Carlos Penarrubia†, Jose J. Valero-Mas†,‡, Antonio Javier Gallego†, and Jorge Calvo-Zaragoza†
†University Institute for Computer Research, University of Alicante, Alicante, Spain
‡Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain
Extensions to different Multilabel Prototype Generation methods to deal with imbalance data. Work accepted at the Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) 2023.
- MPG/ : Contains the implementations of the base multilabel Prototype Generation methods together with the proposed extensions. These methods are (together with their original reference):
- Experiments.py : Main script for performing the experimentation included in the manuscript.
- Metrics.py: Class including the evaluation metrics.
- StatisticalAnalysis.py: Script prepared for performing the statistical analysis once the results have been obtained.
For the reproduction of the experiments included in the paper, please proceed as follows:
$ pip install -r requirements.txt
$ python Experiments.py
$ python StatisticalAnalysis.py
Footnotes
-
Ougiaroglou, S., Filippakis, P., & Evangelidis, G. (2021). Prototype generation for multi-label nearest neighbours classification. In: Proceedings of the 16th International Conference on Hybrid Artificial Intelligent Systems, Bilbao, Spain, September 22–24, 2021, (pp. 172-183). ↩
-
Valero-Mas, J. J., Gallego, A. J., Alonso-Jiménez, P., & Serra, X. (2023). Multilabel Prototype Generation for data reduction in K-Nearest Neighbour classification. Pattern Recognition, 135, 109190. ↩ ↩2