Learn More
An important way to make large training sets is to gather noisy labels from crowds of nonexperts. We propose a minimax entropy principle to improve the quality of these labels. Our method assumes that labels are generated by a probability distribution over workers, items, and labels. By maximizing the entropy of this distribution, the method naturally(More)
Statistical models on full and partial rankings of n items are often of limited practical use for large n due to computational consideration. We explore the use of non-parametric models for partially ranked data and derive efficient procedures for their use for large n. The derivations are largely possible through combinatorial and algebraic manipulations(More)
The popular bag of words assumption represents a document as a histogram of word occurrences. While computationally efficient, such a representation is unable to maintain any sequential information. We present an effective sequential document representation that goes beyond the bag of words representation and its n-gram extensions. This representation uses(More)
Clinical study found that early detection and intervention are essential for preventing clinical deterioration in patients, for patients both in intensive care units (ICU) as well as in general wards but under real-time data sensing (RDS). In this paper, we develop an integrated data mining approach to give early deterioration warnings for patients under(More)
UNLABELLED Human beclin 1 is the first identified mammalian gene to induce autophagy. It is commonly expressed at reduced levels in breast tumors; however, it is overexpressed in hepatitis B virus (HBV)-infected cancerous liver tissues. To expose the possible mechanism and biological significance of this up-regulation of beclin 1, we investigated the(More)
BACKGROUND Emergence agitation is a common problem in pediatric anesthesia, especially after sevoflurane induction and maintenance anesthesia. The purpose of this study was to investigate the effect of sufentanil to reduce emergence agitation after sevoflurane anesthesia in children undergoing adenotonsillectomy compared with fentanyl. METHODS One hundred(More)
BACKGROUND AND AIMS There is an imbalance between Th1 and Th2 in the development and progression of atherosclerosis and in patients with acute coronary syndrome (ACS) including acute myocardial infarction (AMI) and unstable angina. T helper cell type 3 (Th3), which primarily secretes transforming growth factor beta-1 (TGF-beta1), has been shown to inhibit(More)
Documents and other categorical valued time series are often characterized by the frequencies of short range sequential patterns such as n-grams. This representation converts sequential data of varying lengths to high dimensional histogram vectors which are easily modeled by standard statistical models. Unfortunately, the histogram representation ignores(More)
BACKGROUND CXCL16 has been shown to be involved in atherosclerotic lesion development, but its role in preexisting lesions is still unclear. This study aims to assess the effect of CXCL16 on the stability of preexisting lesions. METHODS We firstly measured plasma CXCL16 level in Apolipoprotein E-Knockout (ApoE KO) mice with either high-cholesterol diet(More)