Classification of Imbalanced Data Using a Modified Fuzzy-Neighbor Weighted Approach

Journal Title: International Journal of Intelligent Engineering and Systems - Year 2017, Vol 10, Issue 1

Abstract

Classification of imbalanced datasets is one of the widely explored challenges of the decade. The imbalance occurs in many real world datasets due to uneven distribution of data into classes, i.e. one class has more instances while others have a few that results in the biased performances of traditional classifiers towards the majority class with large number of instances and ignorance of other classes with less data. Many solutions have been proposed to deal with this issue in various crisp and fuzzy methods. This paper proposes a new hybrid fuzzy weighted nearest neighbor approach to find better overall classification performance for both minority and majority classes of imbalanced data. Benefits of neighbor weighted K nearest neighbor approach i.e. assignment of large weights to small classes and small weights to large classes are merged with fuzzy logic. Fuzzy classification helps in classifying objects more adequately as it determines that how much an object belongs to a class. Experimental results exhibit the improvements in classification of imbalanced data of different imbalance ratios in comparison with other methods.

Authors and Affiliations

Harshita Patel

Keywords

Related Articles

Multi Agent Based Diabetes Diagnosing and Classification with the Aid of Hybrid Firefly-Neural Network

A multi agent distributed data mining system for diagnosing diabetes and classification is proposed. Here we are introducing four agents namely user agent, connection agent, updation agent, and security agent. In which e...

Autonomous Distributed Power Control in Multi-Channel Cognitive Femtocell Network: Feasibility and Convergence

Dynamic user in mobile communication encourages the implementation of self-organized and non-cooperative distributed power control. To be implemented, the power control must meet the feasible and convergent conditions. F...

Image Adaptive Watermarking Using Feature Point Extraction Model

Watermarking is one of the efficient approaches for digital authentication. An adaptive feature point extraction model is proposed in this paper for robust watermarking. The host image is treated with number of geometric...

Classification of Imbalanced Data Using a Modified Fuzzy-Neighbor Weighted Approach

Classification of imbalanced datasets is one of the widely explored challenges of the decade. The imbalance occurs in many real world datasets due to uneven distribution of data into classes, i.e. one class has more inst...

Base Station Positioning in Wireless Sensor Network to aid Cluster Head Selection Process

In this paper, we propose an (SAPSO) Self-Adaptive Particle Swarm Optimization algorithm to solve the base station positioning problem. This algorithm is used to minimize the distance between the base station and cluster...

Download PDF file
  • EP ID EP229394
  • DOI 10.22266/ijies2017.0228.07
  • Views 123
  • Downloads 0

How To Cite

Harshita Patel (2017). Classification of Imbalanced Data Using a Modified Fuzzy-Neighbor Weighted Approach. International Journal of Intelligent Engineering and Systems, 10(1), 56-64. https://europub.co.uk/articles/-A-229394