Map-Optimize-Learn: Predicting Cardiac Pathology in Children and Teenagers with a Deep Learning Based Tabular Learning Method

• Type: Article in International Conference Proceedings Book
• Date: 2022

Authors

Neto, MTRS (Author) Other; Ines Dutra (Author) FCUP; Mollinetti, MAF (Author) Other

Conference proceedings International

Title: International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy, July 18-23, 2022

Pages: 1-8

Indexing

ISI Web of Knowledge - 0 Citations

Scopus

Other information

Authenticus ID: P-00X-BGV

DOI: 10.1109/ijcnn55064.2022.9889788

Abstract (EN): Convolutional Neural Networks (CNN) have been successfully applied to images, text and audio, but their performance are not so good when applied to feature-based tabular data. Exceptions are works such as TabNet and DeepInsight, which employ end-to-end approaches. In this work, we propose an alternative way of using CNNs to model tabular data where knowledge is extracted from the feature space before being introduced to the network. Our strategy, Map-Optimize-Learn (MOL), changes the shape representation of samples in order to produce suitable input data for the CNN architecture. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against baseline and state of the art Machine Learning (ML) algorithms for tabular datasets. Preliminary results suggest that the strategy has potential to improve prediction quality of tabular data over end-to-end CNN methods and classical ML methods.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8