Work

A Multilayered Back Propagation Algorithm to Predict Significant Attributes of UG Pursuing Students Absenteeism at Rural Educational Institution

Year: 2018
Type: article
Abstract: Recently Educational data mining has gained the attention of the researcher in the research industry and also in the society because of the availability of a large amount of data. There is a need for turning such data into useful information and knowledge. At present, there is a lack of well defined diagnostic algorithm to predict the reason for student absenteeism. It is critical to identify the most significant attributes in a dataset using the traditional statistical methods. This paper focuses on overcoming the difficulties involved in analyzing the student dataset by using Machine Learning Techniques. For mining purpose, Data pre-processing is done on the dataset which is a collection of questionnaire gathered from students in a semirural institution. Multilayered Back Propagation Algorithm was used to construct the neural network with weights and bias by applying a transfer function in the dataset. The highly influencing attributes having high weights and bias from the dataset was chosen and a Neural Network was constructed. This knowledge is used to identify the reason for the leave taken by the students and helps the management and staff members to improve the performance of the student.
Language: English
Open Access status: hybrid
OpenAlex ID: W2929931265
FWCI: 0.205
Cites: 12
Cited by: 1
Related to: 10