A comparison of ANFIS and MLP models for the prediction of precipitable water vapor

Wayan Suparta, Kemal Maulana Alhasa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper aimed to compare the adaptive neuro fuzzy inference system (ANFIS) with multi layer perceptron (MPL) of artificial neural network (ANN) structure in estimating the precipitable water vapor (PWV) value. The estimation is based on the surface meteorological data as input from the Malaysian environment and the results of these models were compared with PWV observed by GPS. Two kinds of training data sets were provided to develop these models based on the data gathered from UKMB and UMSK stations at one-minute resolution. To perform of these models, a correlation coefficient (r), root mean square (RMSE) and percent error (PE) were employed. Results showed that the correlation coefficient (r), RMSE and PE of ANFIS model for UKMB station were 0.999, 0.018, and 0.023 and 0.979, 0.019, 0.028 for UMSK station, respectively. For MLP model, the values are 0.975, 0.337 and 0.390 for UKMB station and 0.978, 0.305 and 0.443 for UMSK station. Based on the above results, both models showed strongest correlation. However, RMSE and PE for MLP model are higher ∼5.5% and 5.59% compared with the ANFIS model. This indicated that ANFIS model has better performance and can be proposed as an alternative method in estimating the PWV value where the GPS data in a specific location is absent.

Original languageEnglish
Title of host publicationInternational Conference on Space Science and Communication, IconSpace
Pages243-247
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 3rd IEEE International Conference on Space Science and Communication, IconSpace 2013 - Melaka
Duration: 1 Jul 20133 Jul 2013

Other

Other2013 3rd IEEE International Conference on Space Science and Communication, IconSpace 2013
CityMelaka
Period1/7/133/7/13

Fingerprint

Fuzzy inference
Water vapor
water
system model
Values
Global positioning system
neural network
Multilayer neural networks
Neural networks
performance

Keywords

  • ANFIS
  • Estimation
  • Meteorological Aplications
  • MLP
  • PWV

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Communication

Cite this

Suparta, W., & Alhasa, K. M. (2013). A comparison of ANFIS and MLP models for the prediction of precipitable water vapor. In International Conference on Space Science and Communication, IconSpace (pp. 243-247). [6599473] https://doi.org/10.1109/IconSpace.2013.6599473

A comparison of ANFIS and MLP models for the prediction of precipitable water vapor. / Suparta, Wayan; Alhasa, Kemal Maulana.

International Conference on Space Science and Communication, IconSpace. 2013. p. 243-247 6599473.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Suparta, W & Alhasa, KM 2013, A comparison of ANFIS and MLP models for the prediction of precipitable water vapor. in International Conference on Space Science and Communication, IconSpace., 6599473, pp. 243-247, 2013 3rd IEEE International Conference on Space Science and Communication, IconSpace 2013, Melaka, 1/7/13. https://doi.org/10.1109/IconSpace.2013.6599473
Suparta W, Alhasa KM. A comparison of ANFIS and MLP models for the prediction of precipitable water vapor. In International Conference on Space Science and Communication, IconSpace. 2013. p. 243-247. 6599473 https://doi.org/10.1109/IconSpace.2013.6599473
Suparta, Wayan ; Alhasa, Kemal Maulana. / A comparison of ANFIS and MLP models for the prediction of precipitable water vapor. International Conference on Space Science and Communication, IconSpace. 2013. pp. 243-247
@inproceedings{2a6bba832140438791b98117f61104da,
title = "A comparison of ANFIS and MLP models for the prediction of precipitable water vapor",
abstract = "This paper aimed to compare the adaptive neuro fuzzy inference system (ANFIS) with multi layer perceptron (MPL) of artificial neural network (ANN) structure in estimating the precipitable water vapor (PWV) value. The estimation is based on the surface meteorological data as input from the Malaysian environment and the results of these models were compared with PWV observed by GPS. Two kinds of training data sets were provided to develop these models based on the data gathered from UKMB and UMSK stations at one-minute resolution. To perform of these models, a correlation coefficient (r), root mean square (RMSE) and percent error (PE) were employed. Results showed that the correlation coefficient (r), RMSE and PE of ANFIS model for UKMB station were 0.999, 0.018, and 0.023 and 0.979, 0.019, 0.028 for UMSK station, respectively. For MLP model, the values are 0.975, 0.337 and 0.390 for UKMB station and 0.978, 0.305 and 0.443 for UMSK station. Based on the above results, both models showed strongest correlation. However, RMSE and PE for MLP model are higher ∼5.5{\%} and 5.59{\%} compared with the ANFIS model. This indicated that ANFIS model has better performance and can be proposed as an alternative method in estimating the PWV value where the GPS data in a specific location is absent.",
keywords = "ANFIS, Estimation, Meteorological Aplications, MLP, PWV",
author = "Wayan Suparta and Alhasa, {Kemal Maulana}",
year = "2013",
doi = "10.1109/IconSpace.2013.6599473",
language = "English",
isbn = "9781467352314",
pages = "243--247",
booktitle = "International Conference on Space Science and Communication, IconSpace",

}

TY - GEN

T1 - A comparison of ANFIS and MLP models for the prediction of precipitable water vapor

AU - Suparta, Wayan

AU - Alhasa, Kemal Maulana

PY - 2013

Y1 - 2013

N2 - This paper aimed to compare the adaptive neuro fuzzy inference system (ANFIS) with multi layer perceptron (MPL) of artificial neural network (ANN) structure in estimating the precipitable water vapor (PWV) value. The estimation is based on the surface meteorological data as input from the Malaysian environment and the results of these models were compared with PWV observed by GPS. Two kinds of training data sets were provided to develop these models based on the data gathered from UKMB and UMSK stations at one-minute resolution. To perform of these models, a correlation coefficient (r), root mean square (RMSE) and percent error (PE) were employed. Results showed that the correlation coefficient (r), RMSE and PE of ANFIS model for UKMB station were 0.999, 0.018, and 0.023 and 0.979, 0.019, 0.028 for UMSK station, respectively. For MLP model, the values are 0.975, 0.337 and 0.390 for UKMB station and 0.978, 0.305 and 0.443 for UMSK station. Based on the above results, both models showed strongest correlation. However, RMSE and PE for MLP model are higher ∼5.5% and 5.59% compared with the ANFIS model. This indicated that ANFIS model has better performance and can be proposed as an alternative method in estimating the PWV value where the GPS data in a specific location is absent.

AB - This paper aimed to compare the adaptive neuro fuzzy inference system (ANFIS) with multi layer perceptron (MPL) of artificial neural network (ANN) structure in estimating the precipitable water vapor (PWV) value. The estimation is based on the surface meteorological data as input from the Malaysian environment and the results of these models were compared with PWV observed by GPS. Two kinds of training data sets were provided to develop these models based on the data gathered from UKMB and UMSK stations at one-minute resolution. To perform of these models, a correlation coefficient (r), root mean square (RMSE) and percent error (PE) were employed. Results showed that the correlation coefficient (r), RMSE and PE of ANFIS model for UKMB station were 0.999, 0.018, and 0.023 and 0.979, 0.019, 0.028 for UMSK station, respectively. For MLP model, the values are 0.975, 0.337 and 0.390 for UKMB station and 0.978, 0.305 and 0.443 for UMSK station. Based on the above results, both models showed strongest correlation. However, RMSE and PE for MLP model are higher ∼5.5% and 5.59% compared with the ANFIS model. This indicated that ANFIS model has better performance and can be proposed as an alternative method in estimating the PWV value where the GPS data in a specific location is absent.

KW - ANFIS

KW - Estimation

KW - Meteorological Aplications

KW - MLP

KW - PWV

UR - http://www.scopus.com/inward/record.url?scp=84889057554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889057554&partnerID=8YFLogxK

U2 - 10.1109/IconSpace.2013.6599473

DO - 10.1109/IconSpace.2013.6599473

M3 - Conference contribution

SN - 9781467352314

SP - 243

EP - 247

BT - International Conference on Space Science and Communication, IconSpace

ER -