基于监督抽检数据的肉类食品安全风险分析及预测
|
摘要
为通过数据挖掘预测食品安全风险、隐患和趋势,进行预警和快速反应,基于2015—2017年国家肉类食品监督抽检的18 378批次样品数据,分析我国肉与肉制品主要安全现状与风险种类,并基于检测指标及属性运用BP(back propagation)神经网络方法构建以抽样省份、产品类型、产地、生产日期、年份、是否大型企业6大属性指标为输入层、包含2个隐藏层、以是否合格为输出层的肉类食品安全神经网络预测模型。结果表明:经数据准备、模型生成、数据训练和验证及参数优化,得到的3层BP神经网络预警模型总体百分比矫正为96.2%;对于合格样本,判定正确的概率为96.5%,错判概率为3.5%,预测模型具有较好的参考和应用价值。基于BP神经网络的食品安全预警方法能够对输入样本进行有效预测,为食品安全风险研判和风险预警提供技术支撑。
In order to predict food safety risks, hazards and trends through data mining for the purpose of early warning and rapid response, we collected 18 378 batches of supervision and sampling data on meat products in the period from 2015 to2017 from the China Food and Drug Administration to analyze the current status of meat and meat product safety and the types of risks, and we further constructed a meat safety prediction model by back propagation(BP) neural network with two hidden layers based on the indices and attributes tested using sampling province, product type, geographical origin, date of production, year, and whether the manufacture is a large-size company as input variables and using whether products are qualified as output layer. The overall fitting accuracy of the three-layer neural network prediction model obtained after data preparation, model generation, data training and validation, and parameter optimization was 96.2%. For qualified samples,the probability of correct judgment was 96.5% and the probability of misjudgment was 3.5%. The model may serve as a reference and have application potential. The results show that the food safety early warning method based on BP neural network can effectively predict input samples and therefore can provide technical support for food safety risk analysis and early warning.
In order to predict food safety risks, hazards and trends through data mining for the purpose of early warning and rapid response, we collected 18 378 batches of supervision and sampling data on meat products in the period from 2015 to2017 from the China Food and Drug Administration to analyze the current status of meat and meat product safety and the types of risks, and we further constructed a meat safety prediction model by back propagation(BP) neural network with two hidden layers based on the indices and attributes tested using sampling province, product type, geographical origin, date of production, year, and whether the manufacture is a large-size company as input variables and using whether products are qualified as output layer. The overall fitting accuracy of the three-layer neural network prediction model obtained after data preparation, model generation, data training and validation, and parameter optimization was 96.2%. For qualified samples,the probability of correct judgment was 96.5% and the probability of misjudgment was 3.5%. The model may serve as a reference and have application potential. The results show that the food safety early warning method based on BP neural network can effectively predict input samples and therefore can provide technical support for food safety risk analysis and early warning.
引文
[1]国家市场监督管理总局.食品抽检公告[EB/OL].(2017-12-31)[2018-11-05]. http://www.sda.gov.cn/WS01/CL1698/.
[2]付文丽,陶婉亭,李宁,等.借鉴国际经验完善我国食品安全风险监测制度的探讨[J].中国食品卫生杂志,2015, 27(3):271-276.DOI:10.13590/j.cjfh.2015.03.011.
[3]张星联,张慧媛,唐晓纯.国内外农产品质量安全预警系统现状研究[J].农产品质量与安全,2012(3):19-21. DOI:10.3969/j.issn.1674-8255.2012.03.007.
[4]顾小林,张大为,张可,等.基于关联规则挖掘的食品安全信息预警模型[J].软科学,2011,25(11):136-141. DOI:10.3969/j.issn. 1001-8409.2011.11.030.
[5]朱佳,张萍,高志国.大数据挖掘技术在进出口食品农产品安全风险预警中的应用研究[J].山东农业大学学报(社会科学版),2014,16(3):99-102; 132.
[6] HUANG Y, KANGAS L J, RASCO B A. Applications of artificial neural networks(ANNs)in food science[J]. Critical Reviews in Food Science and Nutrition, 2007, 47(2):113-126.DOI:10.1080/10408390600626453.
[7] CARRILLO-CASTRILLO J A, MARTIN J G, DE LA VEGA R G, et al.Neural network application for risk factors estimation in manufacturing accidents[M]. New York:Springer, 2014:277-283. DOI:10.1007/978-3-319-04705-8-32.
[8] WU Y, SCHUSTER M, CHEN Z, et al. Google's neural machine translation system:bridging the gap between human and machine translation[J]. 2016.
[9]徐学良.人工神经网络的发展及现状[J].微电子学,2017, 47(2):239-242.
[10] ZHANG K, CHAI Y, YANG S X, et al. Pre-warning analysis and application in traceability systems for food production supply chains[J]. Expert Systems with Applications, 2011, 38(3):2500-2507.DOI:10.1016/j.eswa.2010.08.039.
[11] LIU Tongjuan, HU Anqi. Model of combined transport of perishable foodstuffs and safety inspection based on data mining[J]. Food and Nutrition Sciences, 2017, 8(7):760-777. DOI:10.4236/fns.2017.87054.
[12]章德宾,徐家鹏,许建军,等.基于监测数据和BP神经网络的食品安全预警模型[J].农业工程学报,2010(1):221-226. DOI:10.3969/j.issn. 1002-6819.2010.01.039.
[13] MITTAL G S, ZHANG J. Prediction of freezing time for food products using a neural network[J]. Food Research International, 2000,33(7):557-562. DOI:10.1016/S0963-9969(00)00091-0.
[14] GONI S M, ODDONE S, SEGURA J A, et al. Prediction of foods freezing and thawing times:artificial neural networks and genetic algorithm approach[J]. Journal of Food Engineering, 2008, 84(1):164-178. DOI:10.1016/j.jfoodeng.2007.05.006.
[15]黄宇锋,刘冬虹,聂炎炎,等.肉和肉制品中肠杆菌科细菌的检测和计数[J].现代食品科技,2013, 29(2):409-412; 428.
[16]张哲奇,臧明伍,张凯华,等.国内外肉品品质变化机制机理研究进展[J].肉类研究,2017. 31(2):57-63. DOI:10.7506/rlyj1001-8123-201702011.
[17]李贺楠,时宏霞,李莹莹,等.传统腌腊肉制品酸价和过氧化值指标适用性[J].肉类研究,2014, 28(1):17-21. DOI:10.3969/j.issn.1001-8123.2014.01.005.
[18]张曼,张璟,普蓂喆,等.我国农业产地环境污染成因及治理对策:以镉大米为例[J].林业经济,2014(6):20-29.
[19] HECHT-NIELSEN R. Neural computers[M]. New York:Springer,1989:445-453. DOI:10.1007/978-3-642-83740-1_45.
[20]卢日刚,陈薇,苏浩.基于大数据的食品药品检测数据管理系统构建设想[J].中国药事,2016, 30(7):661-665. DOI:10.16153/j.1002-7777.2016.07.005.
[21]王雅洁,杨冰,罗艳,等.大数据挖掘在食品安全风险预警领域的应用[J].安徽农业科学,2015, 43(8):332-334. DOI:10.3969/j.issn.0517-6611.2015.08.130.
[22] MCMEEKIN T A, BARANYI J, BOWMAN J, et al. Information systems in food safety management[J]. International Journal of Food Microbiology, 2006, 112(3):181-194. DOI:10.1016/j.ijfoodmicro.2006.04.048.
[23]薛薇,陈欢歌. SPSS Modeler数据挖掘方法及应用[M].北京:电子工业出版社,2014:181-204.
[24]熊平.数据挖掘算法与Clementine实践[M].北京:清华大学出版社,2011:196-228.
[25]高秀芬,杨大进.国内外食品安全风险预警比较研究[J].中国卫生工程学,2014(3):254-256.
[26] MOHAMMADFAM I, SOLTANZADEH A, MOGHIMBEIGI A, et al.Analysis and modeling of threatening factors of workforce's health in large-scale workplaces:comparison of four-fitting methods to select optimum technique[J]. Electronic Physician, 2016, 8(2):1918-1926.DOI:10.19082/1918.
[27] GARCIA-GONZALEZ D L, MANNINA L, D'IMPERIO M, et al.Using 1H and 13C NMR techniques and artificial neural networks to detect the adulteration of olive oil with hazelnut oil[J]. European Food Research and Technology, 2004, 219(5):545-548. DOI:10.1007/s00217-004-0996-0.
[28] DEVI B R, RAO K N, SETTY S P, et al. Disaster prediction system using IBM SPSS data mining tool[J]. International Journal of Engineering Trends and Technology, 2013, 4(8):3352-3357.
[29] MITTAL G S. Handbook of farm, dairy and food machinery engineering:artificial neural network(ANN)based process modeling[M]. 2nd. Salt Lake City:Academic Press, 2013:467-473.DOI:10.1016/B978-0-12-385881-8.00018-5.
[30]蔡强,王君君,李海生,等.基于神经网络的食品安全评价模型构建研究[J].食品科学技术学报,2014, 32(1):69-77. DOI:10.3969/j.issn.2095-6002.2014.01.013.
[2]付文丽,陶婉亭,李宁,等.借鉴国际经验完善我国食品安全风险监测制度的探讨[J].中国食品卫生杂志,2015, 27(3):271-276.DOI:10.13590/j.cjfh.2015.03.011.
[3]张星联,张慧媛,唐晓纯.国内外农产品质量安全预警系统现状研究[J].农产品质量与安全,2012(3):19-21. DOI:10.3969/j.issn.1674-8255.2012.03.007.
[4]顾小林,张大为,张可,等.基于关联规则挖掘的食品安全信息预警模型[J].软科学,2011,25(11):136-141. DOI:10.3969/j.issn. 1001-8409.2011.11.030.
[5]朱佳,张萍,高志国.大数据挖掘技术在进出口食品农产品安全风险预警中的应用研究[J].山东农业大学学报(社会科学版),2014,16(3):99-102; 132.
[6] HUANG Y, KANGAS L J, RASCO B A. Applications of artificial neural networks(ANNs)in food science[J]. Critical Reviews in Food Science and Nutrition, 2007, 47(2):113-126.DOI:10.1080/10408390600626453.
[7] CARRILLO-CASTRILLO J A, MARTIN J G, DE LA VEGA R G, et al.Neural network application for risk factors estimation in manufacturing accidents[M]. New York:Springer, 2014:277-283. DOI:10.1007/978-3-319-04705-8-32.
[8] WU Y, SCHUSTER M, CHEN Z, et al. Google's neural machine translation system:bridging the gap between human and machine translation[J]. 2016.
[9]徐学良.人工神经网络的发展及现状[J].微电子学,2017, 47(2):239-242.
[10] ZHANG K, CHAI Y, YANG S X, et al. Pre-warning analysis and application in traceability systems for food production supply chains[J]. Expert Systems with Applications, 2011, 38(3):2500-2507.DOI:10.1016/j.eswa.2010.08.039.
[11] LIU Tongjuan, HU Anqi. Model of combined transport of perishable foodstuffs and safety inspection based on data mining[J]. Food and Nutrition Sciences, 2017, 8(7):760-777. DOI:10.4236/fns.2017.87054.
[12]章德宾,徐家鹏,许建军,等.基于监测数据和BP神经网络的食品安全预警模型[J].农业工程学报,2010(1):221-226. DOI:10.3969/j.issn. 1002-6819.2010.01.039.
[13] MITTAL G S, ZHANG J. Prediction of freezing time for food products using a neural network[J]. Food Research International, 2000,33(7):557-562. DOI:10.1016/S0963-9969(00)00091-0.
[14] GONI S M, ODDONE S, SEGURA J A, et al. Prediction of foods freezing and thawing times:artificial neural networks and genetic algorithm approach[J]. Journal of Food Engineering, 2008, 84(1):164-178. DOI:10.1016/j.jfoodeng.2007.05.006.
[15]黄宇锋,刘冬虹,聂炎炎,等.肉和肉制品中肠杆菌科细菌的检测和计数[J].现代食品科技,2013, 29(2):409-412; 428.
[16]张哲奇,臧明伍,张凯华,等.国内外肉品品质变化机制机理研究进展[J].肉类研究,2017. 31(2):57-63. DOI:10.7506/rlyj1001-8123-201702011.
[17]李贺楠,时宏霞,李莹莹,等.传统腌腊肉制品酸价和过氧化值指标适用性[J].肉类研究,2014, 28(1):17-21. DOI:10.3969/j.issn.1001-8123.2014.01.005.
[18]张曼,张璟,普蓂喆,等.我国农业产地环境污染成因及治理对策:以镉大米为例[J].林业经济,2014(6):20-29.
[19] HECHT-NIELSEN R. Neural computers[M]. New York:Springer,1989:445-453. DOI:10.1007/978-3-642-83740-1_45.
[20]卢日刚,陈薇,苏浩.基于大数据的食品药品检测数据管理系统构建设想[J].中国药事,2016, 30(7):661-665. DOI:10.16153/j.1002-7777.2016.07.005.
[21]王雅洁,杨冰,罗艳,等.大数据挖掘在食品安全风险预警领域的应用[J].安徽农业科学,2015, 43(8):332-334. DOI:10.3969/j.issn.0517-6611.2015.08.130.
[22] MCMEEKIN T A, BARANYI J, BOWMAN J, et al. Information systems in food safety management[J]. International Journal of Food Microbiology, 2006, 112(3):181-194. DOI:10.1016/j.ijfoodmicro.2006.04.048.
[23]薛薇,陈欢歌. SPSS Modeler数据挖掘方法及应用[M].北京:电子工业出版社,2014:181-204.
[24]熊平.数据挖掘算法与Clementine实践[M].北京:清华大学出版社,2011:196-228.
[25]高秀芬,杨大进.国内外食品安全风险预警比较研究[J].中国卫生工程学,2014(3):254-256.
[26] MOHAMMADFAM I, SOLTANZADEH A, MOGHIMBEIGI A, et al.Analysis and modeling of threatening factors of workforce's health in large-scale workplaces:comparison of four-fitting methods to select optimum technique[J]. Electronic Physician, 2016, 8(2):1918-1926.DOI:10.19082/1918.
[27] GARCIA-GONZALEZ D L, MANNINA L, D'IMPERIO M, et al.Using 1H and 13C NMR techniques and artificial neural networks to detect the adulteration of olive oil with hazelnut oil[J]. European Food Research and Technology, 2004, 219(5):545-548. DOI:10.1007/s00217-004-0996-0.
[28] DEVI B R, RAO K N, SETTY S P, et al. Disaster prediction system using IBM SPSS data mining tool[J]. International Journal of Engineering Trends and Technology, 2013, 4(8):3352-3357.
[29] MITTAL G S. Handbook of farm, dairy and food machinery engineering:artificial neural network(ANN)based process modeling[M]. 2nd. Salt Lake City:Academic Press, 2013:467-473.DOI:10.1016/B978-0-12-385881-8.00018-5.
[30]蔡强,王君君,李海生,等.基于神经网络的食品安全评价模型构建研究[J].食品科学技术学报,2014, 32(1):69-77. DOI:10.3969/j.issn.2095-6002.2014.01.013.