Deep Learning-Based Model Using DensNet201 for Mobile User Interface Evaluation

Soui, Makram; Haddad, Zainab

doi:10.1080/10447318.2023.2175494

Cited by 15 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weight matrix W for the layout metrics is: W = 0.227020 0.095302 0.141894 0.178283 0.156697 0.111903 0.088901 . (31) Thus, the formula for calculating the comprehensive evaluation Y i is as follows:…”

Section: Results Of Multiple Regression and Entropy Weight Methods Ca...mentioning

confidence: 99%

“…There are also studies that apply machine learning methods to identify features related to aesthetics, thereby creating models to predict aesthetics. For instance, Soui and Haddad combined the Densnet201 architecture with the K-Nearest Neighbor (KNN) classifier to evaluate mobile user interfaces, assessing this approach using a publicly available large dataset, with the model achieving an average accuracy of 93% [31]. These methods can capture rich or complex aesthetic perceptions, providing excellent results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Utilizing Multiple Regression Analysis and Entropy Method for Automated Aesthetic Evaluation of Interface Layouts

Wang,

Tong,

Song

et al. 2024

Symmetry

View full text Add to dashboard Cite

Aesthetic evaluation of increasingly complex and personalized human–computer interaction interfaces serves as a critical bridge between humans and machines, fundamentally enhancing various interaction factors. This study addresses the challenges in aesthetic evaluation by adjusting existing methodologies to incorporate seven aesthetic metrics: density, symmetry, balance, proportionality, uniformity, simplicity, and sequence. These metrics were effectively integrated into a composite evaluation metric through both multiple regression analysis and entropy methods, with the efficacy of both fitting methods validated. Leveraging automatic segmentation and recognition technology for interface screenshots, this research enables rapid, automated acquisition of evaluations for the seven metrics and the composite index, leading to the development of a prototype system for interface layout aesthetic assessment. Aimed at reducing the time, manpower, and resources required for interface evaluation, this study enhances the universality, compatibility, and flexibility of layout assessments. It promotes integration at any stage of the design process, significantly benefiting lightweight rapid evaluation and iterative design cycles, thereby advancing the field of interface aesthetic evaluation.

show abstract

Section: Results Of Multiple Regression and Entropy Weight Methods Ca...mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Utilizing Multiple Regression Analysis and Entropy Method for Automated Aesthetic Evaluation of Interface Layouts

Wang,

Tong,

Song

et al. 2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…Planning, recruiting participants, gathering data, and analyzing results are all essential parts of a successful usability test (Soui & Haddad, 2023). The test objectives, test scenarios, and evaluation criteria are all parts of the test planning process.…”

Section: User-centered Designmentioning

confidence: 99%

Human-Computer Interaction: Enhancing User Experience in Interactive Systems

Kheder

2023

kje

View full text Add to dashboard Cite

In this research, we investigate how human-computer interaction (HCI) can be used to improve the user experience (UX) of interactive systems. Studies in cognitive psychology, information processing, and human factors are examined as they relate to the development of HCI. It highlights how HCI has shifted its focus from functionality to user-friendliness, teaching ability, efficiency, enjoyment, and emotion. To better understand the current state of HCI and UX research, practice, and theory, a systematic literature study is performed. Focusing on users' goals wants, and characteristics at every stage of the design process is central to user-centered design (UCD) ideas and approaches, which are discussed at length in this article. We investigate usability testing as a crucial technique for bettering HCI, focusing on its advantages in pinpointing usability problems, boosting system efficacy, and boosting user pleasure. Methods for creating tests, finding participants, collecting data, and analyzing results are discussed. The importance of prototype methods in HCI and user-centric design is also emphasized in the study. This article delves into the practice of creating prototypes to collect user feedback, iterate designs, and perfect interactive systems. Techniques covered include paper prototyping, interactive wireframes, and high-fidelity prototypes. We propose interaction design frameworks like the User-Centered Design Process (UCDP) and the Double Diamond model to help designers prioritize users when developing interactive systems. The study also delves into how technologies like augmented reality, virtual reality, natural language processing, machine learning, and gesture-based interfaces have revolutionized HCI in recent years. The paper defends user-centric design's place in HCI, pointing out how UX affects user happiness, participation, and output. Researchers and practitioners in HCI and software engineering can greatly benefit from this paper's findings.

show abstract

“…Its application in electronic learning is mainly to understand the learners' emotional states and motivations, thereby providing personalized and adaptive teaching support. For example, Soui et al (2023) proposed an emotion recognition model based on deep neural networks, which accurately recognizes seven basic emotions (anger, disgust, fear, happiness, neutrality, sadness, and surprise) by analyzing the learners' facial expressions, speech, and text. This model can be used on online education platforms to help teachers monitor and regulate learners' emotions.…”

Section: Application Of Artificial Intelligence In Online Learningmentioning

confidence: 99%

Evaluation Model of Modern Network Teaching Quality Based on Artificial Intelligence E-Learning

Xie,

Xiao,

Hao

2023

International Journal of Web-Based Learning and Teaching Technologies

View full text Add to dashboard Cite

Modern e-learning system is a representative service form in innovative service industry. This paper designs a personalized service domain system, optimizes various parameters and can be applied to different education quality evaluation, and proposes a decision tree recommendation algorithm. Information gain is carried out through many existing principles of improved decision tree algorithm, and the information gain of the algorithm determines the inheritance of information. The process of modern e-learning system is based on personalized teaching and humanized intelligent interaction. This paper theoretically analyzes the improvement performance of the existing e-learning system in teaching quality evaluation and shows a good classification effect. This model provides reference materials for the expansion of education and teaching and provides a feasible practical model for personalized teaching in online schools. The authors provide good educational conditions and environment for students and cultivate all-around talents for the society.

show abstract

Deep Learning-Based Model Using DensNet201 for Mobile User Interface Evaluation

Cited by 15 publications

References 53 publications

Utilizing Multiple Regression Analysis and Entropy Method for Automated Aesthetic Evaluation of Interface Layouts

Utilizing Multiple Regression Analysis and Entropy Method for Automated Aesthetic Evaluation of Interface Layouts

Human-Computer Interaction: Enhancing User Experience in Interactive Systems

Evaluation Model of Modern Network Teaching Quality Based on Artificial Intelligence E-Learning

Contact Info

Product

Resources

About