Parsimonious random vector functional link network for data streams
The majority of the existing work on random vector functional link networks (RVFLNs) is not scalable for data stream analytics because they work under a batch learning scenario and lack a self-organizing property. A novel RVLFN, namely the parsimonious random vector functional link network (pRVFLN),...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/89370 http://hdl.handle.net/10220/44904 |
| _version_ | 1811679922875269120 |
|---|---|
| author | Pratama, Mahardhika Angelov, Plamen P. Lughofer, Edwin Er, Meng Joo |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Pratama, Mahardhika Angelov, Plamen P. Lughofer, Edwin Er, Meng Joo |
| author_sort | Pratama, Mahardhika |
| collection | NTU |
| description | The majority of the existing work on random vector functional link networks (RVFLNs) is not scalable for data stream analytics because they work under a batch learning scenario and lack a self-organizing property. A novel RVLFN, namely the parsimonious random vector functional link network (pRVFLN), is proposed in this paper. pRVFLN adopts a fully flexible and adaptive working principle where its network structure can be configured from scratch and can be automatically generated, pruned and recalled from data streams. pRVFLN is capable of selecting and deselecting input attributes on the fly as well as capable of extracting important training samples for model updates. In addition, pRVFLN introduces a non-parametric type of hidden node which completely reflects the real data distribution and is not constrained by a specific shape of the cluster. All learning procedures of pRVFLN follow a strictly single-pass learning mode, which is applicable for online time-critical applications. The advantage of pRVFLN is verified through numerous simulations with real-world data streams. It was benchmarked against recently published algorithms where it demonstrated comparable and even higher predictive accuracies while imposing the lowest complexities. |
| first_indexed | 2024-10-01T03:16:51Z |
| format | Journal Article |
| id | ntu-10356/89370 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:16:51Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/893702020-03-07T11:49:00Z Parsimonious random vector functional link network for data streams Pratama, Mahardhika Angelov, Plamen P. Lughofer, Edwin Er, Meng Joo School of Computer Science and Engineering School of Electrical and Electronic Engineering Random Vector Functional Link Evolving Intelligent System The majority of the existing work on random vector functional link networks (RVFLNs) is not scalable for data stream analytics because they work under a batch learning scenario and lack a self-organizing property. A novel RVLFN, namely the parsimonious random vector functional link network (pRVFLN), is proposed in this paper. pRVFLN adopts a fully flexible and adaptive working principle where its network structure can be configured from scratch and can be automatically generated, pruned and recalled from data streams. pRVFLN is capable of selecting and deselecting input attributes on the fly as well as capable of extracting important training samples for model updates. In addition, pRVFLN introduces a non-parametric type of hidden node which completely reflects the real data distribution and is not constrained by a specific shape of the cluster. All learning procedures of pRVFLN follow a strictly single-pass learning mode, which is applicable for online time-critical applications. The advantage of pRVFLN is verified through numerous simulations with real-world data streams. It was benchmarked against recently published algorithms where it demonstrated comparable and even higher predictive accuracies while imposing the lowest complexities. Accepted version 2018-05-30T05:16:14Z 2019-12-06T17:24:01Z 2018-05-30T05:16:14Z 2019-12-06T17:24:01Z 2017 Journal Article Pratama, M., Angelov, P. P., Lughofer, E., & Er, J. M. (2018). Parsimonious random vector functional link network for data streams. Information Sciences, 430-431, 519-537. 0020-0255 https://hdl.handle.net/10356/89370 http://hdl.handle.net/10220/44904 10.1016/j.ins.2017.11.050 en Information Sciences © 2017 Elsevier Inc. This is the author created version of a work that has been peer reviewed and accepted for publication by Information Sciences, Elsevier Inc. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1016/j.ins.2017.11.050]. 41 p. application/pdf |
| spellingShingle | Random Vector Functional Link Evolving Intelligent System Pratama, Mahardhika Angelov, Plamen P. Lughofer, Edwin Er, Meng Joo Parsimonious random vector functional link network for data streams |
| title | Parsimonious random vector functional link network for data streams |
| title_full | Parsimonious random vector functional link network for data streams |
| title_fullStr | Parsimonious random vector functional link network for data streams |
| title_full_unstemmed | Parsimonious random vector functional link network for data streams |
| title_short | Parsimonious random vector functional link network for data streams |
| title_sort | parsimonious random vector functional link network for data streams |
| topic | Random Vector Functional Link Evolving Intelligent System |
| url | https://hdl.handle.net/10356/89370 http://hdl.handle.net/10220/44904 |
| work_keys_str_mv | AT pratamamahardhika parsimoniousrandomvectorfunctionallinknetworkfordatastreams AT angelovplamenp parsimoniousrandomvectorfunctionallinknetworkfordatastreams AT lughoferedwin parsimoniousrandomvectorfunctionallinknetworkfordatastreams AT ermengjoo parsimoniousrandomvectorfunctionallinknetworkfordatastreams |