Efectos del número de clases y resolución del mapa de presión en la clasificación de postura detallada en la cama
Autores: Fonseca, Luís; Ribeiro, Fernando; Metrôlho, José
Idioma: Inglés
Editor: MDPI
Año: 2023
Acceso abierto
Artículo científico
2023
Efectos del número de clases y resolución del mapa de presión en la clasificación de postura detallada en la cama
Categoría
Ingeniería y Tecnología
Subcategoría
Ingeniería de Sistemas
Palabras clave
Clasificación de posturas
Mapas de presión
Algoritmos de aprendizaje automático
Conjuntos de datos
Posturas
Precisión
Licencia
CC BY-SA – Atribución – Compartir Igual
Consultas: 36
Citaciones: Sin citaciones
La clasificación de posturas en la cama ha atraído un considerable interés de investigación y tiene un gran potencial para mejorar las aplicaciones de atención médica. Los trabajos recientes generalmente utilizan enfoques basados en mapas de presión, algoritmos de aprendizaje automático y se centran principalmente en encontrar soluciones para lograr una alta precisión en la clasificación de posturas. Typically, these solutions use different datasets with varying numbers of sensors and classify the four main postures (supine, prone, left-facing, and right-facing) or, in some cases, include some variants of those main postures. Following this, this article has three main objectives: fine-grained detection of postures of bedridden people, identifying a large number of postures, including small variations-consideration of 28 different postures will help to better identify the actual position of the bedridden person with a higher accuracy. The number of different postures in this approach is considerably higher than the of those used in any other related work; analyze the impact of pressure map resolution on the posture classification accuracy, which has also not been addressed in other studies; and use the PoPu dataset, a dataset that includes pressure maps from 60 participants and 28 different postures. The dataset was analyzed using five distinct ML algorithms (k-nearest neighbors, linear support vector machines, decision tree, random forest, and multi-layer perceptron). This study"s findings show that the used algorithms achieve high accuracy in 4-posture classification (up to 99% in the case of MLP) using the PoPu dataset, with lower accuracies when attempting the finer-grained 28-posture classification approach (up to 68% in the case of random forest). The results indicate that using ML algorithms for finer-grained applications is possible to specify the patient"s exact position to some degree since the parent posture is still accurately classified. Furthermore, reducing the resolution of the pressure maps seems to affect the classifiers only slightly, which suggests that for applications that do not need finer-granularity, a lower resolution might suffice.
Descripción
La clasificación de posturas en la cama ha atraído un considerable interés de investigación y tiene un gran potencial para mejorar las aplicaciones de atención médica. Los trabajos recientes generalmente utilizan enfoques basados en mapas de presión, algoritmos de aprendizaje automático y se centran principalmente en encontrar soluciones para lograr una alta precisión en la clasificación de posturas. Typically, these solutions use different datasets with varying numbers of sensors and classify the four main postures (supine, prone, left-facing, and right-facing) or, in some cases, include some variants of those main postures. Following this, this article has three main objectives: fine-grained detection of postures of bedridden people, identifying a large number of postures, including small variations-consideration of 28 different postures will help to better identify the actual position of the bedridden person with a higher accuracy. The number of different postures in this approach is considerably higher than the of those used in any other related work; analyze the impact of pressure map resolution on the posture classification accuracy, which has also not been addressed in other studies; and use the PoPu dataset, a dataset that includes pressure maps from 60 participants and 28 different postures. The dataset was analyzed using five distinct ML algorithms (k-nearest neighbors, linear support vector machines, decision tree, random forest, and multi-layer perceptron). This study"s findings show that the used algorithms achieve high accuracy in 4-posture classification (up to 99% in the case of MLP) using the PoPu dataset, with lower accuracies when attempting the finer-grained 28-posture classification approach (up to 68% in the case of random forest). The results indicate that using ML algorithms for finer-grained applications is possible to specify the patient"s exact position to some degree since the parent posture is still accurately classified. Furthermore, reducing the resolution of the pressure maps seems to affect the classifiers only slightly, which suggests that for applications that do not need finer-granularity, a lower resolution might suffice.