【摘要】：隨著人民生活質(zhì)量的改善,對農(nóng)產(chǎn)品的質(zhì)量安全意識越來越高,農(nóng)產(chǎn)品的種類、安全因素和流通環(huán)節(jié)復(fù)雜,建立全過程的監(jiān)管與追溯非常重要,而大數(shù)據(jù)技術(shù)的迅猛發(fā)展更是為農(nóng)產(chǎn)品質(zhì)量監(jiān)管追溯系統(tǒng)提供了新的平臺。在分析國內(nèi)外農(nóng)產(chǎn)品質(zhì)量監(jiān)管方面和追溯系統(tǒng)技術(shù)的基礎(chǔ)上,利用大數(shù)據(jù)技術(shù),基于Hadoop平臺架構(gòu)了農(nóng)產(chǎn)品質(zhì)量監(jiān)管與追溯系統(tǒng)。通過對SVM和BP神經(jīng)網(wǎng)絡(luò)算法的深入分析,構(gòu)建了基于SVM算法的農(nóng)產(chǎn)品區(qū)域質(zhì)量監(jiān)管預(yù)測模型,在選擇最佳的懲罰因子和核函數(shù)參數(shù)時,將原始數(shù)據(jù)中的農(nóng)藥污染指數(shù)和重金屬污染指數(shù)平均分為K組,每組數(shù)據(jù)分別做一次驗證集,剩下的K-1組數(shù)據(jù)作為訓(xùn)練集,用驗證集的分類精度的平均值作為分類器最終的交叉驗證精度,用最大精度對應(yīng)的懲罰因子和核函數(shù)參數(shù)進行訓(xùn)練,實現(xiàn)對需要重點監(jiān)管的農(nóng)產(chǎn)品區(qū)域的預(yù)測,與BP神經(jīng)網(wǎng)絡(luò)算法進行對比,SVM算法的分類準確率提高了10%;為了實現(xiàn)對農(nóng)產(chǎn)品腐敗率數(shù)據(jù)未來一段時間的預(yù)測,構(gòu)建了基于SVR算法的農(nóng)產(chǎn)品時序質(zhì)量預(yù)測模型,將農(nóng)產(chǎn)品近期的腐敗率數(shù)據(jù)分為兩組,最佳的懲罰因子和核函數(shù)參數(shù)選取與上一模型相同,用第一組數(shù)據(jù)訓(xùn)練得到的模型進行預(yù)測,預(yù)測數(shù)據(jù)與第二組真實數(shù)據(jù)進行絕對誤差和相對誤差分析,與BP神經(jīng)網(wǎng)絡(luò)算法進行對比,在預(yù)測值和真實值的相關(guān)系數(shù)方面SVR算法比BP神經(jīng)網(wǎng)絡(luò)算法提高了近5%,更加逼近真實值。從Web端和Android端的角度對農(nóng)產(chǎn)品質(zhì)量監(jiān)管與追溯系統(tǒng)進行設(shè)計。搭建測試環(huán)境,分別對Hadoop監(jiān)管追溯平臺、Web端和Android端的主要功能進行了測試,測試結(jié)果表明該系統(tǒng)在農(nóng)產(chǎn)品質(zhì)量監(jiān)管與追溯方面具有一定的實用價值。
[Abstract]:With the improvement of the people's quality of life, the awareness of the quality and safety of agricultural products is becoming higher and higher, and the types, safety factors and circulation links of agricultural products are complicated. It is very important to establish the supervision and traceability of the whole process. The rapid development of big data technology also provides a new platform for the traceability system of agricultural product quality supervision. Based on the analysis of domestic and foreign agricultural product quality supervision and traceability system technology, using big data technology, the agricultural product quality supervision and traceability system is constructed based on Hadoop platform. Based on the analysis of SVM and BP neural network algorithm, the prediction model of agricultural product regional quality supervision based on SVM algorithm is constructed. When selecting the best penalty factor and kernel function parameter, The pesticide pollution index and heavy metal pollution index in the original data were divided into two groups: group K, each group of data made a verification set, and the remaining group of K-1 data as a training set. The average value of the classification accuracy of the verification set is used as the final cross validation accuracy of the classifier, and the penalty factor corresponding to the maximum accuracy and the kernel function parameters are used to train the forecast of the agricultural product area which needs the key supervision. Compared with the BP neural network algorithm, the classification accuracy of the SVM algorithm is improved by 10%. In order to predict the corruption rate of agricultural products for some time in the future, a forecasting model of agricultural product time series quality based on SVR algorithm is constructed, and the recent data of agricultural corruption rate are divided into two groups. The best penalty factor and kernel function parameters are chosen the same as the previous model. The model trained by the first group of data is used to predict, and the absolute error and relative error between the predicted data and the second real data are analyzed. Compared with the BP neural network algorithm, the correlation coefficient between the predicted value and the real value is improved by nearly 5% by the SVR algorithm compared with the BP neural network algorithm, and the real value is closer to the real value. From the point of view of Web and Android, the system of agricultural product quality supervision and traceability is designed. The main functions of Hadoop supervisory traceability platform, Web terminal and Android terminal are tested in the test environment. The test results show that the system has certain practical value in agricultural product quality supervision and traceability.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP311.52

【參考文獻】

相關(guān)期刊論文 前10條

1 楊文秀;周莉;張曉林;;促進互聯(lián)網(wǎng)+農(nóng)產(chǎn)品物流發(fā)展的對策分析[J];物流工程與管理;2016年06期

2 任廣濤;;談農(nóng)產(chǎn)品質(zhì)量安全檢驗檢測技術(shù)推廣相關(guān)措施[J];黑龍江生態(tài)工程職業(yè)學(xué)院學(xué)報;2016年03期

3 楊云;魏琨;;農(nóng)產(chǎn)品質(zhì)量安全追溯系統(tǒng)的構(gòu)建[J];電腦知識與技術(shù);2015年32期

4 朱衷衛(wèi);劉盛梅;;新疆地區(qū)農(nóng)產(chǎn)品質(zhì)量信息化追溯系統(tǒng)設(shè)計[J];數(shù)字技術(shù)與應(yīng)用;2015年07期

5 任瑞;趙向東;王海榮;李曉飛;廉敬業(yè);胡博珂;;關(guān)于農(nóng)產(chǎn)品質(zhì)量監(jiān)測現(xiàn)場抽樣環(huán)節(jié)信息化建設(shè)的幾點思考[J];河北企業(yè);2015年04期

6 李宗迅;;試析農(nóng)產(chǎn)品質(zhì)量檢測體系現(xiàn)狀與完善策略[J];農(nóng)家顧問;2015年06期

7 劉瑾;;新時代形勢下我國農(nóng)產(chǎn)品供應(yīng)鏈中利益分配體系與風(fēng)險應(yīng)對分析[J];物流技術(shù);2014年23期

8 吳俊森;;Hadoop云計算平臺的研究及實現(xiàn)[J];硅谷;2014年15期

9 謝黨恩;頓貝貝;張志立;;基于百度地圖API的校內(nèi)路徑導(dǎo)航系統(tǒng)的實現(xiàn)[J];許昌學(xué)院學(xué)報;2014年02期

10 董銀果;邱荷葉;;基于追溯、透明和保證體系的中國豬肉競爭力分析[J];農(nóng)業(yè)經(jīng)濟問題;2014年02期

相關(guān)碩士學(xué)位論文 前7條

1 段小云;我國大宗農(nóng)產(chǎn)品價格波動對通脹影響的實證研究[D];山東財經(jīng)大學(xué);2015年

2 周濤麗;基于支持向量機的多分類方法研究[D];電子科技大學(xué);2015年

3 曹秋勤;基于支持向量機的蔬菜質(zhì)量安全預(yù)測及溯源模型的研究與應(yīng)用[D];華南理工大學(xué);2014年

4 張文靜;農(nóng)產(chǎn)品物流質(zhì)量安全多維碼組合追溯系統(tǒng)研究[D];北京交通大學(xué);2014年

5 賀燦衛(wèi);電子商務(wù)環(huán)境下特色農(nóng)產(chǎn)品團購模式研究[D];中南林業(yè)科技大學(xué);2013年

6 丁源;農(nóng)產(chǎn)品質(zhì)量安全追溯系統(tǒng)的設(shè)計與實現(xiàn)[D];哈爾濱工業(yè)大學(xué);2012年

7 朱梅;基于多類損失函數(shù)的SVR算法的比較研究[D];華東師范大學(xué);2012年

，

本文編號：2379182