Feature Selection for Heavy Rain Prediction Using Genetic Algorithms

被引：0

作者：

Lee, Jaedong ^{[1
]}

Kim, Jaekwang ^{[1
]}

Lee, Jee-Hyong ^{[1
]}

Cho, Ik-Hyun ^{[2
]}

Lee, Jeong-Whan ^{[2
]}

Park, Kyoung-Hee ^{[2
]}

Park, JeongGyun ^{[3
]}

机构：

[1] Sungkyunkwan Univ, Dept Elect Comp Engn, Suwon, South Korea

[2] Korea Meteorol Adm, Forecast Technol Div, Seoul, South Korea

[3] LG CNS, Seoul, South Korea

来源：

6TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS, AND THE 13TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS | 2012年

关键词：

Support Vector Machine; Genetic Algorithm; Big Data Mining; Heavy Rain Prediction;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

ECMWF (European Centere of Medium-Range Weather Forecasts) produces weather data every six hours. In the case of ECMWF 1.125 degree weather data, the northern hemisphere is divided into 320x161 grids and each grid has 254 weather features. Since we are aim to forecast heavy rain in the Korea Peninsula, we need only 10x10 grids around the Korean Peninsula. However, the number of inputs to the forecasting system will be 100 dimensions (10x10) even if we consider only one weather feature. If we consider 3 features, it is 300 dimensions (10x10x3). Therefore, as more features are combined, the size of the data is increased and it causes the computational cost high. In order to reduce the size of inputs to the forecasting system, we apply genetic algorithms for the feature selection in this paper. As a result, it has been found out that it is possible to assort with a higher accuracy rate with a smaller data set.

引用

页码：830 / 833

页数：4

共 50 条

[41] Feature Selection Algorithms for Wind Turbine Failure Prediction
Marti-Puig, Pere
Blanco-M, Alejandro
Jose Cardenas, Juan
Cusido, Jordi
Sole-Casals, Jordi
[J]. ENERGIES, 2019, 12 (03)
[42] Genetic algorithms for pattern recognition: Feature selection, classification, clustering, and prediction in a single step.
Lavine, BK
Davidson, CE
[J]. ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2004, 228 : U111 - U111
[43] Conditional Random Fields feature subset selection based on Genetic Algorithms for phosphorylation site prediction
Thanh Hai Dang
Engelen, Kristof
Meysman, Pieter
Marchal, Kathleen
Verschoren, Alain
Laukens, Kris
[J]. INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2009), 2009, : 7 - +
[44] Genetic Feature Selection for Software Defect Prediction
Wahono, Romi Satria
Herman, Nanna Suryana
[J]. ADVANCED SCIENCE LETTERS, 2014, 20 (01) : 239 - 244
[45] Genetic algorithms for feature selection and weighting, a review and study
Hussein, F
Kharma, N
Ward, R
[J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 1240 - 1244
[46] FCFilter: Feature Selection based on Clustering and Genetic Algorithms
Ferreira, Charles H. P.
de Medeiros, Debora M. R.
Santana, Fabiana
[J]. 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2016, : 2106 - 2113
[47] Feature selection by genetic algorithms for mass spectral classifiers
Yoshida, H
Leardi, R
Funatsu, K
Varmuza, K
[J]. ANALYTICA CHIMICA ACTA, 2001, 446 (1-2) : 485 - 494
[48] Balanced accuracy for feature subset selection with genetic algorithms
Peterson, MR
Raymer, ML
Lamont, GB
[J]. 2005 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-3, PROCEEDINGS, 2005, : 2506 - 2513
[49] Fast feature selection with genetic algorithms: A filter approach
Lanzi, PL
[J]. PROCEEDINGS OF 1997 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION (ICEC '97), 1997, : 537 - 540
[50] GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms
Tolba, Mai F.
Moustafa, Mohamed
[J]. PROCEEDINGS OF THE 8TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE, VOL 1: ECTA, 2016, : 156 - 163

← 1 2 3 4 5 →