人工智能开始走进生活方方面面,并已经开始应用于各行各业。随着深度卷积神经网络的快速发展,深度卷积网络结构的优化、完善,深度卷积神经网络在图像识别、检测领域发挥着重要的作用。目前,给定相机图像来识别手机品牌的相机模式识别在...人工智能开始走进生活方方面面,并已经开始应用于各行各业。随着深度卷积神经网络的快速发展,深度卷积网络结构的优化、完善,深度卷积神经网络在图像识别、检测领域发挥着重要的作用。目前,给定相机图像来识别手机品牌的相机模式识别在图像溯源领域引起了很大的关注。本文首先应用当前流行的深度卷积神经网络(Goog Le Net、Res Net、Dense Net)在多种手机相机模式上进行识别,同时针对三种深度卷积网络在网络结构上、识别效果上进行分析比较,我们的实验结果证明了深度卷积神经网络在相机模式识别上的高效性。展开更多
Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness o...Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness of the system. To solve this problem, a novel integration method was proposed to combine hi-static ultra-wideband radar and cameras. In this recognition system, two cameras are used to localize the object＇s region, regions while a radar is used to obtain its 3D motion models on a mobile robot. The recognition results can be matched in the 3D motion library in order to recognize its motions. To confirm the effectiveness of the proposed method, the experimental results of recognition using vision sensors and those of recognition using the integration method were compared in different environments. Higher correct-recognition rate is achieved in the experiment.展开更多
This study presented an off-line identification method of induction motor (IM) parameters. Before startup,the inverter drive performed automatically a modified DC test, a locked-rotor test, a no-load test and a step-v...This study presented an off-line identification method of induction motor (IM) parameters. Before startup,the inverter drive performed automatically a modified DC test, a locked-rotor test, a no-load test and a step-voltage test to identify all the parameters of an induction motor. No manual operation and speed signals were required in the process. In order to obtain effective messages and improve the accuracy of identification, the discrete fast Fourier transform (DFFT) and the least-squares were used to process the signals of currents and voltages. A phase-voltage measuring method for motors was also proposed, which measured directly the actual conducting time of three upper switches in the inverter without need for a dead-time compensator. The validity, reliability and accuracy of the presented methods have been verified by the experiments on a VSI-fed IM drive system.展开更多
Enantiomer separation is one of the most important prerequisites for the investigation of environmental enantioselective behavior for chiral pesticides.The enantiomeric separation of three chiral pesticides,indoxacarb...Enantiomer separation is one of the most important prerequisites for the investigation of environmental enantioselective behavior for chiral pesticides.The enantiomeric separation of three chiral pesticides,indoxacarb,lambda-cyhalothrin,and simeconazole,were studied on cellulose tris-(3,5-dimethylphenyl-carbamate)-coated chiral stationary phase(CDMPC-CSP) using high-performance liquid chromatography under normal phase condition.The effects of chromatographic conditions,such as the mobile phase composition including the concentration and type of alcohol modifiers in hexane,flow rate and column temperature,on enantiomer separation were examined.The thermodynamical mechanism of enantioseparation and chiral recognition mechanism were discussed.Better separation were achieved using 20% n-propanol for indoxacarb,2% iso-butanol for lambda-cyhalothrin,and 20% iso-propanol for simeconazole as modifiers in hexane at 25℃ with the selectivity factor(a) of 1.69,1.82 and 1.70,respectively.The resolution factor(Rs) decreased as the flow rate increased from 0.4 to 1.1 ml·min-1.The retention factor(k') and selectivity factor for the enantiomers of analytes decreased as temperature increased.The lna-1/T plots for racemic chiral pesticides were linear in the range of 15-35℃ in hexane/iso-propanol and the chiral separation was controlled by enthalpy.Hydrogen bonding,π-π and dipole-dipole interactions between enantiomers and CDMPC-CSP play an important role in chiral identification,and the fitting of the asymmetric portion of solutes in a chiral cavity or channel of the CSP is also important.展开更多
The spread of social media has increased contacts of members of communities on the lntemet. Members of these communities often use account names instead of real names. When they meet in the real world, they will find ...The spread of social media has increased contacts of members of communities on the lntemet. Members of these communities often use account names instead of real names. When they meet in the real world, they will find it useful to have a tool that enables them to associate the faces in fiont of them with the account names they know. This paper proposes a method that enables a person to identify the account name of the person （＂target＂） in front of him/her using a smartphone. The attendees to a meeting exchange their identifiers （i.e., the account name） and GPS information using smartphones. When the user points his/her smartphone towards a target, the target＇s identifier is displayed near the target＇s head on the camera screen using AR （augmented reality）. The position where the identifier is displayed is calculated from the differences in longitude and latitude between the user and the target and the azimuth direction of the target from the user. The target is identified based on this information, the face detection coordinates, and the distance between the two. The proposed method has been implemented using Android terminals, and identification accuracy has been examined through experiments.展开更多
文摘人工智能开始走进生活方方面面,并已经开始应用于各行各业。随着深度卷积神经网络的快速发展,深度卷积网络结构的优化、完善,深度卷积神经网络在图像识别、检测领域发挥着重要的作用。目前,给定相机图像来识别手机品牌的相机模式识别在图像溯源领域引起了很大的关注。本文首先应用当前流行的深度卷积神经网络(Goog Le Net、Res Net、Dense Net)在多种手机相机模式上进行识别,同时针对三种深度卷积网络在网络结构上、识别效果上进行分析比较,我们的实验结果证明了深度卷积神经网络在相机模式识别上的高效性。
基金Supported by National Natural Science Foundation of China(No.50875193)
文摘Cameras can reliably detect human motions in a normal environment, but they are usually affected by sudden illumination changes and complex conditions, which are the major obstacles to the reliability and robustness of the system. To solve this problem, a novel integration method was proposed to combine hi-static ultra-wideband radar and cameras. In this recognition system, two cameras are used to localize the object＇s region, regions while a radar is used to obtain its 3D motion models on a mobile robot. The recognition results can be matched in the 3D motion library in order to recognize its motions. To confirm the effectiveness of the proposed method, the experimental results of recognition using vision sensors and those of recognition using the integration method were compared in different environments. Higher correct-recognition rate is achieved in the experiment.
文摘This study presented an off-line identification method of induction motor (IM) parameters. Before startup,the inverter drive performed automatically a modified DC test, a locked-rotor test, a no-load test and a step-voltage test to identify all the parameters of an induction motor. No manual operation and speed signals were required in the process. In order to obtain effective messages and improve the accuracy of identification, the discrete fast Fourier transform (DFFT) and the least-squares were used to process the signals of currents and voltages. A phase-voltage measuring method for motors was also proposed, which measured directly the actual conducting time of three upper switches in the inverter without need for a dead-time compensator. The validity, reliability and accuracy of the presented methods have been verified by the experiments on a VSI-fed IM drive system.
基金Supported by China Postdoctoral Science Fund (20090461007)Postdoctoral Research Funding Special Plans of Hunan(2010RC4025)Graduate Innovation Research Project of Hunan (CX2010B295)
文摘Enantiomer separation is one of the most important prerequisites for the investigation of environmental enantioselective behavior for chiral pesticides.The enantiomeric separation of three chiral pesticides,indoxacarb,lambda-cyhalothrin,and simeconazole,were studied on cellulose tris-(3,5-dimethylphenyl-carbamate)-coated chiral stationary phase(CDMPC-CSP) using high-performance liquid chromatography under normal phase condition.The effects of chromatographic conditions,such as the mobile phase composition including the concentration and type of alcohol modifiers in hexane,flow rate and column temperature,on enantiomer separation were examined.The thermodynamical mechanism of enantioseparation and chiral recognition mechanism were discussed.Better separation were achieved using 20% n-propanol for indoxacarb,2% iso-butanol for lambda-cyhalothrin,and 20% iso-propanol for simeconazole as modifiers in hexane at 25℃ with the selectivity factor(a) of 1.69,1.82 and 1.70,respectively.The resolution factor(Rs) decreased as the flow rate increased from 0.4 to 1.1 ml·min-1.The retention factor(k') and selectivity factor for the enantiomers of analytes decreased as temperature increased.The lna-1/T plots for racemic chiral pesticides were linear in the range of 15-35℃ in hexane/iso-propanol and the chiral separation was controlled by enthalpy.Hydrogen bonding,π-π and dipole-dipole interactions between enantiomers and CDMPC-CSP play an important role in chiral identification,and the fitting of the asymmetric portion of solutes in a chiral cavity or channel of the CSP is also important.
文摘The spread of social media has increased contacts of members of communities on the lntemet. Members of these communities often use account names instead of real names. When they meet in the real world, they will find it useful to have a tool that enables them to associate the faces in fiont of them with the account names they know. This paper proposes a method that enables a person to identify the account name of the person （＂target＂） in front of him/her using a smartphone. The attendees to a meeting exchange their identifiers （i.e., the account name） and GPS information using smartphones. When the user points his/her smartphone towards a target, the target＇s identifier is displayed near the target＇s head on the camera screen using AR （augmented reality）. The position where the identifier is displayed is calculated from the differences in longitude and latitude between the user and the target and the azimuth direction of the target from the user. The target is identified based on this information, the face detection coordinates, and the distance between the two. The proposed method has been implemented using Android terminals, and identification accuracy has been examined through experiments.
