A ResNet-Enhanced Framework for Modelling Aesthetic Preferences in User-Centred Decision Systems

Jiadi Liu; Yixin Zhang; Shuhui Liu

doi:10.31181/dmame7120241491

Authors

Jiadi Liu BA, School of Architecture and Design, Beijing Jiaotong University, Beijing 100044, China
Yixin Zhang BA, Art Institute, Lanzhou University, Lanzhou, China, 730,000.
Shuhui Liu BA, School of Mechanical Engineering, Dongguan University of Technology, Dongguan China, 523808.

DOI:

https://doi.org/10.31181/dmame7120241491

Keywords:

Aesthetic Preference Modelling, Multimodal Interaction, Deep Learning, Multimedia Analysis, Decision Support Systems

Abstract

Modelling user aesthetic preferences is essential in contemporary multimodal interaction systems, as it enhances content relevance, user engagement, and decision-making efficacy. This study introduces a deep learning-based framework that integrates visual feature extraction with user interaction data to estimate the aesthetic quality of multimedia content, using images and videos as illustrative cases. The framework utilises statistical image analysis as input to deep convolutional architectures, specifically Residual Neural Networks (ResNets), to compute key aesthetic attributes such as colour harmony, lightness, and visual complexity. Additionally, user engagement indicators, including likes and collections, are incorporated alongside these visual features to infer patterns of aesthetic preference. Given the inherent subjectivity and variability in user data, the framework applies annotation normalisation and layer-freezing strategies to enhance model generalisation and training efficiency. The proposed system demonstrates robust capabilities in aesthetic scoring and preference modelling, facilitating informed content presentation and decision support across various digital environments. This work contributes to the advancement of intelligent, user-aware systems within the domains of multimedia interaction and human-computer interface design

Downloads

Download data is not yet available.

References

[1] Adilova, A., & Shamoi, P. (2024). Personalized Aesthetic Assessment: integrating fuzzy logic and color preferences. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3427706

[2] Xu, L., Pan, C., Xu, B., Sun, Z., Zhou, K., Yan, R., Weng, K., Wu, Y., & Li, H. (2025). A qualitative exploration of a user-centered model for smartwatch comfort using grounded theory. International Journal of Human–Computer Interaction, 41(2), 1091-1106. https://doi.org/10.1080/10447318.2024.2313273

[3] Wang, Z. (2024). Research on Intelligent Human-Machine Interaction System Design and Data Visualization Based on Multimodal Data Fusion. International Conference on Artificial Intelligence for Society, 692-701. https://doi.org/10.1007/978-3-031-69457-8_63

[4] Rosati, R., Senesi, P., Lonzi, B., Mancini, A., & Mandolini, M. (2024). An automated CAD-to-XR framework based on generative AI and Shrinkwrap modelling for a User-Centred design approach. Advanced Engineering Informatics, 62, 102848. https://doi.org/10.1016/j.aei.2024.102848

[5] Jones, E. K., Hultman, G., Schmoke, K., Ninkovic, I., Dodge, S., Bahr, M., Melton, G. B., Marquard, J., & Tignanelli, C. J. (2022). Combined expert and user-driven usability assessment of trauma decision support systems improves user-centered design. Surgery, 172(5), 1537-1548. https://doi.org/10.1016/j.surg.2022.05.037

[6] Zhang, Y., Chen, Y., & Li, X. (2023). Integrated framework of knowledge-based decision support system for user-centered residential design. Expert Systems with Applications, 216, 119412. https://doi.org/10.1016/j.eswa.2022.119412

[7] Tupayachi, J., Xu, H., Omitaomu, O. A., Camur, M. C., Sharmin, A., & Li, X. (2024). Towards next-generation urban decision support systems through ai-powered construction of scientific ontology using large language models—A case in optimizing intermodal freight transportation. Smart Cities, 7(5), 2392-2421. https://doi.org/10.3390/smartcities7050094

[8] Gavrilova, M. L. (2025). Information Fusion: A Decade of Innovations in Biometric Multimodal Research. Computer, 58(4), 27-36. https://doi.org/10.1109/MC.2025.3526135

[9] Sun, Q., Xue, Y., & Song, Z. (2024). Adaptive user interface generation through reinforcement learning: A data-driven approach to personalization and optimization. arXiv preprint arXiv:2412.16837. https://doi.org/10.48550/arXiv.2412.16837

[10] Min, Q., Zhao-Xian, R., Can, W., & Li, X. (2025). Integrating user feedback into air purifier innovation: The FKANO-DEMATEL-VIKOR decision framework. Engineering Management Journal, 1-18. https://doi.org/10.1080/10429247.2024.2447233

[11] Yuan, Z., Ding, H., Li, M., Li, L., & Huang, G. Q. (2024). AiFashion: Multi-Modal and Multi-Dimensional Large Model Based on Self-Trained Customer Digital-Twin for Fashion Design and Manufacturing. 2024 International Conference on Automation in Manufacturing, Transportation and Logistics (ICaMaL), 9798350378658. https://doi.org/10.1109/ICaMaL62577.2024.10919567

[12] Xu, W., Cao, Y., & Chen, R. (2024). A multimodal analytics framework for product sales prediction with the reputation of anchors in live streaming e-commerce. Decision Support Systems, 177, 114104. https://doi.org/10.1016/j.dss.2023.114104

[13] Alhamadi, M. (2024). User Modelling and Adaptive Interaction on Interactive Dashboards The University of Manchester (United Kingdom)]. https://www.proquest.com/openview/3784ae26ed9add512ee8b3ebe1e9648c/1?cbl=2026366&diss=y&pq-origsite=gscholar

[14] Ren, M., Fan, J., Yu, C., & Zheng, P. (2024). CockpitGemini: A personalized design framework for smart vehicle cockpits integrating generative model-based multi-agent systems and human digital twins. International Journal of AI for Materials and Design, 1(3), 4-19. https://dx.doi.org/10.36922/ijamd.4220

[15] Dauber-Decker, K. L., Serafini, M. A., Monane, R., Grossman Liu, L., Sales, A., Mizhquiri Barbecho, J., Diamond, M. E., Levy, S., King, D. A., & McGinn, T. (2025). User-Centered Design of a Preference-Driven Patient Activation Tool for Optimizing Depression Treatment in Integrated Primary Care Settings (The Transform DepCare Study). Journal of general internal medicine, 40(3), 556-568. https://doi.org/10.1007/s11606-024-08833-4

[16] Ji, Y., Sun, Y., Qiu, S., & Geng, X. (2025). Simultaneous multimodal measures for aesthetic evaluation of furniture color and form. Scientific Reports, 15(1), 2920. https://doi.org/10.1038/s41598-025-87086-5

[17] Torkamaan, H., Tahaei, M., Buijsman, S., Xiao, Z., Wilkinson, D., & Knijnenburg, B. P. (2024). The role of human-centered ai in user modeling, adaptation, and personalization—models, frameworks, and paradigms. In A Human-Centered Perspective of Intelligent Personalized Environments and Systems (pp. 43-84). Springer. https://doi.org/10.1007/978-3-031-55109-3_2

[18] Wang, Y., Zhou, Y., Chen, X., & Fang, H. (2024). Operational Performance and Subjective Preferences of Elderly Users in Intelligent Interactive Interfaces: A Systematic Review. International Journal of Human–Computer Interaction, 1-15. https://doi.org/10.1080/10447318.2024.2352226

[19] Maroto-Gómez, M., Castro-González, Á., Castillo, J. C., Malfaz, M., & Salichs, M. Á. (2023). An adaptive decision-making system supported on user preference predictions for human–robot interactive communication. User Modeling and User-Adapted Interaction, 33(2), 359-403. https://doi.org/10.1007/s11257-022-09321-2

[20] Peng, J., & Wang, X. (2023). User-Device-Interaction Model: A Multimodal Interaction Εvaluation System Based on Analytic Hierarchy Process. International Conference on Human-Computer Interaction, 181-199. https://doi.org/10.1007/978-3-031-35596-7_13

[21] Nie, X., Hu, B., Gao, X., Li, L., Zhang, X., & Xiao, B. (2023). BMI-Net: a brain-inspired multimodal interaction network for image aesthetic assessment. Proceedings of the 31st ACM International Conference on Multimedia, 5514-5522. https://doi.org/10.1145/3581783.3611996

[22] Zhang, J., Wang, S., He, W., Li, J., Wu, S., Cao, Z., & Wang, M. (2024). Perception and Decision-Making for Multi‑Modal Interaction Based on Fuzzy Theory in the Dynamic Environment. International Journal of Human–Computer Interaction, 40(24), 8794-8808. https://doi.org/10.1080/10447318.2023.2291607

[23] Yuan, B., Wu, K., Wu, X., & Yang, C. (2024). Form generative approach for front face design of electric vehicle under female aesthetic preferences. Advanced Engineering Informatics, 62, 102571. https://doi.org/10.1016/j.aei.2024.102571

[24] Kyelem, Y., Zo, M., Kabore, K. K., & Ouedraogo, F. T. (2023). Automatic Graphical User Interface aesthetic evaluation tool using the UIED segmentation algorithm. Proceedings of the 2023 3rd International Conference on Human Machine Interaction, 20-26. https://doi.org/10.1145/3604383.3604387

[25] Özdiler Çopur, F., Çökeliler Serdaroğlu, D., İç, Y. T., & Arı, F. (2023). Development of a decision support system to use in the strategic purchasing of dental implants. Advances in Computational Intelligence, 3(4), 13. https://doi.org/10.1007/s43674-023-00060-4

[26] Zhai, Y. (2022). Research and Implementation of Colour Optimal Matching Model for Art Design Based on Bayesian Decision‐Making. Mathematical Problems in Engineering, 2022(1), 5068340. https://doi.org/10.1155/2022/5068340

[27] Ji, T., Lin, Y., & Yang, Y. (2024). ForestAdvisor: A multi-modal forest decision-making system based on carbon emissions. Environmental Modelling & Software, 181, 106190. https://doi.org/10.1016/j.envsoft.2024.106190

[28] Tolomei, G., Campagnano, C., Silvestri, F., & Trappolini, G. (2023). Prompt-to-os (P2OS): revolutionizing operating systems and human-computer interaction with integrated AI generative models. 2023 IEEE 5th International Conference on Cognitive Machine Intelligence (CogMI), 128-134. https://doi.org/10.1109/CogMI58952.2023.00027

[29] Siriwatana, K., & Pongpanich, S. (2025). Developing and evaluating a dental incident reporting system: a user-centered approach to risk management. BMC Oral Health, 25(1), 1-19. https://doi.org/10.1186/s12903-025-05729-5

[30] Gohari, A., Ahmad, A. B., Balasbaneh, A. T., Gohari, A., Hasan, R., & Sholagberu, A. T. (2022). Significance of intermodal freight modal choice criteria: MCDM-based decision support models and SP-based modal shift policies. Transport Policy, 121, 46-60. https://doi.org/10.1016/j.tranpol.2022.03.015

[31] Szabo, B., & Hercegfi, K. (2023). User‐centered approaches in software development processes: Qualitative research into the practice of Hungarian companies. Journal of Software: Evolution and Process, 35(2), e2501. https://doi.org/10.1002/smr.2501

[32] AlSaad, R., Abd-Alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024). Multimodal large language models in health care: applications, challenges, and future outlook. Journal of medical Internet research, 26, e59505. https://doi.org/10.2196/59505

[33] Vincalek, J., Walton, S., & Evans, B. (2021). A user-centered approach to evolutionary algorithms and their use in industry. Cogent Engineering, 8(1), 1995110. https://doi.org/10.1080/23311916.2021.1995110

[34] Yao, Z., Wu, X., Wu, Y., & Wen, X. (2023). Enhancing industrial design competitiveness: Research and application of a machine tool industrial design decision-making method based on product family architecture and systematic evaluation. Applied Sciences, 13(21), 11831. https://doi.org/10.3390/app132111831

[35] Duan, S. (2025). Systematic analysis of user perception for interface design enhancement. Journal of Computer Science and Software Applications, 5(2). https://doi.org/10.5281/zenodo.14832445