Development of sensitive and specific multiplex PCR method for the detection of microcystin producing cyanobacteria in spirulina food supplements

Food Science and Biotechnology - Spirulina has emerged as the next-generation dietary supplement owing to its health benefits. Despite the advantages, there have been reports of contamination by...     

Design standardization of unit operations for reducing the capital intensity and cost of small-scale chemical processes

A methodology is proposed to reduce the cost and capital intensity of small-scale chemical processes by creating new opportunities for economies of numbers through standardizing the equipment designs across multiple processes. We depart from asynchronous design of single-processes and adopt a common-functionality based simultaneous design of multiple processes that use similar unit operations. A generalized cost function is used to appropriately balance the trade-offs between economies of scale and economies of numbers. An optimization-based framework for design standardization is developed and illustrated using two case studies. The first involves the simultaneous synthesis of methanol and ammonia processes, and the second addresses the optimal synthesis of multi-column natural gas liquid (NGL) fractionation processes for different natural gas sources. We observe that considerable reduction in capital intensity of small-scale processes is possible through equipment standardization.     

Learning with rationales for document classification

We present a simple and yet effective approach for document classification to incorporate rationales elicited from annotators into the training of any off-the-shelf classifier. We empirically show on several document classification datasets that our classifier-agnostic approach, which makes no assumptions about the underlying classifier, can effectively incorporate rationales into the training of multinomial naïve Bayes, logistic regression, and support vector machines. In addition to being classifier-agnostic, we show that our method has comparable performance to previous classifier-specific approaches developed for incorporating rationales and feature annotations. Additionally, we propose and evaluate an active learning method tailored specifically for the learning with rationales framework.     

Text-mining-based Fake News Detection Using Ensemble Methods

Machine Intelligence Research - Social media is a platform to express one’s views and opinions freely and has made communication easier than it was before. This also opens up an opportunity...     

Active learning: an empirical study of common baselines

Most of the empirical evaluations of active learning approaches in the literature have focused on a single classifier and a single performance measure. We present an extensive empirical evaluation of common active learning baselines using two probabilistic classifiers and several performance measures on a number of large datasets. In addition to providing important practical advice, our findings highlight the importance of overlooked choices in active learning experiments in the literature. For example, one of our findings shows that model selection is as important as devising an active learning approach, and choosing one classifier and one performance measure can often lead to unexpected and unwarranted conclusions. Active learning should generally improve the model’s capability to distinguish between instances of different classes, but our findings show that the improvements provided by active learning for one performance measure often came at the expense of another measure. We present several such results, raise questions, guide users and researchers to better alternatives, caution against unforeseen side effects of active learning, and suggest future research directions.     

Effect of PVP K30 and/or L-arginine on stability constant of etoricoxib-HPbetaCD inclusion complex: preparation and characterization of etoricoxib-HPbetaCD binary system

The effect of polyvinyl pyrrolidone (PVP) K30 and/or L-arginine on etoricoxib-HPbetaCD complex was investigated. The phase solubility profiles were classified as A(L)-type, both in absence or presence of auxiliary substances used. The apparent stability constant (K(c)) of binary complex obtained at room temperature, 371.80 +/- 2.61 M(-1), was decreased with the addition of PVP and arginine indicating no benefit of addition of auxiliary substances to promote higher complexation efficiency. Therefore, solid etoricoxib-HPbetaCD binary systems were prepared and characterized by proton nuclear magnetic resonance spectroscopy (1HNMR), X-ray powder diffractometry, Fourier transformation-infrared spectroscopy, and dissolution studies. Among all binary systems, a lyophilized product showed superior performance in enhancing dissolution of etoricoxib.     

Evidence-based uncertainty sampling for active learning

Active learning methods select informative instances to effectively learn a suitable classifier. Uncertainty sampling, a frequently utilized active learning strategy, selects instances about which the model is uncertain but it does not consider the reasons for why the model is uncertain. In this article, we present an evidence-based framework that can uncover the reasons for why a model is uncertain on a given instance. Using the evidence-based framework, we discuss two reasons for uncertainty of a model: a model can be uncertain about an instance because it has strong, but conflicting evidence for both classes or it can be uncertain because it does not have enough evidence for either class. Our empirical evaluations on several real-world datasets show that distinguishing between these two types of uncertainties has a drastic impact on the learning efficiency. We further provide empirical and analytical justifications as to why distinguishing between the two uncertainties matters.