Digital Labor Education System using Neural Autoregressive Distribution Estimator based Visual Geometry Group-16 Network

Recently, there is a lack of research in developing Labor Education System (LES) using digital platform and which assist to guide labors. However, the ineffective teaching model lead to decrease the effectiveness of labor education using digital platform. To overcome this, a Neural Autoregressive Distribution Estimator based Visual Geometry Group-16 (NADE-VGG-16) network to analyze effectiveness of teaching model in labor education system. In the context of labor education, the NADE method helps the VGG-16 network model to capture interdependencies between various factors such as teaching techniques, student engagement, practical outcomes to provide a more accurate evaluation results of the teaching model. Initially, the data related to education are acquired from four different datasets with various classes and fed to preprocessing phase to enhance the data quality by word embedding method. Then, the preprocessed data is passed to proposed teaching evaluation model to analyze the efficiency of teaching model. The experimental results of proposed method achieved mean and standard deviation of 0.15 and 0.22 when compared to the existing evaluation method such as Collaborative Filter and Content based filter (CFC).