An Ensemble of Fine-Tuned Heterogeneous Bayesian Classifiers
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 2
Abstract
Bayesian network (BN) classifiers use different structures and different training parameters which leads to diversity in classification decisions. This work empirically shows that building an ensemble of several fine-tuned BN classifiers increases the overall classification accuracy. The accuracy of the constituent classifiers can be achieved by fine-tuning each classifier and the diversity is achieved using different BN classifiers. The proposed ensemble combines a Naive Bayes (NB) classifier, five different models of Tree Augmented Naive Bayes (TAN), and four different model of Bayesian Augmented Naive Bayes (BAN). This work also proposes a new Distance-based Diversity Measure (DDM) and uses it to analyze the diversity of the ensembles. The ensemble of fine-tuned classifier achieves better average classification accuracy than any of its constituent classifiers or the ensemble of un-tuned classifiers. Moreover, the empirical experiments present better significant results for many data sets.
Authors and Affiliations
Amel Alhussan, Khalil El Hindi
Keywords
Related Articles
- EP ID EP112238
- DOI 10.14569/IJACSA.2016.070259
- Views 112
- Downloads 0
SmartFit: A Step Count Based Mobile Application for Engagement in Physical Activities
Research has found that relatively few people en-gage in regular exercise or other physical activities. Despite the availability of numerous mobile applications and specialized devices for self-tracking, people mostly la...
Secure user Authentication and File Transfer in Wireless Sensor Network using Improved AES Algorithm
The WSN technology is a highly efficient and effective way of gathering highly sensitive information and is often deployed in mission-critical applications, which makes the security of its data transmission of vital sign...
A Novel approach for Implementing Security over Vehicular Ad hoc network using Signcryption through Network Grid
Security over Vehicular ad hoc network and identifying accurate vehicle location has always been a major challenge over VANET. Even though GPS system can be used to identify the location of the vehicle they too suf...
QRS Detection Based on an Advanced Multilevel Algorithm
This paper presents an advanced multilevel algorithm used for the QRS complex detection. This method is based on three levels. The first permits the extraction of higher peaks using an adaptive thresholding technique. Th...
Enhanced Textual Password Scheme for Better Security and Memorability
Traditional textual password scheme provides a large number of password combinations but users generally use a small portion of available password space. Complex textual passwords are difficult to remember, therefore mos...