PERFORMANCE COMPARISON OF TWO ACTIVATION FUNCTIONS NAMELY SIGMOID AND HYPERBOLIC TANGENT IN ARTIFICIAL NEURALNETWORKS FOR STORM RUNOFF COEFFICIENT FORECASTING (CASE STUDY: BARARIYEH WATERSHED, NEISHABOUR)

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

JAFARI M.; VAFAKHAH M.; ABGHARI H.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Journal of Water and Soil Conservation Year:2013 | Volume:20 | Issue:2 Page(s): 85-103

Download Full-Text

Persian Verion

View:

3,398

Download:

Cites:

Information Journal Paper

Title

PERFORMANCE COMPARISON OF TWO ACTIVATION FUNCTIONS NAMELY SIGMOID AND HYPERBOLIC TANGENT IN ARTIFICIAL NEURALNETWORKS FOR STORM RUNOFF COEFFICIENT FORECASTING (CASE STUDY: BARARIYEH WATERSHED, NEISHABOUR)

Author(s)

JAFARI M. | VAFAKHAH M. | ABGHARI H. | Issue Writer Certificate

Keywords

ANNQ2

SIGMOID FUNCTIONQ2

HYPERBOLIC TANGENT FUNCTIONQ2

RUNOFF COEFFICIENTQ2

BARARIYEH NEISHABOUR WATERSHEDQ2

Abstract

The rainfall-runoff process and flooding are hydrologic phenomena that are difficult to study due to the influence of different parameters. So far, different methods and models are provided to analyze these phenomena. Therefore, the purpose of this study is evaluation of artificial neural networks (ANNs) for storm RUNOFF COEFFICIENT forecasting using two transfer functions, hyperbolic tangent and sigmoid, in hidden layer and linear in output layer. For this reason, Barariyeh watershed was chosen in Neishabour and the data of 33 events were collected during 1952 to 2006. The factor analysis (FA) were used for determination of independent variables in storm RUNOFF COEFFICIENT forecasting in which four variables were selected as independent variables, including average rainfall amount, third, first and fourth quartiles rainfall intensity and also five variables including j index and first to fourth quartiles rainfall intensity. ANN was performed using sigmoid and HYPERBOLIC TANGENT FUNCTIONs. The result of variables through factor analysis was acceptable for ANN using sigmoid transfer function but wasn't acceptable for ANN using hyperbolic tangent transfer function due to different performance of this activation function. So, other variables combined based on their hydrological role, were considered as ANN inputs. The results revealed that ANN using first to fourth quartile rainfall intensity, rainfall duration, average rainfall amount and total rainfall of five days ago inputs and hyperbolic tangent transfer function can predict storm RUNOFF COEFFICIENT with R2=0.98 and RMSE=0.0337 and MAE=0.0275.

Cites

PREDICTION COMMERCIAL AND CORDWOOD VOLUME OF BROADLEAVES USING ARTIFICIAL NEURAL NETWORKS (CASE STUDY: GORAZBON DISTRIC OF KHEYROOD FOREST, NOWSHAHR)

References

No record.

Cite

APA: Copy

JAFARI, M., VAFAKHAH, M., & ABGHARI, H.. (2013). PERFORMANCE COMPARISON OF TWO ACTIVATION FUNCTIONS NAMELY SIGMOID AND HYPERBOLIC TANGENT IN ARTIFICIAL NEURALNETWORKS FOR STORM RUNOFF COEFFICIENT FORECASTING (CASE STUDY: BARARIYEH WATERSHED, NEISHABOUR). JOURNAL OF WATER AND SOIL CONSERVATION (JOURNAL OF AGRICULTURAL SCIENCES AND NATURAL RESOURCES), 20(2), 85-103. SID. https://sid.ir/paper/156552/en

Vancouver: Copy

JAFARI M., VAFAKHAH M., ABGHARI H.. PERFORMANCE COMPARISON OF TWO ACTIVATION FUNCTIONS NAMELY SIGMOID AND HYPERBOLIC TANGENT IN ARTIFICIAL NEURALNETWORKS FOR STORM RUNOFF COEFFICIENT FORECASTING (CASE STUDY: BARARIYEH WATERSHED, NEISHABOUR). JOURNAL OF WATER AND SOIL CONSERVATION (JOURNAL OF AGRICULTURAL SCIENCES AND NATURAL RESOURCES)[Internet]. 2013;20(2):85-103. Available from: https://sid.ir/paper/156552/en

IEEE: Copy

M. JAFARI, M. VAFAKHAH, and H. ABGHARI, “PERFORMANCE COMPARISON OF TWO ACTIVATION FUNCTIONS NAMELY SIGMOID AND HYPERBOLIC TANGENT IN ARTIFICIAL NEURALNETWORKS FOR STORM RUNOFF COEFFICIENT FORECASTING (CASE STUDY: BARARIYEH WATERSHED, NEISHABOUR),” JOURNAL OF WATER AND SOIL CONSERVATION (JOURNAL OF AGRICULTURAL SCIENCES AND NATURAL RESOURCES), vol. 20, no. 2, pp. 85–103, 2013, [Online]. Available: https://sid.ir/paper/156552/en

Related Journal Papers