The substitution of conventional bench-top instrumentation by fully integrated lab-on-chip systems continues to be a challenge. The integration of microfluidics and integrated optics in glass is an important step towards this goal, forming the focus of this work [1]. In particular, excitation and detection of fluorescence emitted by labeled biomolecules flowing through a microfluidic channel is...

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...

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 propose a procedure for training a pronunciation network with criteria consistent with the optimality objectives for speech recognition systems. In particular, we describe a framework for using maximum likelihood(ML) and minimum classi cation error(MCE) criteria for pronunciation network optimization. The ML criterion is used to obtain an optimal structure for the pronunciatio...

abstract. today, there is no specific method or criterion for selecting contractors in the researches’ field. usually this selection is regarded as a matter of taste and as a result, there is no coordinated approach in the mentioned domain. sometimes, after signing the contract, the inappropriate selection became clear. the managers are in direct need of a pattern for selecting the contractors....

E-learning is a type of learning supported by information communication technology that improves the quality of teaching and learning. This paper explores how a group of 95 respondents consisted of administrative and academic staff, and post graduate students evaluated five elearning approaches by using multi-criteria methods. They were asked to assess the relative importance of five e-learning...

When evaluating data mining algorithms that are applied to solve real-world problems there are often several, conflicting criteria that need to be considered. We investigate the concept of generic multi-criteria (MC) classifier and algorithm evaluation and perform a comparison of existing methods. This comparison makes explicit some of the important characteristics of MC analysis and focuses on...