Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/56057
標題: 稻米貯藏鮮度監測模式之建構
Toward a Statistical Model for Monitoring the Freshness of Rice Grains
作者: 林俊隆
陳宗禮
關鍵字: 應用研究;農藝
摘要: 
本研究之目的在建立一個監測稻米貯藏鮮度的統計程序。在前一年度,本研究以混合常態分布模式為基礎,開發了一套統計程序(RiceMix 1.0)以供檢驗一批稻米是否混有貯藏期不同的米粒成份、以及各個新/舊米粒成份的混合比率。本年度將藉模擬試驗確認 擴大拔靴重抽樣的重複次數及/ 或向下調校舊米混入率的估值是否可以改善舊米混入率較低時的檢驗力與估計精確度。其次,將以95-II期、96-I期及96-II期之稻穀模擬各種混合狀態,生產實地測試數據;進行RiceMix 1.0之檢驗靈敏度與專一性的評估。

This study aims to develop a statistical procedure for monitoring the freshness of rice grains during storage.In the last year, a statistical procedure based on normal mixture model, named as RiceMix 1.0, was developed to test the number of components of rice grains with different storage durations, and to estimate the mixing proportions of each components in a batch of rice grains. Simulation experiments will be carried out to see if the test power and estimation precision could be improved by increasing the bootstrap replications and /or downward calibrating the estimates of the mixing proportion of old grains of RiceMix 1.0. Then the sensitivity and specificity of RiceMix 1.0 will be evaluated by filed testing, using the data generated from batches of grains with various mixing proportions of rice grains produced in the previous three crop seasons.
URI: http://hdl.handle.net/11455/56057
其他識別: 97農科-4.2.1-糧-Z5(2)
Appears in Collections:農藝學系

Show full item record
 

Google ScholarTM

Check


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