Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network

Standard classification algorithms are often inaccurate when used in a wireless sensor network (WSN), where the observed data occur in imbalanced classes. The imbalanced data classification problem occurs when the number of samples in one class, usually the class of interest, is much lower than the...

Full description

Saved in:
Bibliographic Details
Main Authors: Hang Yang, Simon Fong, Raymond Wong, Guangmin Sun
Format: Article
Language:English
Published: Wiley 2013-01-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2013/460641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832547772802269184
author Hang Yang
Simon Fong
Raymond Wong
Guangmin Sun
author_facet Hang Yang
Simon Fong
Raymond Wong
Guangmin Sun
author_sort Hang Yang
collection DOAJ
description Standard classification algorithms are often inaccurate when used in a wireless sensor network (WSN), where the observed data occur in imbalanced classes. The imbalanced data classification problem occurs when the number of samples in one class, usually the class of interest, is much lower than the number in the other classes. Many classification models have been studied in the data-mining research community. However, they all assume that the input data are stationary and bounded in size, so that resampling techniques and postadjustment by measuring the classification cost can be applied. In this paper, we devise a new scheme that extends a popular stream classification algorithm to the analysis of WSNs for reducing the adverse effects of the imbalanced class in the data. This new scheme is resource light at the algorithm level and does not require any data preprocessing. It uses weighted naïve Bayes predictors at the decision tree leaves to effectively reduce the impact of imbalanced classes. Experiments show that our modified algorithm outperforms the original stream classification algorithm.
format Article
id doaj-art-45628895ff1949e1a33c5caa4cc9d769
institution Kabale University
issn 1550-1477
language English
publishDate 2013-01-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-45628895ff1949e1a33c5caa4cc9d7692025-02-03T06:43:16ZengWileyInternational Journal of Distributed Sensor Networks1550-14772013-01-01910.1155/2013/460641Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor NetworkHang Yang0Simon Fong1Raymond Wong2Guangmin Sun3 Department of Computer and Information Science, University of Macau, Taipa, Macau Department of Computer and Information Science, University of Macau, Taipa, Macau School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia Department of Electronic Engineering, Beijing University of Technology, Beijing 100022, ChinaStandard classification algorithms are often inaccurate when used in a wireless sensor network (WSN), where the observed data occur in imbalanced classes. The imbalanced data classification problem occurs when the number of samples in one class, usually the class of interest, is much lower than the number in the other classes. Many classification models have been studied in the data-mining research community. However, they all assume that the input data are stationary and bounded in size, so that resampling techniques and postadjustment by measuring the classification cost can be applied. In this paper, we devise a new scheme that extends a popular stream classification algorithm to the analysis of WSNs for reducing the adverse effects of the imbalanced class in the data. This new scheme is resource light at the algorithm level and does not require any data preprocessing. It uses weighted naïve Bayes predictors at the decision tree leaves to effectively reduce the impact of imbalanced classes. Experiments show that our modified algorithm outperforms the original stream classification algorithm.https://doi.org/10.1155/2013/460641
spellingShingle Hang Yang
Simon Fong
Raymond Wong
Guangmin Sun
Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
International Journal of Distributed Sensor Networks
title Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
title_full Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
title_fullStr Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
title_full_unstemmed Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
title_short Optimizing Classification Decision Trees by Using Weighted Naïve Bayes Predictors to Reduce the Imbalanced Class Problem in Wireless Sensor Network
title_sort optimizing classification decision trees by using weighted naive bayes predictors to reduce the imbalanced class problem in wireless sensor network
url https://doi.org/10.1155/2013/460641
work_keys_str_mv AT hangyang optimizingclassificationdecisiontreesbyusingweightednaivebayespredictorstoreducetheimbalancedclassprobleminwirelesssensornetwork
AT simonfong optimizingclassificationdecisiontreesbyusingweightednaivebayespredictorstoreducetheimbalancedclassprobleminwirelesssensornetwork
AT raymondwong optimizingclassificationdecisiontreesbyusingweightednaivebayespredictorstoreducetheimbalancedclassprobleminwirelesssensornetwork
AT guangminsun optimizingclassificationdecisiontreesbyusingweightednaivebayespredictorstoreducetheimbalancedclassprobleminwirelesssensornetwork