Two approaches to the classi\fcation of dierent locomotor activities performed. at various speeds are here presented and compared: a maximum a posteriori. (MAP) Bayes' classi\fcation scheme and a Support Vector Machine (SVM). are applied on a 2D projection of 16 features extracted from accelerometer. data. The locomotor activities (level walking, stair climbing, and stair de-. scending) were recorded by a single-axis accelerometer placed on the shank. (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy. young adults (age 25-35 yrs.). From each segmented activity epoch, sixteen. features were chosen in the frequency and time domain. Dimension reduc-. tion was then performed through 2D Sammon's mapping. An Arti\fcial Neural. Network (ANN) was then trained to mimic Sammon's mapping on the whole. dataset. In the Bayes' approach, the two features were then fed to a Bayes'. classi\fer that incorporates an update rule, while, in the SVM scheme, the. ANN was considered as the kernel function of the classi\fer. Bayes' approach. performed slightly better than SVM on both the training set (91.4% vs. 90.7%). and the testing set (84.2% vs. 76.0%), favoring the proposed Bayes' scheme. as more suitable than the proposed SVM in distinguishing among the dierent. monitored activities.

SVM versus MAP on accelerometer data to distinguish among locomotor activities executed at different speeds

LAUDANI, ANTONINO;
2013-01-01

Abstract

Two approaches to the classi\fcation of dierent locomotor activities performed. at various speeds are here presented and compared: a maximum a posteriori. (MAP) Bayes' classi\fcation scheme and a Support Vector Machine (SVM). are applied on a 2D projection of 16 features extracted from accelerometer. data. The locomotor activities (level walking, stair climbing, and stair de-. scending) were recorded by a single-axis accelerometer placed on the shank. (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy. young adults (age 25-35 yrs.). From each segmented activity epoch, sixteen. features were chosen in the frequency and time domain. Dimension reduc-. tion was then performed through 2D Sammon's mapping. An Arti\fcial Neural. Network (ANN) was then trained to mimic Sammon's mapping on the whole. dataset. In the Bayes' approach, the two features were then fed to a Bayes'. classi\fer that incorporates an update rule, while, in the SVM scheme, the. ANN was considered as the kernel function of the classi\fer. Bayes' approach. performed slightly better than SVM on both the training set (91.4% vs. 90.7%). and the testing set (84.2% vs. 76.0%), favoring the proposed Bayes' scheme. as more suitable than the proposed SVM in distinguishing among the dierent. monitored activities.
2013
DAILY PHYSICAL-ACTIVITY
TRIAXIAL ACCELEROMETER
WEARABLE SENSORS
NEURAL-NETWORKS
DYNAMIC HYSTERESIS
ENERGY-EXPENDITURE
MIMO APPLICATIONS
OPTIMIZATION
SYSTEM
IDENTIFICATION
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/575464
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 16
social impact