Resumen: Las técnicas de data augmentation son esenciales para entrenar algoritmos de machine learning, donde el conjunto de datos inicial es más pequeño que lo requerido debido a la complejidad del modelo. En modelos de aprendizaje automático, la robustez del proceso de entrenamiento depende altamente de grandes volúmenes de datos etiquetados, los cuales son costosos de producir. Un enfoque eficaz para tratar con este problema es generar automáticamente nuevos ejemplos etiquetados usando técnicas de data augmentation. En el procesamiento del lenguaje natural, en particular en el idioma español, hay una falta de técnicas bien definidas que permitan incrementar un conjunto de datos. En este artículo, se proponen un conjunto de heurísticas para data augmentation en NLP, las cuales son aplicadas en el dominio de las revisiones de artículos científicos.Abstract: Data augmentation techniques are essential for training machine learning algorithms, where the initial data set is smaller than required due to the model complexity. In machine learning models, the robustness of the training process is highly dependent on large volumes of labeled data, which are expensive to produce. An effective approach to deal with this problem is to automatically generate new tagged examples using data augmentation techniques. In the processing of natural language, particularly in the Spanish language, there is a lack of well-defined techniques that allow increasing a set of data. In this article, we propose a set of heuristics for data augmentation in NLP, which are applied to the domain of reviews of scientific articles.
This paper describes the design and implementation of an alternative system to measure electrical parameters (voltage and current) in order to characterize MOSFET-Like sensors. To design a signal conditioning circuit is necessary to understand the sensor behavior, therefore knowing its characteristics is essential. As sensor manufacturers do not usually provide the whole technical information about them, a measurement system is proposed to obtain those sensor characteristics with the aim of modeling the sensor device. This system is based on a MCU which generates voltages and measures currents via an external transimpedance amplifier, and it is supported by a software platform developed upon python based open source tools. Such combination offers a low cost system to stimulate and capture sensor responses which could be processed later to extract the characteristic parameters. The system was tested principally with an Ion Sensitive Field Effect Transistor (ISFET) and results show the VDS-IDS and VGS curves obtained with it.
This paper describes the design and implementation of an alternative system to measure electrical parameters (voltage and current) in order to characterize MOSFET-Like sensors. To design a signal conditioning circuit is necessary to understand the sensor behavior, therefore knowing its characteristics is essential. As sensor manufacturers do not usually provide the whole technical information about them, a measurement system is proposed to obtain those sensor characteristics with the aim of modeling the sensor device. This system is based on a MCU which generates voltages and measures currents via an external transimpedance amplifier, and it is supported by a software platform developed upon python based open source tools. Such combination offers a low cost system to stimulate and capture sensor responses which could be processed later to extract the characteristic parameters. The system was tested principally with an Ion Sensitive Field Effect Transistor (ISFET) and results show the VDS-IDS and VGS curves obtained with it.
Andes virus (ANDV) is a rodent-borne zoonotic orthohantavirus endemic in South America that causes hantavirus pulmonary syndrome in humans, with up to a 40% case fatality rate. We developed ANDV mRNA vaccines based on the M segment of the viral genome that codes for glycoproteins Gn and Gc in a single open reading frame of glycoprotein precursor (GPC). We generated RNAs either with regular uridine (U-mRNA) or N1-methylpseudouridine (m1Ψ-mRNA). Mice immunized by either ANDV U-mRNA or m1Ψ-mRNA developed similar germinal center responses in lymph nodes. Single cell RNA and BCR sequencing of germinal center B cells from vaccinated mice demonstrated similar levels of activation, except an additional cluster of cells exhibiting strong interferon response that was present in animals vaccinated with U-mRNA but not m1Ψ-mRNA. Furthermore, similar immunoglobulin class-switching and somatic hypermutations were observed for the two vaccines. Golden Syrian hamsters were immunized intramuscularly with 2 doses of the vaccines on days 0 and 21. The titers of Gn/Gc-binding antibodies were moderately greater for U-mRNA construct than for m1Ψ-mRNA construct, however, the titers of ANDV-neutralizing antibodies were equivalent. Vaccinated animals were challenged with a lethal dose of ANDV at 21 days after the boost, along with the naïve control group. All control animals succumbed to infection whereas all vaccinated animals survived without any detectable disease or viral load. The data demonstrate the development of effective vaccines against ANDV and the lack of a significant effect of m1Ψ mRNA modification on immunogenicity and protection in the hamster model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.