Análisis comparativo de algoritmos de aprendizaje supervisado para la detección de caídas
Autor:
Solórzano, Santigo
; Pozo, David
; Morales, Luis
; Villalonga, Claudia
Fecha:
2019Palabra clave:
Tipo de Ítem:
Articulo Revista IndexadaDirección web:
http://www.risti.xyz/index.php?option=com_content&view=article&id=32&Itemid=131&lang=esResumen:
La naturaleza y las condiciones propias del adulto mayor hacen que
éste sea propenso a enfermedades y situaciones en donde su integridad física puede
verse afectada; donde, las caídas son uno de los factores de mayor riesgo. En este
artículo como principal aporte, se realiza un análisis sobre el efecto de la reducción
del espacio de características usadas para el proceso de clasificación mediante la
aplicación de la Matriz de Pearson. Para tal efecto, se presenta un análisis comparativo
mediante métricas de 3 algoritmos: naive bayes, máquinas de soporte vectorial y
redes neuronales en la detección de caídas. Las señales utilizadas son aceleraciones
en tres ejes obtenidas de la base de datos del Institute of Communications and
Navigations correspondiente a muestras de 16 sujetos masculinos y femeninos de
entre 23 y 50 años. Los resultados muestran que naive bayes presenta el mejor
desempeño considerando una reducción en las características
Descripción:
The nature and conditions of the elderly make it prone to diseases and
situations where their physical integrity may be affected; where falls are one of the
highest risk factors. In this article as a main contribution, an analysis is carried
out on the effect of the reduction of the space of characteristics in the classification
process through the application of the Pearson Matrix. For this purpose, a
comparative analysis based on metrics of 3 algorithms is presented: naive bayes,
vector support machines and neural networks in the detection of falls. The signals
used are accelerations in three axes obtained from the database of the Institute of
Communications and Navigations corresponding to samples of 16 male and female
subjects between 23 and 50 years old. The results show that naive bayes has the best
performance considering the reduction in the characteristics
Este ítem aparece en la(s) siguiente(s) colección(es)
Estadísticas de uso
Año |
2012 |
2013 |
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
2022 |
2023 |
2024 |
Vistas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
117 |
125 |
96 |
97 |
116 |
Descargas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Multi-agent systems in the field of urbane-mobility: A Systematic Review
Ruiz de Gauna, David Eneko ; Villalonga, Claudia ; Sánchez, Luis Enrique (IEEE Latin America Transactions, 12/2020)Initiatives based on improving urban mobility havebeen traditionally a high priority. The introduction of the electric vehicle to solve the problems of congestion and pollution withincities has made it possible to solve ... -
Improving Wearable Activity Recognition via Fusion of Multiple Equally-Sized Data Subwindows
Banos, Oresti; Gálvez, Juan Manuel; Damas, Miguel; Guillén, Alberto; Herrera, Luis Javier; Pomares, Héctor; Rojas, Ignacio; Villalonga, Claudia (Lecture Notes in Computer Science, 2019)The automatic recognition of physical activities typically involves various signal processing and machine learning steps used to transform raw sensor data into activity labels. One crucial step has to do with the segmentation ... -
Semiautomatic Grading of Short Texts for Open Answers in Higher Education
de-la-Fuente-Valentín, Luis ; Verdú, Elena ; Padilla-Zea, Natalia ; Villalonga, Claudia; Blanco Valencia, Xiomara Patricia ; Baldiris, Silvia (Communications in Computer and Information Science, 2022)Grading student activities in online courses is a time-expensive task, especially with a high number of students in the course. To avoid a bottleneck in the continuous evaluation process, quizzes with multiple choice ...