A dynamic routing algorithm of CapsNet for drift prognosis

•Drift prognosis aims to detect a coming drift, but lacks research.•We propose a drift prognosis algorithm (DR-DD) of capsule neural network.•We tailor Kullback-Leibler divergence to quantify the difference among capsules.•Compared with other 11 drift detection methods on 7 datasets, only DR-DD can...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Expert systems with applications Ročník 296; s. 128925
Hlavní autoři: Lin, Borong, Jin, Nanlin, Woodward, John R.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 15.01.2026
Témata:
Capsule networks
Data stream mining
Drift detection
Data stream mining
Capsule networks
Drift detection
ISSN:0957-4174
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Drift prognosis aims to detect a coming drift, but lacks research.•We propose a drift prognosis algorithm (DR-DD) of capsule neural network.•We tailor Kullback-Leibler divergence to quantify the difference among capsules.•Compared with other 11 drift detection methods on 7 datasets, only DR-DD can achieve drift prognosis. In data stream mining, detecting significant changes in a data stream is called drift detection. Detecting drift before it starts is an important problem, but there is very limited research. We call it “drift prognosis”. Many existing drift detection methods only report a drift after it has occurred. This paper tackles this challenge, taking advantage of Capsule Networks (CapsNets), a recent deep-learning architecture. CapsNets can encapsulate the properties of features. We propose a novel dynamic routing algorithm for drift prognosis, named DR-DD, which can transform between capsule layers to capture subtle changes, indicating a potential drift. Compared to 11 drift detection methods in the literature, our DR-DD algorithm is the only one that can pre-diagnose a drift, before it occurs.
ISSN:0957-4174
DOI:10.1016/j.eswa.2025.128925