PENGARUH FITUR KELEMBABAN TERHADAP AKURASI ALGORITMA EVOLVING NEURAL NETWORK PREDIKSI CURAH HUJAN

Bambang Lareno, Liliana Swastina, Feiliana Tan

Abstract


Penambahan fitur kelembaban berpengaruh terhadap akurasi BackPropagation Neural Network (BPNN). Penelitian lebih lanjut pengaruh fitur kelembaban terhadap akurasi prediksi curah hujan, khususnya ketika menggunakan pendekatan algoritma genetika perlu dilakukan. Penelitian ini menggunakan algoritma Evolving Neural Network (ENN) sebagai pendekatan untuk memprediksi curah hujan. Pengolahan dan perhitungan data menggunakan MatLab. Parameter yang akan digunakan dalam penelitian ini adalah Waktu, Curah hujan, dan Kelembaban. Hasil penelitian juga dibandingkan dengan hasil pengujian BPNN dan prediksi BMKG. Hasil penelitian yang dilakukan menunjukkan bahwa penambahan fitur dapat memperbaiki akurasi neural network. Khususnya, penerapan ENN dengan tambahan fitur kelembaban mengalami perbaikan akurasi 1,95% - 6,10%, dengan rata-rata perbaikan 3,96% pada arsitektur 4-2-1 dan 2,42% pada 4-4-1.


Full Text:

PDF

References


Handoko, Ed., Klimatologi Dasar. Jakarta: Pustaka Jaya, 1994.

BMKG - Stasiun Klimatologi Banjarbaru, Analisis Hujan Bulan Maret 2011, Prakiraan Hujan Bulan Juni, Juli dan Agustus 2011, 2011.

Wint Thida Zaw and Thinn Thu Naing, "Modeling of Rainfall Prediction over Myanmar Using Polynomial Regression," in 2009 International Conference on Computer Engineering and Technology, 2009, pp. 316-320.

Zhi-liang Wang and Hui-hua Sheng, "Rainfall Prediction Using Generalized Regression Neural Network: Case study Zhengzhou," in 2010 International Conference on Computational and Information Sciences, 2010, pp. 1265-1268.

Yuhui Wang, Yunzhong Jiang, Xiaohui Lei, and Wang Hao, "Rainfall-Runoff Simulation Using Simulated Annealing Wavelet BP Neural Network," in 2010 International Conference on Intelligent Computation Technology and Automation, 2010, pp. 963-967.

Pei-Chann Chang, Yen-Wen Wang, and C.Y. Tsai, "Evolving Neural Network for Printed Circuit Board Sales," Expert System Application, vol. 29(1), pp. 83-92, 2005. [7] Li Chungui, Xu Shu’an, and Wen Xin, "Traffic Flow forecasting Algorithm Using Simulated Annealing Genetic BP Network," in 2010 International Conference on Measuring Technology and Mechatronics Automation, 2010, pp. 1043-1046.

Ganji Huang and Lingzhi Wang, "Hybrid Neural Network Models for Hydrologic Time Series Forecasting Based on Genetic Algorithm," in 2011 Fourth International Joint Conference on Computational Sciences and Optimization, 2011, pp. 1347-1350.

Liliana Swastina, Subhan Panji Cipta, and Bambang Lareno, "Penerapan Algoritma Evolving Neural Network Untuk Prediksi Curah Hujan," in Konferensi Nasional Sistem & Informatika;, Bali, 2014, pp. 802-806.

Sani Susanto and Dedy Suryadi, Pengantar Data Mining : Menggali Pengetahuan Dari Bongkahan Data. Yogyakarta: Andi, 2010.

Pei-Chann Chang and Yen-Wen Wang, "Using Soft Computing Methods for Time Series Forecasting," in Series on Computers and Operations Research (Vol.6) - Recent Advances in Data Mining of Enterprise Data: Algorithms and Applications , P.M Pardalos, Ed. Singapore: World Scientific, 2007, ch. 4, pp. 189- 246.

Suyanto, Soft Computing: Membangun Mesin Ber-IQ Tinggi. Bandung, Jawa Barat, Indonesia: Informatika, 2008.

Suyanto, Evolutionary Computing: Komputasi Berbasis 'Evolusi' dan 'Genetika'. Bandung: Informatika, 2008.

Matlab 7.9.0 (R2009b), "Function minimization by conjugate gradients," in Neural Network, R Fletcher and Reeves C.M, Eds.: Computer Journal, Vol. 7, 1964, pp. 149-154.

Philip J. Ross, Taguchi Techniques For Quality Engineering: Loss Function, Orthogonal Experiments, Parameters and Tolerance Design, 2nd ed. New York: Mc Graw-Hill Companies, Inc., 1996.

Carlo Vercellis, Business Intelligenc: data Mining and Optimization For decision making. Milano, Italy: John Wiley& Son Ltd., 2009.

The MathWorks, Neural Network Toolbox: User’s Guide ver.7, Mark Hudson Beale, Martin T. Hagan, and Howard B Demuth, Eds., 2010.


Refbacks

  • There are currently no refbacks.