POPaweł Olszewski

Paweł Olszewski

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Paweł Olszewski has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    WiP: GlucoFuse: Early Results on BLE-MQTT Fusion of Bioimpedance and Simulated Optical Signals for Wearable Glucose Trend Estimation

    by Dominik Gnaś, Monika Kulisz, Grzegorz Kłosowski, Tomasz Rymarczyk, Dariusz Wójcik, Paweł Olszewski

    Wearable diet- and vital-sign-tracking devices increasingly target non-invasive glucose sensing, but single-modality approaches, such as electrical impedance spectroscopy (EIS) or photoplethysmography (PPG) alone achieve R2 values of approximately 0.7–0.8 because each path carries its own physiological nuisance variance. This research presents GlucoFuse, fusing an on-body 40-80 kHz bioimpedance front-end with a simulated PPG/NIR optical pipeline over a BLE→MQTT→microservice architecture. Across 8,043 real impedance sweeps paired with simulated optical data, the simulated optical branch reaches R2=0.789, while Ridge-stacking reaches R2=0.872 in this hybrid real/simulated setting naive feature-level concatenation remains worse than either branch (R2=0.583), a cautionary result for mobile-sensing fusion. The prototype closed-loop pipeline, from sensor sweep to fused prediction, completes in 8.5 s end-to-end (≤10 s budget) with 31.1 ms of that spent on hybrid inference. These findings are presented as early, preliminary results from an ongoing wearable-health systems effort, alongside a discussion of network-architecture lessons that generalize beyond glucose sensing.

  • Intelligent wireless control system for crystallization using Ultrasound Tomographic Imaging and Deep Reinforcement Learning

    by Konrad Niderla, Tomasz Rymarczyk, Monika Kulisz, Grzegorz Kłosowski, Paweł KALETA, Paweł OLSZEWSKI

    This study presents a wireless edge-intelligent control framework for crystallization processes that integrates ultrasound tomography (UST) with deep reinforcement learning (DRL). Ultrasound tomography delivers non-invasive in-situ images of opaque media which makes it possible to observe precipitation fronts and spatial heterogeneity directly. A dedicated measurement platform acquires raw signals reconstructs images compresses salient tomographic features and forwards them to an edge controller for real-time inference. The reconstructed images serve as the state for a Proximal Policy Optimization agent that autonomously modulates cooling dosing and stirring to shorten cycle time while safeguarding product morphology. Simulation results indicate fast policy convergence and more than a twenty percent reduction in average crystallization time relative to baseline controllers. The principal contribution is the use of tomographic images as the decision substrate which elevates tomography from purely diagnostic use to a core component of closed-loop control. A wireless and modular architecture underscores suitability for Industry 4.0 settings and points toward adaptive image-drive

  • Open Access

    Fabrykacja w architektonicznym projektowaniu parametrycznym — problematyka i możliwości optymalizacji studium przypadku detalu architektonicznego

    by Wojciech Kocki, Paweł Olszewski

    Projektowanie architektoniczne stale rozwija się pod względem jakości i cyfryzacji procesu projektowego. Wśród wielu zaawansowanych metod, jak na przykład projektowanie 2D w środowisku CAD lub modelowanie BIM, istnieją również rozwiązania cyfrowe, umożliwiające wprowadzenie kodu parametrów określających architekturę obiektu. Takie środowisko projektowania można wykorzystać m.in. w Revit Dynamo lub Rhino 3D Grasshopper. Celem badań naukowych jest zweryfikowanie zaplanowanego sposobu fabrykacji poprzez wykorzystanie wybranej aparatury sterowanej numerycznie. Wykorzystanie parametryzacji danych dotyczących wymiarów, podziałów, ilości elementów itp. umożliwia dowolną ich modyfikację i wybór najlepszego i najbardziej optymalnego rozwiązania projektowego, zbieżnego z początkową ideą twórcy. W większości przykładów zaprojektowane elementy, ze względu na skomplikowaną geometrię, nie są możliwe w realizacji poprzez tradycyjne i powszechnie stosowane technologie. Elementy architektoniczne zaprojektowane w ten sposób fabrykowane są przy użyciu danych projektowych oraz odpowiednich maszyn i narzędzi. Metodyka badań uwzględnia specjalistyczne oprogramowanie oraz narzędzia umożliwiające wytworzenie rzeczywistego, fizycznego elementu. Główne zakresy metodyki to oprogramowanie oraz aparatura, natomiast realizacja elementu architektonicznego nie byłaby możliwa bez użycia odpowiednich materiałów oraz odczynników do ich obróbki. Wykorzystanie technologii CNC oraz obróbki danych CAM umożliwia precyzyjną fabrykację zaprojektowanych elementów z wykorzystaniem specjalnie przygotowanego na ten cel procesu. Natomiast w tym procesie istnieje wiele wyzwań oraz konieczność optymalizacji, które usprawniają i ułatwiają wykonanie rzeczywistych elementów na podstawie cyfrowych modeli. Realizacja detalu, od momentu zaprojektowania jako modelu cyfrowego, aż do fizycznego modelu, ujawnia pozytywne aspekty wybranych sposobów, jak i niedoskonałości wynikające z kalibracji urządzeń oraz wybranych materiałów. Wyniki badań wykazują potwierdzenie słuszności zaplanowanych czynności fabrykacyjnych, wybranej aparatury, materiałów oraz odczynników.

  • Open Access

    Poster: Application of differential architecture in neural networks to improve reconstruction quality in ultrasound tomography

    by Monika Kulisz, Grzegorz Kłosowski, Tomasz Rymarczyk, Konrad Niderla, Paweł Olszewski, Dariusz Wójcik

  • Open Access

    Classification of lungs disease with Electrical impedance tomography

    by Barbara Stefaniak, Amelia Kosior-Romanowska, Paweł Tchórzewski, Dariusz Wójcik, Tomasz Rymarczyk, Paweł Olszewski

    The article discusses research on a wearable medical diagnostic system using electrical impedance tomography. This system aims to diagnose long-term respiratory diseases, particularly COPD, ARDS, pneumothorax, pneumonia, bron-chospasm, and pulmonary hypertension. It seeks to reduce the number of tests needed for accurate diagnoses, thus saving time. The article compares two classification models for distinguishing between diseased and healthy individuals. This approach helps streamline the diagnostic process.

  • Open Access

    Poster Abstract: A Computer Vision System for Human Motion Monitoring on a Bicycle Trainer | Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems

    by Marcin Dziadosz, Mariusz Mazurek, Tomasz Rymarczyk, Dariusz Wójcik, Paweł Olszewski

    During the first stage of the project a computer vision system for human motion tracking was developed. For its implementation, a pair of cameras and a bicycle trainer are required. Human movement is monitored in real time by an effective algorithm that determines the key angles between the joints of a person exercising on a bike trainer. The following phase of the work focused on comparing the discussed system with a reference professional set, based on human motion sensors. The gathered data was then further analysed and compared, indicating that the accuracy of the developed system is fully satisfactory.

  • Open Access

    Analysis of the effectiveness of two different loss functions in training a neural network in lung image reconstruction using impedance tomography

    by Malgorzata Lalak-Dybała, Barbara Stefaniak, Paweł Olszewski

    The article presents research findings on developing a medical diagnostic system based on electrical impedance tomography technology. One of the key components of this project is developing a method for reconstructing the structure of human lungs using this technology. The authors of the article compared the effectiveness of two different loss functions in training a neural network, which is tasked with accurately replicating the lung structure based on electrical impedance tomography data. The researchers analyzed various approaches to calculating loss functions, including cosine embedding loss and InfoNCE loss. They compared the results obtained using these two functions to identify which one performs better in lung structure reconstruction. The findings of these studies may have significant implications for the development of diagnostic systems based on electrical impedance tomography and for improving the effectiveness of lung disease diagnosis. Additionally, the authors discuss potential future directions for the project, including possible applications of the research findings in clinical practice. Future research efforts may focus on optimizing neural network parameters, exploring alternative loss functions, or utilizing advanced machine learning techniques for even more precise lung structure reconstruction. The pursuit of improving such diagnostic systems could lead to significant advancements in the field of medicine, particularly in diagnosing and treating respiratory diseases.

  • Open Access

    Analysis of medical correlation models using ultrasound tomography and electric impedance tomography

    by Dariusz Kasperek, Paweł Olszewski, Mirosław Jarosz

    Summary The main goal of the work was to develop a method for the fusion of images from two different measurement techniques. A project has been designed to integrate electrical impedance tomography (EIT) and ultrasonic tomography (UST) data. The next stage was to analyze the correlation between the EIT results and the occurrence of lower urinary tract dysfunctions and establish boundary parameters for visualization and segmentation. Additionally, the relationships between UST data and the dysfunctions were examined, which also required defining parameters for segmentation. The work also involves establishing standards and methods for the arrangement of measurement electrodes, which is crucial for the precision of both techniques. The proposed approach and results constitute an essential step towards implementing more advanced diagnostic tools to improve patient's quality of life by diagnosing lower urinary tract dysfunctions faster and more precisely.

  • Open Access

    Use of electrical impedance tomography for lung volume reconstruction

    by Paweł Tchórzewski, Małgorzata Lalak - Dybała, Bartosz Przysucha, Paweł Olszewski

    The article presents a study of the application of electro-impedance tomography (EIT) in diagnosing lung capacity using the Tikhonov regularization method. The possibility of reconstructing the lungs to monitor the degree of air filling was investigated. The experiment included a series of tests using a torso phantom designed to simulate different states of the lungs - from fully inflated to fully deflated. Lung-filling states were manipulated in controlled scenarios to test nine main experimental conditions reflecting different lung-filling states. In addition, the quality of reconstruction was checked using various types of reference backgrounds. The results show significant differences in lung volume reconstructions depending on the lung filling state. The most successful reconstructions, which were obtained using the 'No phantom' background, provided the most explicit visualization of the lungs, reassuring the method's reliability. The experiments confirm the potential of EIT to distinguish between different lung states and reconstruct the degree of lung filling. The study also underscores the need to optimize the reference background to increase the precision of the images, especially for the left lung.