Konsultacje:
poniedziałki 13-15 - proszę o wcześniejszą informację za pośrednictwem poczty elektronicznej
Zainteresowania badawcze:
Kierownik
projektów:
Zaangażowany w
projektach:
O pracowniku
Positions held
- Chair of the Department of Systems and Computer Networks
Elected member of
Editor-in-Chief of Pattern Analysis and Applications (Springer)
Member of the Scientific Council of the Institute of Computer Science PAS
Board member of the Committee on Informatics of the Polish Academy of Sciences
Former chair of the Scientific Council of Information and Communication Technology (Wroclaw University of Science and Technology) (2021-2024)
Fields of interest
- machine learning and unlearning,
- pattern classification,
- data stream classification, concept drift,
- continual learning (life-long machine learning),
- ensemble learning, classifier ensemble
- inductive learning, data and web mining,
- learning from distributed and streaming data
- imbalanced data classification,
Google Scholar profile
ORCID
ResearchGate profile
ResearchID profile
List of publication in DONA database - maintained by my University
New publications
- Jędrzej Kozal, Jan Wasilewski, Alif Ashrafee, Bartosz Krawczyk, Michał Woźniak, What is the role of memorization in Continual Learning?
- Alif Ashrafee, Jedrzej Kozal, Michal Wozniak, Bartosz Krawczyk, Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment
- M. Panek, I. Jablonski and M. Wozniak, Automatic Performance Assessment -- Step Toward Autonomous Mobile Network Management Systems, IEEE Communications Magazine, doi: 10.1109/MCOM.001.2400101 (OPEN ACCESS).
- Joanna Klikowska, Michał Woźniak, Using Multi-Objective Optimization to build non-Random Forest, Logic Journal of the IGPL, jzae110, https://doi.org/10.1093/jigpal/jzae110
- Radek Svoboda, Sebastián Basterrech, Jędrzej Kozal, Jan Platoš, Michał Woźniak,A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism - FREE ACCESS, Knowledge-Based Systems, Volume 304 , 25 November 2024, 112482.
- Duan, H., Jiang, Q., Jin, X., Xin Jin, Wozniak M., Zhao Y., Wu L, Yao S, Zhou W., Mf-net: multi-feature fusion network based on two-stream extraction and multi-scale enhancement for face forgery detection. Complex Intell. Syst. 11, 11 (2025). https://doi.org/10.1007/s40747-024-01634-6
- Jędrzej Kozal, Jan Wasilewski, Bartosz Krawczyk, Michał Woźniak, Continual Learning with Weight Interpolation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 4187-4195 BEST PAPER AWARD FOR CLVISION CVPR WORKSHOP 2024
- Guorui Wang, Qian Jiang, Xin Jin, Michał Woźniak, Shaowen Yao, RTM-UAVDet: a real-time multimodal UAV detector, IEEE Transactions on Aerospace and Electronic Systems. 2024.
- Michał Koziarski, Michał Woźniak, Local neighborhood encodings for imbalanced data classification, Machine Laerning, 2024
- Huanyu Guo, Xin Jin, Qian Jiang, Michal Wozniak, Puming Wang, Shaowen Yao, DMF-net: a dual remote sensing image fusion network based on multi-scale convolutional dense connectivity with performance measure, IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-15, 2024, Art no. 5013415, doi: 10.1109/TIM.2024.3370816.
MSc thesis topics
- Fake news detection.
- Video/image manipulation discovery.
- Explainable AI/ML.
- Data stream classification.
- Learning from imbalanced data.
Wybrane publikacje
