A novel online ensemble approach for concept drift in data streams

Sidhu, Parneeta; Bhatia, M. P. S.; Bindal, Aditya

doi:10.1109/iciip.2013.6707652

Cited by 4 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the literature, methods based on ensemble are better in maintaining previous knowledge to handle recurring concepts. Two of the very recent methods that attend these characteristics are: Early Dynamic Weighted Majority (ERDWM), proposed by Sidhu et al [8]; and Accuracy Updated Ensemble (AUE2), proposed by Brzezinski & Stefanowski [9]. Both methods create a new classifier member for every incoming data chunk of examples to replace the oldest member (ERDWM); or the poorest performing member (AUE2).…”

Section: Related Workmentioning

confidence: 98%

A Dissimilarity-Based Drift Detection Method

Pinage

Santos

2015

2015 IEEE 27th International Conference on Tools With Artificial Intelligence (ICTAI)

View full text Add to dashboard Cite

In real-world applications, machine learning algorithms can be employed in spam detection, environmental monitoring, fraud detection, medical diagnoses, among others. Most of these problems present an environment which changes over time. The problem involving classification tasks in dynamic environments has become one of the major challenges in machine learning domain in the last decades. Currently in the literature, methods based on accuracy monitoring are commonly used to detect changes explicitly. However, these methods may become infeasible in some real-world applications especially due to two aspects: they may need human operator feedback, and may depend on a significant decrease of accuracy to be able to detect changes. In addition, most of these methods are also incremental learning-based, since they update the decision model for every incoming example. However, this may lead to system unnecessary updates. In order to overcome these problems, this paper proposes a method to detect changes based on data distribution dissimilarity and to update the decision model only after drift detection. The achievement of this method is relevant to allow change detection and reaction be applicable in several practical problems. The experiments conducted indicate that the proposed method attains performance and detection rates similar to the traditional DDM and EDDM, which are incremental learningbased and performance monitoring-based drift detectors.

show abstract

Section: Related Workmentioning

confidence: 98%

A Dissimilarity-Based Drift Detection Method

Pinage

Santos

2015

2015 IEEE 27th International Conference on Tools With Artificial Intelligence (ICTAI)

View full text Add to dashboard Cite

show abstract

“…In addition, ERDWM reduces the need of creating new classifier members and consequently, it decreases time and memory resources requirements. Even though, Sidhu et al conclude that ERDWM does not outperform EDDM in terms of memory and execution time. On the other hand, ERDWM is better in retaining previous knowledge to support predictions.…”

Section: Current Solutions For Concept Driftsmentioning

confidence: 99%

“…Sidhu et al proposed an online ensemble approach called Early Dynamic Weighted Majority (ERDWM). The weighted strategy is undertaken using three options: (1) decrease the weight of members whose prediction is incorrect; (2) increase the weight of members whose local prediction is correct but global prediction is incorrect; and (3) no weight update when both local and global predictions are correct.…”

Section: Current Solutions For Concept Driftsmentioning

confidence: 99%

Classification systems in dynamic environments: an overview

Pinage

Santos

Gama

2016

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Data mining and machine learning algorithms can be employed to perform a variety of tasks. However, since most of these problems may depend on environments that change over time, performing classification tasks in dynamic environments has been a challenge in data mining research domain in the last decades. Currently, in the literature, the most common strategies used to detect changes are based on accuracy monitoring, which relies on previous knowledge of the data in order to identify whether or not correct classifications are provided. However, such a feedback can be infeasible in practical problems. In this work, we present a comprehensive overview of current machine learning/data mining approaches proposed to deal with dynamic environments problems. The objective is to highlight the main drawbacks and open issues, as well as future directions and problems worthy of investigation. In addition, we provide the definitions of the main terms used to represent this problem in the literature, such as concept drift and novelty detection. WIREs Data Mining Knowl Discov 2016, 6:156–166. doi: 10.1002/widm.1184 This article is categorized under: Technologies > Classification Technologies > Machine Learning

show abstract

“…Compared with block-based ensemble method, online ensemble can effectively improve the real-time performance of the model. Typical methods include: 1) Concept drift adaptation method based on dynamic weighted voting [17], [18]. It initialized weights based on the accuracy of prediction for new samples and updated weights based on global and local predictions to dynamically update the base classifier.…”

Section: B Ensemble Learningmentioning

confidence: 99%

“…The ensemble-based learning method can be further divided into data block-based ensemble [15], [16] and online ensemble [17], [18], [19]. Online ensemble is an ensemble learning method that processes samples one by one.…”

Section: Introductionmentioning

confidence: 99%

Streaming Data Classification Based on Hierarchical Concept Drift and Online Ensemble

Liu,

Zhao

2023

IEEE Access

View full text Add to dashboard Cite

In order to improve the performance of online learning in the real-time distribution of streaming data, a streaming data classification algorithm based on hierarchical concept drift and online ensemble(SCHCDOE) is proposed in this paper. The concept drift index is calculated based on the newly arrived data instance, and the streaming data is divided into three states: stable state, concept drift warning state, and concept drift occurrence state. When the streaming data is in a stable state, the classifier is not updated. When the streaming data is in a concept drift warning state, online ensemble learning is achieved through random subspaces method to perform feature selection and efficiently update the classifier. When the streaming data is in a concept drift occurrence state, anomaly detection mechanism is used to eliminate abnormal data, and online ensemble learning method and incremental learning method are combined for learning. Local information and global distribution information of the streaming data are fully utilized to train the model, so that the learning model can respond quickly after concept drift occurs. Experiments are conducted on both synthetic and real datasets, and the experimental results show that the proposed algorithm performs well. Compared with other classic algorithms, classification accuracy and concept drift adaptability of the proposed algorithm are improved.

show abstract

A novel online ensemble approach for concept drift in data streams

Cited by 4 publications

References 21 publications

A Dissimilarity-Based Drift Detection Method

A Dissimilarity-Based Drift Detection Method

Classification systems in dynamic environments: an overview

Streaming Data Classification Based on Hierarchical Concept Drift and Online Ensemble

Contact Info

Product

Resources

About