Data Domain Change and Feature Selection to Predict Cardiac Pathology with a 2D Clinical Dataset and Convolutional Neural Networks (Student Abstract)

Authors

  • Mário Serra Neto University of Porto (FCUP)
  • Marco Mollinetti School of Systems Information and Engineering, University of Tsukuba
  • Inês Dutra University of Porto (FCUP)

DOI:

https://doi.org/10.1609/aaai.v35i18.17938

Keywords:

Machine Learning, Applications, Feature Selection

Abstract

This work discusses a strategy named Map, Optimize and Learn (MOL) which analyzes how to change the representation of samples of a 2D dataset to generate useful patterns for classification tasks using Convolutional Neural Networks (CNN) architectures. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against state of the art Machine Learning (ML) algorithms for 2D datasets. Preliminary results suggests that the strategy has potential to improve the prediction quality.
AAAI-21 Proceedings Cover

Downloads

Published

2021-05-18

How to Cite

Serra Neto, M., Mollinetti, M., & Dutra, I. (2021). Data Domain Change and Feature Selection to Predict Cardiac Pathology with a 2D Clinical Dataset and Convolutional Neural Networks (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15883-15884. https://doi.org/10.1609/aaai.v35i18.17938

Issue

Vol. 35 No. 18: AAAI-21 Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program