Learn More
BACKGROUND Increased susceptibility for developing alcohol dependence (AD) might be related to structural differences in brain circuits that influence the salience of rewards and/or modify the efficiency of information processing. The role of the orbitofrontal cortex (OFC) in regulating emotional processing is increasingly being recognized along with its(More)
We study the problem of large-scale social identity linkage across different social media platforms, which is of critical importance to business intelligence by gaining from social data a deeper understanding and more accurate profiling of users. This paper proposes HYDRA, a solution framework which consists of three key steps: (I) modeling heterogeneous(More)
For large scale image data mining, a challenging problem is to design a method that could work efficiently under the situation of little ground-truth annotation and a mass of unlabeled or noisy data. As one of the major solutions, semi-supervised learning (SSL) has been deeply investigated and widely used in image classification, ranking and retrieval.(More)
BACKGROUND Suicide officially kills approximately 30,000 annually in the United States. Analysis of this leading public health problem is complicated by undercounting. Despite persisting socioeconomic and health disparities, non-Hispanic Blacks and Hispanics register suicide rates less than half that of non-Hispanic Whites. METHODS This cross-sectional(More)
A simultaneous and fast determination of 18 phthalic acid esters (PAEs) in edible vegetable oils was developed. After solvent extraction, the PAEs in the oil sample were further cleaned up by solid-phase extraction. After concentration, the extract was directly injected into gas chromatography tandem mass spectrometry (GC-MS/MS) in positive-ion electron(More)
Real-world problems usually exhibit dual-heterogeneity, i.e., every task in the problem has features from multiple views, and multiple tasks are related with each other through one or more shared views. To solve these multi-task problems with multiple views, we propose a shared structure learning framework, which can learn shared predictive structures on(More)
Recently, the sparse coding based codebook learning and local feature encoding have been widely used for image classification. The sparse coding model actually assumes the reconstruction error follows Gaussian or Laplacian distribution, which may not be accurate enough. Besides, the ignorance of spatial information during local feature encoding process also(More)