Conservative Noise Filters
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 5
Abstract
Noisy training data have a huge negative impact on machine learning algorithms. Noise-filtering algorithms have been proposed to eliminate such noisy instances. In this work, we empirically show that the most popular noise-filtering algorithms have a large False Positive (FP) error rate. In other words, these noise filters mistakenly identify genuine instances as outliers and eliminate them. Therefore, we propose more conservative outlier identification criteria that improve the FP error rate and, thus, the performance of the noise filters. With the new filter, an instance is eliminated if and only if it is misclassified by a mutual decision of Naïve Bayesian (NB) classifier and the original filtering criteria being used. The number of genuine instances that are incorrectly eliminated is reduced as a result, thereby improving the classification accuracy.
Authors and Affiliations
Mona M. Jamjoom, Khalil El Hindi
Keywords
Related Articles
- EP ID EP101638
- DOI 10.14569/IJACSA.2016.070548
- Views 107
- Downloads 0
Three Layer Hierarchical Model for Chord
Increasing popularity of decentralized Peer-to-Peer (P2P) architecture emphasizes on the need to come across an overlay structure that can provide efficient content discovery mechanism, accommodate high churn rate and ad...
Enhancing Gray Scale Images for Face Detection under Unstable Lighting Condition
Facial expression plays a vital role in no verbal communication between human beings. The brain, in a quarter of second, can determine the state of mind and the behaviour of a person using different traits in a stable li...
UML based Formal Model of Smart Transformer Power System
Recently many significant improvements have been done in traditionally power system. But still a lot of work is needed in traditional power system to mend many challenges. We propose formal method based on subnet model f...
Smile Detection Tool using OpenCV-Python to Measure Response in Human-Robot Interaction with Animal Robot PARO
Human-robot interaction (HRI) is a field of study that defines the relationship between humans and robot. In robot-assisted mental healthcare, there is still a lack in the methodology especially in evaluating the outcome...
Enhancing eHealth Information Systems for chronic diseases remote monitoring systems
Statistics and demographics for the aging population in Europe are compelling. The stakes are then in terms of disability and chronic diseases whose proportions will increase because of increased life expectancy. Heart f...