Classroom Behaviour of Talent Cultivation in Colleges and Universities Supported by Deep Learning Technology

Abstract

Among the current significant issues in talent cultivation is changing colleges’ unique talent cultivation strategies and regulating the spontaneous connection of the talent cultivation, industrial, and entrepreneurial chains. In other terms, the growing disparity between college and university incorporation and industry demand for talent has made the growth of creative applied skills targeted to the industry want an acute problem. That is why colleges and universities must cultivate practical talent in a way that is effective, strong, low-cost, and creative. As a result, this research uses deep learning to develop an ensemble convolutional neural network with an attention mechanism to increase the performance and reliability of talent cultivation in universities and colleges and assess the talents properly. For this research, the datasets are gathered with the primary student and classroom information. Followed by standardising the data, the normalization technique is utilised. Then, the proposed method is employed for the data analysis. ANOVA, Chi-square test, and Student’s t -test are applied for the statistical analysis. Finally, the performance of the proposed technique is examined and compared with existing methods to prove the students’ highest performance in talent cultivation.