Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/92924
標題: Genetic Algorithm Base Cabbage Transfer Quantity Prediction of Wholesale Market in Taiwan
基於基因演算法預測台灣批發市場甘藍交易量
作者: 楊長憲
Chang Hsien Yang
關鍵字: Genetic Algorithm
Cabbage
Amount of Cabbage Production
Trading Volume
Wholesale Market
基因演算法
甘藍
產量預測
市場到後量
批發市場
引用: Reference [1] 行政院農業委員會, '102年9月農業產銷概況 ', 第247期-258期,2013. [2] 許雅筑,'產銷問題 政府應積極作為'.國立交通大學,2012. [3] 行政院農委會農業知識入口網, '甘藍主題館', 2015. From http://kmweb.coa.gov.tw/subject/mp.asp?mp=134 [4] 西螺農產品市場,2015.From http://www.xamc.com.tw/main.htm?pid=11 [5] 農糧署大宗蔬菜種植登記暨供育苗量統計資訊系統,2015.From http://mvrs.afa.gov.tw/tbix/index.jsp [6] 洪忠修, '我國農牧業農情調查之檢討與展望',農政與農情,135期,2003. [7] 吳惠萍, '全球氣候變遷下糧食安全問題與建議',國家政策研究基金會,2002. [8] 行政院農業委員會, '農產品交易行情站'. 2015. From http://amis.afa.gov.tw/. [9] 行政院農業委員會, '農業統計資料查詢',2015 .From http://agrstat.coa.gov.tw/sdweb/public/inquiry/InquireAdvance.aspx [10] 農糧署統計室, '農產品產地價格查報系統',2015.Fromhttp://apis.afa.gov.tw/pagepub/AppInquiryPage.aspx [11] 交通部中央氣象局,2015.From http://www.cwb.gov.tw/V7/climate/agri/agrb.htm [12] 行政院主計總處, '農漁產品運銷實況調查報將告',2015.From http://www.dgbas.gov.tw/np.asp?ctNode=2847   [13] Canesio, P., C. Jason, H. Peter, M. John, and P. Kevin. Profitable use of seasonal climate forecasts: Farm management case studies in the Philippinnes and Australia. Philippine J. Crop Science 32: 41-42,2007. [14] Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D., Genetic Programming– An Introduction on the Automatic Evolution of Computer Programs and its Applications. Morgan Kaufmann, Germany, ISBN: 978-1-55860- 510-7, 1997. [15] Muhlenbein, Heinz, and Dirk Schlierkamp-Voosen. 'Predictive models for the breeder genetic algorithm i. continuous parameter optimization.' Evolutionary computation 1.1 pp.25-49, 1993. [16] Apipattanavis, S., F. Bert, Guillermo Podesta, and Balaji Rajagopalan, Linking weather generators and crop models for assessment of climate forecast Outcomes. Agricultural and Forest Meteorology, 150, pp.166–174, 2010. [17] Brown, C., P. Rogers, and U. Lall. Demand Management of Groundwater with Monsoon forecasting. Agricultural Systems 90: pp.293-311, 2006. [18] Qian Wen1, Weisong Mu, Li Sun, Su Hua, Zhijian ZhouDaily: Sales Forecasting for Grapes by Support Vector Machine. IFIP AICT 420, pp.351–360 ,2014. [19] S.P. Nitsure , S.N.Londhe , K.C.Khare : Wave forecasts using wind information and genetic programming . Ocean Engineering 54 pp.61–69,2012. [20] Mohammad AliGhorbani, RahmanKhatibi, AliAytek , OlegMakarynskyy , JalalShiri :Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks . Computers & Geosciences pp. 620–627, 2010. [21] Soumadip Ghosh+, Sushanta Biswas*, Debasree Sarkar*, Partha Pratim Sarkar : Mining Frequent Itemsets Using Genetic Algorithm. International Journal of Artificial Intelligence & Applications (IJAIA), Vol.1, No.4, 2010. [22] Randy L. Haupt,Sue Ellen HauptPractical ,Genetic Algorithms,2004.
摘要: Cabbage is one of the bulk vegetables in Taiwan. The production period of cabbage is mainly concentrated in spring and winter seasons, prone to supply and demand imbalance. It hence often results in a lower sale price and causes great losses to the farmers. If the amount of cabbage production can be precisely predicted, according to the prediction, the farmers can adjust the amount of cabbage which they intend to plant. In addition, the government can follow it to give adaptive countermeasures to regulate the market supply and demand. Different species of Cabbage has different yield capacity. Moreover, cabbage is very susceptible to soil properties, plantation technology, pests and diseases, and climatic factors during its growth period. Since many factors will determine the amount of cabbage production, accurately predicting the future amount of cabbage production is very difficult and impractical. The traditional method predicts the amount of cabbage production via the planting acreage and production amount per unit area of cabbage. It is the most labor-intensive and time-consuming and often cannot give a precise prediction results since too many factors affect the cabbage production. Many computer applications employed smart algorithms to predict the amount of cabbage production. Unfortunately, it cannot provide satisfying prediction results neither since the historic real amount of cabbage production is very difficult to be obtained. In Taiwan, about 77.21% of cabbage production is sold to the wholesale markets. In the wholesale markets, there are specialized staffs writing down every trade volume. It is hence much easier to get the cabbage trade volumes in the wholesale markets than to estimate the cabbage planting areas since there are only a few wholesale markets in Taiwan relative to the cabbage planting areas. Hence predicting the cabbage trade volumes in all the wholesale markets and then changing them into the amount of cabbage production is feasible. Moreover, it can offer more accurate prediction results and is more cost-saving. This study will develop a genetic based algorithm to predict the trading volume of cabbage in a wholesale market via cabbage planting areas and sale price, and climatic factors during the cabbage growing period. This study used the historic cabbage trading volumes in the wholesale markets of Siluo county and Nanto county in Taiwan as the test data. The experimental results show that the proposed algorithm achieves more than 80% accuracy for every case and over 90% accuracy in many cases. Keywords: Genetic Algorithm, Cabbage, Amount of Cabbage Production, Trading Volume, Wholesale Market.
甘藍為台灣重要大宗蔬菜之一. 然因產量大多集中於冬春季節, 易產生供需失調, 致屢見價格偏低, 造成農民極大損失. 若能對甘藍產量進行精確預測, 不僅可提供農人對種植面積進行調節, 及政府調節市場供應量之因應對策之參考, 期能平穩交易價格, 以避免菜賤傷農情況發生. 甘藍產量易受種植甘藍品種、土壤性質、裁培技術、病蟲害、及成長期間之氣候等因素影響. 欲精確預測甘藍未來產量, 實太複雜而不可行. 現有些系統藉估算種植面積及單位面積產量, 來推算產量. 然影響甘藍產量因素相當複雜, 且無法取得歷年各區域甘藍實際產量資料, 智慧型資訊技術難提供精確預測產量. 台灣批發市場甘藍流通量約佔總生產量的77.21%. 因有專門人員進行記錄, 批發市場到貨量能有完整紀錄. 全國批發市場分佈於僅少數地點, 資料取得也較容易. 因此透過預測各個批發市場甘藍到貨量, 後再轉換算成產量實為可行, 也較來得精確且較省成本. 故本研究將從已估算之種植面積及種植期間的氣候因素, 來預測甘藍的未來市場到貨量. 本研究將結合歷史到貨量及氣候資料, 透過基因演算法預測西螺及南投果菜市場甘藍到貨量. 實驗結果顯示對西螺及南投果菜市場之各月份甘藍到貨量預測準確度, 至少都在80%以上, 且在許多月份可達到90%以上. 關鍵字:基因演算法、甘藍、產量預測、市場到後量、批發市場
URI: http://hdl.handle.net/11455/92924
其他識別: U0005-1108201513301600
文章公開時間: 10000-01-01
Appears in Collections:資訊管理學系

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.