TY - GEN
T1 - Improving Mobile Application GUI Testability with Deep Learning-based Test Case Generation
AU - Andyartha, Putu Krisna
AU - Mardiana, Bella Dwi
AU - Hasan, Umar
AU - Elqolby, Nazhifah
AU - Siahaan, Daniel
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The proliferation of mobile applications created the need to automate graphical user interface (GUI) testing, and one notable practice is deep learning-based test case generation. However, the testability impact of this practice has yet to be explored. Testability and automation are strongly correlated, where low testability reduces the benefits of automation, while ineffective automation will negatively affect testability. This work aimed to explore the effect of deep learning-based GUI test generation on the testability of mobile applications. First, we compared four deep learning algorithms to classify mobile GUI elements (Detectron2, EfficientDet, YOLOv5, and YOLOv8). Comparison results showed that YOLOv8 outperformed the other models in precision, recall, and AP50 scores. Afterward, we applied test case generation on two Android applications where metrics defined by ISO/IEC 25023:2016 provide standards to measure testability. Evaluation results showed improvements in both applications' testability, where the generated test cases increased the conformance of the required test coverage. We noted at least six times improvement in testability. This work concluded that deep learning-based GUI test case generation could improve the testability of mobile applications by creating dozens of applicable test cases.
AB - The proliferation of mobile applications created the need to automate graphical user interface (GUI) testing, and one notable practice is deep learning-based test case generation. However, the testability impact of this practice has yet to be explored. Testability and automation are strongly correlated, where low testability reduces the benefits of automation, while ineffective automation will negatively affect testability. This work aimed to explore the effect of deep learning-based GUI test generation on the testability of mobile applications. First, we compared four deep learning algorithms to classify mobile GUI elements (Detectron2, EfficientDet, YOLOv5, and YOLOv8). Comparison results showed that YOLOv8 outperformed the other models in precision, recall, and AP50 scores. Afterward, we applied test case generation on two Android applications where metrics defined by ISO/IEC 25023:2016 provide standards to measure testability. Evaluation results showed improvements in both applications' testability, where the generated test cases increased the conformance of the required test coverage. We noted at least six times improvement in testability. This work concluded that deep learning-based GUI test case generation could improve the testability of mobile applications by creating dozens of applicable test cases.
KW - deep learning
KW - graphical user interface
KW - mobile applications
KW - test case generation
KW - testability
UR - http://www.scopus.com/inward/record.url?scp=85189934735&partnerID=8YFLogxK
U2 - 10.1109/IWAIIP58158.2023.10462806
DO - 10.1109/IWAIIP58158.2023.10462806
M3 - Conference contribution
AN - SCOPUS:85189934735
T3 - IWAIIP 2023 - Conference Proceeding: International Workshop on Artificial Intelligence and Image Processing
SP - 28
EP - 33
BT - IWAIIP 2023 - Conference Proceeding
A2 - Jusman, Yessi
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023
Y2 - 1 December 2023 through 2 December 2023
ER -