基于栈式自编码融合极限学习机的药品鉴别
|
摘要
近红外光谱数据维度较高,传统的特征提取方法不足以提取更高层次的抽象特征,为此提出一种栈式自编码融合极限学习机的药品鉴别方法,利用ELM代替SAE的反向微调和Softmax分类阶段,减少了SAE的训练时间,提高了SAE的应用能力。以不同厂商生产的非铝塑包装的头孢克肟片药品的近红外光谱为实例,在不同规模的数据集下,验证该算法,并与其它机器学习方法进行对比。实验结果表明,SAE-ELM减少了SAE的训练时间,具有较高分类准确率和稳定性。
Near infrared spectroscopy data are high dimensional,and the traditional feature extraction method is not enough to extract higher-level abstract features.To solve the problems,a drug discrimination method based on stacked auto encoders(SAE-ELM)fusion extreme learning machine was proposed.By introducing ELM instead of the back fine-tuning and Softmax classification stages of SAE,the training time was reduced and the ability of applications of SAE was improved.Using NIRS of cefixime tablet with non-Aluminum packaged by different manufacturers with different sizes of data sets as an example to verify the proposed method,and compared to others machine methods,the result shows that SAE-ELM not only reduces the training time,but shows high classification accuracy and stability.
Near infrared spectroscopy data are high dimensional,and the traditional feature extraction method is not enough to extract higher-level abstract features.To solve the problems,a drug discrimination method based on stacked auto encoders(SAE-ELM)fusion extreme learning machine was proposed.By introducing ELM instead of the back fine-tuning and Softmax classification stages of SAE,the training time was reduced and the ability of applications of SAE was improved.Using NIRS of cefixime tablet with non-Aluminum packaged by different manufacturers with different sizes of data sets as an example to verify the proposed method,and compared to others machine methods,the result shows that SAE-ELM not only reduces the training time,but shows high classification accuracy and stability.
引文
[1]Porep JU,Kammerer DR,Carle R.On-line application of near infrared(NIR)spectroscopy in food production[J].Trends in Food Science&Technology,2015,46(2):211-230.
[2]Askari MS,O’Rourke SM,Holden NM.Evaluation of soil quality for agricultural production using visible-near-infrared spectroscopy[J].Geoderma,2015,243(243):80-91.
[3]Gurzhieva AG,Elizarova TE, Morozova MA.Near-infrared spectroscopy for the analysis of solid dosage forms:Does the shell influence drug identification results[J].Pharmaceutical Chemistry Journal,2016,50(2):114-119.
[4]Deconinck E,SacréP,Coomans D,et al.Classification trees based on infrared spectroscopic data to discriminate between genuine and counterfeit medicines[J].Journal of pharmaceutical and Biomedical Analysis,2012,57(1):68-75.
[5]LIU Zhenbing,JIANG Shujie,YANG Huihua,et al.Drug discrimination by near infrared spectroscopy based on summation wavelet extreme learning machine[J].Spectroscopy and Spectral Analysis,2014,34(10):2815-2820(in Chinese).[刘振丙,蒋淑洁,杨辉华,等.基于波形叠加极限学习机的近红外光谱药品鉴别[J].光谱学与光谱分析,2014,34(10):2815-2820.]
[6]Huihua Yang,Baichao Hu,Xipeng Pan,et al.Deep belief networks based drug identification using near infrared spectroscopy[J].Journal of Innovative Optical Health Sciences,2016,10(2):1630011.
[7]YANG Huihua,LUO Zhichao,JIANG Shujie,et al.Sparse denoising autoencoder application in identification of counterfeit pharmaceutical[J].Spectroscopy&Spectral Analysis,2016,36(9):2774-2779(in Chinese).[杨辉华,雒志超,蒋淑洁,等.稀疏降噪自编码算法用于近红外光谱鉴别真假药的研究[J].光谱学与光谱分析,2016,36(9):2774-2779.]
[8]Maria J,Amaro J,Falcao G,et al.Stacked autoencoders using low-power accelerated architectures for object recognition in autonomous systems[J].Neural Processing Letters,2016,43(2):445-458.
[9]Huang GB,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification[J].IEEE Transactions on Systems Man&Cybernetics Part B,2012,42(2):513-529.
[10]Tang XS,Hao K,Wei H,et al.Using line segments to train multi-stream stacked auto encoders for image classification[J].Pattern Recognition Letters,2017,94(C):55-61.
[11]Tang J,Deng C,Huang GB.Extreme learning machine for multilayer perceptron[J].IEEE Transactions on Neural Networks&Learning Systems,2017,27(4):809-821.
[12]Feng G,Lan Y,Zhang X,et al.Dynamic adjustment of hidden node parameters for extreme learning machine[J].IEEE Transactions on Cybernetics,2015,45(2):279-288.
[2]Askari MS,O’Rourke SM,Holden NM.Evaluation of soil quality for agricultural production using visible-near-infrared spectroscopy[J].Geoderma,2015,243(243):80-91.
[3]Gurzhieva AG,Elizarova TE, Morozova MA.Near-infrared spectroscopy for the analysis of solid dosage forms:Does the shell influence drug identification results[J].Pharmaceutical Chemistry Journal,2016,50(2):114-119.
[4]Deconinck E,SacréP,Coomans D,et al.Classification trees based on infrared spectroscopic data to discriminate between genuine and counterfeit medicines[J].Journal of pharmaceutical and Biomedical Analysis,2012,57(1):68-75.
[5]LIU Zhenbing,JIANG Shujie,YANG Huihua,et al.Drug discrimination by near infrared spectroscopy based on summation wavelet extreme learning machine[J].Spectroscopy and Spectral Analysis,2014,34(10):2815-2820(in Chinese).[刘振丙,蒋淑洁,杨辉华,等.基于波形叠加极限学习机的近红外光谱药品鉴别[J].光谱学与光谱分析,2014,34(10):2815-2820.]
[6]Huihua Yang,Baichao Hu,Xipeng Pan,et al.Deep belief networks based drug identification using near infrared spectroscopy[J].Journal of Innovative Optical Health Sciences,2016,10(2):1630011.
[7]YANG Huihua,LUO Zhichao,JIANG Shujie,et al.Sparse denoising autoencoder application in identification of counterfeit pharmaceutical[J].Spectroscopy&Spectral Analysis,2016,36(9):2774-2779(in Chinese).[杨辉华,雒志超,蒋淑洁,等.稀疏降噪自编码算法用于近红外光谱鉴别真假药的研究[J].光谱学与光谱分析,2016,36(9):2774-2779.]
[8]Maria J,Amaro J,Falcao G,et al.Stacked autoencoders using low-power accelerated architectures for object recognition in autonomous systems[J].Neural Processing Letters,2016,43(2):445-458.
[9]Huang GB,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification[J].IEEE Transactions on Systems Man&Cybernetics Part B,2012,42(2):513-529.
[10]Tang XS,Hao K,Wei H,et al.Using line segments to train multi-stream stacked auto encoders for image classification[J].Pattern Recognition Letters,2017,94(C):55-61.
[11]Tang J,Deng C,Huang GB.Extreme learning machine for multilayer perceptron[J].IEEE Transactions on Neural Networks&Learning Systems,2017,27(4):809-821.
[12]Feng G,Lan Y,Zhang X,et al.Dynamic adjustment of hidden node parameters for extreme learning machine[J].IEEE Transactions on Cybernetics,2015,45(2):279-288.