THE INTEGRATION OF FUZZY ALGORITHM AND VISUAL COMMUNICATION TECHNOLOGY IN THE DIGITAL EXHIBITION MODE OF MUSEUMS

Zhu Ziyou

References

  1. [1] L. Yan and H. Wang, Research and practice of digitalmedia interaction design in the field of museum exhibition,Probe-Media and Communication Studies, 5(3), 2023, 14-23.https://doi.org/10.59429/pmcs.v5i3.1888.
  2. [2] M. Cheng, Analysis of digital curating in museums, Interdisci-plinary Humanities and Communication Studies, 1(5), 2024.https://doi.org/10.61173/twhbyn17.
  3. [3] L. Hu, Interactive media design method in digital exhibitionof art museum based on big data, in Proceedings ofInternational Conference on Innovative Computing, Singapore,2023, 264–272.
  4. [4] H. Yang and L. Guo, Evolution of exhibition space strategiesin smart museums: A historical transition from traditional todigital, Heran¸ca, 7(1), 2024, 1–11.
  5. [5] F. Taormina and S. B. Baraldi, Museums and digital technology:A literature review on organisational issues, Rethinking Cultureand Creativity in the Digital Transformation, 30, 2023, 69–87.
  6. [6] D. Xu, W. Zhang, C. Zhang, R. Mao, and C. Wang, Digitallyenriched exhibitions: Perspectives from museum professionals,Tourism Management, 105, 2024, 104970.
  7. [7] R. Wang, Computer-aided interaction of visual communicationtechnology and art in new media scenes, Computer-AidedDesign and Applications, 19(S3), 2021, 75–84.
  8. [8] Y. Wang and Y. Li, Application of artificial intelligencealgorithm in indoor virtual display system, Procedia ComputerScience, 228, 2023, 1294–1301.
  9. [9] J. Liu, C. Li, J. Pan, and J. Guo, Visual communication ofmoving images based on AI recognition and light sensing imageedge detection algorithm, Optical and Quantum Electronics,56(4), 2024, 695.
  10. [10] A. Calise, Inhabiting the museum: A history of physical presencefrom analog to digital exhibition spaces, AN-ICON, 2(2), 2023,56–73.
  11. [11] G. Shan and W. Yufei, Application analysis of new media digitalart in museum exhibition design, Media and CommunicationResearch, 4(9), 2023, 6–10.
  12. [12] L. Chang, D. Cai, and Z. Liu, Research on the multimodalintegration of visual communication design and public artin digital perspective, Applied Mathematics and NonlinearSciences, 9(1), 1–15.https://doi.org/10.2478/amns-2024-1286
  13. [13] L. Su, H. Liu, and W. Zhao, Supergroup algorithm andknowledge graph construction in museum digital displayplatform, Heliyon, 10(19), 2024, e38076.
  14. [14] G. Varma, R. Chauhan, and E. Yafi, ARTYCUL: A privacy-preserving ML-driven framework to determine the popularityof a cultural exhibit on display, Sensors, 21(4), 2021, 1527.
  15. [15] K. Yang and H. Wang, The application of interactive humanoidrobots in the history education of museums under artificialintelligence, International Journal of Humanoid Robotics,20(6), 2023, 2250016.
  16. [17], PIP
  17. [18], FCA [23], EFA-AHP [24], and thenewly suggested FuzzAIF-MDE. As higher ratings indicate,the FuzzAIF-MDE method consistently outperforms otheralgorithms in all exhibition modes, particularly in renderedvirtual visits.5.4 Interaction EfficiencyThe heatmap graph shown in Fig. 5 below displays theresults of various algorithms concerning the efficiencyof interactions across different museum exhibits. Foranalysing visitor engagement and interaction with digitalexhibits, interaction efficiency analysis per exhibit acrossdifferent algorithms shows how different algorithmsperform. Compared to FCA and IGA-CNN, FuzzAIF-MDEperforms moderately well but with the best engagementand interaction scores. While PIP has many interactions,engagement is minimal, and EFA-AHP has the worst10Figure 5. Average Escore analysis of different algorithms.Figure 6. Interaction efficiency analysis per exhibit over different algorithms.11Table 3Comparison of Visual Quality Metrics and VCI Scores for Different AlgorithmsAlgorithms Glare Level Connection toOutdoorsLight onObjectsLightingQualityColourTemperatureComfortLevelVCI ScoreFuzzAIF-MDE 0.85 0.8 0.9 0.88 0.85 0.84 0.85FCA 0.75 0.7 0.8 0.76 0.75 0.72 0.74IGA-CNN 0.7 0.65 0.75 0.72 0.7 0.68 0.71PIP 0.65 0.6 0.7 0.65 0.68 0.6 0.63EFA-AHP 0.6 0.55 0.65 0.6 0.62 0.55 0.58Table 4Comparative Analysis of Engagement and Interaction Efficiency Across Different MethodsMethod NE ScoreEscorei−EscoreminEscoremax −EscoreminNI CountIi−IminImax−IminMembershipValue µiWeightedEngagement SumWeightedInteraction SumIEFuzzAIF-MDE 0.95 0.95 0.9 0.855 0.9 1.85FCA 0.85 0.7 0.8 0.595 0.65 1.245IGA-CNN 0.75 0.6 0.75 0.525 0.55 1.075PIP 0.7 0.65 0.7 0.455 0.55 1.005EFA-AHP 0.6 0.6 0.65 0.36 0.45 0.81Figure 7. ARAS analysis on varying visitors.overall performance. Each algorithm has a unique effecton enhancing digital display experiences, and the graphicemphasises these variations. By comparing the impactof each method on various exhibitions, the graph showswhere each algorithm excels and falls short. Additionally,it can help with exhibit location and design by revealingpatterns where specific exhibits always do better orworse, independent of the algorithm. Finding anomaliesin the data can help optimise algorithms by uncoveringtheir strengths and weaknesses. Incorporating confidenceintervals or error bars would demonstrate the data’sreliability over trials. Figure 6 shows that the FuzzAIF-MDE framework is more effective in improving the digitalFigure 8. ARAS analysis on varying digital exhibitionmodes.museum experience by increasing visitor engagement thanother algorithms.Table 4 provides a comparison of different approachesto improving the effectiveness of interactions in virtualmuseum exhibits. Due to its exceptional performance inengagement and interaction, FuzzAIF-MDE stands outwith the greatest NE Score usingEscorei−EscoreminEscoremax −Escoreminas 0.95,NI Count using Ii−IminImax−Iminas 0.95, membership value asµi 0.9, and an interaction efficiency (IE) score of 1.85.IGA-CNN and PIP have lower IE scores of 1.075 and12Figure 9. Cognitive load index.1.005, respectively, while FCA follows with an IE of 1.245.EFA-AHP has the worst performance, with an IE of 0.81.5.5 AR Adaptability ScoreThe AR adaptability score (ARAS) measures the efficiencywith which AR information adjusts to visitor engagementsand feedback in digital exhibitions. It assesses how wellthe AR content improves user engagement and happiness.This indicator evaluates the efficacy of adapting ARtechniques to enhance visitors’ overall experience. A higherARAS signifies the AR material’s greater adaptability andresponsiveness to visitor feedback, resulting in improvedengagement and pleasure. A lower ARAS indicates thatthe digital adaptation may require enhancement to matchvisitor interactions more effectively. This suggests that theAR information is compassionate and flexible, adjustingitself according to the comments and interactions fromvisitors (Refer to Figs. 7 and 8).5.6 Cognitive Load IndexThe NASA-TLX metric was used to evaluate the cognitiveload index (CLI) (Fig. 9). This metric measures how muchmental demand, effort, and irritation users feel as partof their task. The FuzzAIF-MDE architecture reducedcognitive strain by 16.2% compared to more conventionaldigital exhibition models. The improved fuzzy–drivencontent architecture is responsible for this enhancement;it adapts the visual complexity, interaction frequency, andinformation density of AR in real time according to visitors’engagement levels. Reduced cognitive burden, improvedinformation processing, and an improved user experienceresult from the system’s usage of adaptive membershipfunctions and rule-based customisation. Visitors feel lesstired when engaging with exhibits, resulting in a moreimmersive and approachable museum experience, whichcorresponds with higher engagement retention.With engagement-driven measures like adaptive reac-tion time, interaction efficiency, and content personalisedaccuracy, FuzzAIF-MDE might be tested against baselinemodels to provide it more solid empirical support.Quantifying performance increases might be done bystatistical comparisons using ANOVA or Wilcoxon signed-rank tests. Separating the components of fuzzy logic andAR could be done using ablation research, which wouldclarify their distinct contributions. Better generalisabilityand believability, as well as a stronger advantage overtraditional digital display methods, might be achieved byconducting validation tests of the framework in variousmuseum settings with varied visitor demographics andexhibit types.Using a dynamic fuzzy inference system, the FuzzAIF-MDE framework guarantees real-time adaptability. Thissystem modifies material displays according to visitordemographics, engagement patterns, and interaction pref-erences. It uses a fuzzy rule-based engine to dynamicallymodify AR material depending on input variables from sev-eral sources, including dwell duration, gaze tracking, ges-ture intensity, and past interaction history. The system usesan adaptive membership function tuning mechanism tohandle different degrees of input uncertainty. Metaheuristicmethods, such as particle swarm optimisation (PSO), areused to optimise the thresholds of linguistic variables. Sinceelaborate fuzzy rule sets increased processing overhead,balancing computational efficiency with inference accuracybecame crucial. This study addressed this by implementinga rule-pruning technique that uses entropy-based relevanceweighting. This ensures that our system can make real-timedecisions without sacrificing responsiveness. The systemalso improved exhibition customisation across diversevisitor groups by integrating a knowledge-driven fuzzyrule adjustment mechanism, which helped manage culturaldifferences in content adaption.6. Research SummaryImproved comprehension of the effects of various visualcommunication technologies on museum exhibition experi-ences can be achieved through fuzzy algorithms to combinequestionnaire data with participant characteristics. The13goal is to incorporate these findings into digital exhibitionsin a more efficient, engaging, and personalised way forindividual visitors. Combining fuzzy logic with AR, theFuzzAIF-MDE promotes museum visitors’ engagement andsatisfaction with digital exhibitions by enabling real-timecontent customisation according to visitor feedback andconditions. Based on better VCI scores, this strategyoutperforms others in optimising digital exhibitions acrossmedia like videos, photos, and renderings, providing amore immersive and individualised museum experience.While the results are encouraging, there is still room forimprovement in scalability and compatibility with otherforms of digital material. The effectiveness and adaptabilityof the framework should be further investigated byinvestigating its impact on different visitor demographicsand its application across various museum culturalenvironments integrated with the VR platform. UsingAR-based multimodal interaction and dynamic fuzzyrule tuning, FuzzAIF-MDE’s modular design allows foreasy adaption across various museum settings withoutrequiring substantial reconfiguration. Future researchwill examine deployments across institutions, using real-time visitor analytics and varied cultural datasets toconfirm their scalability. Furthermore, self-optimising fuzzyrules that include reinforcement learning might improveadaptability in the long run. To make the framework moreapplicable to large-scale digital exhibits, future work shouldalso concentrate on improving computational efficiency,especially enhancing real-time inference in edge-computingcontexts.FundingThis paper is supported by the 2023 Discipline Co-construction Project of Guangdong Provincial Philosophyand Social Sciences Planning, titled “Research on UserExperience of Virtual-Reality Technology EmpoweringExhibitions in Guangdong Folk Custom Museums”(Project No.: GD23XYS051).References[1] L. Yan and H. Wang, Research and practice of digitalmedia interaction design in the field of museum exhibition,Probe-Media and Communication Studies, 5(3), 2023, 14-23.https://doi.org/10.59429/pmcs.v5i3.1888.[2] M. Cheng, Analysis of digital curating in museums, Interdisci-plinary Humanities and Communication Studies, 1(5), 2024.https://doi.org/10.61173/twhbyn17.[3] L. Hu, Interactive media design method in digital exhibitionof art museum based on big data, in Proceedings ofInternational Conference on Innovative Computing, Singapore,2023, 264–272.[4] H. Yang and L. Guo, Evolution of exhibition space strategiesin smart museums: A historical transition from traditional todigital, Heran¸ca, 7(1), 2024, 1–11.[5] F. Taormina and S. B. Baraldi, Museums and digital technology:A literature review on organisational issues, Rethinking Cultureand Creativity in the Digital Transformation, 30, 2023, 69–87.[6] D. Xu, W. Zhang, C. Zhang, R. Mao, and C. Wang, Digitallyenriched exhibitions: Perspectives from museum professionals,Tourism Management, 105, 2024, 104970.[7] R. Wang, Computer-aided interaction of visual communicationtechnology and art in new media scenes, Computer-AidedDesign and Applications, 19(S3), 2021, 75–84.[8] Y. Wang and Y. Li, Application of artificial intelligencealgorithm in indoor virtual display system, Procedia ComputerScience, 228, 2023, 1294–1301.[9] J. Liu, C. Li, J. Pan, and J. Guo, Visual communication ofmoving images based on AI recognition and light sensing imageedge detection algorithm, Optical and Quantum Electronics,56(4), 2024, 695.[10] A. Calise, Inhabiting the museum: A history of physical presencefrom analog to digital exhibition spaces, AN-ICON, 2(2), 2023,56–73.[11] G. Shan and W. Yufei, Application analysis of new media digitalart in museum exhibition design, Media and CommunicationResearch, 4(9), 2023, 6–10.[12] L. Chang, D. Cai, and Z. Liu, Research on the multimodalintegration of visual communication design and public artin digital perspective, Applied Mathematics and NonlinearSciences, 9(1), 1–15.https://doi.org/10.2478/amns-2024-1286[13] L. Su, H. Liu, and W. Zhao, Supergroup algorithm andknowledge graph construction in museum digital displayplatform, Heliyon, 10(19), 2024, e38076.[14] G. Varma, R. Chauhan, and E. Yafi, ARTYCUL: A privacy-preserving ML-driven framework to determine the popularityof a cultural exhibit on display, Sensors, 21(4), 2021, 1527.[15] K. Yang and H. Wang, The application of interactive humanoidrobots in the history education of museums under artificialintelligence, International Journal of Humanoid Robotics,20(6), 2023, 2250016.[16] M. J. Rani and S. Periyasamy, Theory of matrixes forintuitionistic fuzzy hypersoft sets and their use in decision-making system with multiple attributes, PatternIQ Mining,1(2), 2024, 65–75. https://doi.org/10.70023/piqm24126.[17] C. Lin, X. Hu, T. Cheng, and R. Yin, Development of thedigital retrieval system integrating intelligent information andimproved genetic algorithm: A study based on art museums,Plos One, 19(6), 2024, e0305690.[18] M. Yang, J. X. Zhang, Y. Shi, B. Liu, L. X. Guo, Z. P. Yu,B. Sheng, and L. Z. Ma, Framework of personalised layout fora museum exhibition hall, Multimedia Tools and Applications,83(8), 2024, 24563–24587.
  18. [19] Y. Xiong, Research on the management system of graphicdesign works based on virtual reality technology, in Proceedingsof 6th International Conference on Smart Grid and ElectricalAutomation (ICSGEA), 2021, 334–337.
  19. [20] L. Chang, D. Cai, and Z. Liu, Research on the multimodalintegration of visual communication design and public artin digital perspective, Applied Mathematics and NonlinearSciences, 9(1), 2024, 1–15. https://doi.org/10.2478/amns-2024-1286.
  20. [21] Z. Liu and S. Chang, A study of digital exhibition visual designled by digital twin and VR technology, Measurement: Sensors,31, 2024, 100970.
  21. [23], EFA-AHP
  22. [24], and thenewly suggested FuzzAIF-MDE. As higher ratings indicate,the FuzzAIF-MDE method consistently outperforms otheralgorithms in all exhibition modes, particularly in renderedvirtual visits.5.4 Interaction EfficiencyThe heatmap graph shown in Fig. 5 below displays theresults of various algorithms concerning the efficiencyof interactions across different museum exhibits. Foranalysing visitor engagement and interaction with digitalexhibits, interaction efficiency analysis per exhibit acrossdifferent algorithms shows how different algorithmsperform. Compared to FCA and IGA-CNN, FuzzAIF-MDEperforms moderately well but with the best engagementand interaction scores. While PIP has many interactions,engagement is minimal, and EFA-AHP has the worst10Figure 5. Average Escore analysis of different algorithms.Figure 6. Interaction efficiency analysis per exhibit over different algorithms.11Table 3Comparison of Visual Quality Metrics and VCI Scores for Different AlgorithmsAlgorithms Glare Level Connection toOutdoorsLight onObjectsLightingQualityColourTemperatureComfortLevelVCI ScoreFuzzAIF-MDE 0.85 0.8 0.9 0.88 0.85 0.84 0.85FCA 0.75 0.7 0.8 0.76 0.75 0.72 0.74IGA-CNN 0.7 0.65 0.75 0.72 0.7 0.68 0.71PIP 0.65 0.6 0.7 0.65 0.68 0.6 0.63EFA-AHP 0.6 0.55 0.65 0.6 0.62 0.55 0.58Table 4Comparative Analysis of Engagement and Interaction Efficiency Across Different MethodsMethod NE ScoreEscorei−EscoreminEscoremax −EscoreminNI CountIi−IminImax−IminMembershipValue µiWeightedEngagement SumWeightedInteraction SumIEFuzzAIF-MDE 0.95 0.95 0.9 0.855 0.9 1.85FCA 0.85 0.7 0.8 0.595 0.65 1.245IGA-CNN 0.75 0.6 0.75 0.525 0.55 1.075PIP 0.7 0.65 0.7 0.455 0.55 1.005EFA-AHP 0.6 0.6 0.65 0.36 0.45 0.81Figure 7. ARAS analysis on varying visitors.overall performance. Each algorithm has a unique effecton enhancing digital display experiences, and the graphicemphasises these variations. By comparing the impactof each method on various exhibitions, the graph showswhere each algorithm excels and falls short. Additionally,it can help with exhibit location and design by revealingpatterns where specific exhibits always do better orworse, independent of the algorithm. Finding anomaliesin the data can help optimise algorithms by uncoveringtheir strengths and weaknesses. Incorporating confidenceintervals or error bars would demonstrate the data’sreliability over trials. Figure 6 shows that the FuzzAIF-MDE framework is more effective in improving the digitalFigure 8. ARAS analysis on varying digital exhibitionmodes.museum experience by increasing visitor engagement thanother algorithms.Table 4 provides a comparison of different approachesto improving the effectiveness of interactions in virtualmuseum exhibits. Due to its exceptional performance inengagement and interaction, FuzzAIF-MDE stands outwith the greatest NE Score usingEscorei−EscoreminEscoremax −Escoreminas 0.95,NI Count using Ii−IminImax−Iminas 0.95, membership value asµi 0.9, and an interaction efficiency (IE) score of 1.85.IGA-CNN and PIP have lower IE scores of 1.075 and12Figure 9. Cognitive load index.1.005, respectively, while FCA follows with an IE of 1.245.EFA-AHP has the worst performance, with an IE of 0.81.5.5 AR Adaptability ScoreThe AR adaptability score (ARAS) measures the efficiencywith which AR information adjusts to visitor engagementsand feedback in digital exhibitions. It assesses how wellthe AR content improves user engagement and happiness.This indicator evaluates the efficacy of adapting ARtechniques to enhance visitors’ overall experience. A higherARAS signifies the AR material’s greater adaptability andresponsiveness to visitor feedback, resulting in improvedengagement and pleasure. A lower ARAS indicates thatthe digital adaptation may require enhancement to matchvisitor interactions more effectively. This suggests that theAR information is compassionate and flexible, adjustingitself according to the comments and interactions fromvisitors (Refer to Figs. 7 and 8).5.6 Cognitive Load IndexThe NASA-TLX metric was used to evaluate the cognitiveload index (CLI) (Fig. 9). This metric measures how muchmental demand, effort, and irritation users feel as partof their task. The FuzzAIF-MDE architecture reducedcognitive strain by 16.2% compared to more conventionaldigital exhibition models. The improved fuzzy–drivencontent architecture is responsible for this enhancement;it adapts the visual complexity, interaction frequency, andinformation density of AR in real time according to visitors’engagement levels. Reduced cognitive burden, improvedinformation processing, and an improved user experienceresult from the system’s usage of adaptive membershipfunctions and rule-based customisation. Visitors feel lesstired when engaging with exhibits, resulting in a moreimmersive and approachable museum experience, whichcorresponds with higher engagement retention.With engagement-driven measures like adaptive reac-tion time, interaction efficiency, and content personalisedaccuracy, FuzzAIF-MDE might be tested against baselinemodels to provide it more solid empirical support.Quantifying performance increases might be done bystatistical comparisons using ANOVA or Wilcoxon signed-rank tests. Separating the components of fuzzy logic andAR could be done using ablation research, which wouldclarify their distinct contributions. Better generalisabilityand believability, as well as a stronger advantage overtraditional digital display methods, might be achieved byconducting validation tests of the framework in variousmuseum settings with varied visitor demographics andexhibit types.Using a dynamic fuzzy inference system, the FuzzAIF-MDE framework guarantees real-time adaptability. Thissystem modifies material displays according to visitordemographics, engagement patterns, and interaction pref-erences. It uses a fuzzy rule-based engine to dynamicallymodify AR material depending on input variables from sev-eral sources, including dwell duration, gaze tracking, ges-ture intensity, and past interaction history. The system usesan adaptive membership function tuning mechanism tohandle different degrees of input uncertainty. Metaheuristicmethods, such as particle swarm optimisation (PSO), areused to optimise the thresholds of linguistic variables. Sinceelaborate fuzzy rule sets increased processing overhead,balancing computational efficiency with inference accuracybecame crucial. This study addressed this by implementinga rule-pruning technique that uses entropy-based relevanceweighting. This ensures that our system can make real-timedecisions without sacrificing responsiveness. The systemalso improved exhibition customisation across diversevisitor groups by integrating a knowledge-driven fuzzyrule adjustment mechanism, which helped manage culturaldifferences in content adaption.6. Research SummaryImproved comprehension of the effects of various visualcommunication technologies on museum exhibition experi-ences can be achieved through fuzzy algorithms to combinequestionnaire data with participant characteristics. The13goal is to incorporate these findings into digital exhibitionsin a more efficient, engaging, and personalised way forindividual visitors. Combining fuzzy logic with AR, theFuzzAIF-MDE promotes museum visitors’ engagement andsatisfaction with digital exhibitions by enabling real-timecontent customisation according to visitor feedback andconditions. Based on better VCI scores, this strategyoutperforms others in optimising digital exhibitions acrossmedia like videos, photos, and renderings, providing amore immersive and individualised museum experience.While the results are encouraging, there is still room forimprovement in scalability and compatibility with otherforms of digital material. The effectiveness and adaptabilityof the framework should be further investigated byinvestigating its impact on different visitor demographicsand its application across various museum culturalenvironments integrated with the VR platform. UsingAR-based multimodal interaction and dynamic fuzzyrule tuning, FuzzAIF-MDE’s modular design allows foreasy adaption across various museum settings withoutrequiring substantial reconfiguration. Future researchwill examine deployments across institutions, using real-time visitor analytics and varied cultural datasets toconfirm their scalability. Furthermore, self-optimising fuzzyrules that include reinforcement learning might improveadaptability in the long run. To make the framework moreapplicable to large-scale digital exhibits, future work shouldalso concentrate on improving computational efficiency,especially enhancing real-time inference in edge-computingcontexts.FundingThis paper is supported by the 2023 Discipline Co-construction Project of Guangdong Provincial Philosophyand Social Sciences Planning, titled “Research on UserExperience of Virtual-Reality Technology EmpoweringExhibitions in Guangdong Folk Custom Museums”(Project No.: GD23XYS051).References[1] L. Yan and H. Wang, Research and practice of digitalmedia interaction design in the field of museum exhibition,Probe-Media and Communication Studies, 5(3), 2023, 14-23.https://doi.org/10.59429/pmcs.v5i3.1888.[2] M. Cheng, Analysis of digital curating in museums, Interdisci-plinary Humanities and Communication Studies, 1(5), 2024.https://doi.org/10.61173/twhbyn17.[3] L. Hu, Interactive media design method in digital exhibitionof art museum based on big data, in Proceedings ofInternational Conference on Innovative Computing, Singapore,2023, 264–272.[4] H. Yang and L. Guo, Evolution of exhibition space strategiesin smart museums: A historical transition from traditional todigital, Heran¸ca, 7(1), 2024, 1–11.[5] F. Taormina and S. B. Baraldi, Museums and digital technology:A literature review on organisational issues, Rethinking Cultureand Creativity in the Digital Transformation, 30, 2023, 69–87.[6] D. Xu, W. Zhang, C. Zhang, R. Mao, and C. Wang, Digitallyenriched exhibitions: Perspectives from museum professionals,Tourism Management, 105, 2024, 104970.[7] R. Wang, Computer-aided interaction of visual communicationtechnology and art in new media scenes, Computer-AidedDesign and Applications, 19(S3), 2021, 75–84.[8] Y. Wang and Y. Li, Application of artificial intelligencealgorithm in indoor virtual display system, Procedia ComputerScience, 228, 2023, 1294–1301.[9] J. Liu, C. Li, J. Pan, and J. Guo, Visual communication ofmoving images based on AI recognition and light sensing imageedge detection algorithm, Optical and Quantum Electronics,56(4), 2024, 695.[10] A. Calise, Inhabiting the museum: A history of physical presencefrom analog to digital exhibition spaces, AN-ICON, 2(2), 2023,56–73.[11] G. Shan and W. Yufei, Application analysis of new media digitalart in museum exhibition design, Media and CommunicationResearch, 4(9), 2023, 6–10.[12] L. Chang, D. Cai, and Z. Liu, Research on the multimodalintegration of visual communication design and public artin digital perspective, Applied Mathematics and NonlinearSciences, 9(1), 1–15.https://doi.org/10.2478/amns-2024-1286[13] L. Su, H. Liu, and W. Zhao, Supergroup algorithm andknowledge graph construction in museum digital displayplatform, Heliyon, 10(19), 2024, e38076.[14] G. Varma, R. Chauhan, and E. Yafi, ARTYCUL: A privacy-preserving ML-driven framework to determine the popularityof a cultural exhibit on display, Sensors, 21(4), 2021, 1527.[15] K. Yang and H. Wang, The application of interactive humanoidrobots in the history education of museums under artificialintelligence, International Journal of Humanoid Robotics,20(6), 2023, 2250016.[16] M. J. Rani and S. Periyasamy, Theory of matrixes forintuitionistic fuzzy hypersoft sets and their use in decision-making system with multiple attributes, PatternIQ Mining,1(2), 2024, 65–75. https://doi.org/10.70023/piqm24126.[17] C. Lin, X. Hu, T. Cheng, and R. Yin, Development of thedigital retrieval system integrating intelligent information andimproved genetic algorithm: A study based on art museums,Plos One, 19(6), 2024, e0305690.[18] M. Yang, J. X. Zhang, Y. Shi, B. Liu, L. X. Guo, Z. P. Yu,B. Sheng, and L. Z. Ma, Framework of personalised layout fora museum exhibition hall, Multimedia Tools and Applications,83(8), 2024, 24563–24587.[19] Y. Xiong, Research on the management system of graphicdesign works based on virtual reality technology, in Proceedingsof 6th International Conference on Smart Grid and ElectricalAutomation (ICSGEA), 2021, 334–337.[20] L. Chang, D. Cai, and Z. Liu, Research on the multimodalintegration of visual communication design and public artin digital perspective, Applied Mathematics and NonlinearSciences, 9(1), 2024, 1–15. https://doi.org/10.2478/amns-2024-1286.[21] Z. Liu and S. Chang, A study of digital exhibition visual designled by digital twin and VR technology, Measurement: Sensors,31, 2024, 100970.[22] G. Salvadori, G. Tambellini, A. C¸evik, Z. T. Kazanasmaz, andF. Leccese, Dataset of virtual and real-life visual experiencesinside a museum: Survey on visual perception with objectiveand subjective measures, Data in Brief, 47, 2023, 108963.[23] Y. Nan, N. Yao, Y. Huang, and D. Jiao, The conservation andutilization of museum relics based on internet of things andfuzzy control, Journal of Computational Methods in Sciencesand Engineering, 23, 2023, 1–12.[24] M. Li and Y. Dai, Optimisation strategies for the mod-ular resource construction of art gallery’s exhibition hallsbased on Kansei engineering, IEEE Access, 12, 2024,27870–27886.
  23. [25] Z. Xing, X. Zhu, and Y. Wu, A new real-time 3Ddense semantic mapping system for large-scale environments,International Journal of Robotics and Automation, 39(1), 2024,12–23.
  24. [26] Dataset of virtual and real-life visual experiences inside amuseum: survey on visual perception with objective andsubjective measures—Videos and questionnaire results, 2023.https://data.mendeley.com/datasets/s2v84tvn96/3.
  25. [27] S. Dong, Research on the application of digital mediatechnology in museum exhibition design: A case study of thenational museum of Singapore, in Proceedings of SHS Web ofConferences, 2024, 4031.14
  26. [28] Y. Qi, Q. Ni, Q. Xue, J. Wu, and S. Lee, Analysis of museumexhibition space optimisation design: Grounded theory andanalytic hierarchy process, Asia-Pacific Journal of ConvergentResearch Interchange (APJCRI), 2024, 439–453.
  27. [29] M.J.B. Enojas, A fuzzy inference system for hand injury levelclassification using surface electromyography signals, IAESInternational Journal of Robotics and Automation, 14(1), 2025,103.
  28. [30] S. Swami, R. Singh, A. Gehlot, S.D. Sharma, and D. Kumar,An approach for modern gardening through monitoring andmaintenance of plant health, IAES International Journal ofRobotics and Automation, 13(3), 2024, 307.

Important Links:

Go Back