基于近红外光谱技术和LSPTSVM模型的镉污染贻贝检测研究

曾绍庚; 刘瑶; 刘忠艳

doi:10.13205/j.hjgc.202401030

基于近红外光谱技术和LSPTSVM模型的镉污染贻贝检测研究

doi: 10.13205/j.hjgc.202401030

1. 岭南师范学院计算机与智能教育学院, 广东湛江 524048;
2. 岭南师范学院电子与电气工程学院, 广东湛江 524048

基金项目:

国家自然科学基金青年科学基金项目“贝类重金属污染的高光谱无损检测机理、模型及综合性能评估研究”(62005109)；广东省自然科学基金面上项目“贝类毒素的高光谱快速检测机理及方法研究”(2020A515011368)；广东省教育厅普通高校新冠肺炎疫情防控专项研究项目“基于公共卫生服务的社区疫情防控系统”(2020KZDZX1143)；广东省科技创新战略专项资金(大学生科技创新培育)立项项目(pdjh2024a240)

详细信息

通讯作者:
曾绍庚(1981-),男,讲师,主要研究方向为人工智能、物联网应用。foxzenith@qq.com

计量
- 文章访问数: 76
- HTML全文浏览量: 6
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2023-02-07
- 网络出版日期: 2024-04-29

DETECTION OF MUSSELS CONTAMINATED WITH CADMIUM BASED ON NEAR-INFRARED SPECTROSCOPY AND LSPTSVM

1. School of Computer and Intelligence Education, Lingnan Normal University, Zhanjiang 524048, China;
2. School of Electronic and Electrical Engineering, Lingnan Normal University, Zhanjiang 524048, China

摘要

摘要: 贝类重金属污染已成为亟待解决的海洋食品安全问题,镉是重要的污染源之一。食用被重金属镉污染的翡翠贻贝会严重危害身体健康。研究了基于近红外反射光谱的镉污染贻贝无损、快速检测方法。通过采集正常贻贝和镉污染贻贝的950~1700 nm光谱数据,构建基于最小二乘投影孪生支持向量机(least squares projection twin support vector machine, LSPTSVM)检测模型,优化模型参数和正交投影轴数量获得最佳检测性能。提出的LSPTSVM模型检测镉污染贻贝准确率达到99.50%,优于其他孪生支持向量机模型。LSPTSVM模型适用于小样本数据集。针对难以获得大量镉污染训练样本情况,LSPTSVM模型较其他模型具有更好的稳健性。结果表明:近红外光谱结合LSPTSVM模型可实现镉污染贻贝检测,为贝类的品质评价和安全检测提供一种新的方法。
- 近红外光谱 /
- 镉污染 /
- 最小二乘投影孪生支持向量机 /
- 贻贝 /
- 重金属检测
Abstract: Heavy metal contamination of shellfish has become an urgent problem of marine food safety, among which cadmium is one of the important contamination sources. The consumption of mussels contaminated with heavy metal cadmium is a serious health hazard. A non-destructive and rapid detection method for mussels contaminated with cadmium based on near-infrared reflectance spectroscopy was researched in this study. By collecting spectral data of normal and cadmium-contaminated mussels in the range of 950~1700 nm, a detection model based on the least squares projection twin support vector machine(LSPTSVM) was constructed. The parameters of the model and the number of orthogonal projection axes were optimized to obtain the best detection performance. The accuracy of the proposed LSPTSVM model achieved 99.50% for detecting cadmium-contaminated mussels, which was superior to other twin support vector machine models. The LSPTSVM model was suitable for the datasets with small samples. In the case that it was difficult to obtain many cadmium-contaminated training samples, the LSPTSVM model had better robustness than other models. The results showed that near-infrared spectroscopy combined with the LSPTSVM model can realize the detection of cadmium-contaminated mussels, which provides a new method for quality evaluation and safety detection of shellfish.
- near-infrared spectroscopy /
- cadmium contamination /
- least squares projection twin support vector machine /
- mussels /
- heavy metal detection

HTML全文

参考文献(41)

[1]	农业部渔业局编制.中国渔业统计年鉴[M].北京:中国农业出版社,2022.
[2]	翟毓秀,郭萌萌,江艳华,等.贝类产品质量安全风险分析[J].中国渔业质量与标准,2020,10(4):1-25.
[3]	SATARUG S,BAKER J R,REILLY P E B,et al.Evidence for a synergistic interaction between cadmium and endotoxin toxicity and for nitric oxide and cadmium displacement of metals in the kidney[J].Nitric Oxide,2000,4(4):431-440.
[4]	王倩茹,安文佳,蒋宁,等.市售水产品中镉污染状况评价及健康风险评估[J].中国食品卫生杂志,2020,32(2):201-206.
[5]	梁辉,刘志婷,周少君,等.广东省居民贝类水产品中镉暴露的风险评估[J].中国食品卫生杂志,2017,29(4):492-495.
[6]	林功师.厦门市售贝类中重金属镉含量分析与评价[J].中国渔业质量与标准,2022,12(2):54-59.
[7]	黄国清,陈国薇.青岛市场上常见贝类Cd污染情况调查研究[J].青岛农业大学学报:自然科学版,2014,31(1):41-44.
[8]	杜睿贤,贾雪峰,林艺佳,等.海洋贝类重金属富集特征及影响因素研究进展[J].中国农学通报,2019,35(11):155-159.
[9]	陈海刚,林钦,蔡文贵,等.3种常见海洋贝类对重金属HgPb和Cd的积累与释放特征比较[J].农业环境科学学报,2008,27(3):1163-1167.
[10]	ALELUIA A C M,DE SANTANA F A,BRANDAO G C,et al.Sequential determination of cadmium and lead in organic pharmaceutical formulations using high-resolution continuum source graphite furnace atomic absorption spectrometry[J].Microchemical Journal,2017,130:157-161.
[11]	方玲,马海霞,李来好,等.贝类中重金属镉的研究进展[J].核农学报,2019,33(7):1408-1414.
[12]	ALEXANDER D,ELLERBY R,HERNANDEZ A,et al.Investigation of simultaneous adsorption properties of Cd,Cu,Pb and Zn by pristine rice husks using ICP-AES and LA-ICP-MS analysis[J].Microchemical Journal,2017,135:129-139.
[13]	赵艳芳,尚德荣,宁劲松,等.体积排阻高效液相色谱-电感耦合等离子体质谱法测定海产贝类中镉的形态[J].分析化学,2012,40(5):681-686.
[14]	刘爽,柴春祥.近红外光谱技术在水产品检测中的应用进展[J].食品安全质量检测学报,2021,12(21):8590-8596.
[15]	占可,陈季旺,徐言,等.树脂吸附结合近红外光谱同时检测小龙虾中铅,镉模型的建立[J].食品安全质量检测学报,2022,13(15):4858-486.
[16]	李玉环.贝类体内重金属镉的富集和消除规律及食用安全性的研究[D].青岛:中国海洋大学,2005.
[17]	林冬秀,刘科,陈孝敬.基于近红外光谱的重金属污染泥蚶的快速检测[J].中国食品学报,2015,15(4):189-195.
[18]	LIU Y,XU L,WANG R,et al.Study on the detection of heavy metal lead (Pb) in mussels based on near-infrared spectroscopy technology and a REELM classifier[J].Microchemical Journal,2022,178:107394.
[19]	CHEN X,LIU K,CAI J,et al.Identification of heavy metal-contaminated Tegillarca granosa using infrared spectroscopy[J].Analytical Methods,2015,7(5):2172-2181.
[20]	熊建芳,乔付,刘忠艳,等.基于高光谱图像的贝类重金属污染快速无损检测方法研究[J].环境工程,2022,40(10):141-149.
[21]	DENG N,TIAN Y,ZHANG C.Support vector machines:optimization based theory,algorithms,and extensions[M].CRC Press,2012.
[22]	JAYADEVA,KHEMCHANDANI R,CHANDRA S.Twin support vector machines for pattern classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5):905-910.
[23]	CHEN X,JIAN Y,YE Q,et al.Recursive projection twin support vector machine via within-class variance minimization[J].Pattern Recognition,2011,44(10):2643-2655.
[24]	KUMAR M A,GOPAL M.Least squares twin support vector machines for pattern classification[J].Expert Systems with Applications,2009,36(4):7535-7543.
[25]	SHAO Y H,DENG N Y,YANG Z M.Least squares recursive projection twin support vector machine for classification[J].Pattern Recognition,2012,45(6):2299-2307.
[26]	马藏允,刘海,姚波,等.几种大型底栖生物对Cd,Zn,Cu的积累实验研究[J].中国环境科学,1997,17(2):56-60.
[27]	马胜伟,林钦,陈海刚,等.混合重金属对翡翠贻贝的积累与排放规律研究[J].南方水产,2008,4(6):78-82.
[28]	彭玲,曾江宁,陈全震,等.镉对厚壳贻贝急性毒性及对其鳃抗氧化酶活性的影响[J].环境科学与技术,2015,38(2):13-18 ,24.
[29]	王晓玲.紫贻贝体内重金属镉的富集代谢及脱除方法研究[D].舟山:浙江海洋学院,2015.
[30]	张少娜,孙耀,宋云利,于志刚.紫贻贝(Mytilus edulis)对4种重金属的生物富集动力学特性研究[J].海洋与湖沼,2004,35(5):438-445.
[31]	刘宏明,刘玉娟,仲志成,等.一种油田原油含水率的近红外光谱检测与分析方法[J].光谱学与光谱分析,2021,41(2):505-510.
[32]	中华人民共和国农业部.NY 5073—2006,无公害食品水产品中有毒有害物质限量[S].
[33]	张中卫,温志渝,曾甜玲,等.微型近红外光纤光谱仪用于奶粉中蛋白质脂肪的定量检测研究[J].光谱学与光谱分析,2013,33(7):1796-1800.
[34]	李瑞,李博,王学文,等.基于XGBoost与可见-近红外光谱的煤矸识别方法[J].光谱学与光谱分析,2022,42(9):2947-2955.
[35]	周燕萍,业巧林.基于L₁-范数距离的最小二乘对支持向量机[J].计算机科学,2018,45(4):100-105 ,130.
[36]	姜涛,王长江,陈厚合,等.基于正则化投影孪生支持向量机的电力系统暂态稳定评估[J].电力系统自动化,2019,43(1):141-148.
[37]	王动民,纪俊敏,高洪智.多元散射校正预处理波段对近红外光谱定标模型的影响[J].光谱学与光谱分析,2014,34(9):2387-2390.
[38]	HSU C W,LIN C J.A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
[39]	DING S,HUA X.Recursive least squares projection twin support vector machines for nonlinear classification[J].Neurocomputing,2014,130:3-9.
[40]	LI C N,HUANG Y F,WU H J,et al.Multiple recursive projection twin support vector machine for multi-class classification[J].International Journal of Machine Learning and Cybernetics,2016,7(5):729-740.
[41]	SHAO Y H,WANG Z,CHEN W J,et al.A regularization for the projection twin support vector machine[J].Knowledge-Based Systems,2013,37:203-210.