Enhancing aesthetic education can boost individuals’ skills in recognizing, understanding, appreciating, and creating beauty. Nevertheless, traditional methods for evaluating aesthetic education are often subjective and have limited capacity to handle complex features effectively. This article was based on artificial intelligence to develop an aesthetic education evaluation model, and used an improved K-means clustering algorithm and a pre-trained ResNet-101 model for feature extraction. This article used WikiArt as an experimental data set, which contains 77,229 artworks from 15 art styles. This study used silhouette coefficient, Davies-Bouldin index, Calinski-Harabasz index, and Dunn index to evaluate the model clustering effect. Experimental results indicated that with a clustering \(k\) value of 10, the enhanced algorithm significantly advanced clustering quality, computational efficiency, and memory usage. This model has enhanced the objectivity and efficiency of aesthetic education evaluation and introduced new approaches for classifying and assessing artistic works.
EryongXLiJ. What is the ultimate education task in China? exploring “strengthen moral education for cultivating people” (“Li De Shu Ren”). Educ Philos Theor2021; 53(2): 128–139.
2.
OlyaHJungTHTom DieckMC, et al.Engaging visitors of science festivals using augmented reality: asymmetrical modelling. Int J Contemp Hospit Manag2020; 32(2): 769–796.
3.
BhandariUChangKNebenT. Understanding the impact of perceived visual aesthetics on user evaluations: an emotional perspective. Inf Manag2019; 56(1): 85–93.
4.
YuZLeungB-W. Music teachers and their implementation of the new music curriculum standards in China. Int J Music Educ2019; 37(2): 178–197.
5.
BurkeA. Student retention models in higher education: a literature review. Coll Univ2019; 94(2): 12–21.
6.
WuCZhaoKZhuH, et al.Beautiful environment, beautiful heart–the role of environmental aesthetic on moral education. Eur J Dev Psychol2023; 20(2): 367–383.
7.
ZhangB. Implementation path of extracurricular aesthetic education practices based on interdisciplinary theme learning. Aca J Hum Social Sci2024; 7(3): 114–119.
8.
KarthikeyanVGThangarajPKarthikS. Towards developing hybrid educational data mining model (HEDM) for efficient and accurate student performance evaluation. Soft Comput2020; 24(24): 18477–18487.
9.
YuanWNeubigGLiuP. Bartscore: evaluating generated text as text generation. Adv Neural Inf Process Syst2021; 34: 27263–27277.
10.
SariIPAl-KhowarizmiA-KHanif BatubaraI. Cluster analysis using K-means algorithm and fuzzy C-means clustering for grouping students’ abilities in online learning process. J Computer Sci Inf Tech Telecom Eng2021; 2(1): 139–144.
11.
GovenderPSivakumarV. Application of k-means and hierarchical clustering techniques for analysis of air pollution: a review (1980–2019). Atmos Pollut Res2020; 11(1): 40–56.
12.
GhazalTM. Performances of k-means clustering algorithm with different distance metrics. Int Auto Soft Com2021; 30(2): 735–742.
13.
ChoY-JLeeH-CLimBKimS-B. Classification of weather patterns in the East Asia region using the K-means clustering analysis. Atmosphere2019; 29.4: 451–461.
14.
RanXZhouXLeiM, et al.A novel k-means clustering algorithm with a noise algorithm for capturing urban hotspots. Appl Sci2021; 11(23): 11202.
15.
WangDMaCSunS. Novel paintings from the latent diffusion model through transfer learning. Appl Sci2023; 13(18): 10379.
16.
ZebariRAbdulazeezAZeebareeD, et al.A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction. J Appl Sci Tech Trends2020; 1(1): 56–70.
WenLLiXGaoL. A transfer convolutional neural network for fault diagnosis based on ResNet-50. Neural Comput Appl2020; 32(10): 6111–6124.
19.
LiuCLiuXNgDWK, et al.Deep residual learning for channel estimation in intelligent reflecting surface-assisted multi-user communications. IEEE Trans Wireless Commun2021; 21(2): 898–912.
20.
YuanCYangH. Research on K-value selection method of K-means clustering algorithm. J Multidiscip Res2019; 2.2: 226–235.
21.
BaldassiC. Recombinator-k-means: an evolutionary algorithm that exploits k-means++ for recombination. IEEE Trans Evol Comput2022; 26(5): 991–1003.
22.
AmorSBBelaidFBenkraiemR, et al.Multi-criteria classification, sorting, and clustering: a bibliometric review and research agenda. Ann Oper Res2023; 325(2): 771–793.
23.
Pineda-MoncusíMDernieFDell'IsolaA, et al.Classification of patients with osteoarthritis through clusters of comorbidities using 633 330 individuals from Spain. Rheumatology2023; 62.11: 3592–3600.
24.
AdhikariASenS. Cluster analysis on institutional commitment and organizational climate. Int J Res Pub Rev2023; 4(5): 4974–4988.
25.
StarczewskiAGoetzenPMengJE. A new method for automatic determining of the DBSCAN parameters. J Artif Intell Soft Comput Res2020; 10(3): 209–221.
26.
ZhangYLiMWangS, et al.Gaussian mixture model clustering with incomplete data. ACM Trans Multimed Comput Commun Appl2021; 17(1): 1–14.
27.
WangFChenJLiuF. Keyframe generation method via improved clustering and silhouette coefficient for video summarization. J Web Eng2021; 20(1): 147–170.
28.
WijayaYA. Davies Bouldin index algorithm for optimizing clustering case studies mapping school facilities. Tem J2021; 10(3): 1099–1103.
29.
LimaSPCruzMD. A genetic algorithm using Calinski-Harabasz index for automatic clustering problem. Rev Bras Ciência Avícola2020; 12(3): 97–106.
30.
ReyesAKaestnerEFergusonL, et al.Cognitive phenotypes in temporal lobe epilepsy utilizing data‐and clinically driven approaches: moving toward a new taxonomy. Epilepsia2020; 61(6): 1211–1220.
31.
ChenSZhongSXueB, et al.Iterative scale-invariant feature transform for remote sensing image registration. IEEE Trans Geosci Rem Sens2020; 59(4): 3244–3265.
32.
AgrawalPSharmaTVermaNK. Supervised approach for object identification using speeded up robust features. Int J Adv Intell Paradigms2020; 15(2): 165–182.
