Ensemble Classification for Drifting Concept

نویسندگان

  • E. Padmalatha
  • C. R. K. Reddy
  • B. Padmaja Rani
  • Nick Street
  • Yong Seog Kim
  • Pedro Domingos
  • Geoff Hulten
  • Laurie Spencer
  • Haixun Wang
  • Wei Fan
  • Philip S. Yu
  • Jiawei Han
  • Mohammad M. Masud
  • Jing Gao
  • Latifur Khan
  • H. Wang
  • W. Fan
  • P. S. Yu
چکیده

Traditional data mining classifiers are used for mining the static data, in which incremental learning assumed data streams come under stationary distribution where data concepts remain unchanged. The concept of data can be changed at any time in real world application this refers to change in the class definitions over time. Classifier ensembles are rapidly gaining popularity in data mining Community, because they are comparatively more accurate, easy and react better to concept drift than single classifiers. They are general way of boosting classification accuracy. Their modularity provides natural path of absorbing changes by modifying ensemble member.The proposed approach uses ensemble classifiers to improve the accuracy of the classification in data streams .The performance of the classifiers tested with benchmark datasets from UCI machine learning repository.the experimental results prove that this approach great accuracy when comparing to the single classifier.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Mining Concept-Drifting Data Stream to Detect Peer to Peer Botnet Traffic

We propose a novel stream data classification technique to detect Peer to Peer botnet. Botnet traffic can be considered as stream data having two important properties: infinite length and drifting concept. Thus, stream data classification technique is more appealing to botnet detection than simple classification technique. However, no other botnet detection approaches so far have applied stream...

متن کامل

A Multi-partition Multi-chunk Ensemble Technique to Classify Concept-Drifting Data Streams

We propose a multi-partition, multi-chunk ensemble classifier based data mining technique to classify concept-drifting data streams. Existing ensemble techniques in classifying concept-drifting data streams follow a single-partition, single-chunk approach, in which a single data chunk is used to train one classifier. In our approach, we train a collection of v classifiers from r consecutive dat...

متن کامل

An adaptive ensemble classifier for mining concept drifting data streams

Traditional data mining techniques cannot be directly applied to the real-time data streaming environment. Existing mining classifiers therefore need to be updated frequently to adopt the changes in data streams. In this paper, we address this issue and propose an adaptive ensemble approach for classification and novel class detection in concept-drifting data streams. The proposed approach uses...

متن کامل

Mining Concept-Drifting Data Streams

Knowledge discovery from infinite data streams is an important and difficult task.We are facing two challenges, the overwhelming volume and the concept drifts of the streaming data. In this chapter, we introduce a general framework for mining concept-drifting data streams using weighted ensemble classifiers. We train an ensemble of classification models, such as C4.5, RIPPER, naive Bayesian, et...

متن کامل

Detecting Concept Drift in Data Stream Using Semi-Supervised Classification

Data stream is a sequence of data generated from various information sources at a high speed and high volume. Classifying data streams faces the three challenges of unlimited length, online processing, and concept drift. In related research, to meet the challenge of unlimited stream length, commonly the stream is divided into fixed size windows or gradual forgetting is used. Concept drift refer...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013