   4500000000100000000000100001008004100002260001200043100002000055700002200075700002300097700002400120700001900144700002400163700002000187700002500207700001900232700002100251245012200272490000700394520197300401022001402374       2025                            d  c09/20251 aKamil Książek1 aWilhelm Masarczyk1 aPrzemysław Głomb1 aMichał Romaszewski1 aKrisztian Buza1 aPrzemysław Sekuła1 aMichał Cholewa1 aKatarzyna Kołodziej1 aPiotr Gorczyca1 aMagdalena Piegza00aDeep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals0 v213 a<p>Schizophrenia and bipolar disorder are severe mental illnesses that significantly impact quality of life. These disorders are associated with autonomic nervous system dysfunction, which can be assessed through heart activity analysis. Heart rate variability (HRV) has shown promise as a potential biomarker for diagnostic support and early screening of those conditions. This study aims to develop and evaluate an automated classification method for schizophrenia and bipolar disorder using short-duration electrocardiogram (ECG) signals recorded with a low-cost wearable device. We conducted classification experiments using machine learning techniques to analyze R-R interval windows extracted from short ECG recordings. The study included 60 participants—30 individuals diagnosed with schizophrenia or bipolar disorder and 30 control subjects. We evaluated multiple machine learning models, including Support Vector Machines, XGBoost, multilayer perceptrons, Gated Recurrent Units, and ensemble methods. Two time window lengths (about 1 and 5 minutes) were evaluated. Performance was assessed using 5-fold cross-validation and leave-one-out cross-validation, with hyperparameter optimization and patient-level classification based on individual window decisions. Our method achieved classification accuracy of 83% for the 5-fold cross-validation and 80% for the leave-one-out scenario. Despite the complexity of our scenario, which mirrors real-world clinical settings, the proposed approach yielded performance comparable to advanced diagnostic methods reported in the literature. The results highlight the potential of short-duration HRV analysis as a cost-effective and accessible tool for aiding in the diagnosis of schizophrenia and bipolar disorder. Our findings support the feasibility of using wearable ECG devices and machine learning-based classification for psychiatric screening, paving the way for further research and clinical applications.</p>
  a1553-735800317nas a2200109   4500000000100000000000100001008004100002100002000043700002400063700002300087245009700110       2025                            d1 aMichał Cholewa1 aMichał Romaszewski1 aPrzemysław Głomb00aData structure better than labels? Unsupervised heuristics for SVM hyperparameter estimation00485nas a2200169   4500000000100000000000100001008004100002260001200043100002500055700002000080700002300100700001900123700002400142245009500166856004600261490000800307       2026                            d  c02/20261 aKatarzyna Kołodziej1 aMichał Cholewa1 aPrzemysław Głomb1 aWojciech Koral1 aMichał Romaszewski00aEfficient Numerical Calibration of Water Delivery Network Using Short-Burst Hydrant Trials  uhttps://doi.org/10.1061/JWRMD5.WRENG-68390 v15200365nas a2200145   4500000000100000000000100001008004100002100001800043700002000061700001700081700002300098700002400121700002000145245005400165       2026                            d1 aAnna Zawadzka1 aMateusz Żarski1 aKamil Drejer1 aPrzemysław Głomb1 aMichał Romaszewski1 aMichał Cholewa00a Map-Guided Cross-Training for Building Detection