定量包装商品净含量精度保证系统及质量控制
|
摘要
随着定量包装商品在市场的不断涌现,在计量监管领域面临着许多需要研究解决的新课题,其中如何保证定量包装商品净含量的精度、有效地对其质量进行控制等关键理论与技术问题,基本处于空白状态,是亟待解决的热点问题。
本文根据作者近年来所承担的科研课题的研究成果,以皇上皇肉食制品厂生产的广式腊肠为主要研究对象,深入研究了定量包装商品净含量的控制理论;探讨了提取和分析定量包装商品净含量多种影响因素的方法;应用主成分分析法建立了净含量精度保证与质量控制模型;应用控制图与支持向量机对净含量进行有效地预测与控制。本文的主要研究内容、结论及创造性工作总结如下:
着重分析现有的定量包装商品计量监督的法规与准则,以及目前企业为保证定量包装商品净含量精度所采取的评价标准与技术规范,按照由政府执行监管和兼顾消费者与生产企业两者的利益的原则,对定量包装商品净含量计量监管的过程进行剖析。对明确净含量的定义、确定合理的单件负偏差要求、确定合理的合格质量水平AQL、确定合适的监督抽样方案、确定检验批、在检验批中进行正确抽样、准确地检验样本、正确判断检验批的合格与否等方面存在的问题在理论上提出了计量监管的依据。另外深入探讨了定量包装商品净含量的控制目标值,建立了确定定量包装商品净含量目标值的数学模型。
对不同形态商品净含量影响因素进行基本考虑,着重分析了流体传输、物料混合以及物料的去湿与干燥过程中如何进行质量控制,在此基础上,以皇上皇广式腊肠为例,经过实地考察与实验,对其净含量的动态过程控制对象进行了剖析研究,从中发现了制作过程中某些控制不当之处,也得出了许多有用的结论:(1)由于目前厂家尚未普及自动化生产,灌肠生产线与包装生产线仍以劳动力密集型的模式进行加工,目前腊肠灌装线的动态控制能力十分不足:(2)实验数据表明,腊肠流失的重量与肥肉所占比重成线性关系y=54.9907-0.37157x。肥肉所占比例越大,则腊肠重量的流失越小;(3)不同肉馅搅拌时间所得肉馅的均匀度存在一定得差别,从单根腊肠得重量分析,差别并不明显,但将若干条腊肠进行包装,此差异将会被扩大,影响最终包装净含量得精度;(4)人工灌制的腊肠重量的均匀性明显比机器灌制的低;(5)机器灌装的腊肠重量可能受交流电压的影响,因此采取稳压措施将会进一步提高腊肠重量的均匀性,提高腊肠包装的净含量精度;(6)风干过程中,肠体失重主要集中在前四小时,而干燥40小时后失重率变化不大,基本上在2%上下浮动。在经历了初期比较快速的干燥阶段之后出现了一个长时间的比较缓慢的干燥过程,一直持续到腊肠的成品阶段。
广式腊肠的制作需经过原料肉的处理、绞肉拌馅、灌制、干燥、包装等多道工序,每道工序中存在的主客观影响因素错综复杂,腊肠最终成品的净含量正是多变量作用的综合反映。使用多元回归建立和求解多因素模型的过程中发现模型存在着严重的多重共线性问题。然后基于影响腊肠定量包装净含量因素数量多、且具有错综复杂的相关性等特点,利用主成分分析法进行多维特征空间建模,有效地筛选出影响腊肠包装净含量的主要因素,通过模型的求解,得出一个有用的结论,在每根腊肠灌肠后重量均衡的前提下,肉馅肥瘦比例决定了腊肠风干后的重量,根据肉馅配比与腊肠重量的关系,通过改变灌肠长度实现了对腊肠包装净含量精度的改进,验证了该净含量保证系统的应用价值。
使用混合核函数的支持向量机分类技术应用于控制图在线检测和分析系统,利用遗传算法对混合核函数支持向量机的参数进行优化。研究证明,混合核函数的多类分类支持向量机用于控制图模式识别和异常模式下的参数估计是可行的,可以有效地提高系统的识别精度,特别是降低了控制图模式识别中Ⅰ型错判。控制图在线检测技术有效地改进了广式腊肠灌肠线的实时控制。
Along with the coming forth of quantificational packaging merchandise in market, there are many issues need to be solved in the area of quality management. Some problems even haven't been touched, such as how to assure the suttle precision and how to control the quality, which are the hotspots need to be paid attention to imperatively.
In recent years, the author participate several national projects and has some new discoveries in this field. This paper mainly conducts systematic and deep analysis and research on suttle precision assuring system of sausage quantificational packaging and quality control, explores the methods of distilling and analyzing the factors that influence the accuracy of suttle, tries to establish a model to forecast and control the suttle effectively, applying PCA and SVM. The paper brings forth the main results and originality as follows:
Mainly analyze the rule of law of measuring and managing quantificational packaging merchandises, according to the principle that manage by government and pay attention to both consumer and producer. Bring forward some measuring basis to several aspects of problems, such as comprehending the concept of suttle, make the negative warp and AQL reasonly, make logical scheme of sampling, etc. Besides, deeply discuss the target value of controlling, establish a mathematical model to make reasonable target value of controlling.
Consider the influencing factors of the suttle which is in different forms. Give some suggestions on how to control quality in the course of liquid transfers, materiel tmix and dryness. On the basis of it, a lot of useful results are given by investigating the product line of sausage: roboticized production hasn't been gained ground, the product line of sausage is also in the mode of dense working, it comes with the weak capability of dynamic controlling. experimental data showed that the relation between the weight of sausage lost and proportion of fat is linear. In the dryness course, the weight of sausage loses mainly in the front four hours, after that, it will experience a slow dryness course to become product.
Sausage machining contains several working procedures: material disposal, mix round, material filling, dryness and packaging. The influencing factors in each working procedure are anfractuous, and the suttle of sausage is the result of the action of multiplex factors. Model established by multianalysis shows that it exists serious mulriple collective linear problem. Considering the relativity of the influencing factors, the paper applys PCA to establish a multiplex factors model, which can distill some main factors effectively. Via calculating, it concludes that in the precondition of the weight of sausage is uniform, the proportion of muscle and fat decides the weight of the final product.
Apply the sort technology basis on SVM to on-line detection and analysis system, use genetic arithmetic to optimize the parameter of SVM. The study shows that SVM is capable to do preferences in the exceptional mode of the control chart, which is able to make the system be more accurate. The technology of on-line detection basis on the control chart can improve real time control of the sausage product line.
本文根据作者近年来所承担的科研课题的研究成果,以皇上皇肉食制品厂生产的广式腊肠为主要研究对象,深入研究了定量包装商品净含量的控制理论;探讨了提取和分析定量包装商品净含量多种影响因素的方法;应用主成分分析法建立了净含量精度保证与质量控制模型;应用控制图与支持向量机对净含量进行有效地预测与控制。本文的主要研究内容、结论及创造性工作总结如下:
着重分析现有的定量包装商品计量监督的法规与准则,以及目前企业为保证定量包装商品净含量精度所采取的评价标准与技术规范,按照由政府执行监管和兼顾消费者与生产企业两者的利益的原则,对定量包装商品净含量计量监管的过程进行剖析。对明确净含量的定义、确定合理的单件负偏差要求、确定合理的合格质量水平AQL、确定合适的监督抽样方案、确定检验批、在检验批中进行正确抽样、准确地检验样本、正确判断检验批的合格与否等方面存在的问题在理论上提出了计量监管的依据。另外深入探讨了定量包装商品净含量的控制目标值,建立了确定定量包装商品净含量目标值的数学模型。
对不同形态商品净含量影响因素进行基本考虑,着重分析了流体传输、物料混合以及物料的去湿与干燥过程中如何进行质量控制,在此基础上,以皇上皇广式腊肠为例,经过实地考察与实验,对其净含量的动态过程控制对象进行了剖析研究,从中发现了制作过程中某些控制不当之处,也得出了许多有用的结论:(1)由于目前厂家尚未普及自动化生产,灌肠生产线与包装生产线仍以劳动力密集型的模式进行加工,目前腊肠灌装线的动态控制能力十分不足:(2)实验数据表明,腊肠流失的重量与肥肉所占比重成线性关系y=54.9907-0.37157x。肥肉所占比例越大,则腊肠重量的流失越小;(3)不同肉馅搅拌时间所得肉馅的均匀度存在一定得差别,从单根腊肠得重量分析,差别并不明显,但将若干条腊肠进行包装,此差异将会被扩大,影响最终包装净含量得精度;(4)人工灌制的腊肠重量的均匀性明显比机器灌制的低;(5)机器灌装的腊肠重量可能受交流电压的影响,因此采取稳压措施将会进一步提高腊肠重量的均匀性,提高腊肠包装的净含量精度;(6)风干过程中,肠体失重主要集中在前四小时,而干燥40小时后失重率变化不大,基本上在2%上下浮动。在经历了初期比较快速的干燥阶段之后出现了一个长时间的比较缓慢的干燥过程,一直持续到腊肠的成品阶段。
广式腊肠的制作需经过原料肉的处理、绞肉拌馅、灌制、干燥、包装等多道工序,每道工序中存在的主客观影响因素错综复杂,腊肠最终成品的净含量正是多变量作用的综合反映。使用多元回归建立和求解多因素模型的过程中发现模型存在着严重的多重共线性问题。然后基于影响腊肠定量包装净含量因素数量多、且具有错综复杂的相关性等特点,利用主成分分析法进行多维特征空间建模,有效地筛选出影响腊肠包装净含量的主要因素,通过模型的求解,得出一个有用的结论,在每根腊肠灌肠后重量均衡的前提下,肉馅肥瘦比例决定了腊肠风干后的重量,根据肉馅配比与腊肠重量的关系,通过改变灌肠长度实现了对腊肠包装净含量精度的改进,验证了该净含量保证系统的应用价值。
使用混合核函数的支持向量机分类技术应用于控制图在线检测和分析系统,利用遗传算法对混合核函数支持向量机的参数进行优化。研究证明,混合核函数的多类分类支持向量机用于控制图模式识别和异常模式下的参数估计是可行的,可以有效地提高系统的识别精度,特别是降低了控制图模式识别中Ⅰ型错判。控制图在线检测技术有效地改进了广式腊肠灌肠线的实时控制。
Along with the coming forth of quantificational packaging merchandise in market, there are many issues need to be solved in the area of quality management. Some problems even haven't been touched, such as how to assure the suttle precision and how to control the quality, which are the hotspots need to be paid attention to imperatively.
In recent years, the author participate several national projects and has some new discoveries in this field. This paper mainly conducts systematic and deep analysis and research on suttle precision assuring system of sausage quantificational packaging and quality control, explores the methods of distilling and analyzing the factors that influence the accuracy of suttle, tries to establish a model to forecast and control the suttle effectively, applying PCA and SVM. The paper brings forth the main results and originality as follows:
Mainly analyze the rule of law of measuring and managing quantificational packaging merchandises, according to the principle that manage by government and pay attention to both consumer and producer. Bring forward some measuring basis to several aspects of problems, such as comprehending the concept of suttle, make the negative warp and AQL reasonly, make logical scheme of sampling, etc. Besides, deeply discuss the target value of controlling, establish a mathematical model to make reasonable target value of controlling.
Consider the influencing factors of the suttle which is in different forms. Give some suggestions on how to control quality in the course of liquid transfers, materiel tmix and dryness. On the basis of it, a lot of useful results are given by investigating the product line of sausage: roboticized production hasn't been gained ground, the product line of sausage is also in the mode of dense working, it comes with the weak capability of dynamic controlling. experimental data showed that the relation between the weight of sausage lost and proportion of fat is linear. In the dryness course, the weight of sausage loses mainly in the front four hours, after that, it will experience a slow dryness course to become product.
Sausage machining contains several working procedures: material disposal, mix round, material filling, dryness and packaging. The influencing factors in each working procedure are anfractuous, and the suttle of sausage is the result of the action of multiplex factors. Model established by multianalysis shows that it exists serious mulriple collective linear problem. Considering the relativity of the influencing factors, the paper applys PCA to establish a multiplex factors model, which can distill some main factors effectively. Via calculating, it concludes that in the precondition of the weight of sausage is uniform, the proportion of muscle and fat decides the weight of the final product.
Apply the sort technology basis on SVM to on-line detection and analysis system, use genetic arithmetic to optimize the parameter of SVM. The study shows that SVM is capable to do preferences in the exceptional mode of the control chart, which is able to make the system be more accurate. The technology of on-line detection basis on the control chart can improve real time control of the sausage product line.
引文
[1]李红兵、刘伟俊、黄锋,定量包装商品净含量保证指南,北京:中国计量出版社,2005.
[2]张文彤 主编,SPSS 11统计分析教程(高级篇),北京:北京希望电子出版社.2002.
[3]庄楚强、何春雄,应用数理统计基础,广州:华南理工大学出版社,2006.
[4]王岩、隋思涟、王爱青,数理统计与MATLAB工程数据分析,北京:清华大学出版社,2006.
[5]李国勇,智能控制及其MATLAB实现,北京:电子工业出版社,2005.
[6]高隽,人工神经网络原理及仿真实例,北京:机械工业出版社,2003.
[7]苏金明、张莲花、刘波,MATLAB工具箱应用,北京:电子工业出版社,2004.
[8]孙文爽、陈兰祥,多元统计分析,北京:高等教育出版社,1994.
[9]王学仁、王松桂,实用多元统计分析,上海:上海科学技术出版社,1990.
[10]高惠璇,应用多元统计分析,北京:北京大学出版社,2005.
[11](美)Vladimir N.Vapnik著,张学工译,统计学习理论的本质,北京:清华大学出版社,2000.
[12]邓乃扬、田英杰著,数据挖掘中的新方法 支持向量机,北京:科学出版社,2004.
[13]克里斯蒂亚尼尼,N.(Cristianini,Nello),肖-泰勒,J.(Shawe-Taylor,John),李国正,王猛,曾华军,支持向量机导论,北京:电子工业出版社,2004.
[14]杜达,R.o.(Duda,Richard O.),哈特,P.E.(Hart,Peter E.),1941-,斯托克,D.G (Stork,David G),李宏东,姚天翔,模式分类,北京:机械工业出版社,2003.
[15]郑德如,回归分析和相关分析,上海:上海人民出版社,1984.
[16]方开泰等,实用回归分析,北京:科学出版社,1988.
[17]费业泰主编,误差理论与数据处理(第四版),北京:机械工业出版社,2000.
[18]国家质量技术监督局计量司,中国计量测试学会编著,现代企业计量工作指导手册上册,北京:中国标准出版社,1999.
[19]吴亚森、孙爱霞,概率论与数理统计,广州:华南理工大学出版社,1996.
[20]李慎安、施昌彦、刘凤,中华人民共和国国家计量技术规范测量不确定度评定与评定,北京:中国计量出版社,2005.
[21]于振凡、楚安静、乔丹·丹编著,抽样检验教程,北京:中国计量出版社,1998.
[22]王庆仁、康学政、信海红,抽样检验技术,北京:中国计量出版社,1998.
[23]国家质量技术监督局计量司,定量包装商品净含量计量检验指南,北京:中 国计量出版社,2000.
[24]国家质量技术监督检验检疫总局质量司,质量专业理论与务实--中级,北京:中国人事出版社,2001.
[25]袁建国,抽样检验原理与应用,北京:中国计量出版社,2002.
[26]国家质量技术监督局计量司,定量包装商品法规手册,北京:中国计量出版社,2001.
[27]张旭光,食品工程原理,北京:中国轻工业出版社,2006.
[28]王钦德、杨坚,食品试验设计与统计分析,北京:中国农业出版社,2003.
[29]回增梅、徐侠,如何理解定量包装商品的净含量[J],消费指南,Vol.22,No.4,2002,P70-71,74.
[30]沈海强.对定量包装商品检验的几点想法[J].法制计量,Vol.11,2003,P20.
[31]王波,常见定量包装商品计量问题的成因与对策,计量,Vol.31,No.6,2001,P31.
[32]王喜阳、林红,定量包装商品净含量检验系统程序设计时应注意的问题,衡器,36(4),2007,P50-51.
[33]陈涛,对定量包装商品净含量监控的两点分析,中国计量,11,2007.P21-24
[34]马明、桑晓鸣,对JJF1070-2005《定量包装商品净含量计量检验规则》的探讨,中国计量,11,2007.P50
[35]陈立,定量包装商品净含量计量不合格的原因,质量春秋,5,2007,P43
[36]郑飞,关于定量包装商品净含量检验的一点看法,中国计量,2,2007.P9
[37]王珏、张明芬、马海燕,定量包装商品净含量计量检验不确定度评定,计量与测试技术,33(10),2006.P43
[38]李文香,对《定量包装商品净含量计量检验规则》的几点见解,计量技术,4,2006.P51-52
[39]高春冰,定量包装商品净含量不足的原因及对策,计量与测试技术,33(4),2006.P24-25.
[40]黄锋、谭山,定量包装商品净含量合格与否判定点上的器具选择问题,中国计量,6,2005.P19-20.
[41]陈恒美,定量包装商品净含量计量检验程序,工业计量,14(3),2004,P51
[42]杨国基、王振文,定量包装商品净含量计量偏差现状的评估,中国计量,3,2004,P32.
[43]骆钦华,于雁军,对定量包装商品净含量及其允许负偏差的进一步探讨,中国计量,8,2004,P38.44
[44]卢生、屈笑宇,定量包装商品净含量不足的原因,质量天地,4,2003,P38.
[45]沈承为,定量包装商品净含量检验中有关问题的探讨,质量监督与消费,2,2003,P43-44.
[46]赵振山,对“定量包装商品净含量计量检验规则”的几点建议,中国计量,11,2001,P32.
[47]龚英亮、杜效荣,检验定量包装商品净含量应注意的几个问题,中国计量,6,2001,P17.
[48]张吉仙,浅议《定量包装商品计量监督规定》和《定量包装商品净含量计量检验规则》,中国计量,7,2003,P19.
[49]杨美群,定量包装商品净含量计量检验抽样方案之我见,中国计量,7,2003,P33.
[50]苏冠,定量包装商品净含量计量不合格原因分析,中国计量,4,2003,P15-16
[51]吕占海,定量包装商品净含量计量检验工作研究,计量与测试技术,28(5),2001,P49.
[52]Martin,Shawn,An approximate version of kernel PCA,5th International Conference on Machine Learning and Applications,ICMLA 2006,p 239-244
[53]宋永发、王颖、王建东、鞠平,基于主成分分析法的特征价格模型,价值工程,27(4),2008,P134-137.
[54]Xavier Capron,Desire Luc Massart,Multivariate authentication of the geographical origin of wines:a kernel SVM approach,European Food Research and Technology,2007 Vol.225(No.3-4).
[55]麻荣永、郑二伟、王魁、李建,基于主成分分析法的广西水资源可持续利用综合评价,广西大学学报:自然科学版,33(1),2008,P16-19
[56]Wang,Li-Wei;Wang,Xiao;Chang,Ming;Feng,Ju-Fu,Is two-dimensional PCA a new technique,Zidonghua Xuebao/Acta Automatica Sinica,v 31,September 2005,p 782-787
[57]WANG Huan-liang,HAN Ji-qing,SVM with discriminative dynamic time alignment,Journal of Harbin Institute of Technology,2007 Vol.14(No.5).
[58]徐秋云,山东省投资环境的主成分分析与评价,中国高新技术企业,6,2008,P1-6
[59]G.Y.Chen,W.F.Xie,Pattern recognition with SVM and dual-tree complex wavelets,Image and Vision Computing,2007 Vol.25(No.6).
[60]Ismail Hmeidi,Bilal Hawashin,Performance of KNN and SVM classifiers on full word Arabic articles,Advanced Engineering Informatics,2008vol.22(no.1).
[61]梁剑、 张健,多元统计分析在四川退耕还林区土壤肥力评价中的运用,环境科学研究,21(2),2008.P68-72.
[62]DING Wenrui,TONG Yubing,Image and Video Quality Assessment Using Neural Network and SVM,Tsinghua Science and Technology,2008Vol.13(no.1).
[63]吴振华、钟城、赖景生,湖北省县域经济综合实力的主成分分析,价格月刊, 3,2008,P57-60.
[64]高建、周丽萍、王文科、刘志新,主成分分析法在住宅特征价格模型中的应用,山东建筑大学学报,23(1),2008.P15-19.
[65]赵彦锋、郭恒亮、孙志英、史学正、吴克宁,基于土壤学知识的主成分分析判断土壤重金属来源,地理科学,28(1),2008,P45-50.
[66]袁田,主成分分析法在研究武汉市各区经济状况中的应用,科技创业月刊,21(3),2008,P95-96.
[67]Yin,PP,Sun,FC,An adaptive feature fusion framework for multi-class classification based on SVM,Soft computing,2008 vol.12(no.7).
[68]焦合军、施进发、李济顺,网络化制造资源状态估计研究--基于主成分分析(PCA)和加权支持向量机(WSVM),郑州航空工业管理学院学报,26(2),2008,P78-80.
[69]Wang,MH,Li,CH,PSPhos:PK-Specific phosphorylation site prediction using profile SVM,Journal of computational and theoretical nanoseience,2007 vol.4(no.7-8).
[70]Shinn-Ying Ho,Fu-Chieh Yu,Design of accurate predictors for DNA-binding sites in proteins using hybrid SVM-PSSM method,BioSystems,2007 vol.90(no.1).
[71]蒋文明,基于主成分分析法的我国制造业自主创新能力研究,经济研究导刊,2,2008,P31-33.
[72]Rathi,Yogesh;Dambreville,Samuel;Tannenbaum,Allen,Statistical shape analysis using Kernel PCA,Image Processing:Algorithms and Systems,Neural Networks,and Machine Learning,2006,p 60641B
[73]高尚,基于主成分分析和支持向量机的威胁判断模型,数学的实践与认识,38(4).2008.P1-6
[74]Chen,QS,Zhao,JW,Feasibility study on identification of green,black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine(SVM),Spectrochimica Acta.Part A,Molecular and Biomolecular Spectroscopy,2007 vol.66(no.3).
[75]金蛟,主成分分析方法在综合评价中的应用,中国卫生统计,25(1),2008,P72-74.
[76]Jia Jia,Lianhong Cai,Fingerprint matching based on weighting method and the SVM,Neurocomputing,2007 Vol.70(No.4-6).
[77]YUK YING CHUNG,ERIC H.C.CHOI,An Improved Audio Classification Algorithm using SVM Weight Factor,WSEAS Transactions on Communications,2007 vol.6(no.3).
[78]Bazi,Y.,Melgani,F.,Semisupervised PSO-SVM Regression for Biophysical Parameter Estimation, IEEE Transactions on Geoscience and Remote Sensing,2007 Vol.45(No.6).
[79] Guoping Xu , Weifeng Tian , EMD- and SVM-based temperature drift modeling and compensation for a dynamically tuned gyroscope (DTG),Mechanical Systems and Signal Processing, 2007 vol.21(no.8).
[80] Guoping Xu , Weifeng Tian, Temperature drift modelling and compensation for a dynamically tuned gyroscope by combining WT and SVM method, Measurement Science and Technology, 2007 vol.18(no.5).
[81] Bilan ZHU , Masaki NAKAGAWA ,Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition, IEICE Transactions on Information and Systems, 2008 Vol.E91-D(No.1).
[82] Dehong Xu , Bo Feng , A Zero Voltage Switching SVM (ZVS-SVM) Controlled Three-Phase Boost Rectifier, IEEE Transactions on Power Electronics, 2007 vol.22(no.3).
[83] Piotr BOJARCZAK , Piotr LESIAK , SVM based classification method of railway's defectsSiec SVM w klasyfikacji uszkodzen szyn kolejowych,Pomiary Automatyka Kontrola, 2007 Vol.53(No.12).
[84] Liu, Y; Zheng, Y. F,Soft SVM and Its Application in Video-Object Extraction, IEEE Transactions on Signal Processing, 2007 Vol.55(No.7).
[85] Sun, Qiang; BeJong, Gerald, Explanation-augmented SVM: An approach to incorporating domain knowledge into SVM learning, ICML 2005: 22nd International Conference on Machine Learning,Bonn, Germany, 2005,p865-872
[86] Lardeux, Cedric; Frison, Pierre-Louis; Rudant, Jean-Paul; Souyris,Jean-Claude; Tison, Celine; Stoll, Benoit, Use of the SVM classification with polarimetric SAR data for land use cartography, 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS, p493-496
[87] Matias, Jose M., Partially parametric SVM, 12th Portuguese Conference on Artificial Intelligence, EPIA 2005 - Progress in Artificial Intelligence,2005, p67-75
[88] Vapnik, Vladimir, Learning hidden information: SVM+,2006 IEEE International Conference on Granular Computing, p22
[89] Gao, Ke; Lin, Shou-Xun; Zhang, Yong-Dong; Tang, Sheng, Clustering guided SVM for semantic image retrieval, 2007 2nd International Conference on Pervasive Computing and Applications, ICPCA'07, p199-203
[90] Zhan, Yiqiang; Shen, Dinggang , An adaptive error penalization method for training an efficient and generalized SVM, Department of Computer Science, v 39,March 2006, p 342-350
[91] Zhang, Jian-Pei; Li, Zhong-Wei; Yang, Jing, A parallel SVM training algorithm on large-scale classification problems, International Conference on Machine Learning and Cybernetics, ICMLC 2005, p1637-1641
[92] Cao, Yunbo; Xu, Jun; Liu, Tie-Yan; Li, Hang; Huang, Yalou; Hon,Hsiao-Wuen , Adapting ranking SVM to document retrieval, 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2006, p186-193
[93] Liu, Yi; Zheng, Yuan F. , Soft SVM and its application to video object extraction, 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, p V193-V196
[94] Hiremath, P.S.; Prabhakar, C.J., Face recognition technique using symbolic PCA method, 1st International Conference on Pattern Recognition and Machine Intelligence, PReMI 2005, p 266-271
[95] Adamos, Dimitrios A.; Kosmidis, Efstratios K.; Theophilidis, George ,Performance evaluation of PCA-based spike sorting algorithms, Computer Methods and Programs in Biomedicine, v 91, September 2008, p 232-244
[96] Brunskill, Emma; Roy, Nicholas, SLAM using incremental probabilistic PCA and dimensionality reduction, 2005 IEEE International Conference on Robotics and Automation, p 342-347
[97] Xu, Xin; Wang, Xuening, An adaptive network intrusion detection method based on PCA and support vector machines, 1st International Conference on Advanced Data Mining and Applications, ADMA 2005, p 696-703
[98] Conde, Olga M.; Amado, Marta; Garcia-Allende, Pilar B.; Cobo, Adolfo;Lopez-Higuera, Jose Miguel , Evaluation of PCA dimensionality reduction techniques in imaging spectroscopy for foreign object detection,Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIII, 2007, p 65650M
[99] Kimura, Masahiro; Saito, Kazumi; Ueda, Naonori, Multinomial PCA for extracting major latent topics from document streams, International Joint Conference on Neural Networks, IJCNN 2005, p 238-243
[100]Doan, Xuan-Tien; Srinivasan, R., Augmented dynamic PCA approach for online monitoring of multi-phase batch processes, 05AIChE: 2005 AIChE Annual Meeting and Fall Showcase, p 6673-6695
[101]Islam, M.M.; Alam, M.S. , Mine detection in multispectral imagery using PCA and matched filtering, Automatic Target Recognition XVIII, 2008, p 69670D
[102]Nhat, Vo Dinh Minh; Lee, Sung Young , Two-dimensional weighted PCA algorithm for face recognition, 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005, p 219-223
[103]Gabrys, Bogdan; Baruque, Bruno; Corchado, Emilio, Outlier resistant PCA ensembles, 10th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES 2006, p 432-440
[2]张文彤 主编,SPSS 11统计分析教程(高级篇),北京:北京希望电子出版社.2002.
[3]庄楚强、何春雄,应用数理统计基础,广州:华南理工大学出版社,2006.
[4]王岩、隋思涟、王爱青,数理统计与MATLAB工程数据分析,北京:清华大学出版社,2006.
[5]李国勇,智能控制及其MATLAB实现,北京:电子工业出版社,2005.
[6]高隽,人工神经网络原理及仿真实例,北京:机械工业出版社,2003.
[7]苏金明、张莲花、刘波,MATLAB工具箱应用,北京:电子工业出版社,2004.
[8]孙文爽、陈兰祥,多元统计分析,北京:高等教育出版社,1994.
[9]王学仁、王松桂,实用多元统计分析,上海:上海科学技术出版社,1990.
[10]高惠璇,应用多元统计分析,北京:北京大学出版社,2005.
[11](美)Vladimir N.Vapnik著,张学工译,统计学习理论的本质,北京:清华大学出版社,2000.
[12]邓乃扬、田英杰著,数据挖掘中的新方法 支持向量机,北京:科学出版社,2004.
[13]克里斯蒂亚尼尼,N.(Cristianini,Nello),肖-泰勒,J.(Shawe-Taylor,John),李国正,王猛,曾华军,支持向量机导论,北京:电子工业出版社,2004.
[14]杜达,R.o.(Duda,Richard O.),哈特,P.E.(Hart,Peter E.),1941-,斯托克,D.G (Stork,David G),李宏东,姚天翔,模式分类,北京:机械工业出版社,2003.
[15]郑德如,回归分析和相关分析,上海:上海人民出版社,1984.
[16]方开泰等,实用回归分析,北京:科学出版社,1988.
[17]费业泰主编,误差理论与数据处理(第四版),北京:机械工业出版社,2000.
[18]国家质量技术监督局计量司,中国计量测试学会编著,现代企业计量工作指导手册上册,北京:中国标准出版社,1999.
[19]吴亚森、孙爱霞,概率论与数理统计,广州:华南理工大学出版社,1996.
[20]李慎安、施昌彦、刘凤,中华人民共和国国家计量技术规范测量不确定度评定与评定,北京:中国计量出版社,2005.
[21]于振凡、楚安静、乔丹·丹编著,抽样检验教程,北京:中国计量出版社,1998.
[22]王庆仁、康学政、信海红,抽样检验技术,北京:中国计量出版社,1998.
[23]国家质量技术监督局计量司,定量包装商品净含量计量检验指南,北京:中 国计量出版社,2000.
[24]国家质量技术监督检验检疫总局质量司,质量专业理论与务实--中级,北京:中国人事出版社,2001.
[25]袁建国,抽样检验原理与应用,北京:中国计量出版社,2002.
[26]国家质量技术监督局计量司,定量包装商品法规手册,北京:中国计量出版社,2001.
[27]张旭光,食品工程原理,北京:中国轻工业出版社,2006.
[28]王钦德、杨坚,食品试验设计与统计分析,北京:中国农业出版社,2003.
[29]回增梅、徐侠,如何理解定量包装商品的净含量[J],消费指南,Vol.22,No.4,2002,P70-71,74.
[30]沈海强.对定量包装商品检验的几点想法[J].法制计量,Vol.11,2003,P20.
[31]王波,常见定量包装商品计量问题的成因与对策,计量,Vol.31,No.6,2001,P31.
[32]王喜阳、林红,定量包装商品净含量检验系统程序设计时应注意的问题,衡器,36(4),2007,P50-51.
[33]陈涛,对定量包装商品净含量监控的两点分析,中国计量,11,2007.P21-24
[34]马明、桑晓鸣,对JJF1070-2005《定量包装商品净含量计量检验规则》的探讨,中国计量,11,2007.P50
[35]陈立,定量包装商品净含量计量不合格的原因,质量春秋,5,2007,P43
[36]郑飞,关于定量包装商品净含量检验的一点看法,中国计量,2,2007.P9
[37]王珏、张明芬、马海燕,定量包装商品净含量计量检验不确定度评定,计量与测试技术,33(10),2006.P43
[38]李文香,对《定量包装商品净含量计量检验规则》的几点见解,计量技术,4,2006.P51-52
[39]高春冰,定量包装商品净含量不足的原因及对策,计量与测试技术,33(4),2006.P24-25.
[40]黄锋、谭山,定量包装商品净含量合格与否判定点上的器具选择问题,中国计量,6,2005.P19-20.
[41]陈恒美,定量包装商品净含量计量检验程序,工业计量,14(3),2004,P51
[42]杨国基、王振文,定量包装商品净含量计量偏差现状的评估,中国计量,3,2004,P32.
[43]骆钦华,于雁军,对定量包装商品净含量及其允许负偏差的进一步探讨,中国计量,8,2004,P38.44
[44]卢生、屈笑宇,定量包装商品净含量不足的原因,质量天地,4,2003,P38.
[45]沈承为,定量包装商品净含量检验中有关问题的探讨,质量监督与消费,2,2003,P43-44.
[46]赵振山,对“定量包装商品净含量计量检验规则”的几点建议,中国计量,11,2001,P32.
[47]龚英亮、杜效荣,检验定量包装商品净含量应注意的几个问题,中国计量,6,2001,P17.
[48]张吉仙,浅议《定量包装商品计量监督规定》和《定量包装商品净含量计量检验规则》,中国计量,7,2003,P19.
[49]杨美群,定量包装商品净含量计量检验抽样方案之我见,中国计量,7,2003,P33.
[50]苏冠,定量包装商品净含量计量不合格原因分析,中国计量,4,2003,P15-16
[51]吕占海,定量包装商品净含量计量检验工作研究,计量与测试技术,28(5),2001,P49.
[52]Martin,Shawn,An approximate version of kernel PCA,5th International Conference on Machine Learning and Applications,ICMLA 2006,p 239-244
[53]宋永发、王颖、王建东、鞠平,基于主成分分析法的特征价格模型,价值工程,27(4),2008,P134-137.
[54]Xavier Capron,Desire Luc Massart,Multivariate authentication of the geographical origin of wines:a kernel SVM approach,European Food Research and Technology,2007 Vol.225(No.3-4).
[55]麻荣永、郑二伟、王魁、李建,基于主成分分析法的广西水资源可持续利用综合评价,广西大学学报:自然科学版,33(1),2008,P16-19
[56]Wang,Li-Wei;Wang,Xiao;Chang,Ming;Feng,Ju-Fu,Is two-dimensional PCA a new technique,Zidonghua Xuebao/Acta Automatica Sinica,v 31,September 2005,p 782-787
[57]WANG Huan-liang,HAN Ji-qing,SVM with discriminative dynamic time alignment,Journal of Harbin Institute of Technology,2007 Vol.14(No.5).
[58]徐秋云,山东省投资环境的主成分分析与评价,中国高新技术企业,6,2008,P1-6
[59]G.Y.Chen,W.F.Xie,Pattern recognition with SVM and dual-tree complex wavelets,Image and Vision Computing,2007 Vol.25(No.6).
[60]Ismail Hmeidi,Bilal Hawashin,Performance of KNN and SVM classifiers on full word Arabic articles,Advanced Engineering Informatics,2008vol.22(no.1).
[61]梁剑、 张健,多元统计分析在四川退耕还林区土壤肥力评价中的运用,环境科学研究,21(2),2008.P68-72.
[62]DING Wenrui,TONG Yubing,Image and Video Quality Assessment Using Neural Network and SVM,Tsinghua Science and Technology,2008Vol.13(no.1).
[63]吴振华、钟城、赖景生,湖北省县域经济综合实力的主成分分析,价格月刊, 3,2008,P57-60.
[64]高建、周丽萍、王文科、刘志新,主成分分析法在住宅特征价格模型中的应用,山东建筑大学学报,23(1),2008.P15-19.
[65]赵彦锋、郭恒亮、孙志英、史学正、吴克宁,基于土壤学知识的主成分分析判断土壤重金属来源,地理科学,28(1),2008,P45-50.
[66]袁田,主成分分析法在研究武汉市各区经济状况中的应用,科技创业月刊,21(3),2008,P95-96.
[67]Yin,PP,Sun,FC,An adaptive feature fusion framework for multi-class classification based on SVM,Soft computing,2008 vol.12(no.7).
[68]焦合军、施进发、李济顺,网络化制造资源状态估计研究--基于主成分分析(PCA)和加权支持向量机(WSVM),郑州航空工业管理学院学报,26(2),2008,P78-80.
[69]Wang,MH,Li,CH,PSPhos:PK-Specific phosphorylation site prediction using profile SVM,Journal of computational and theoretical nanoseience,2007 vol.4(no.7-8).
[70]Shinn-Ying Ho,Fu-Chieh Yu,Design of accurate predictors for DNA-binding sites in proteins using hybrid SVM-PSSM method,BioSystems,2007 vol.90(no.1).
[71]蒋文明,基于主成分分析法的我国制造业自主创新能力研究,经济研究导刊,2,2008,P31-33.
[72]Rathi,Yogesh;Dambreville,Samuel;Tannenbaum,Allen,Statistical shape analysis using Kernel PCA,Image Processing:Algorithms and Systems,Neural Networks,and Machine Learning,2006,p 60641B
[73]高尚,基于主成分分析和支持向量机的威胁判断模型,数学的实践与认识,38(4).2008.P1-6
[74]Chen,QS,Zhao,JW,Feasibility study on identification of green,black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine(SVM),Spectrochimica Acta.Part A,Molecular and Biomolecular Spectroscopy,2007 vol.66(no.3).
[75]金蛟,主成分分析方法在综合评价中的应用,中国卫生统计,25(1),2008,P72-74.
[76]Jia Jia,Lianhong Cai,Fingerprint matching based on weighting method and the SVM,Neurocomputing,2007 Vol.70(No.4-6).
[77]YUK YING CHUNG,ERIC H.C.CHOI,An Improved Audio Classification Algorithm using SVM Weight Factor,WSEAS Transactions on Communications,2007 vol.6(no.3).
[78]Bazi,Y.,Melgani,F.,Semisupervised PSO-SVM Regression for Biophysical Parameter Estimation, IEEE Transactions on Geoscience and Remote Sensing,2007 Vol.45(No.6).
[79] Guoping Xu , Weifeng Tian , EMD- and SVM-based temperature drift modeling and compensation for a dynamically tuned gyroscope (DTG),Mechanical Systems and Signal Processing, 2007 vol.21(no.8).
[80] Guoping Xu , Weifeng Tian, Temperature drift modelling and compensation for a dynamically tuned gyroscope by combining WT and SVM method, Measurement Science and Technology, 2007 vol.18(no.5).
[81] Bilan ZHU , Masaki NAKAGAWA ,Segmentation of On-Line Freely Written Japanese Text Using SVM for Improving Text Recognition, IEICE Transactions on Information and Systems, 2008 Vol.E91-D(No.1).
[82] Dehong Xu , Bo Feng , A Zero Voltage Switching SVM (ZVS-SVM) Controlled Three-Phase Boost Rectifier, IEEE Transactions on Power Electronics, 2007 vol.22(no.3).
[83] Piotr BOJARCZAK , Piotr LESIAK , SVM based classification method of railway's defectsSiec SVM w klasyfikacji uszkodzen szyn kolejowych,Pomiary Automatyka Kontrola, 2007 Vol.53(No.12).
[84] Liu, Y; Zheng, Y. F,Soft SVM and Its Application in Video-Object Extraction, IEEE Transactions on Signal Processing, 2007 Vol.55(No.7).
[85] Sun, Qiang; BeJong, Gerald, Explanation-augmented SVM: An approach to incorporating domain knowledge into SVM learning, ICML 2005: 22nd International Conference on Machine Learning,Bonn, Germany, 2005,p865-872
[86] Lardeux, Cedric; Frison, Pierre-Louis; Rudant, Jean-Paul; Souyris,Jean-Claude; Tison, Celine; Stoll, Benoit, Use of the SVM classification with polarimetric SAR data for land use cartography, 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS, p493-496
[87] Matias, Jose M., Partially parametric SVM, 12th Portuguese Conference on Artificial Intelligence, EPIA 2005 - Progress in Artificial Intelligence,2005, p67-75
[88] Vapnik, Vladimir, Learning hidden information: SVM+,2006 IEEE International Conference on Granular Computing, p22
[89] Gao, Ke; Lin, Shou-Xun; Zhang, Yong-Dong; Tang, Sheng, Clustering guided SVM for semantic image retrieval, 2007 2nd International Conference on Pervasive Computing and Applications, ICPCA'07, p199-203
[90] Zhan, Yiqiang; Shen, Dinggang , An adaptive error penalization method for training an efficient and generalized SVM, Department of Computer Science, v 39,March 2006, p 342-350
[91] Zhang, Jian-Pei; Li, Zhong-Wei; Yang, Jing, A parallel SVM training algorithm on large-scale classification problems, International Conference on Machine Learning and Cybernetics, ICMLC 2005, p1637-1641
[92] Cao, Yunbo; Xu, Jun; Liu, Tie-Yan; Li, Hang; Huang, Yalou; Hon,Hsiao-Wuen , Adapting ranking SVM to document retrieval, 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2006, p186-193
[93] Liu, Yi; Zheng, Yuan F. , Soft SVM and its application to video object extraction, 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, p V193-V196
[94] Hiremath, P.S.; Prabhakar, C.J., Face recognition technique using symbolic PCA method, 1st International Conference on Pattern Recognition and Machine Intelligence, PReMI 2005, p 266-271
[95] Adamos, Dimitrios A.; Kosmidis, Efstratios K.; Theophilidis, George ,Performance evaluation of PCA-based spike sorting algorithms, Computer Methods and Programs in Biomedicine, v 91, September 2008, p 232-244
[96] Brunskill, Emma; Roy, Nicholas, SLAM using incremental probabilistic PCA and dimensionality reduction, 2005 IEEE International Conference on Robotics and Automation, p 342-347
[97] Xu, Xin; Wang, Xuening, An adaptive network intrusion detection method based on PCA and support vector machines, 1st International Conference on Advanced Data Mining and Applications, ADMA 2005, p 696-703
[98] Conde, Olga M.; Amado, Marta; Garcia-Allende, Pilar B.; Cobo, Adolfo;Lopez-Higuera, Jose Miguel , Evaluation of PCA dimensionality reduction techniques in imaging spectroscopy for foreign object detection,Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIII, 2007, p 65650M
[99] Kimura, Masahiro; Saito, Kazumi; Ueda, Naonori, Multinomial PCA for extracting major latent topics from document streams, International Joint Conference on Neural Networks, IJCNN 2005, p 238-243
[100]Doan, Xuan-Tien; Srinivasan, R., Augmented dynamic PCA approach for online monitoring of multi-phase batch processes, 05AIChE: 2005 AIChE Annual Meeting and Fall Showcase, p 6673-6695
[101]Islam, M.M.; Alam, M.S. , Mine detection in multispectral imagery using PCA and matched filtering, Automatic Target Recognition XVIII, 2008, p 69670D
[102]Nhat, Vo Dinh Minh; Lee, Sung Young , Two-dimensional weighted PCA algorithm for face recognition, 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005, p 219-223
[103]Gabrys, Bogdan; Baruque, Bruno; Corchado, Emilio, Outlier resistant PCA ensembles, 10th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES 2006, p 432-440