Recognition of substrates in cobalt crust mining areas can improve mining efficiency.Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust min...Recognition of substrates in cobalt crust mining areas can improve mining efficiency.Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust mining area,a method based on multiple-feature sets is proposed.Features of the target echoes are extracted by linear prediction method and wavelet analysis methods,and the linear prediction coefficient and linear prediction cepstrum coefficient are also extracted.Meanwhile,the characteristic matrices of modulus maxima,sub-band energy and multi-resolution singular spectrum entropy are obtained,respectively.The resulting features are subsequently compressed by kernel Fisher discriminant analysis(KFDA),the output features are selected using genetic algorithm(GA)to obtain optimal feature subsets,and recognition results of classifier are chosen as genetic fitness function.The advantages of this method are that it can describe the signal features more comprehensively and select the favorable features and remove the redundant features to the greatest extent.The experimental results show the better performance of the proposed method in comparison with only using KFDA or GA.展开更多
黄曲霉毒素是广泛存在于玉米中且具有剧毒的一种代谢产物,以美国农业部农业研究署(USDA-ARS) Toxicology and Mycotoxin Research Unit提供的2010年先锋玉米为研究对象,验证了高光谱成像技术对玉米中黄曲霉毒素检测的可行性。以甲...黄曲霉毒素是广泛存在于玉米中且具有剧毒的一种代谢产物,以美国农业部农业研究署(USDA-ARS) Toxicology and Mycotoxin Research Unit提供的2010年先锋玉米为研究对象,验证了高光谱成像技术对玉米中黄曲霉毒素检测的可行性。以甲醇为溶剂制备四种不同浓度的黄曲霉毒素溶液,并将其逐一滴在等量的4组共120粒玉米颗粒表面,以未处理的30粒洁净玉米作为一组对照样本,将大小、形状相似的150个样品随机分为训练集103个,验证集47个;对获取的400~1000 nm波段范围内的高光谱图像,先进行标准正态变量变换(standard normal variate transformation ,SNV)预处理,然后引入基于 Fisher判别最小误判率的方法选择最优波长,并以所选波长作为Fisher判别分析法的输入建立判别模型,对玉米颗粒表面不同浓度的黄曲霉毒素进行识别,最后对模型判别正确率进行了验证。结果表明,选取四个最优波长(812.42,873.00,900.36和965.00 nm )时Fisher判别分析模型对训练集与验证集的准确率分别为87.4%和80.9%。该方法为含黄曲霉毒素玉米颗粒便携式检测仪器的开发,以及对田间霉变玉米自然代谢产生毒素的检测奠定了技术基础。展开更多
子空间特征提取是人脸识别中的关键技术之一,结合局部Fisher判别分析技术和张量子空间分析技术的优点,本文提出了一种新的张量局部Fisher判别分析(Tensor local Fisher discriminant analysis,TLFDA)子空间降维技术.首先,通过对局部Fis...子空间特征提取是人脸识别中的关键技术之一,结合局部Fisher判别分析技术和张量子空间分析技术的优点,本文提出了一种新的张量局部Fisher判别分析(Tensor local Fisher discriminant analysis,TLFDA)子空间降维技术.首先,通过对局部Fisher判别技术进行分析,调整了其类间散度目标泛函,使算法的识别性能更高且时间复杂度更低;其次,引入张量型降维技术对输入数据进行双边投影变换而非单边投影,获得了更高的数据压缩率;最后,采用迭代更新的方法计算最优的变换矩阵.通过ORL和PIE两个人脸库验证了所提算法的有效性.展开更多
针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样...针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样本中的故障信息,避免了因有标记故障样本不足引起的过学习问题,同时采用正交迭代方式求解最优正交映射矩阵,克服现有方法无法得到正交映射矩阵的不足。正交映射矩阵的基矢量统计不相关,可有效地提高所得低维特征矢量的可辨识性。通过正交映射矩阵对故障样本集和新增样本进行维数约简,并将维数约简的结果输入粗糙优化k最近邻分类器(Coarse to fine k nearest neighbor classifier,CFKNNC)进行学习训练和故障识别。所提方法集成了OSELF在维数约简和CFKNNC在模式识别的优势,有效地提高了故障诊断的精度。通过齿轮箱故障模拟试验验证了该方法的有效性。展开更多
基金Project(51874353)supported by the National Natural Science Foundation of ChinaProject(GCX20190898Y)supported by Mittal Student Innovation Project,China。
文摘Recognition of substrates in cobalt crust mining areas can improve mining efficiency.Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust mining area,a method based on multiple-feature sets is proposed.Features of the target echoes are extracted by linear prediction method and wavelet analysis methods,and the linear prediction coefficient and linear prediction cepstrum coefficient are also extracted.Meanwhile,the characteristic matrices of modulus maxima,sub-band energy and multi-resolution singular spectrum entropy are obtained,respectively.The resulting features are subsequently compressed by kernel Fisher discriminant analysis(KFDA),the output features are selected using genetic algorithm(GA)to obtain optimal feature subsets,and recognition results of classifier are chosen as genetic fitness function.The advantages of this method are that it can describe the signal features more comprehensively and select the favorable features and remove the redundant features to the greatest extent.The experimental results show the better performance of the proposed method in comparison with only using KFDA or GA.
文摘黄曲霉毒素是广泛存在于玉米中且具有剧毒的一种代谢产物,以美国农业部农业研究署(USDA-ARS) Toxicology and Mycotoxin Research Unit提供的2010年先锋玉米为研究对象,验证了高光谱成像技术对玉米中黄曲霉毒素检测的可行性。以甲醇为溶剂制备四种不同浓度的黄曲霉毒素溶液,并将其逐一滴在等量的4组共120粒玉米颗粒表面,以未处理的30粒洁净玉米作为一组对照样本,将大小、形状相似的150个样品随机分为训练集103个,验证集47个;对获取的400~1000 nm波段范围内的高光谱图像,先进行标准正态变量变换(standard normal variate transformation ,SNV)预处理,然后引入基于 Fisher判别最小误判率的方法选择最优波长,并以所选波长作为Fisher判别分析法的输入建立判别模型,对玉米颗粒表面不同浓度的黄曲霉毒素进行识别,最后对模型判别正确率进行了验证。结果表明,选取四个最优波长(812.42,873.00,900.36和965.00 nm )时Fisher判别分析模型对训练集与验证集的准确率分别为87.4%和80.9%。该方法为含黄曲霉毒素玉米颗粒便携式检测仪器的开发,以及对田间霉变玉米自然代谢产生毒素的检测奠定了技术基础。
文摘子空间特征提取是人脸识别中的关键技术之一,结合局部Fisher判别分析技术和张量子空间分析技术的优点,本文提出了一种新的张量局部Fisher判别分析(Tensor local Fisher discriminant analysis,TLFDA)子空间降维技术.首先,通过对局部Fisher判别技术进行分析,调整了其类间散度目标泛函,使算法的识别性能更高且时间复杂度更低;其次,引入张量型降维技术对输入数据进行双边投影变换而非单边投影,获得了更高的数据压缩率;最后,采用迭代更新的方法计算最优的变换矩阵.通过ORL和PIE两个人脸库验证了所提算法的有效性.
文摘针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样本中的故障信息,避免了因有标记故障样本不足引起的过学习问题,同时采用正交迭代方式求解最优正交映射矩阵,克服现有方法无法得到正交映射矩阵的不足。正交映射矩阵的基矢量统计不相关,可有效地提高所得低维特征矢量的可辨识性。通过正交映射矩阵对故障样本集和新增样本进行维数约简,并将维数约简的结果输入粗糙优化k最近邻分类器(Coarse to fine k nearest neighbor classifier,CFKNNC)进行学习训练和故障识别。所提方法集成了OSELF在维数约简和CFKNNC在模式识别的优势,有效地提高了故障诊断的精度。通过齿轮箱故障模拟试验验证了该方法的有效性。