Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution mat...Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching.Simultaneously,the discriminative information of both domains is also neglected,which is important for improving the performance on the target domain.In this paper,we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation(BDTFL).The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains.Therefore,balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes.At the same time,discriminative information is exploited to alleviate category confusion during feature matching.And with assistance of the category discriminative information captured from both domains,the source classifier can be transferred to the target domain more accurately and boost the performance of target classification.Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.展开更多
Traffic characteristics of several typical instant messager services under certain scenarios are firstly analyzed,based on real-time data collected in the commercial mobile network.Then criteria for the evaluation of ...Traffic characteristics of several typical instant messager services under certain scenarios are firstly analyzed,based on real-time data collected in the commercial mobile network.Then criteria for the evaluation of the efficiency of the mobile network for the transmission of packet services are proposed in both transport layer and physical layer over air interface.The transmission efficiency of IM services is evaluated and compared under the proposed criteria.Furthermore,a so-called smart resource adaptation algorithm is verified in the effectiveness of improving the wireless transmission efficiency.Finally,improvements to the smart resource adaptation are proposed to further improve the wireless transmission efficiency,and its effectiveness is verified by the calculations.展开更多
Quantitative structure-activity relationships (QSARs) for the toxicity of substituted phenols, anilines and nitrobenzenes to algae (Scenedesmus obliquus) have been studied. Chemicals were divided into polar narcotics ...Quantitative structure-activity relationships (QSARs) for the toxicity of substituted phenols, anilines and nitrobenzenes to algae (Scenedesmus obliquus) have been studied. Chemicals were divided into polar narcotics and electrophiles based on structure criteria according to the toxicity mechanisms of action. A good relationship between the toxicity and octanol/water partition coefficient (logP) was observed for the polar narcotic compounds. The results confirmed that hydrophobicity is the determining physicochemical parameter in modelling narcotics. However, no statistically significant mono-parametric QSAR models could be made from descriptors calculated in this study for all the compounds. In order to investigate the mechanisms of toxic action and develop QSAR models for all compounds, Abraham solvation descriptors were calculated from the program of Pharma-Algorithms. Stepwise regression produced a three-parameter QSAR model (polarizability/dipolarity, hydrogen-bond basicity and molecular volume) with a good statistical fit for all the compounds studied, which had square of the correlation coefficient R2=0.83. We have also developed an interpretable QSAR model by using parameter of logP, which represents the bio-uptake process, and polarizability/dipolarity (S), which represents the interaction of chemicals with the acceptor micromolecules (target receptor) at the active site. No hydrogen-bond interaction was observed between the chemicals and receptor micromolecules.展开更多
文摘Transfer learning aims to transfer source models to a target domain.Leveraging the feature matching can alleviate the domain shift effectively,but this process ignores the relationship of the marginal distribution matching and the conditional distribution matching.Simultaneously,the discriminative information of both domains is also neglected,which is important for improving the performance on the target domain.In this paper,we propose a novel method called Balanced Discriminative Transfer Feature Learning for Visual Domain Adaptation(BDTFL).The proposed method can adaptively balance the relationship of both distribution matchings and capture the category discriminative information of both domains.Therefore,balanced feature matching can achieve more accurate feature matching and adaptively adjust itself to different scenes.At the same time,discriminative information is exploited to alleviate category confusion during feature matching.And with assistance of the category discriminative information captured from both domains,the source classifier can be transferred to the target domain more accurately and boost the performance of target classification.Extensive experiments show the superiority of BDTFL on popular visual cross-domain benchmarks.
基金Supported by the National Natural Science Foundation of China(No.61301103)the Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions(No.CIT&TCD201504039)Funding Project for Academic Human Resources Development in Beijing Union University(No.BPHR2014A03,Rkl00201510)
文摘Traffic characteristics of several typical instant messager services under certain scenarios are firstly analyzed,based on real-time data collected in the commercial mobile network.Then criteria for the evaluation of the efficiency of the mobile network for the transmission of packet services are proposed in both transport layer and physical layer over air interface.The transmission efficiency of IM services is evaluated and compared under the proposed criteria.Furthermore,a so-called smart resource adaptation algorithm is verified in the effectiveness of improving the wireless transmission efficiency.Finally,improvements to the smart resource adaptation are proposed to further improve the wireless transmission efficiency,and its effectiveness is verified by the calculations.
基金Supported by the Northest Normal University Foundations (Grant Nos. 106111065202, 20080501)
文摘Quantitative structure-activity relationships (QSARs) for the toxicity of substituted phenols, anilines and nitrobenzenes to algae (Scenedesmus obliquus) have been studied. Chemicals were divided into polar narcotics and electrophiles based on structure criteria according to the toxicity mechanisms of action. A good relationship between the toxicity and octanol/water partition coefficient (logP) was observed for the polar narcotic compounds. The results confirmed that hydrophobicity is the determining physicochemical parameter in modelling narcotics. However, no statistically significant mono-parametric QSAR models could be made from descriptors calculated in this study for all the compounds. In order to investigate the mechanisms of toxic action and develop QSAR models for all compounds, Abraham solvation descriptors were calculated from the program of Pharma-Algorithms. Stepwise regression produced a three-parameter QSAR model (polarizability/dipolarity, hydrogen-bond basicity and molecular volume) with a good statistical fit for all the compounds studied, which had square of the correlation coefficient R2=0.83. We have also developed an interpretable QSAR model by using parameter of logP, which represents the bio-uptake process, and polarizability/dipolarity (S), which represents the interaction of chemicals with the acceptor micromolecules (target receptor) at the active site. No hydrogen-bond interaction was observed between the chemicals and receptor micromolecules.
