Please use this identifier to cite or link to this item: http://nopr.niscpr.res.in/handle/123456789/43584
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBharti, V. S.-
dc.contributor.authorInamdar, A. B.-
dc.contributor.authorPurushothaman, C. S.-
dc.contributor.authorYadav, V.K.-
dc.date.accessioned2018-02-12T09:33:05Z-
dc.date.available2018-02-12T09:33:05Z-
dc.date.issued2018-02-
dc.identifier.issn0975-1033 (Online); 0379-5136 (Print)-
dc.identifier.urihttp://nopr.niscair.res.in/handle/123456789/43584-
dc.description365-377en_US
dc.description.abstractThree water quality parameters – dissolved oxygen (DO), coloured dissolved organic matter (CDOM) and Chlorophyll - a loaded on the first principal component under the dimensional reduction method were used for deriving the Eutrophication Index (EI). Fuzzy logic (Mamdani) method of EI estimation is smoother than the Principal Component Analysis (PCA) method. Eutrophication potential obtained from the rule-based fuzzy approach and the multiple regressions derived from the first principal component were selected as the target variables for the artificial neural network (ANN) model in training and prediction. The performance of the ANN models with PCA-derived target and fuzzy-derived target was compared through the mean absolute error, root mean square error, and correlation coefficient computed from the measured and model-simulated EI values.  EI predictions of this model has positive, high correlation (r = 0.968) with the measured EI values derived from the fuzzy approach as compared to the PCA-derived EI (r = 0.851) implying that the model predictions explain around 93.7% of the variation in the measured EI values derived by fuzzy approach as compared to 72.4% in the case of PCA-derived measured value.en_US
dc.language.isoen_USen_US
dc.publisherNISCAIR-CSIR, Indiaen_US
dc.rights CC Attribution-Noncommercial-No Derivative Works 2.5 Indiaen_US
dc.sourceIJMS Vol.47(02) [February 2018]en_US
dc.subjectFuzzy logicen_US
dc.subjectPrincipal component analysisen_US
dc.subjectEutrophication modelingen_US
dc.subjectMumbai coastal wateren_US
dc.subjectArtificial neural networken_US
dc.titleSoft computing and statistical technique - Application to eutrophication potential modelling of Mumbai coastal areaen_US
dc.typeArticleen_US
Appears in Collections:IJMS Vol.47(02) [February 2018]

Files in This Item:
File Description SizeFormat 
IJMS 47(2) 365-377.pdf662.53 kBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.