Knowledge Inferencing Using Artificial Bee Colony and Rough Set for Diagnosis of Hepatitis Disease

Abstract

Vast volumes of raw data are generated from the digital world each day. Acquiring useful information and chief features from this data is challenging, and it has become a prime area of current research. Another crucial area is knowledge inferencing. Much research has been carried out in both directions. Swarm intelligence is used for feature selection whereas for knowledge inferencing either fuzzy or rough computing is widely used. Hybridization of intelligent and swarm intelligence techniques are booming recently. In this research work, the authors hybridize both artificial bee colony and rough set. At the initial phase, they employ an artificial bee colony to find the chief features. Further, these main features are analyzed using rough set generating rules. The proposed model indeed helps to diagnose a disease carefully. An empirical analysis is carried out on hepatitis dataset. In addition, a comparative study is also presented. The analysis shows the viability of the proposed model.

RETRACTED: Liver Disease Detection

“…Recent studies from machine learning shows prediction of road accidents and thereby developing a smart transportation system using different machine learning models have been used by where the highest mean accuracy was achieved from Decision Tree. Artificial bee colony and rough set hybridization technique was used by Acharjya et. al (2021) which was applied on a hepatitis dataset and the proposed model helps in detection of the disease accurately with an accuracy of 96.2%.…”