fseval: A Benchmarking Framework for Feature Selection and Feature Ranking Algorithms
Journal of Open Source Software — A Python package for benchmarking Feature Selection and Feature Ranking algorithms at scale: parallel and distributed experiments, fully reproducible from a config file, with results exported to SQL.
A novel evaluation methodology for supervised Feature Ranking algorithms
arXiv — A new, systematic evaluation methodology for Feature Rankers using synthetic datasets with known feature importances, and a large-scale benchmark run with fseval on an HPC cluster.
A fusion between a deep-learning and a filter-based approach for road marker detection
Fusing the outputs of a supervised deep-learning and an unsupervised filter-based road marker detector into a new supervised model, reaching 95% accuracy.
