Open AccessAutomatic forecasting of student’s province towards Information and communication technology awareness
Author(s) -
Chaman Verma,
Deepak Kumar,
Zoltán Illés,
Veronika Stoffová
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/872/1/012043
Subject(s) - random forest , artificial intelligence , machine learning , artificial neural network , residence , computer science , classifier (uml) , workbench , cross validation , statistics , data mining , mathematics , demography , sociology , visualization
An experimental study is conducted to forecast the residence state of the students based on their response provided in the ICT survey held during the academic year 2015-2016 at two universities of India. The dataset consists of 560 instances and 59 features. We considered the state as the response variable and 35 features as predictors after self-reduction. The dataset is trained and tested with k-fold cross validation using three popular supervised machine learning classifiers named Artificial Neural Network (ANN), Sequential Minimal Optimization (SMO) and random forest (RF) in the Weka 3.8.1 workbench. The outcomes of the study reveal that RF classifier outperformed with highest accuracy (83.39%) the ANN and SMO at 6-Fold of Cross-Validation (CV). Finally, the authors presented state forecast models which accurately forecasting the state of the student based on their answers during the survey with stabilizing the value of k=6 of CV. The maximum accurate forecasting count for Punjab student is found 239 out of 282 and for Haryana student is found 228 out of 278 with k=6. The findings of study prove a significant difference between the RF and the ANN, the SMO in accuracy and there is no significant difference between accuracy gained by SMO and ANN for state forecasting against student’s response during the survey.