|
Descripción
|
|
|---|---|
| This paper states the development of a machine learning model capable of classifying whether a person who has cardiac problems is able to escape from a building if it is affected by an earthquake. The data used to train the model was obtained from a simulation which considered some parameters like earthquake magnitude, BMI, cardiovascular disease, person location within the building, and current evacuation routes. The result of this implementation presents a model able to determine whether a person inside the building could or could not go out of it depending on the parameters previously described, for achieving this goal the use of supervised learning algorithms like KNN and Decision Tree was needed. Also, the case study presents two scenarios, the first scenario presents an evaluation metric at normal walking speed and the second at fast walking speed for a person to escape from an affected building. | |
|
Internacional
|
Si |
|
Nombre congreso
|
2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC) |
|
Tipo de participación
|
960 |
|
Lugar del congreso
|
Las Vegas, NV, USA |
|
Revisores
|
Si |
|
ISBN o ISSN
|
978-1-5386-4649-6 |
|
DOI
|
10.1109/CCWC.2018.8301618 |
|
Fecha inicio congreso
|
08/01/2018 |
|
Fecha fin congreso
|
10/10/2018 |
|
Desde la página
|
702 |
|
Hasta la página
|
706 |
|
Título de las actas
|
Proceeding of 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC) |