ACADSTAFF UGM

CREATION
Title : ESSPI : Exponential Smoothing Seasonal Planting Index, A New Algorithm For Prediction Rainfall
Author :

KRISTOKO DWI HARTOMO (1) Prof. Drs. Subanar, Ph.D. (2) Drs. Edi Winarko, M.Sc.,Ph.D. (3)

Date : 0 2016
Keyword : exponential, smoothing, algorithm, seasonal planting index, predictions, accuracy, rainfall, novelty exponential, smoothing, algorithm, seasonal planting index, predictions, accuracy, rainfall, novelty
Abstract : Exponential smoothing algorithm is a prediction algorithm recommended by the Food and Agriculture Organization. The weakness of the this exponential smoothing prediction algorithm is low accuracy for the prediction of long-term and ineffective in determining the value of smoothing to minimize error. The proposed research is to build a model rainfall prediction using a new algorithm Seasonal Planting Index (ESSPI). By using the algorithm planting seasonal index, rainfall prediction model will generate higher accuracy. The results showed seasonal planting method is the dominant index (5 of 6 test size) have an average accuracy is better than the method of exponential smoothing. Index planting seasonal prediction accuracy of 95.73?tter than the exponential smoothing ? = 0.1 by 56.55%, and exponential smoothing of ? = 55.53. Novelty of this research is new algorithms for classifying data based on seasonal planting index, a new algorithm for determining the smoothing (value), the new fitting algorithm using seasonal planting index, and new algorithms using seasonal rainfall prediction planting index for the determination of the growing season
Group of Knowledge : Ilmu Komputer
Original Language : English
Level : Internasional
Status :
Published
Document
No Title Document Type Action
1 Artikel Exponential smoothing seasonal planting index-IJCSIS Juni 2016-HSW.pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
2 ESSPI _ Exponential Smoothing Seasonal Planting Index, A New Algorithm For Prediction Rainfall.pdf
Document Type : [PAK] Cek Similarity
[PAK] Cek Similarity View