Drift Detection Using Stream Volatility

Huang, David Tse Jung; Koh, Yun Sing; Dobbie, Gillian; Bifet, Albert

doi:10.1007/978-3-319-23528-8_26

Cited by 22 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Again we stress that, as pointed out by Huang et al (2015) and Bifet et al (2009), the locations of concept drifts are not known in these data streams. We therefore follow the work of Huang et al (2015) and establish our evaluations based on the number of alarms for concept drifts and the classification error-rates. Our experimental results are summarized in Tables 9 to 11. Since we are not aware of the exact drift locations, we do not make strong conclusions about the performance, in terms of drift detection, of the algorithms.…”

Section: Experiments On Real-world Data Streamsmentioning

confidence: 62%

“…The Drift Detection Method (DDM) (Gama et al 2004) CUSUM and its variant Page-Hinkley (PH) are some of the pioneer methods in the community. DDM, EDDM, and ADWIN have frequently been considered as benchmarks in the literature (Huang et al 2015;Frías-Blanco et al 2015;Baena-Garcıa et al 2006;Nishida and Yamauchi 2007;Bifet and Gavalda 2007;. SeqDrift2 and HDDMs are recently proposed methods, and have shown comparable results to the other benchmarks.…”

Section: Drift Detection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Reservoir of diverse adaptive learners and stacking fast hoeffding drift detection methods for evolving data streams

2018

View full text Add to dashboard Cite

The last decade has seen a surge of interest in adaptive learning algorithms for data stream classification, with applications ranging from predicting ozone level peaks, learning stock market indicators, to detecting computer security violations. In addition, a number of methods have been developed to detect concept drifts in these streams. Consider a scenario where we have a number of classifiers with diverse learning styles and different drift detectors. Intuitively, the current 'best' (classifier, detector) pair is application dependent and may change as a result of the stream evolution. Our research builds on this observation. We introduce the Tornado framework that implements a reservoir of diverse classifiers, together with a variety of drift detection algorithms. In our framework, all (classifier, detector) pairs proceed, in parallel, to construct models against the evolving data streams. At any point in time, we select the pair which currently yields the best performance. We further incorporate two novel stacking-based drift detection methods, namely the FHDDMS and FHDDMS add approaches. The experimental evaluation confirms that the current 'best' (classifier, detector) pair is not only heavily dependent on the characteristics of the stream, but also that this selection evolves as the stream flows. Further, our FHDDMS variants detect concept drifts accurately in a timely fashion while outperforming the state-of-the-art.

show abstract

Section: Experiments On Real-world Data Streamsmentioning

confidence: 62%

Section: Drift Detection Methodsmentioning

confidence: 99%

Reservoir of diverse adaptive learners and stacking fast hoeffding drift detection methods for evolving data streams

2018

View full text Add to dashboard Cite

show abstract

“…The algorithm updates the variables µ t w and µ m w over time (lines [15][16][17]. Finally, a drift is detected if (µ m w − µ t w ) ≥ ε w (lines [18][19][20][21]. Recall that we have…”

Section: Fig 3: Mcdiarmid Drift Detection Methods (General Scheme)mentioning

confidence: 99%

McDiarmid Drift Detection Methods for Evolving Data Streams

Pesaranghader

Viktor

Paquet

2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Increasingly, Internet of Things (IoT) domains, such as sensor networks, smart cities, and social networks, generate vast amounts of data. Such data are not only unbounded and rapidly evolving. Rather, the content thereof dynamically evolves over time, often in unforeseen ways. These variations are due to so-called concept drifts, caused by changes in the underlying data generation mechanisms. In a classification setting, concept drift causes the previously learned models to become inaccurate, unsafe and even unusable. Accordingly, concept drifts need to be detected, and handled, as soon as possible. In medical applications and emergency response settings, for example, change in behaviours should be detected in near real-time, to avoid potential loss of life. To this end, we introduce the McDiarmid Drift Detection Method (MDDM), which utilizes McDiarmid's inequality [1] in order to detect concept drift. The MDDM approach proceeds by sliding a window over prediction results, and associate window entries with weights. Higher weights are assigned to the most recent entries, in order to emphasize their importance. As instances are processed, the detection algorithm compares a weighted mean of elements inside the sliding window with the maximum weighted mean observed so far. A significant difference between the two weighted means, upper-bounded by the McDiarmid inequality, implies a concept drift. Our extensive experimentation against synthetic and real-world data streams show that our novel method outperforms the state-of-the-art. Specifically, MDDM yields shorter detection delays as well as lower false negative rates, while maintaining high classification accuracies.

show abstract

“…PRESS works under the assumption that many data streams concept drifts in the real-world follow behavioural patterns. This characteristic has been exploited by previous research in the area method to capture the regularity of these concept drifts [Kosina et al, 2010;. In such realworld cases with regular concept drifts, each concept drift is caused by some events.…”

Section: Introductionmentioning

confidence: 99%

“…Because drift detectors cannot make the perfect approximation of a stream and real-world streams are largely susceptible to noise, detectors may signal a false alarm, known as false positive, when in fact, there is no actual concept drift in the stream. To reduce false positive rates, Huang et al [2015] use stream volatility, a measure of how frequent the concept drift occurrence is in a stream, to capture the trend of concept drifts. Based on these trends, their algorithms predicts the future drift positions and probability.…”

Section: Introductionmentioning

confidence: 99%