When using AdaBoost to select discriminant features from some feature space (e.g. Gabor feature space) for face recognition, cascade structure is usually adopted to leverage the asymmetry in the distribution of positi...When using AdaBoost to select discriminant features from some feature space (e.g. Gabor feature space) for face recognition, cascade structure is usually adopted to leverage the asymmetry in the distribution of positive and negative samples. Each node in the cascade structure is a classifier trained by AdaBoost with an asymmetric learning goal of high recognition rate but only moderate low false positive rate. One limitation of AdaBoost arises in the context of skewed example distribution and cascade classifiers: AdaBoost minimizes the classification error, which is not guaranteed to achieve the asymmetric node learning goal. In this paper, we propose to use the asymmetric AdaBoost (Asym- Boost) as a mechanism to address the asymmetric node learning goal. Moreover, the two parts of the selecting features and forming ensemble classifiers are decoupled, both of which occur simultaneously in AsymBoost and AdaBoost. Fisher Linear Discriminant Analysis (FLDA) is used on the selected fea- tures to learn a linear discriminant function that maximizes the separability of data among the different classes, which we think can improve the recognition performance. The proposed algorithm is dem- onstrated with face recognition using a Gabor based representation on the FERET database. Ex- perimental results show that the proposed algorithm yields better recognition performance than AdaBoost itself.展开更多
Reusable launch vehicle is an important way to realize fast,cheap and reliable space transportation.A combined cycle engine system provides a more efficient and flexible form of power.The investigation on the research...Reusable launch vehicle is an important way to realize fast,cheap and reliable space transportation.A combined cycle engine system provides a more efficient and flexible form of power.The investigation on the research status of the combined cycle engine technology,including basic principle,research programs and classification of structure is firstly discussed in this paper.Then the bilevel hierarchical and integrated parameters/trajectory overall optimization technologies are applied to improve the efficiency and effectiveness of overall vehicle design.Simulations are implemented to compare and analyze the effectiveness and adaptability of the two algorithms,in order to provide the technical reserves and beneficial references for further research on combined cycle engine reusable launch vehicles.展开更多
基金Supported by the NSFC-RGC Joint Research Fund (No.60518002)Talent Promotion Foundation of Anhui Province (No.2004Z026)The Science Research Fund of MOE-Microsoft Key Laboratory of Multimedia Com-puting and Communication (No.05071811)
文摘When using AdaBoost to select discriminant features from some feature space (e.g. Gabor feature space) for face recognition, cascade structure is usually adopted to leverage the asymmetry in the distribution of positive and negative samples. Each node in the cascade structure is a classifier trained by AdaBoost with an asymmetric learning goal of high recognition rate but only moderate low false positive rate. One limitation of AdaBoost arises in the context of skewed example distribution and cascade classifiers: AdaBoost minimizes the classification error, which is not guaranteed to achieve the asymmetric node learning goal. In this paper, we propose to use the asymmetric AdaBoost (Asym- Boost) as a mechanism to address the asymmetric node learning goal. Moreover, the two parts of the selecting features and forming ensemble classifiers are decoupled, both of which occur simultaneously in AsymBoost and AdaBoost. Fisher Linear Discriminant Analysis (FLDA) is used on the selected fea- tures to learn a linear discriminant function that maximizes the separability of data among the different classes, which we think can improve the recognition performance. The proposed algorithm is dem- onstrated with face recognition using a Gabor based representation on the FERET database. Ex- perimental results show that the proposed algorithm yields better recognition performance than AdaBoost itself.
文摘Reusable launch vehicle is an important way to realize fast,cheap and reliable space transportation.A combined cycle engine system provides a more efficient and flexible form of power.The investigation on the research status of the combined cycle engine technology,including basic principle,research programs and classification of structure is firstly discussed in this paper.Then the bilevel hierarchical and integrated parameters/trajectory overall optimization technologies are applied to improve the efficiency and effectiveness of overall vehicle design.Simulations are implemented to compare and analyze the effectiveness and adaptability of the two algorithms,in order to provide the technical reserves and beneficial references for further research on combined cycle engine reusable launch vehicles.