Ensemble Classifier for Mining Data Streams

International Journal of Computer Applications, 2017

Current research in data mining concentrates on the development of new techniques for mining high-speed data streams. The fundamental data generation mechanism changes over the time, this is common in most real-world data streams, which introduces concept drift into the data. Mobile devices, streaming, remote sensing applications which are networked digital information systems, encounter the issue of the size of data and the capacity to be adaptive to changes in concept in real-time. In this paper the main issue of concept drift is addressed with real and synthetic data streams and the comparison of ensemble classifiers has been made in view of concept drift for the assessment of the performance. Various classifiers were applied on data stream with and without concept drift for analysis. This has resulted in better performance of the classifiers on the type of data whether it is categorical, numeric or alphanumeric.

In Internetworking system, the huge amount of data is scattered, generated and processed over the network. The data mining techniques are used to discover the unknown pattern from the underlying data. A traditional classification model is used to classify the data based on past labelled data. However in many current applications, data is increasing in size with fluctuating patterns. Due to this new feature may arrive in the data. It is present in many applications like sensornetwork, banking and telecommunication systems, financial domain, Electricity usage and prices based on its demand and supplyetc .Thus change in data distribution reduces the accuracy of classifying the data. It may discover some patterns as frequent while other patterns tend to disappear and wrongly classify. To mine such data distribution, traditionalclassification techniques may not be suitable as the distribution generating the items can change over time so data from the past may become irrelevant or even false for the current prediction. For handlingsuch varying pattern of data, concept drift mining approach is used to improve the accuracy of classification techniques. In this paper we have proposed ensemble approach for improving the accuracy of classifier. The ensemble classifier is applied on 3 different data sets. We investigated different features for the different chunk of data which is further given to ensemble classifier. We observed the proposed approach improves the accuracy of classifier for different chunks of data.

International Journal of Data Mining & Knowledge Management Process, 2012

Data mining is a user-centric process that is used to extract useful patterns from large volumes of data. With the growth of the Internet, a data stream is today a key area of advanced analysis and data mining. Handling data streams is a difficult task due to the variations in the data and the frequent occurrences of concept drifts. No single classifier can be relied upon to correctly classify data stream data since they are developed through a specific learning approach. Hence we use a multi-chunk ensemble of classifiers to classify evolving data streams and improve the prediction accuracy over single classifiers. We evaluate our ensemble on synthetic as well as real time data, compute the precision and represent it graphically using both majority voting as well as new proposed weighted averaging and compare its performance against individual classifiers. Current techniques include a single chunk approach, where the entire set of data is considered as a whole, and the used method shows better efficiency.

Intelligent Data Analysis, 2018

Many real-world situations constantly generate concept-drifting data streams at high speed. These situations demand adaptive algorithms able to learn online in accordance with the most recent target function (concept). This paper presents Online Adaptive Classifier Ensemble, a new ensemble algorithm able to learn from concept-drifting data streams. The proposed algorithm uses a change detection mechanism in each base classifier in order to handle possible changes in the underlying target function. Each base classifier in the ensemble can alternate between three different stages during the learning process: stable, warning and drift. In a stable stage, the underlying target function is supposed to remain constant, and the corresponding base classifier is updated with each incoming training instance. In a warning stage, a possible change in the target function can be starting to occur, and an alternative base classifier is created and trained together with the other base classifiers. The alternative classifier is added to the ensemble if the drift stage is reached. The new algorithm is compared with various state-of-the-art ensemble algorithms for online learning. Empirical studies show that this proposal is an effective alternative for learning from non-stationary data streams.

Class evolution is an important research topic for data stream mining. All previous studies implicitly regard class evolution as a transient change, which is not true for many real-world problems. This paper concerns the scenario where classes emerge or disappear gradually. A class-based ensemble approach, namely class-based ensemble for class evolution.Emprical studies demonstrate the effectiveness of CBCE in various class evolution scenarios in comparison to existing class evolution adaptation methods. With the rapid development of incremental learning and online,learning,mining tasks in the context of data stream have been widely studied.Generally,data stream mining refers to the mining task that are conducted on a sequence of rapidly arriving data records. As the environment where the data are collected may change dynamically, the data distribution may also change accordingly. This phenomenon referred to as concept drift is one of the most important challenges in data stream mining. A data stream mining technique should be capable of constructing and dynamically updating a model in order to learn dynamic changes.

2014

We propose a novel methodology of maintaining a classification model on streaming data, such as sensor data or log data. Our approach uses an ensemble for classifying data streams which consists of a set of classifiers. New classifiers of the ensemble on streaming data will be generated dynamically according to the estimated distribution of streaming data instead of periodically building them. Also our approach is able to deal with changes of class distribution as well as changes of data distribution. We compared the results of our approach and of the previous approach which can only deal with changes of data distribution. In experiments with 10 benchmark data sets, our approach produced an average of 3.61% higher classification accuracy.

2018

Classification and analysis of data streams are the most promising fields of research and development in Data stream mining. Ensemble based classification approach is one the most challenging flavor of developing an efficient classifier due to large number available base classifiers and increase in the computational time required for training and classification. This paper emphasizes on various factors which affects the accuracy of an ensemble based classifier.

Mining data streams is concerned with extracting knowledge structures represented in models and patterns in high-speed streams of information. It raises new problems for the data mining community in terms of how to mine continuous highspeed data items that you can only have one look. The increasing focus of applications that generate and receive data streams stimulates the need for online data stream analysis tools. Recently, mining data streams with concept drifts has become an important and challenging task for a wide range of applications such as target marketing, network intrusion detection, credit card fraud protection, etc. Clustering and classification ensemble learning is a frequently used tool for building prediction models from data streams, due to its fundamental nature of managing large volumes of stream data. These both are the tools which help in improving the performance of mining systems. In order to improve the accuracy and error rate of traditional ensemble models, we propose a new ensemble model which combines both classifiers and clusters together and utilizes genetic algorithms for mining data streams. The main reason for using genetic algorithms along with clustering and classification is its high ability to solve optimization.

2016

Data Streams are unbounded, sequential data instances that are generated very rapidly. The storage, querying and mining of such rapid flows of data is computationally very challenging. Data Stream Mining (DSM) is concerned with the mining of such data streams in real-time using techniques that require only one pass through the data. DSM techniques need to be adaptive to reflect changes of the pattern encoded in the stream (concept drift). The relevance of features for a DSM classification task may change due to concept drifts and this paper describes the first step towards a concept drift detection method with online feature tracking capabilities.

International Journal of Computer Applications, 2018

In Machine learning tasks, mainly in classification problems, the performance measures are of major concern in order to determine and compare the performance of classification methods. In classification problem the accuracy of the classifier is one of the most important performance measures commonly used. However, computing performance in the dynamic environment learning offered for concept drifting data streams also requires some performance considerations as compared to classification tasks in static environment. Furthermore, the learning and testing strategies widely used for training and testing of classifiers of static environments cannot be utilized efficiently to meet the requirements of concept drifting data stream mining as the main requirement of online leaning is to perform one pass incremental learning on large datasets conversely to the allowable iterative learning in static environment with small datasets. This paper describes some important performance measures and learning and testing strategies pertaining to online and incremental learning in the presence of concept drifting data streams. Furthermore, this paper also presents performance measures of drift detection methods widely used as an explicit component in many concept drifting data stream mining algorithms.