본문 바로가기

쓰기

 
발표자 이종범 
발표일자 2013-05-08 
저자 Benjamin X. Wang and Nathalie Japkowicz 
학회명 Knowledge and Information Systems 2010 
논문지  
Real world data mining applications must address the issue of learning from imbalanced data sets. 
The problem occurs when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed vector spaces or lack of information. Common approaches for dealing with the class imbalance problem involve modifying the data distribution or modifying the classifier. In this work, we choose to use a combination of both approaches. We use support vector machines with soft margins as the base classifier to solve the skewed vector spaces problem. Then we use a boosting algorithm to get an ensemble classifier that has lower error than a single classifier. We found that this ensemble of SVMs makes an impressive improvement in prediction performance, not only for the majority class, but also for the minority class

    2013

      Event Summarization Using Tweets
      2013.05.27
      발표자: 김경민     발표일자: 2013-05-22     저자: Deepayan Chakrabarti and Kunal Punera     학회명: Proceeding of the Fifth International AAAI conference on weblogs and social media    
      A CORRELATED TOPIC MODEL OF SCIENCE
      2013.05.27
      발표자: 김누리     발표일자: 2013-05-15     저자: Blei, David M, et al.     학회명: The Annals of Applied Statistics, 2007