Accuracy of discriminant analysis methods to classify activities of subjects with Parkinson's Disease using wearable sensors

Sanpablo, Alberto Isaac Pérez; Penaloza, Alicia Meneses; Fresnedo, Jimena Quinzaños; Roiz, Virginia Bueyes; Uriostegui, Ivett Quiñones; Arenas, Claudia Hernández

doi:10.1016/j.apmr.2021.07.797

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para esta exploración de la base de datos original, se extrajeron las observaciones 1 a 126,073; pertenecientes al 80 % de sujetos [9] . Dichas señales se guardaron en una nueva base de datos denominada "mat01" y las señales del 20 % de sujetos restante (variables a 179,755) se guardaron en "mat02".…”

Section: Diseño Rna Tipo Perceptrón Multicapaunclassified

“…La evaluación mediante sensores inerciales de los signos motores y fluctuaciones, pueden proporcionar retroalimentación objetiva y confiable sobre los efectos del manejo terapéutico [6] . A la fecha este tipo de sensores han sido estudiados para detectar actividades de la vida diaria, principalmente caminar y en pocos casos acostarse, sentarse y mantenerse de pie [7][8] [9] . En estas investigaciones se han utilizado diversos tipos, números, ubicaciones de sensores y métodos de clasificación variables sin alcanzar un consenso a la fecha.…”

Section: Introductionunclassified

“…Principalmente se ha utilizado una configuración de un sensor predominantemente en la cadera y de tipo acelerómetro [7][8] [9] . Aunque los primeros experimentos se concentraban en la validación de laboratorio de los registros obtenidos con los sensores inerciales, actualmente el interés parece concentrarse en probar nuevos métodos de clasificación centrados en un propósito clínico, con precisiones reportadas entre un 55.9% y 90.8% [8][9] [10] .…”

Section: Introductionunclassified

See 2 more Smart Citations

Classification of Daily Living Activities in subjects with Parkinson’s Disease using Artificial Neural Networks

Rodriguez Montero,

Ambrosio Bastián,

Pérez Sanpablo

2023

Rev. Mex. Ing. Biomed.

View full text Add to dashboard Cite

This paper is a proposal to contribute with health specialists to enrich the follow-up and support systems in patients with Parkinson's by identifying and classifying Daily Living Activities (DLAs) using Artificial Neural Networks programmed in Python language. The proposed method of supervised learning allowed the classification of 6 DLAs through 22 signals obtained from the application of Principal Component Analysis, creating a database used to train a Multilayer Perceptron. This model achieved an approximation of classification with 93% of the F1-score. The present study demonstrates the versatility of ANNs based on MLP combined with the PCA technique since, even in an unbalanced database such as the one used, it allows excellent values to be achieved in the F1-score measure. The use of Artificial Intelligence and other tools applied in this work may eventually help specialists to perform a more accurate assessment in the monitoring of rehabilitation for patients with Parkinson's disease by improving records and thus avoiding subjectivity in the interpretation of treatment results.

show abstract

Section: Diseño Rna Tipo Perceptrón Multicapaunclassified

Section: Introductionunclassified