OBJECTIVES The purpose was to examine the cardioprotective effects of recombinant P-selectin glycoprotein ligand-immunoglobulin (rPSGL-Ig) in ischemia-reperfusion injury by real-time myocardial contrast echocardiography (MCE). BACKGROUND P-selectin mediates leukocyte recruitment into areas of inflammation. METHODS Sixteen pigs underwent 45 min of left anterior descending coronary artery occ...

In this paper, we present the Maximum Normalized Likelihood Estimation (MNLE) algorithm and its application for discriminative training of HMMs for continuous speech recognition. The objective of this algorithm is to maximize the normalized frame likelihood of training data. Instead of gradient descent techniques usually applied for objective function optimization in other discriminative algori...

Epidermolysis bullosa simplex with migratory circinate erythema (EBS-MCE) is a rare EBS subtype characterised by migratory blistering lesions that resolve with brownish pigmentation. It is caused by a recurrent readthrough mutation, c.1649delG, in the tail of keratin 5. Here, we report a child with EBS-MCE and investigated the immunologic mechanisms underlying the migratory lesions in this pati...

This article shows that the Minimum Classification Error (MCE) criterion function commonly used for discriminative design of speech recognition systems is equivalent to a Parzen window based estimate of the theoretical Bayes classification risk. In this analysis, each training token is mapped to the center of a Parzen kernel in the domain of a suitably defined random variable. The kernels are s...

In this paper, we report our recent development of a novel discriminative learning technique which embeds the concept of discriminative margin into the well established minimum classification error (MCE) method. The idea is to impose an incrementally adjusted “margin” in the loss function of MCE algorithm so that not only error rates are minimized but also discrimination “robustness” between tr...

In this paper, we extend the Maximum Likelihood (ML) training algorithm to the Minimum classificnrtion Emor (MCE) training algorithm for optimal estimation of the state-dependent polynomial coefficients in the trended HMM [2]. The problem of automatic speech recognition is viewed as a discriminative dynamic data-fitting problem, where nlotiue (not absolute) closeness in fitting an array of dyna...

UNLABELLED Asthma patients have been reported to be sensitive to breathlessness, independent of the degree of airway obstruction. Paying attention and task performance may induce changes in breathing pattern and these in turn may mediate such a feeling. The present experiment investigates whether strained breathing induced by an arithmetic task was different in children with asthma compared to ...

Enhanced motor corticospinal excitability (MCE) in passive action observation is thought to signify covert motor resonance with the actions seen. Actions performed by others are an important social stimulus and thus, motor resonance is prevalent during social interaction. However, most studies employ simple/short snippets of recorded movements devoid of any real-life social context, which has r...

asynergic myocardium adjacent to the ischemic area, has been demonstrated in animal hearts, it is not known whether this zone exists in humans. Methods and Results. Myocardial contrast echocardiography (MCE) was performed before and during balloon inflation in the area of coronary stenosis by injecting contrast medium through the guiding catheter in 13 patients with effort angina who underwent ...

We attack the general problem of HMM-based speech recognizer design, and in particular, the problem of isolated letter recognition in the presence of background noise. The standard design method based on maximum likelihood (ML) is known to perform poorly when applied to isolated letter recognition. The more recent minimum classiication error (MCE) approach directly targets the ultimate design c...