IJHCS
Vol. 3 No. 6 (2021): IJHCS

Hybridization of Machine Learning Techniques in Predicting Mental Disorder

Alabi, Emmanuel Oluwadunsin (Unknown)
Adeniji, Oluwashola David (Unknown)
Awoyelu, Tolulope Moyo (Unknown)
Fasae, Oluwakemi Dunsin (Unknown)



Article Info

Publish Date
17 Aug 2021

Abstract

This study applied a hybrid Random Forest and Artificial Neural Network (RF-ANN) model in predicting the chances of IT employees developing mental disorder. To measure the performance of the model, Random Forest and Artificial Neural Networks algorithms were separately developed, their results were recorded and compared with the results of the hybridized model. The result obtained from the hybridized model showed a significant improvement in its performance over the individual performances of the Random Forest model and Artificial Neural Networks models. Hybridizing Random Forest and Artificial Neural Networks using “Bagging Ensemble” produced a model that was able to correctly predict the chances of IT employees developing Mental Disorder with 94% recall and 80% F1-score compared to 65% and 60% respectively in the Random Forest Model. With these results, applying the RF-ANN model on improved dataset could be investigated and compared with the results found in this study.

Copyrights © 2021






Journal Info

Abbrev

IJHCS

Publisher

Subject

Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Neuroscience

Description

The International Journal of Human Computing Studies (IJHCS) publishes original research over the whole spectrum of work relevant to the theory and practice of modern interactive systems of the contemporary world. IJHCS accepts papers in forms of original research articles, review articles, book ...