Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization
It is normal to find at least a few measured values in CO2-alkanolamine-H2O datasets that deviate greatly from the majority of published data, as the data come from different sources. These values, termed as data outliers, are the major source of conflict in modeling, simulation and process developm...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Springer London
2017
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84957558524&doi=10.1007%2fs00521-016-2213-z&partnerID=40&md5=631b3b8d59309e2f35b88e872f419f2c http://eprints.utp.edu.my/19378/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.utp.eprints.19378 |
|---|---|
| record_format |
eprints |
| spelling |
my.utp.eprints.193782018-04-20T00:40:02Z Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization Suleman, H. Maulud, A.S. Man, Z. It is normal to find at least a few measured values in CO2-alkanolamine-H2O datasets that deviate greatly from the majority of published data, as the data come from different sources. These values, termed as data outliers, are the major source of conflict in modeling, simulation and process development studies. Therefore, removal of data outliers is mandatory. However, available statistical techniques are known to lose information at the boundaries of the system and exhibit substantial deviation from holistic data trend. Hence, an adaptive approach combining artificial neural networks and robust winsorization is presented for identification and reconciliation of data outliers in CO2-alkanolamine-H2O system. The proposed approach flexibly transforms to the nonlinear data distribution and predicts corrected values for data outliers (winsorized values), thus maintaining the information at extremes of the system. The results have been graphically analyzed and show good conformance in treated data, with retention of winsorized values. The proposed method improves the shortcomings of previous statistical approaches and can be potentially extended to other nonlinear experimental datasets in chemical process systems. © 2016, The Natural Computing Applications Forum. Springer London 2017 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-84957558524&doi=10.1007%2fs00521-016-2213-z&partnerID=40&md5=631b3b8d59309e2f35b88e872f419f2c Suleman, H. and Maulud, A.S. and Man, Z. (2017) Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization. Neural Computing and Applications, 28 (9). pp. 2621-2632. http://eprints.utp.edu.my/19378/ |
| institution |
Universiti Teknologi Petronas |
| building |
UTP Resource Centre |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Petronas |
| content_source |
UTP Institutional Repository |
| url_provider |
http://eprints.utp.edu.my/ |
| description |
It is normal to find at least a few measured values in CO2-alkanolamine-H2O datasets that deviate greatly from the majority of published data, as the data come from different sources. These values, termed as data outliers, are the major source of conflict in modeling, simulation and process development studies. Therefore, removal of data outliers is mandatory. However, available statistical techniques are known to lose information at the boundaries of the system and exhibit substantial deviation from holistic data trend. Hence, an adaptive approach combining artificial neural networks and robust winsorization is presented for identification and reconciliation of data outliers in CO2-alkanolamine-H2O system. The proposed approach flexibly transforms to the nonlinear data distribution and predicts corrected values for data outliers (winsorized values), thus maintaining the information at extremes of the system. The results have been graphically analyzed and show good conformance in treated data, with retention of winsorized values. The proposed method improves the shortcomings of previous statistical approaches and can be potentially extended to other nonlinear experimental datasets in chemical process systems. © 2016, The Natural Computing Applications Forum. |
| format |
Article |
| author |
Suleman, H. Maulud, A.S. Man, Z. |
| spellingShingle |
Suleman, H. Maulud, A.S. Man, Z. Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| author_facet |
Suleman, H. Maulud, A.S. Man, Z. |
| author_sort |
Suleman, H. |
| title |
Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| title_short |
Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| title_full |
Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| title_fullStr |
Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| title_full_unstemmed |
Reconciliation of outliers in CO2-alkanolamine-H2O datasets by robust neural network winsorization |
| title_sort |
reconciliation of outliers in co2-alkanolamine-h2o datasets by robust neural network winsorization |
| publisher |
Springer London |
| publishDate |
2017 |
| url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84957558524&doi=10.1007%2fs00521-016-2213-z&partnerID=40&md5=631b3b8d59309e2f35b88e872f419f2c http://eprints.utp.edu.my/19378/ |
| _version_ |
1738656061652467712 |
| score |
13.211869 |