No abstract

No abstract

Most approaches to classifying data streams either divide the stream into fixed-size chunks or use gradual forgetting. Due to evolving nature of data streams, finding a proper size or choosing a forgetting rate without prior knowledge about time-scale of change is not a trivial task. These approaches hence suffer from a trade-off between performance and sensitivity. Existing dynamic sliding window based approaches address this problem by tracking changes in classifier error rate, but are supervised in nature. We propose an efficient semi-supervised framework in this paper which uses change detection on classifier confidence to detect concept drifts, and to determine chunk boundaries dynamically. It also addresses concept evolution problem by detecting outliers having strong cohesion among themselves. Experiment results on benchmark and synthetic data sets show effectiveness of the proposed approach.

A typical data stream classification involves predicting label of data instances generated from a non-stationary process. Studies in the past decade have focused on this problem setting to address various challenges such as concept drift and concept evolution. Most techniques assume availability of class labels associated with unlabeled data instances, soon after label prediction, for further training and drift detection. Moreover, training and test data distributions are assumed to be similar. These assumptions are not always true in practice. For instance, a semi-supervised setting that aims to utilize only a fraction of labels may induce bias during data selection. Consequently, the resulting data distribution of training and test instances may differ. In this paper, we present a novel stream classification problem setting involving two independent non-stationary data generating processes, relaxing the above assumptions. A source stream continuously generates labeled data instances whose distribution is biased compared to that of a target stream which generates unlabeled data instances from the same domain. The problem, we call Multistream Classification, is to predict the class labels of data instances in the target stream, while utilizing labels available on the source stream. Since concept drift can occur asynchronously on these two streams, we design an adaptive framework that uses a technique for supervised concept drift detection in the biased source stream, and unsupervised concept drift detection in the target stream. A weighted ensemble of classifiers is updated after each drift detection on either streams, while utilizing a bias correction mechanism that leverage source information to predict labels of target instances whenever necessary. We empirically evaluate the multistream classifier's performance on both real-world and synthetic datasets, while comparing with various baseline methods and its variants.

No abstract

No abstract

No abstract

Classifying instances in evolving data stream is a challenging task because of its properties, e.g., infinite length, concept drift, and concept evolution. Most of the currently available approaches to classify stream data instances divide the stream data into fixed size chunks to fit the data in memory and process the fixed size chunk one after another. However, this may lead to failure of capturing the concept drift immediately. We try to determine the chunk size dynamically by exploiting change point detection (CPD) techniques on stream data. In general, the distribution families before and after the change point are unknown over the stream, therefore non-parametric CPD algorithms are used in this case. We propose a multi-dimensional non-parametric CPD technique to determine chunk boundary over data streams dynamically which leads to better models to classify instances of evolving data streams. Experimental results show that our approach can detect the change points and classify instances of evolving data stream with high accuracy as compared to other baseline approaches.