Artificial Intelligence with uncertainty
Chunyan Xing
Abstract
Management models in education have recently emerged with plans to make school administration more effective and efficient. Higher education (HE), a postsecondary education, leads to academic degrees. An object class having membership grades that run along a continuum is called a fuzzy set. When tested ...
Read More
Management models in education have recently emerged with plans to make school administration more effective and efficient. Higher education (HE), a postsecondary education, leads to academic degrees. An object class having membership grades that run along a continuum is called a fuzzy set. When tested in online classrooms with abnormal data, this method's effectiveness exceeded that of the intelligent education system. The challenging characteristics of such higher education using fuzzy sets are the students' low family income, a complicated network, and skill development due to the low quality of education. Block structure has been developed based on higher education in a fuzzy sets system for students in terms of low family income, complicated networks, and skill development due to the low quality of education. Hence, in this research, Double Deep Q-Learning network-enabled Multi-Criteria Decision-Making (D2QLN-MCDM) technologies have improved students' higher education with fuzzy sets. It has been used to design, develop, and verify students' higher education in fuzzy sets. The workforce tasked with integrating digital technology into HE have a profound effect on students' learning experiences. HE institutions will need experienced individuals with varied digital knowledge to manage and integrate these technologies effectively. The experimental analysis of D2QLN-MCDM outperforms fuzzy sets using the student's HE regarding precision (99.4), accuracy (90.4%), Recall ratio (97.5%), and specificity (93.9%).
