Autor: DAVID MORALES MORALES

A Comparison of Multi-Label Text Classification Models in Research Articles Labeled With Sustainable Development Goals

Roberto Carlos Morales-Hernández Joaquín Gutiérrez Jaguey David Becerra-Alonso (2022)

"The classification of scientific articles aligned to Sustainable Development Goals is crucial for research institutions and universities when assessing their influence in these areas. Machine learning enables the implementation of massive text data classification tasks. The objective of this study is to apply Natural Language Processing techniques to articles from peer-reviewed journals to facilitate their classification according to the 17 Sustainable Development Goals of the 2030 Agenda. This article compares the performance of multi-label text classification models based on a proposed framework with datasets of different characteristics. The results show that the combination of Label Powerset (a transformation method) with Support Vector Machine (a classification algorithm) can achieve an accuracy of up to 87% for an imbalanced dataset, 83% for a dataset with the same number of instances per label, and even 91% for a multiclass dataset."

Artículo

Classification algorithm, multi-label text classification, problem transformation method, scientific articles, sustainable development goals, text classification INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES LENGUAJES ALGORÍTMICOS LENGUAJES ALGORÍTMICOS

Tensile behavior of 3D printed polylactic acid (PLA) based composites reinforced with natural fiber

Eliana M Agaliotis BALTAZAR DAVID AKE CONCHA ALEJANDRO MAY PAT Juan Pablo Morales Arias Celina Bernal Alex Valadez González Pedro Jesús Herrera Franco Gwenaelle Proust JUAN FRANCISCO KOH DZUL José Gonzalo Carrillo Baeza Emmanuel Alejandro Flores Johnson (2022)

Natural fiber-reinforced composite (NFRC) filaments for 3D printing were fabricated using polylactic acid (PLA) reinforced with 1–5 wt% henequen flour comprising particles with sizes between 90–250 μm. The flour was obtained from natural henequen fibers. NFRCs and pristine PLA specimens were printed with a 0° raster angle for tension tests. The results showed that the NFRCs’ measured density, porosity, and degree of crystallinity increased with flour content. The tensile tests showed that the NFRC Young’s modulus was lower than that of the printed pristine PLA. For 1 wt% flour content, the NFRCs’ maximum stress and strain to failure were higher than those of the printed PLA, which was attributed to the henequen fibers acting as reinforcement and delaying crack growth. However, for 2 wt% and higher flour contents, the NFRCs’ maximum stress was lower than that of the printed PLA. Microscopic characterization after testing showed an increase in voids and defects, with the increase in flour content attributed to particle agglomeration. For 1 wt% flour content, the NFRCs were also printed with raster angles of ±45° and 90° for comparison; the highest tensile properties were obtained with a 0° raster angle. Finally, adding 3 wt% content of maleic anhydride to the NFRC with 1 wt% flour content slightly increased the maximum stress. The results presented herein warrant further research to fully understand the mechanical properties of printed NFRCs made of PLA reinforced with natural henequen fibers. © 2022 by the authors.

Artículo

POLYLACTIC ACID (PLA) NATURAL FIBER HENEQUEN FIBER NATURAL FIBER REINFORCED COMPOSITE (NFRC) ADDITIVE MANUFACTURING 3D PRINTING MECHANICAL PROPERTY INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE MATERIALES PROPIEDADES DE LOS MATERIALES PROPIEDADES DE LOS MATERIALES