Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation

Gradual drifts in data streams are usually hard to detect and often do not necessarily trigger the evolution of new fuzzy rules during model adaptation steps in order to represent the new, drifted data distribution(s) appropriately in the fuzzy model. Over time, they thus lead to oversized rules wit...

Full description

Saved in:
Bibliographic Details
Main Authors: Lughofer, Edwin, Pratama, Mahardhika, Skrjanc, Igor
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140102
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140102
record_format dspace
spelling sg-ntu-dr.10356-1401022020-05-26T07:45:59Z Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation Lughofer, Edwin Pratama, Mahardhika Skrjanc, Igor School of Computer Science and Engineering Engineering::Computer science and engineering Data Stream Modeling Drift Compensation Gradual drifts in data streams are usually hard to detect and often do not necessarily trigger the evolution of new fuzzy rules during model adaptation steps in order to represent the new, drifted data distribution(s) appropriately in the fuzzy model. Over time, they thus lead to oversized rules with untypically large local errors (typically also worsening the global model error), as representing joint local data distributions before and after a drift happened likewise. We therefore propose an incremental rule splitting concept for generalized fuzzy rules in order to autonomously compensate these negative effects of gradual drifts. Our splitting condition is based on the local error of rules measured in terms of a weighted contribution to the whole model error and on the size of the rules measured in terms of the volume of the associated clusters. We use the concept of statistical process control in order to omit an extra threshold parameter in our splitting condition. The splitting technique relies on the eigendecomposition of the rule covariance matrix to adequately manipulate the largest eigenvector and eigenvalues in order to retrieve the new centers and contours of the two split rules. Furthermore, we guarantee sufficient flexibility in adapting the shapes and consequents of the split rules to the new drifted situation in the stream by integrating a specific dynamic and smooth forgetting concept of older samples, which formed the original (nonsplit) rules. Robustness against outliers is guaranteed by the realization of a two-layer model building process, where one layer represents the cluster partition and the other layer the rule partition: Only clusters becoming significant over time are accepted as rules in the fuzzy model. The splitting concepts are integrated in the generalized smart evolving learning engine for fuzzy systems (termed as Gen-Smart-EFS) and successfully tested on two real-world application scenarios, engine test benches and rolling mills, the latter including a real-occurring gradual drift (whose position in the data is known). Results show clearly improved error trend lines over time when splitting is applied, compared to the case when it is not applied: reduction of the mean absolute model error by about one third (rolling mills) and about one half (engine test benches). 2020-05-26T07:45:59Z 2020-05-26T07:45:59Z 2017 Journal Article Lughofer, E., Pratama, M., & Skrjanc, I. (2018). Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation. IEEE Transactions on Fuzzy Systems, 26(4), 1854-1865. doi:10.1109/TFUZZ.2017.2753727 1063-6706 https://hdl.handle.net/10356/140102 10.1109/TFUZZ.2017.2753727 2-s2.0-85030639072 4 26 1854 1865 en IEEE Transactions on Fuzzy Systems © 2017 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Data Stream Modeling
Drift Compensation
spellingShingle Engineering::Computer science and engineering
Data Stream Modeling
Drift Compensation
Lughofer, Edwin
Pratama, Mahardhika
Skrjanc, Igor
Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
description Gradual drifts in data streams are usually hard to detect and often do not necessarily trigger the evolution of new fuzzy rules during model adaptation steps in order to represent the new, drifted data distribution(s) appropriately in the fuzzy model. Over time, they thus lead to oversized rules with untypically large local errors (typically also worsening the global model error), as representing joint local data distributions before and after a drift happened likewise. We therefore propose an incremental rule splitting concept for generalized fuzzy rules in order to autonomously compensate these negative effects of gradual drifts. Our splitting condition is based on the local error of rules measured in terms of a weighted contribution to the whole model error and on the size of the rules measured in terms of the volume of the associated clusters. We use the concept of statistical process control in order to omit an extra threshold parameter in our splitting condition. The splitting technique relies on the eigendecomposition of the rule covariance matrix to adequately manipulate the largest eigenvector and eigenvalues in order to retrieve the new centers and contours of the two split rules. Furthermore, we guarantee sufficient flexibility in adapting the shapes and consequents of the split rules to the new drifted situation in the stream by integrating a specific dynamic and smooth forgetting concept of older samples, which formed the original (nonsplit) rules. Robustness against outliers is guaranteed by the realization of a two-layer model building process, where one layer represents the cluster partition and the other layer the rule partition: Only clusters becoming significant over time are accepted as rules in the fuzzy model. The splitting concepts are integrated in the generalized smart evolving learning engine for fuzzy systems (termed as Gen-Smart-EFS) and successfully tested on two real-world application scenarios, engine test benches and rolling mills, the latter including a real-occurring gradual drift (whose position in the data is known). Results show clearly improved error trend lines over time when splitting is applied, compared to the case when it is not applied: reduction of the mean absolute model error by about one third (rolling mills) and about one half (engine test benches).
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Lughofer, Edwin
Pratama, Mahardhika
Skrjanc, Igor
format Article
author Lughofer, Edwin
Pratama, Mahardhika
Skrjanc, Igor
author_sort Lughofer, Edwin
title Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
title_short Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
title_full Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
title_fullStr Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
title_full_unstemmed Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
title_sort incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation
publishDate 2020
url https://hdl.handle.net/10356/140102
_version_ 1681057328161357824