Time filter

Source Type

Liu W.,China University of Petroleum - East China | Tao D.,Intelligent Systems Technology, Inc.
IEEE Transactions on Image Processing | Year: 2013

The rapid development of computer hardware and Internet technology makes large scale data dependent models computationally tractable, and opens a bright avenue for annotating images through innovative machine learning algorithms. Semisupervised learning (SSL) therefore received intensive attention in recent years and was successfully deployed in image annotation. One representative work in SSL is Laplacian regularization (LR), which smoothes the conditional distribution for classification along the manifold encoded in the graph Laplacian, however, it is observed that LR biases the classification function toward a constant function that possibly results in poor generalization. In addition, LR is developed to handle uniformly distributed data (or single-view data), although instances or objects, such as images and videos, are usually represented by multiview features, such as color, shape, and texture. In this paper, we present multiview Hessian regularization (mHR) to address the above two problems in LR-based image annotation. In particular, mHR optimally combines multiple HR, each of which is obtained from a particular view of instances, and steers the classification function that varies linearly along the data manifold. We apply mHR to kernel least squares and support vector machines as two examples for image annotation. Extensive experiments on the PASCAL VOC'07 dataset validate the effectiveness of mHR by comparing it with baseline algorithms, including LR and HR. © 1992-2012 IEEE.

Yeung A.T.,University of Hong Kong | Gu Y.-Y.,China University of Petroleum - East China
Journal of Hazardous Materials | Year: 2011

Electrochemical remediation is a promising remediation technology for soils contaminated with inorganic, organic, and mixed contaminants. A direct-current electric field is imposed on the contaminated soil to extract the contaminants by the combined mechanisms of electroosmosis, electromigration, and/or electrophoresis. The technology is particularly effective in fine-grained soils of low hydraulic conductivity and large specific surface area. However, the effectiveness of the technology may be diminished by sorption of contaminants on soil particle surfaces and various effects induced by the hydrogen ions and hydroxide ions generated at the electrodes. Various enhancement techniques have been developed to tackle these diminishing effects. A comprehensive review of these techniques is given in this paper with a view to providing useful information to researchers and practitioners in this field. © 2011 Elsevier B.V.

Tang X.M.,China University of Petroleum - East China
Science China Earth Sciences | Year: 2011

Rocks in earth's crust usually contain both pores and cracks. This phenomenon significantly affects the propagation of elastic waves in earth. This study describes a unified elastic wave theory for porous rock media containing cracks. The new theory extends the classic Biot's poroelastic wave theory to include the effects of cracks. The effect of cracks on rock's elastic property is introduced using a crack-dependent dry bulk modulus. Another important frequency-dependent effect is the "squirt flow" phenomenon in the cracked porous rock. The analytical results of the new theory demonstrate not only reduction of elastic moduli due to cracks but also significant elastic wave attenuation and dispersion due to squirt flow. The theory shows that the effects of cracks are controlled by two most important parameters of a cracked solid: crack density and aspect ratio. An appealing feature of the new theory is its maintenance of the main characteristics of Biot's theory, predicting the characteristics of Biot's slow wave and the effects of permeability on elastic wave propagation. As an application example, the theory correctly simulates the change of elastic wave velocity with gas saturation in a field data set. Compared to Biot theory, the new theory has a broader application scope in the measurement of rock properties of earth's shallow crust using seismic/acoustic waves. © 2011 Science China Press and Springer-Verlag Berlin Heidelberg.

An C.,University of Illinois at Urbana - Champaign | An C.,China University of Petroleum - East China | Peng S.,Argonne National Laboratory | Sun Y.,Argonne National Laboratory
Advanced Materials | Year: 2010

Figure Equotion Present Highly efficient plasmonic photocatalysts of AgCl:Ag hybrid nanoparticles are successfully synthesized via a one-pot synthetic approach involving a precipitation reaction followed by polyol reduction. The as-synthesized nanoparticles exhibit high catalytic performance under visible light and sunlight for decomposing organics, such as methylene blue. © 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Jian L.,China University of Petroleum - East China | Gao C.,Zhejiang University
IEEE Transactions on Industrial Electronics | Year: 2013

It poses a great challenge to control the blast furnace system, often meaning to control the components of the hot metal within acceptable boundary, such as the silicon content in hot metal. For this reason, this paper focuses on addressing the multiclass classification problem about the silicon change in hope of providing reasonable blast furnace control guidance. Through the proposed binary coding support vector machine (SVM) algorithm, a four-class problem, i.e., sharp descent, slight descent, sharp ascent, and slight ascent of the silicon content in hot metal, is reduced into two binary classification problems to solve. To heel, the confidence level about these classification results is also estimated. Reliable classification effect plus very few binary classifiers make the binary coding SVMs full of competitive power for practical applications, particularly when the confidence level is high. The four-class classification results can indicate not only the silicon change direction but also the rough silicon change amplitude, which can guide the blast furnace operators to determine the blast furnace control span together with the control direction in advance. © 1982-2012 IEEE.

Discover hidden collaborations