RESUMEN
We have developed robust embedded algorithms for the real-time classification of activity detected by our wearable inertial device. We collected 224 h of accelerometric signals from 28 subjects [22 suffering from chronic obstructive pulmonary disease (COPD)] to develop and then evaluate our algorithms. We describe the process for determining the most robust parameters of the algorithms. Our results with COPD patients show the feasibility of conducting real-time classification of their activities in everyday situations, with high fidelity.
Asunto(s)
Actigrafía/métodos , Actividades Cotidianas/clasificación , Algoritmos , Monitoreo Ambulatorio/métodos , Enfermedad Pulmonar Obstructiva Crónica , Procesamiento de Señales Asistido por Computador , Acelerometría , Actigrafía/instrumentación , Adulto , Anciano , Estudios de Factibilidad , Femenino , Humanos , Masculino , Persona de Mediana Edad , Monitoreo Ambulatorio/instrumentación , Postura/fisiología , Curva ROC , Adulto JovenRESUMEN
We developed a low power kinematic sensor, ActimedARM, incorporating three-axis accelerometer and magnetometer, a microcontroller ARM3, a ZigBee wireless communication and µSD memory storage. With embedded algorithms it can detect in real time the postures of the subject. A preliminary assessment conducted on 12 subjects reached a 97% correct classification rate. The device exhibits 32 days of autonomy on a 3600 mAh capacity battery, which makes it convenient for field experiments in true daily life.
