Article: A machine classification learning model based on factor space mathematical theory in higher vocational education Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.25 pp.33 - 47 Abstract: To address teaching semantic gap issues in image sample learning for vocational education evaluation, this paper first applies factor domain theory to the teaching semantic embedding domain. Based on the relationships among semantics, it studies conjunction and reduction of factors, as well as the expansion and contraction of the factor domain. The enhanced factor space approach is then utilised in vocational education evaluation. Visual features are extracted using the residual network (ResNet101), and a generative adversarial network (GAN) is trained to produce more realistic picture characteristics. By combining teaching attributes and noise, the generator outputs picture characteristics which are then combined with class marks to train the categoriser, thereby completing the classification of teaching evaluation images. Experimental results reveal that the offered model achieves a classification accuracy of 92.5%, effectively helping to enhance the quality of higher vocational education. Inderscience Publishers - linking academia, business and industry through research

Title: A machine classification learning model based on factor space mathematical theory in higher vocational education

Authors: Ruishuai Chai

Addresses: Henan Industry and Trade Vocational College, Zhengzhou 450046, China

Abstract: To address teaching semantic gap issues in image sample learning for vocational education evaluation, this paper first applies factor domain theory to the teaching semantic embedding domain. Based on the relationships among semantics, it studies conjunction and reduction of factors, as well as the expansion and contraction of the factor domain. The enhanced factor space approach is then utilised in vocational education evaluation. Visual features are extracted using the residual network (ResNet101), and a generative adversarial network (GAN) is trained to produce more realistic picture characteristics. By combining teaching attributes and noise, the generator outputs picture characteristics which are then combined with class marks to train the categoriser, thereby completing the classification of teaching evaluation images. Experimental results reveal that the offered model achieves a classification accuracy of 92.5%, effectively helping to enhance the quality of higher vocational education.

Keywords: vocational education; factor space mathematical theory; machine classification learning; ResNet101 model; generative adversarial network; GAN.

DOI: 10.1504/IJICT.2025.147142

International Journal of Information and Communication Technology, 2025 Vol.26 No.25, pp.33 - 47

Received: 06 May 2025
Accepted: 23 May 2025
Published online: 10 Jul 2025 *

Title: A machine classification learning model based on factor space mathematical theory in higher vocational education

Keep up-to-date