The use of magnetic nanoparticle(MNP)-labeled immunochromatography test strips(ICTSs) is very important for point-ofcare testing(POCT). However, common diagnostic methods cannot accurately analyze the weak magnetic si...The use of magnetic nanoparticle(MNP)-labeled immunochromatography test strips(ICTSs) is very important for point-ofcare testing(POCT). However, common diagnostic methods cannot accurately analyze the weak magnetic signal from ICTSs, limiting the applications of POCT. In this study, an ultrasensitive multiplex biosensor was designed to overcome the limitations of capturing and normalization of the weak magnetic signal from MNPs on ICTSs. A machine learning model for sandwich assays was constructed and used to classify weakly positive and negative samples, which significantly enhanced the specificity and sensitivity. The potential clinical application was evaluated by detecting 50 human chorionic gonadotropin(HCG) samples and 59 myocardial infarction serum samples. The quantitative range for HCG was 1–1000 mIU mL^(-1) and the ideal detection limit was 0.014 mIU mL^(-1), which was well below the clinical threshold. Quantitative detection results of multiplex cardiac markers showed good linear correlations with standard values. The proposed multiplex assay can be readily adapted for identifying other biomolecules and also be used in other applications such as environmental monitoring, food analysis, and national security.展开更多
针对步态识别在反恐、安防领域亟待解决的小样本问题,提出了一种基于深度卷积神经网络(convolutional and neural network,CNN)和DLTL(dual learning and transfer learning)的步态虚拟样本生成方法。首先用基于VGG19的深度卷积神经网...针对步态识别在反恐、安防领域亟待解决的小样本问题,提出了一种基于深度卷积神经网络(convolutional and neural network,CNN)和DLTL(dual learning and transfer learning)的步态虚拟样本生成方法。首先用基于VGG19的深度卷积神经网络模型低层响应提取步态风格特征图,然后利用基于对抗网络的对偶学习(dual learning,DL)对风格特征图进行风格训练,得到风格特征模型;其次利用VGG19模型的高层响应提取步态内容特征图,然后让步态内容特征图对风格特征模型中的风格特征进行学习;最后使用迁移学习(transfer learning,TL)获得步态虚拟偏移样本。实验结果表明,经过DLTL风格学习生成的步态虚拟样本虽然整体风格发生改变,但人体步态特征没有改变,可有效扩充小样本容量;当虚拟样本增加到一定数量时,步态识别率有所提升。该方法与现有步态虚拟样本生成方法进行对比实验,结果表明该算法优于现有方法,能够大量生成虚拟样本且稳定提高步态识别的识别率。展开更多
Free chlorine is one of the key water quality parameters in tap water.However,a free chlorine sensor with the characteristics of batch processing,durability,antibiofouling/antiorganic passivation and in situ monitorin...Free chlorine is one of the key water quality parameters in tap water.However,a free chlorine sensor with the characteristics of batch processing,durability,antibiofouling/antiorganic passivation and in situ monitoring of free chlorine in tap water continues to be a challenging issue.In this paper,a novel silicon-based electrochemical sensor for free chlorine that can self-clean and be mass produced via microfabrication technique/MEMS(Micro-Electro-Mechanical System)is proposed.A liquid-conjugated Ag/AgCI reference electrode is fabricated,and electrochemically stable BDD/Pt is employed as the working/counter electrode to verify the effectiveness of the as-fabricated sensor for free chlorine detection.The sensor demonstrates an acceptable limit of detection(0.056 mg/L)and desirable linearity(R^(2)=0.998).Particularly,at a potential of+2.5 V,hydroxyl radicals are generated on the BBD electrode by electrolyzing water,which then remove the organic matter attached to the surface of the sensor though an electrochemical digestion process.The performance of the fouled sensor recovers from 50.2 to 94.1%compared with the initial state after self-cleaning for 30 min.In addition,by employing the MEMS technique,favorable response consistency and high reproducibility(RSD<4.05%)are observed,offering the opportunity to mass produce the proposed sensor in the future.A desirable linear dependency between the pH,temperature,and flow rate and the detection of free chlorine is observed,ensuring the accuracy of the sensor with any hydrologic parameter.The interesting sensing and selfcleaning behavior of the as-proposed sensor indicate that this study of the mass production of free chlorine sensors by MEMS is successful in developing a competitive device for the online monitoring of free chlorine in tap water.展开更多
基金support by the National Key Research and Development Program of China (Grant Nos. 2017FYA0205301, and 2017FYA0205303)the National Natural Science Foundation of China (Grant Nos. 81571835 and 81672247)+3 种基金National Key Research and Development Program of China (No. 2017YFA0205303)National Key Basic Research Program (973 Project) (No. 2015CB931802)"13th Five-Year Plan" Science and Technology Project of Jilin Province Education Department (No. JJKH20170410K)Shanghai Science and Technology Fund (No. 15DZ2252000)
文摘The use of magnetic nanoparticle(MNP)-labeled immunochromatography test strips(ICTSs) is very important for point-ofcare testing(POCT). However, common diagnostic methods cannot accurately analyze the weak magnetic signal from ICTSs, limiting the applications of POCT. In this study, an ultrasensitive multiplex biosensor was designed to overcome the limitations of capturing and normalization of the weak magnetic signal from MNPs on ICTSs. A machine learning model for sandwich assays was constructed and used to classify weakly positive and negative samples, which significantly enhanced the specificity and sensitivity. The potential clinical application was evaluated by detecting 50 human chorionic gonadotropin(HCG) samples and 59 myocardial infarction serum samples. The quantitative range for HCG was 1–1000 mIU mL^(-1) and the ideal detection limit was 0.014 mIU mL^(-1), which was well below the clinical threshold. Quantitative detection results of multiplex cardiac markers showed good linear correlations with standard values. The proposed multiplex assay can be readily adapted for identifying other biomolecules and also be used in other applications such as environmental monitoring, food analysis, and national security.
文摘针对步态识别在反恐、安防领域亟待解决的小样本问题,提出了一种基于深度卷积神经网络(convolutional and neural network,CNN)和DLTL(dual learning and transfer learning)的步态虚拟样本生成方法。首先用基于VGG19的深度卷积神经网络模型低层响应提取步态风格特征图,然后利用基于对抗网络的对偶学习(dual learning,DL)对风格特征图进行风格训练,得到风格特征模型;其次利用VGG19模型的高层响应提取步态内容特征图,然后让步态内容特征图对风格特征模型中的风格特征进行学习;最后使用迁移学习(transfer learning,TL)获得步态虚拟偏移样本。实验结果表明,经过DLTL风格学习生成的步态虚拟样本虽然整体风格发生改变,但人体步态特征没有改变,可有效扩充小样本容量;当虚拟样本增加到一定数量时,步态识别率有所提升。该方法与现有步态虚拟样本生成方法进行对比实验,结果表明该算法优于现有方法,能够大量生成虚拟样本且稳定提高步态识别的识别率。
基金supported by a grant from the National Science Foundation of China(61871243).
文摘Free chlorine is one of the key water quality parameters in tap water.However,a free chlorine sensor with the characteristics of batch processing,durability,antibiofouling/antiorganic passivation and in situ monitoring of free chlorine in tap water continues to be a challenging issue.In this paper,a novel silicon-based electrochemical sensor for free chlorine that can self-clean and be mass produced via microfabrication technique/MEMS(Micro-Electro-Mechanical System)is proposed.A liquid-conjugated Ag/AgCI reference electrode is fabricated,and electrochemically stable BDD/Pt is employed as the working/counter electrode to verify the effectiveness of the as-fabricated sensor for free chlorine detection.The sensor demonstrates an acceptable limit of detection(0.056 mg/L)and desirable linearity(R^(2)=0.998).Particularly,at a potential of+2.5 V,hydroxyl radicals are generated on the BBD electrode by electrolyzing water,which then remove the organic matter attached to the surface of the sensor though an electrochemical digestion process.The performance of the fouled sensor recovers from 50.2 to 94.1%compared with the initial state after self-cleaning for 30 min.In addition,by employing the MEMS technique,favorable response consistency and high reproducibility(RSD<4.05%)are observed,offering the opportunity to mass produce the proposed sensor in the future.A desirable linear dependency between the pH,temperature,and flow rate and the detection of free chlorine is observed,ensuring the accuracy of the sensor with any hydrologic parameter.The interesting sensing and selfcleaning behavior of the as-proposed sensor indicate that this study of the mass production of free chlorine sensors by MEMS is successful in developing a competitive device for the online monitoring of free chlorine in tap water.
