A Choquet Fuzzy Integral Vertical Bagging Classifier for Mobile Telematics Data Analysis

TL;DR

This paper introduces a novel Choquet fuzzy integral vertical bagging classifier that effectively detects gender from mobile telematics data, combining multiple classifiers for improved accuracy.

Contribution

It presents a new ensemble classifier using Choquet fuzzy integral fusion of random forests trained on features selected via rough set theory for gender detection.

Findings

Outperforms other classifiers in accuracy

Effective on real telematics dataset

Demonstrates the utility of fuzzy integral fusion

Abstract

Mobile app development in recent years has resulted in new products and features to improve human life. Mobile telematics is one such development that encompasses multidisciplinary fields for transportation safety. The application of mobile telematics has been explored in many areas, such as insurance and road safety. However, to the best of our knowledge, its application in gender detection has not been explored. This paper proposes a Choquet fuzzy integral vertical bagging classifier that detects gender through mobile telematics. In this model, different random forest classifiers are trained by randomly generated features with rough set theory, and the top three classifiers are fused using the Choquet fuzzy integral. The model is implemented and evaluated on a real dataset. The empirical results indicate that the Choquet fuzzy integral vertical bagging classifier outperforms other classifiers.