首页    期刊浏览 2024年11月24日 星期日
登录注册

文章基本信息

  • 标题:CLUSTERING AND SEARCHING TECHNIQUE FOR SELECTION HORTICULTURAL USING SELF ORGANIZING MAPS AND GENETIC ALGORITHM
  • 本地全文:下载
  • 作者:ASTI DWI IRFIANTI ; RETANTYO WARDOYO ; SRI HARTATI
  • 期刊名称:Journal of Theoretical and Applied Information Technology
  • 印刷版ISSN:1992-8645
  • 电子版ISSN:1817-3195
  • 出版年度:2016
  • 卷号:93
  • 期号:2
  • 出版社:Journal of Theoretical and Applied
  • 摘要:The purpose of this study is to develop model for determination of horticultural commodities based on the terms of an area to grow crops. The method use in SOMnGA (Self Organizing Maps and Genetic Algorithm). This method consists of three stages: 1) Clustering, 2) Filtering and 3) Searching based on the shortest distance between the growing crop terms and region parameters (temperature, rainfall and humidity). The data used is secondary data obtained from Litbangdeptan, which is the data collection about the requirement needs of horticultural growth crops consisting of fruits, vegetables, ornamental and biofarmaka plants based on the standardization of the FAO (Food and Agriculture Organization). The test data used in this study were 30 types of horticultural crops. The parameters are used for the process of grouping consists of temperature, rainfall, humidity, base saturation, C-Organic, pH2O, alkalinity, salinity, rocks and Outcrop. SOMnGA method works with an algorithm that can contribute to this research. SOM role classifying plant data based on 10 parameters. Stages Clustering by using SOM created a group of plants that have a closeness characteristics to the needs of plant growth requirements. Then the result of grouped is filtered based on area parameters that user required. Furthermore GA has important part in chooseing the plant filtered result data to produce a list of the closest distance plants towards parameter region. SOMnGA testing consists of two parts: 1) using the method of Davies Bouldin Index (DBI) to produce numbers of 0,017 and an error rate of 10%. 2) comparing with SGA (Simple GA) and SOMnGA. In this study indicates that the SOMnGA method produced shorter iterations to produce outcomes. Testing of 25oC temperature, 125mm Rainfall and 40% Humidity generate a distance of 1941 with each iteration 2276 (SGA) and 25 (SOMnGA) Verify the model in the field using the accuracy method showed a value of 86%. SOMnGA method is a combination of methods that can be used to determine the main commodity based regional horticultural effectively and efficiently. So that the plants election result use SOMnGA could be used as a guide the alternative for farming planning team as one way to determine the main commodity of a region.
  • 关键词:Clustering; Self Organizing Maps; Genetic Algorithm; Horticulture
国家哲学社会科学文献中心版权所有