@InProceedings{SantiagoJúnior:2022:MeExEv,
author = "Santiago J{\'u}nior, Valdivino Alexandre de",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)}",
title = "A Method and Experiment to evaluate Deep Neural Networks as Test
Oracles for Scientific Software",
booktitle = "Proceedings...",
year = "2022",
organization = "IEEE/ACM International Conference on Automation of Software Test
(AST)",
publisher = "IEEE",
keywords = "Test Oracles, Deep Convolutional Neural Networks, Transfer
Learning, , Explainable Artificial Intelligence, Data-Centric
Artificial Intelligenc.",
abstract = "Testing scientific software is challenging because usually such
type of systems have non-deterministic behaviours and, in
addition, they generate non-trivial outputs such as images.
Artificial intelligence (AI) is now a reality which is also
helping in the development of the software testing activity. In
this article, we evaluate seven deep neural networks (DNNs),
precisely deep convolutional neural networks (CNNs) with up to 161
layers, playing the role of test oracle procedures for testing
scientific models. Firstly, we propose a method, TOrC, which
starts by generating training, validation, and test image datasets
via combinatorial interaction testing applied to the original
codes and second-order mutants. Within TOrC we also have classical
steps such as transfer learning, a technique recommended for DNNs.
Then, we verified the performance of the oracles (CNNs). The main
conclusions of this research are: i) not necessarily a greater
number of layers means that a CNN will present better performance;
ii) transfer learning is a valuable technique but eventually we
may need extended solutions to get better performances; iii)
data-centric AI is an interesting path to follow; and iv) there is
not a clear correlation between the software bugs, in the
scientific models, and the errors (image misclassifications)
presented by the CNNs.",
conference-year = "16-20 May 2022",
language = "en",
targetfile = "Paper 2_A Method_Oficial.pdf",
urlaccessdate = "29 jun. 2024"
}