Learn More
This paper evaluates five supervised learning methods in the context of statistical spam filtering. We study the impact of different feature pruning methods and feature set sizes on each learner's performance using cost-sensitive measures. It is observed that the significance of feature selection varies greatly from classifier to classifier. In particular,(More)
Mutations in the MECP2 gene cause the autism spectrum disorder Rett syndrome (RTT). One of the most common MeCP2 mutations associated with RTT occurs at threonine 158, converting it to methionine (T158M) or alanine (T158A). To understand the role of T158 mutations in the pathogenesis of RTT, we generated knockin mice that recapitulate the MeCP2 T158A(More)
In this letter, we introduce an hidden Markov model (HMM)-based inversion system to recovery articulatory movements from speech acoustics. Trajectory HMMs are used as generative models for modelling articulatory data. Experiments on the MOCHA-TIMIT corpus indicate that the jointly trained acoustic-articulatory models are more accurate (lower RMS error) than(More)
The AMI(DA) system is a meeting room speech recognition system that has been developed and evaluated in the context of the NIST Rich Text (RT) evaluations. Recently, the “Distant Access” requirements of the AMIDA project have necessitated that the system operate in real-time. Another more difficult requirement is that the system fit into a live meeting(More)
Persistent organic pollutants (POPs) have been associated with a wide range of adverse health effects. Our case-control study was performed to explore the association between placental levels of selected POPs and risks for neural tube defects (NTDs) in a Chinese population with a high prevalence of NTDs. Cases included 80 fetuses or newborns with NTDs,(More)
Agent-based modeling (ABM) is an in silico technique that is being used in a variety of research areas such as in social sciences, economics and increasingly in biomedicine as an interdisciplinary tool to study the dynamics of complex systems. Here, we describe its applicability to integrative tumor biology research by introducing a multi-scale tumor(More)
BACKGROUND AND PURPOSE Intracranial hemorrhage (ICH) constitutes an important subtype of stroke. In a prior study, we found that the city of Changsha, People's Republic of China, not only had a high incidence of stroke, but also had almost the highest incidence of cerebral hemorrhage. To provide information for preventing and managing ICH, we undertook this(More)
In this review the roles of specific proteins during the first step of mineralization and nucleation are discussed. Mineralization is initiated inside the extracellular organelles-matrix vesicles (MVs). MVs, containing relatively high concentrations of Ca2+ and inorganic phosphate (Pi), create an optimal environment to induce the formation of hydroxyapatite(More)
Artificial selection played an important role in the origin of modern Glycine max cultivars from the wild soybean Glycine soja. To elucidate the consequences of artificial selection accompanying the domestication and modern improvement of soybean, 25 new and 30 published whole-genome re-sequencing accessions, which represent wild, domesticated landrace, and(More)
BACKGROUND To explore the potential role of natural-resistance-associated macrophage protein 1 (NRAMP1) gene, vitamin D receptor (VDR) gene, (human leukocyte antigen, (HLA-DRB1) HLA)-DRB1 gene, and HLA-DQB1 gene polymorphisms in susceptibility to tuberculosis (TB) in the Chinese Kazakh population. METHODS A case-control study was performed on the Chinese(More)