Adaptive windowing based recurrent neural network for drift adaption in non-stationary environment

In today's digital era, many applications generate massive data streams that must be sequenced and processed immediately. Therefore, storing large amounts of data for analysis is impractical. Now, this infinite amount of evolving data confronts concept drifts in data stream classification. Conc...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of ambient intelligence and humanized computing Ročník 14; číslo 10; s. 14125 - 14139
Hlavní autori: Suryawanshi, Shubhangi, Goswami, Anurag, Patil, Pramod, Mishra, Vipul
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Germany Springer Nature B.V 01.10.2023
Springer Berlin Heidelberg
Predmet:
Adaptation
Airlines
Algorithms
Artificial intelligence
Classification
COVID-19
Data transmission
Datasets
Decision making
Deep learning
Drift
Fisher information
Machine learning
Neural networks
Nonstationary environments
Original Research
Pandemics
Recurrent neural networks
Gated recurrent unit
Catastrophic forgetting
Non-stationary data streams
Concept drift
Adaptive window
Fisher information matrix
ISSN:1868-5137, 1868-5145
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In today's digital era, many applications generate massive data streams that must be sequenced and processed immediately. Therefore, storing large amounts of data for analysis is impractical. Now, this infinite amount of evolving data confronts concept drifts in data stream classification. Concept drift is a phenomenon in which the distribution of input data or the relationship between input data and target label changes over time. If the drifts are not addressed, the learning model's performance suffers. Non-stationary data streams must be processed as they arrive, and neural networks' built-in capabilities aid in the processing of huge non-stationary data streams. We proposed an adaptive windowing approach based on a gated recurrent unit, a variant of the recurrent neural network incrementally trained on incoming data (for the real-world airline and synthetic Streaming Ensemble Algorithm (SEA) datasets), and employed elastic weight consolidation with the Fisher information matrix to prevent forgetting. Unlike the traditional fixed window methodology, the proposed model dynamically increases the window size if the prediction is correct and reduces it if drifts occur. As a result, an adaptive recurrent neural network model can adapt to changes in the non-stationary data stream and provide consistent performance. Moreover, the findings revealed that on the airline and the SEA dataset, the proposed model outperforms state-of-the-art methods by achieving 67.74% and 91.70% accuracy, respectively. Further, the results demonstrated that the proposed model has a better accuracy of 3.6% and 1.6% for the SEA and the airline dataset, respectively.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1868-5137
1868-5145
DOI:10.1007/s12652-022-04116-0