Abstract: In a corpus of scientific articles such as a digital library, documents are connected by citations and one document plays two different roles in the corpus: document itself and a citation of other documents. A Bernoulli Process Topic (BPT) model is provided which models the corpus at two levels: document level and citation level. In the BPT model, each document has two different representations in the latent topic space associated with its roles. Moreover, the multi-level hierarchical structure of the citation network is captured by a generative process involving a Bernoulli process. The distribution parameters of the BPT model are estimated by a variational approximation approach.

Abstract: Semi-supervised learning plays an important role in machine learning and data mining. The semi-supervised learning problem is approached by developing semiparametric regularization, which attempts to discover the marginal distribution of the data to learn the parametric function through exploiting the geometric distribution of the data. This learned parametric function can then be incorporated into the supervised learning on the available labeled data as the prior knowledge. A semi-supervised learning approach is provided which incorporates the unlabeled data into the supervised learning by a parametric function learned from the whole data including the labeled and unlabeled data. The parametric function reflects the geometric structure of the marginal distribution of the data. Furthermore, the proposed approach which naturally extends to the out-of-sample data is an inductive learning method in nature.

Abstract: Combining multiple clusterings arises in various important data mining scenarios. However, finding a consensus clustering from multiple clusterings is a challenging task because there is no explicit correspondence between the classes from different clusterings. Provided is a framework based on soft correspondence to directly address the correspondence problem in combining multiple clusterings. Under this framework, an algorithm iteratively computes the consensus clustering and correspondence matrices using multiplicative updating rules. This algorithm provides a final consensus clustering as well as correspondence matrices that gives intuitive interpretation of the relations between the consensus clustering and each clustering from clustering ensembles. Extensive experimental evaluations demonstrate the effectiveness and potential of this framework as well as the algorithm for discovering a consensus clustering from multiple clusterings.

Abstract: Multimodal data mining in a multimedia database is addressed as a structured prediction problem, wherein mapping from input to the structured and interdependent output variables is learned.

Abstract: Relational clustering has attracted more and more attention due to its phenomenal impact in various important applications which involve multi-type interrelated data objects, such as Web mining, search marketing, bioinformatics, citation analysis, and epidemiology. A probabilistic model is presented for relational clustering, which also provides a principal framework to unify various important clustering tasks including traditional attributes-based clustering, semi-supervised clustering, co-clustering and graph clustering. The model seeks to identify cluster structures for each type of data objects and interaction patterns between different types of objects. Under this model, parametric hard and soft relational clustering algorithms are provided under a large number of exponential family distributions.

Abstract: Combining multiple clusterings arises in various important data mining scenarios. However, finding a consensus clustering from multiple clusterings is a challenging task because there is no explicit correspondence between the classes from different clusterings. Provided is a framework based on soft correspondence to directly address the correspondence problem in combining multiple clusterings. Under this framework, an algorithm iteratively computes the consensus clustering and correspondence matrices using multiplicative updating rules. This algorithm provides a final consensus clustering as well as correspondence matrices that gives intuitive interpretation of the relations between the consensus clustering and each clustering from clustering ensembles. Extensive experimental evaluations demonstrate the effectiveness and potential of this framework as well as the algorithm for discovering a consensus clustering from multiple clusterings.

Abstract: There is provided a hierarchical shadow detection system for color aerial images. The system performs well with highly complex images as well as images having different brightness and illumination conditions. The system consists of two hierarchical levels of processing. The first level involves, pixel level classification, through modeling the image as a reliable lattice and then maximizing the lattice reliability using the EM algorithm. Next, region level verification, through further exploiting the domain knowledge is performed. Further analyses show that the MRF model based segmentation is a special case of the pixel level classification model. A quantitative comparison of the system and a state-of-the-art shadow detection algorithm clearly indicates that the new system is highly effective in detecting shadow regions in an image under different illumination and brightness conditions.

Abstract: There is provided a hierarchical shadow detection system for color aerial images. The system performs well with highly complex images as well as images having different brightness and illumination conditions. The system consists of two hierarchical levels of processing. The first level involves, pixel level classification, through modeling the image as a reliable lattice and then maximizing the lattice reliability using the EM algorithm. Next, region level verification, through further exploiting the domain knowledge is performed. Further analyses show that the MRF model based segmentation is a special case of the pixel level classification model. A quantitative comparison of the system and a state-of-the-art shadow detection algorithm clearly indicates that the new system is highly effective in detecting shadow regions in an image under different illumination and brightness conditions.

Abstract: A teleconference system comprises VoIP server, a rootnode presider terminal, a first level conference element and a second level conference element. The first level conference element includes the rootnode presider terminal and at least one first participant terminals as childnode of the rootnode presider terminal, wherein at least one of the first participant terminals is the candidate to be selected as second level presider terminal. The second level conference element includes the second level presider terminal and at least one second participant terminals as childnode of the second level presider terminal. The VoIP server is coupled to the rootnode presider terminal, first participant terminals and second participant terminals.

Abstract: There is provided a hierarchical shadow detection system for color aerial images. The system performs well with highly complex images as well as images having different brightness and illumination conditions. The system consists of two hierarchical levels of processing. The first level involves, pixel level classification, through modeling the image as a reliable lattice and then maximizing the lattice reliability using the EM algorithm. Next, region level verification, through further exploiting the domain knowledge is performed. Further analysis show that the MRF model based segmentation is a special case of the pixel level classification model. A quantitative comparison of the system and a state-of-the-art shadow detection algorithm clearly indicates that the new system is highly effective in detecting shadow regions in an image under different illumination and brightness conditions.

Abstract: The present invention provides a system with virtual audio driver for the VoIP (voice over internet protocol) environment. The virtual audio driver is computer software, and it can be implemented by diverse possibilities. Including being implemented by different programming languages; supporting various operating systems (OS) and so on. It should be appreciated that the virtual audio driver is used for transferring the voice data, instead of producing the sounds. Besides, the present invention also provides a virtual telephone interface. After combining the virtual audio drivers and the virtual telephone interface with the VoIP client applications, users can simply answer VoIP calls from several VoIP client applications by single software.