Title: Toward a CNN-based approach for usability requirements generation

Authors: Dorra Zaibi; Riadh Ksantini; Meriem Riahi; Faouzi Moussa

Addresses: Higher School of Communication of Tunis (SUP'COM), University of Carthage, Tunisia ' Department of Computer Science, College of IT, University of Bahrain, Kingdom of Bahrain ' University of Tunis, ENSIT, 1089, Montfleury, Tunisia; Tunis El Manar University, FST, LIPAH-LR11ES14, 2092 Tunis, Tunisia ' Faculty of Sciences of Tunis, Tunis El Manar University, Tunisia

Abstract: The explosion of data science in many sectors of technology combined with the enormous rise of deep learning techniques in the last decade has resulted in new automation applications. The most prevalent deep learning architecture is the convolutional neural network (CNN) which has been widely applied for face recognition and various applications, has recently emerged as an effective and potentially useful tool for feature extraction. Unfortunately, human factors engineering (HFE), also known as usability engineering, which is concerned with interactive systems, often has limited attention and awareness of deep learning applications and is therefore unable to provide the important breakthroughs that are required to ensure the success of these emerging interactive systems. This article addresses the issue by exploring the generation of consistent usability requirements based on deep CNN models to enable accurate classification in context-aware environments. Our methodology has been tested and performance analysis is carried out through a case study.

Keywords: human-computer interaction; HCI; usability; context-aware environment; deep learning; convolutional neural network; CNN.

DOI: 10.1504/IJADS.2024.139402

International Journal of Applied Decision Sciences, 2024 Vol.17 No.4, pp.411 - 433

Received: 15 Sep 2022
Accepted: 01 Mar 2023
Published online: 02 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article