Risk assessment model of grain resources based on AHP and random forest regression algorithm

Authors

CHEN Zhuo, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
DING Li, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
CAO Tian-hong, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
CHENG Yun-hui, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
WEN Li, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
XU Zhou, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
CHEN Mao-long, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
JIAO Ye, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China
LI Hong-hui, School of Food and Bioengineering, Changsha University of Science & Technology, Changsha, Hunan 410114, China

Abstract

Objective: To ensure the consumption safety of grain resources. Methods: According to the relevant national standards, eight chemical pollutants, such As cadmium （Cd）, arsenic （As）, lead （Pb）, chromium （Cr）, aflatoxin （AFs）, fumonisin （FB）, zearalenone （ZEN） and deoxynivalenone （Don）, were identified as the risk assessment indexes of grain quality and safety, and the entropy weight method was adopted. At the same time, taking the data of evaluation index as the input of risk assessment model, four machine learning algorithms, namely, random forest regression （LR）, support vector machine regression （SVM）, BP neural network regression （BP） and K-nearest neighbor regression （KNN）, are selected to construct and compare the models. Results: The prediction correlation coefficient of the model constructed by AHP-RF based on entropy weight was above 0.99. The risk assessment model was used to predict and analyze the grain detection data in August 2019, and the correlation results were consistent with the reality. Conclusion: The risk assessment model based on AHP-RF method can provide targeted reference suggestions for the safety supervision of grain resources.

Publication Date

12-28-2021

First Page

58

Last Page

66

DOI

10.13652/j.issn.1003-5788.2021.12.009

Recommended Citation

Zhuo, CHEN; Li, DING; Tian-hong, CAO; Yun-hui, CHENG; Li, WEN; Zhou, XU; Mao-long, CHEN; Ye, JIAO; and Hong-hui, LI (2021) "Risk assessment model of grain resources based on AHP and random forest regression algorithm," Food and Machinery: Vol. 37: Iss. 12, Article 9.
DOI: 10.13652/j.issn.1003-5788.2021.12.009
Available at: https://www.ifoodmm.cn/journal/vol37/iss12/9

References

[1] GAO Jie, ZHAO Yun-feng, FENG Yun, et al. Dietary exposure of acrylamide from the fifth Chinese Total Diet Study[J]. Food and Chemical Toxicology, 2016, 87: 97-102.
[2] 周小玲, 李娜, 张冬生. 高温高湿处理对小麦中蛋白质性质的影响[J]. 食品与机械, 2021, 37（7）: 7-13.
[3] 张荣彬, 颜景超, 高文明, 等. 粳米与籼米组合对婴幼儿米粉食用品质的影响[J]. 食品与机械, 2021, 37（1）: 193-198.
[4] 吴晓娟, 吴伟. 米糠油安全生产标准方法的研究与实践[J]. 食品与机械, 2021, 37（5）: 89-94.
[5] FRANK T, ANNE N. Contaminants in grain: A major risk for whole grain safety?[J]. Nutrients, 2018, 10（9）: 1 213-1 215.
[6] KUKUSAMUDE C, SRICHAROEN P, LIMCHOOWONG N, et al. Heavy metals and probabilistic risk assessment via rice consumption in Thailand[J]. Food Chemistry, 2020, 334: 127402.
[7] ALLDRICK A. Chemical contamination of cereals[J]. Chemical Contaminants & Residues in Food, 2017: 427-449.
[8] 蔡文华, 胡曙光, 许秀敏. 2012—2014年广东省大米中铅镉的暴露风险评估[J]. 食品与机械, 2015, 31（4）: 47-50.
[9] JOMOVA K, JENISOVA Z, FESZTEROVA M, et al. Arsenic: Toxicity, oxidative stress and human disease[J]. J Appl Toxicol, 2011, 31（2）: 95-107.
[10] FINK Gremmels. Mycotoxins: Their implications for human and animal health[J]. Veterinary Quarterly, 2009, 21（4）: 115-120.
[11] 李雅静, 秦曙, 杨艳梅, 等. 中国谷物真菌毒素污染研究现状[J]. 中国粮油学报, 2020, 35（3）: 186-194.
[12] LI Rui, WANG Xu, ZHOU Ting, et al. Occurrence of four mycotoxins in cereal and oil products in Yangtze Delta region of China and their food safety risks[J]. Food Control, 2014, 35（1）: 117-122.
[13] XIONG Jiang-lin, XIONG Li-li, ZHOU Hua-lin, et al. Occurrence of aflatoxin B₁ in dairy cow feedstuff and aflatoxin M₁ in UHT and pasteurized milk in central China[J]. Food Control, 2018, 92: 386-390.
[14] YU Xi, LI Zhan-ming, ZHAO Meng-zhe, et al. Quantification of aflatoxin B₁ in vegetable oils using low temperature clean-up followed by immuno-magnetic solid phase extraction[J]. Food chemistry, 2019, 275: 390-396.
[15] ZHAO Ya-rong, WANG Qiong-shan, HUANG Jian-xiang, et al. Mycotoxin contamination and presence of mycobiota in rice sold for human consumption in China[J]. Food Control, 2018, 98: 19-23.
[16] BEHROUZ T O, NABI S, MAHMOOD A, et al. The concentration of heavy metals in instant noodle samples from Iran's market: Probabilistic health risk assessment[J]. Environmental Science and Pollution Research, 2018, 25: 30 928-30 937.
[17] CAI Li-mei, XU Zhen-cheng, QI Jian-ying, et al. Assessment of exposure to heavy metals and health risks among residentsnear Tonglushan mine in Hubei, China[J]. Chemosphere, 2015, 127: 127-135.
[18] YANG Xian-li, ZHAO Zhi-yong, TAN Yang-lan, et al. Risk profiling of exposures to multiclass contaminants through cereals and cereal-based products consumption: A case study for the inhabitants in Shanghai, China[J]. Food Control, 2019, 109: 106964.
[19] GENG Zhi-qiang, ZHAO Shan-shan, TAO Guang-can. Early warning modeling and analysis based on analytic hierarchy process integrated extreme learning machine （AHP-ELM）: Application to food safety[J]. Food Control, 2017, 78: 33-42.
[20] YANG Si-bo, GUAN Sheng-wei, TING Tao, et al. Investigation of neural networks for function approximation[J]. Procedia Computer Science, 2013, 17: 586-594.
[21] ALFARO P, MARGELLES A, CHAIREZ I. Pattern recognition for electro-encephalographic signals based on continuous neural networks[J]. Neural Networks, 2016, 79: 88-96.
[22] GENG Zhi-qiang, QIN Lin, HAN Yong-ming, et al. Energy saving and prediction modeling of petrochemical industries: A novel elm based on fahp[J]. Energy, 2017, 122: 350-362.
[23] SRIDEVI K, SIVARAMAN E, MULLAI P. Back propagation neural network mod-elling of biodegradation and fermentative biohydrogen production using distillerywastewater in a hybrid upflow anaerobic sludge blanket reactor[J]. Bioresource Technology, 2014, 165（8）: 233-240.
[24] 张忠志, 薛欢庆, 范广玲. 基于改进卷积神经网络的红枣缺陷识别[J]. 食品与机械, 2021, 37（8）: 158-162.
[25] 潘斌, 韩强, 姚娅川. 基于卷积神经网络的白酒酒花分类研究[J]. 食品与机械, 2021, 37（10）: 30-37.
[26] 杨富华, 杨乐, 徐晓枫, 等. 2017—2019年内蒙古地区地产谷物与蔬菜中铅、镉、总汞和总砷污染状况[J]. 卫生研究, 2021, 50（5）: 846-848.
[27] 周维斌. 谷物中镉快速检测准确性探究[J]. 现代食品, 2021（14）: 223-225.
[28] 陈春坛, 李亚阑, 唐丽, 等. 川东地区谷类重金属污染状况及健康风险评价[J]. 成都大学学报（自然科学版）, 2021, 40（2）: 134-138, 185.
[29] 张翠霞. 菏泽市主要农产品中铅、镉污染状况调查及膳食暴露评估[J]. 中国卫生检验杂志, 2021, 31（12）: 1 519-1 522.
[30] 张小红, 赵青, 路兴乐. 滨州市谷物及蔬菜中铅、镉、总砷暴露量及风险评估[J]. 中国卫生检验杂志, 2021, 31（7）: 877-879, 883.
[31] 李秋月, 许皓, 方惠千, 等. 桐乡市2015—2018年食品中重金属污染物的监测分析[J]. 中国卫生检验杂志, 2021, 31（7）: 892-895.
[32] 吴艾琳, 罗书全, 赵怡楠, 等. 基于污染指数法对重庆市市售食品中重金属污染调查及评价[J]. 中国食品卫生杂志, 2021, 33（2）: 175-180.
[33] 杨剑洲, 王振亮, 高健翁, 等. 海南省集约化种植园中谷物、蔬菜和水果中重金属累积程度及健康风险[J]. 环境科学, 2021, 42（10）: 4 916-4 924.
[34] 吴丽珠, 高红梅, 马英. 上海市青浦区主要市售谷物及其制品的铅、镉、汞污染及健康风险评估[J]. 上海预防医学, 2019, 31（6）: 451-456.
[35] 董峰光, 王朝霞, 宫春波, 等. 烟台市市售谷物及其制品重金属污染状况及暴露风险评估[J]. 职业与健康, 2017, 33（6）: 756-759.
[36] 黄楚珊, 胡国成, 陈棉彪, 等. 矿区家庭谷物和豆类重金属含量特征及风险评价[J]. 中国环境科学, 2017, 37（3）: 1 171-1 178.
[37] 梁琼, 李拥军. 甘肃省市售谷物制品中铅和镉污染调查及健康风险预警分析[J]. 卫生研究, 2016, 45（5）: 844-846.
[38] 陆文, 刘晶晶, 张亮. 2012—2014年铁岭市谷物及其制品中重金属监测结果分析[J]. 现代预防医学, 2016, 43（15）: 2 729-2 731, 2 751.
[39] 张荷香, 陈江, 章荣华, 等. 2009—2013年浙江省谷物及制品中铅污染状况分析[J]. 卫生研究, 2016, 45（4）: 668-669, 676.
[40] 钞凤. 2013年河南省食品中铅、镉污染物监测与分析[D]. 郑州: 郑州大学, 2016: 9-25.
[41] 朱庆麒. 快速检测粮食谷物制品中镉的方法探讨[D]. 苏州: 苏州大学, 2016: 13-27.
[42] 涂鸿, 秦礼康, 韦柳燕, 等. 不同设备和工艺加工薏仁谷精米和碎米重金属污染评价[J]. 中国酿造, 2016, 35（3）: 120-123.
[43] 王彩霞, 郭蓉, 程国霞, 等. 陕西省谷物中重金属污染状况及健康风险评估[J]. 卫生研究, 2016, 45（1）: 35-38, 44.
[44] 张永发, 邝继云, 谢茵, 等. 海南省农产品重金属污染评价与特征分析[J]. 中国土壤与肥料, 2018（5）: 169-176.
[45] 刘辉, 刘恩岐, 巫永华, 等. 市售谷物中Pb和Cd含量测定与风险评估[J]. 粮油食品科技, 2014, 22（6）: 74-77.
[46] 龚地萍, 王军. 重庆市万州区居民膳食结构与重金属摄入水平研究[J]. 中国初级卫生保健, 2020, 34（12）: 14-15, 25.
[47] 范楷, 祭芳, 徐剑宏, 等. 长三角地区市场常见农产品中40种真菌毒素的污染状况和特征分析[J]. 中国农业科学, 2021, 54（13）: 2 870-2 884.
[48] 唐占敏. 长三角地区谷物中典型真菌毒素识别及污染研究[D]. 上海: 上海海洋大学, 2020: 15-35.
[49] 王燕, 董燕婕, 岳晖, 等. 山东省玉米真菌毒素污染状况调查及分析[J]. 粮油食品科技, 2016, 24（3）: 69-73.
[50] 韩小敏, 李凤琴, 徐文静, 等. 我国五省（市）小麦粉中重要镰刀菌毒素的污染调查[J]. 中国猪业, 2017, 12（6）: 33-39, 45.
[51] 董峰光, 阎西革, 宫春波, 等. 2012—2019年烟台市食品中玉米赤霉烯酮污染状况及暴露评估[J]. 食品安全质量检测学报, 2021, 12（1）: 376-381.
[52] 诸寅, 毛伟峰, 季申, 等. 上海市售薏苡仁中玉米赤霉烯酮的污染状况及暴露评估[J]. 卫生研究, 2020, 49（5）: 840-843, 872.
[53] 李丹迪, 赵丽, 季静, 等. 济南部分地区谷物制品中脱氧雪腐镰刀菌烯醇及玉米赤霉烯酮的污染状况[J]. 食品安全质量检测学报, 2019, 10（23）: 8 081-8 086.
[54] 张梦妍, 郭爱静, 马辉, 等. 河北省市售玉米面中玉米赤霉烯酮和伏马菌毒素B₁、B₂污染状况调查[J]. 医学动物防制, 2018, 34（5）: 490-491.
[55] 郭萍, 薛生辉, 谢恺, 等. 福建省市售食品玉米赤霉烯酮污染状况与暴露评估[J]. 海峡预防医学杂志, 2020, 26（4）: 80-82.
[56] 许嘉, 林楠, 王志, 等. 北京市市售谷物及制品中真菌毒素污染状况的调查[J]. 中国食物与营养, 2019, 25（3）: 28-30.
[57] 赵巍, 王兰惠, 甄玉国, 等. 2020年国内玉米青贮霉菌毒素普查报告[J]. 中国乳业, 2021（8）: 56-59.
[58] 王苏楠, 胡寅瑞, 梁栗源. 2018—2019年洛阳市玉米制品中玉米赤霉烯酮监测结果分析[J]. 应用预防医学, 2021, 27（1）: 42-43.
[59] 王丽英, 任贝贝, 刘印平, 等. 河北地区面制品中脱氧雪腐镰刀菌烯醇及其衍生物和玉米赤霉烯酮污染水平调查与分析[J]. 食品安全质量检测学报, 2020, 11（12）: 4 023-4 028.
[60] 潘红艳. 玉米赤霉烯酮在稻谷中的污染调查及毒理实验研究[D]. 武汉: 武汉工业学院, 2012: 15-27.
[61] 赵一鹏, 惠秋芳, 张系忠, 等. 2016—2017年陕西省部分食品中玉米赤霉烯酮监测分析[J]. 医学动物防制, 2019, 35（3）: 248-251.
[62] 蒋玉寒. 我国三北和西南地区玉米霉菌毒素调查报告[D]. 南京: 南京农业大学, 2015: 13-40.
[63] LI Qiang, LIU Wen, SUN Ai-lan, et al. Study on the risk grading evaluation of processed food[J]. Food and Fermentation Industries, 2015, 41（9）: 220-224.