A Data Mining-Based Model for Assessing Guangzhou's Higher Vocational Colleges 'New Energy Automobile Majors' Vocational Skills

He, Ling and Hamid, Hashima (2024) A Data Mining-Based Model for Assessing Guangzhou's Higher Vocational Colleges 'New Energy Automobile Majors' Vocational Skills. International Journal of Religion, 5 (1). pp. 44-58. ISSN 2633-3538

Text
J17927_0f1dee1b1b0c5f98cb6c5f0c97ada85b.pdf
Restricted to Registered users only
Download (607kB) | Request a copy

Official URL: https://doi.org/10.61707/17kvqf03

Abstract

New Energy Vehicles (NEVs) have evolved the rules in the Automobile Sector (AS), and Higher Vocational Colleges (HVC) must adapt in order in order to provide students with the skills they require to be successful within this rapidly evolving industry. For the purpose of measuring the real-world abilities of students participating in Renewable Energy (RE) vehicle programs at the HVC in Guangzhou, China, this study develops a unique model. The approach employs algorithms for data mining to enhance the accuracy and accessibility of results through the use of Random Forest (RF) and Generalized Additive Models (GAM) in a layering architecture. By combining GAM's detailed study of the features' impact on job performance with RF's accurate feature selection and the theory of evolution, researchers can investigate non-linear relationships and discover several things about the distinct functions performed by distinct personality traits and skills. In endurance validation tests, the hybrid model obtained an acceptable 88% F1 score, 90% recall, 86% precision, and 88% accuracy. The findings show the positive aspects of using modern data-driven methods to more closely match educational institutions with the constantly evolving needs of the AS. This might improve students' skills and job marketability. Along with solving an imbalance in the HVC training market, this study provides an adaptable framework that can be used in different areas of research.

Item Type:	Article
Uncontrolled Keywords:	Vocational Education, Automotive Industry, Random Forest, Data Mining, Generalized Additive Models
Subjects:	L Education > L Education (General)
Depositing User:	Mr. Mohamad Zulkhibri Rahmad
Date Deposited:	31 Jan 2025 03:50
Last Modified:	31 Jan 2025 03:51
URI:	http://eprints.uthm.edu.my/id/eprint/12436

Actions (login required)

View Item