Review of Ensemble Based Classification Algorithms for Nonstationary and Imbalanced Data

“…In recent data mining applications, drift can occur at any moment of time, so it is necessary to take some measures to handle drifted data streams. In this paper we are using ensemble based incremental learning algorithm to handle aforemention phenomena.In ensemble based classification [3] whose individual predictions are combined in some way to classify unseen data. The approach in ensemble systems [4] is to create many classifiers, and combine their outputs in such a way that this combination will improve the performance as compare to single classifier.…”

Section: E(y T )≠μmentioning

confidence: 99%

Incremental Learning on Non-stationary Data Stream using Ensemble Approach

Thalor

Patil

2016

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Incremental Learning on non stationary distribution has been shown to be a very challenging problem in machine learning and data mining, because the joint probability distribution between the data and classes changes over time. Many real time problems suffer concept drift as they changes with time. For example, an advertisement recommendation system, in which customer’s behavior may change depending on the season of the year, on the inflation and on new products made available. An extra challenge arises when the classes to be learned are not represented equally in the training data i.e. classes are imbalanced, as most machine learning algorithms work well only when the training data is balanced. The objective of this paper is to develop an ensemble based classification algorithm for non-stationary data stream (ENSDS) with focus on two-class problems. In addition, we are presenting here an exhaustive comparison of purposed algorithms with state-of-the-art classification approaches using different evaluation measures like recall, f-measure and g-mean</span>

show abstract

“…In this paper we are using ensemble based incremental learning algorithm to handle aforemention phenomena.In ensemble based classification [3] whose individual predictions are combined in some way to classify unseen data. The approach in ensemble systems [4] is to create many classifiers, and combine their outputs in such a way that this combination will improve the performance as compare to single classifier.…”

Section: E(y T )≠μmentioning

confidence: 99%

Incremental Learning on Non-stationary Data Stream using Ensemble Approach

Thalor¹,

Patil²

2016

IJECE

View full text Add to dashboard Cite

Incremental Learning on non stationary distribution has been shown to be a very challenging problem in machine learning and data mining, because the joint probability distribution between the data and classes changes over time. Many real time problems suffer concept drift as they changes with time. For example, an advertisement recommendation system, in which customer's behavior may change depending on the season of the year, on the inflation and on new products made available. An extra challenge arises when the classes to be learned are not represented equally in the training data i.e. classes are imbalanced, as most machine learning algorithms work well only when the training data is balanced. The objective of this paper is to develop an ensemble based classification algorithm for non-stationary data stream (ENSDS) with focus on two-class problems. In addition, we are presenting here an exhaustive comparison of purposed algorithms with state-of-the-art classification approaches using different evaluation measures like recall, fmeasure and g-mean.

show abstract

Review of Ensemble Based Classification Algorithms for Nonstationary and Imbalanced Data

Cited by 6 publications

References 19 publications

Continuous evolution of risk assessment methods for cardiac surgery and intervention

Continuous evolution of risk assessment methods for cardiac surgery and intervention

Incremental Learning on Non-stationary Data Stream using Ensemble Approach

Incremental Learning on Non-stationary Data Stream using Ensemble Approach

Contact Info

Product

Resources

About