Decision Tree Based Wrappers for Hearing Loss

Created by W.Langdon from gp-bibliography.bib Revision:1.8194

@InProceedings{Rabuge:2024:PPSN,

• author = "Miguel Rabuge and Nuno Lourenco",
• title = "Decision Tree Based Wrappers for Hearing Loss",
• booktitle = "18th International Conference on Parallel Problem Solving from Nature",
• year = "2024",
• editor = "Heike Trautmann and Tea Tusar and Penousal Machado and Thomas Baeck",
• volume = "15148",
• series = "Lecture Notes in Computer Science",
• pages = "290--305",
• address = "University of Applied Sciences Upper Austria, Hagenberg, Austria",
• month = "13-18 " # sep,
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming, Grammatical Evolution, Feature Engineering, Audiology",
• isbn13 = "978-3-031-70054-5",
• URL = "https://rdcu.be/d5m25",
• DOI = "doi:10.1007/978-3-031-70055-2_18",
• size = "16 pages",
• abstract = "Audiology entities are using Machine Learning (ML) models to guide their screening towards people at risk. Feature Engineering (FE) focuses on optimizing data for ML models, with evolutionary methods being effective in feature selection and construction tasks. This work aims to benchmark an evolutionary FE wrapper, using models based on decision trees as proxies. The FEDORA framework is applied to a Hearing Loss (HL) dataset, being able to reduce data dimensionality and statistically maintain baseline performance. Compared to traditional methods, FEDORA demonstrates superior performance, with a maximum balanced accuracy of 76.2 percent, using 57 features. The framework also generated an individual that achieved 72.8 percent balanced accuracy using a single feature.",
• notes = "https://ppsn2024.fh-ooe.at/program/",

}

Genetic Programming entries for Miguel Rabuge Nuno Lourenco

Citations