M
Michal Wozniak
Researcher at Wrocław University of Technology
Publications - 135
Citations - 2768
Michal Wozniak is an academic researcher from Wrocław University of Technology. The author has contributed to research in topics: Classifier (UML) & Random subspace method. The author has an hindex of 20, co-authored 121 publications receiving 2470 citations.
Papers
More filters
Advances in Computing, Communications and Informatics (ICACCI)
Sabu M. Thampi,Michal Wozniak,Oge Marques,Dilip Krishnaswamy,Christian Callegari,Hideyuki Takagi,Zoran Bojkovic,Neeli R. Prasad,Jose M. Alcaraz Calero,Joel J. P. C. Rodrigues,Natarajan Meghanathan,Ravi Sandhu +11 more
Journal ArticleDOI
Computer Recognition Systems 3
Marek Kurzynski,Michal Wozniak +1 more
TL;DR: This book is the most comprehensive study of this field and contains a collection of 69 carefully selected articles contributed by experts of pattern recognition with respect to both methodology and applications.
Journal ArticleDOI
Radial-Based Oversampling for Multiclass Imbalanced Data Classification
TL;DR: Results show that by taking into account information coming from all of the classes and conducting a smart oversampling, the MC-RBO algorithm can significantly improve the process of learning from multiclass imbalanced data.
Journal ArticleDOI
Nearest Neighbor Classification for High-Speed Big Data Streams Using Spark
Sergio Ramírez-Gallego,Bartosz Krawczyk,Salvador García,Michal Wozniak,José Manuel Benítez,Francisco Herrera +5 more
TL;DR: This paper proposes an efficient incremental instance selection method for massive data streams that continuously update and remove outdated examples from the case-base, which alleviates the high computational requirements of the original classifier, thus making it suitable for the considered problem.
Journal ArticleDOI
CCR: A combined cleaning and resampling algorithm for imbalanced data classification
Michał Koziarski,Michal Wozniak +1 more
TL;DR: A novel resampling technique focused on proper detection of minority examples in a two-class imbalanced data task is described and results indicate that the proposed algorithm usually outperforms the conventional oversampling approaches, especially when the detection of Minority examples is considered.