%0 Journal Article
%T SVM versus MAP on Accelerometer Data to Distinguish among Locomotor Activities Executed at Different Speeds
%A Maurizio Schmid
%A Francesco Riganti-Fulginei
%A Ivan Bernabucci
%A Antonino Laudani
%A Daniele Bibbo
%A Rossana Muscillo
%A Alessandro Salvini
%A Silvia Conforto
%J Computational and Mathematical Methods in Medicine
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/343084
%X Two approaches to the classification of different locomotor activities performed at various speeds are here presented and evaluated: a maximum a posteriori (MAP) Bayes¡¯ classification 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 descending) were recorded by an inertial sensor placed on the shank (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy young adults (age 25¨C35 yrs.). From each segmented activity epoch, sixteen features were chosen in the frequency and time domain. Dimension reduction was then performed through 2D Sammon¡¯s mapping. An Artificial Neural Network (ANN) was trained to mimic Sammon¡¯s mapping on the whole dataset. In the Bayes¡¯ approach, the two features were then fed to a Bayes¡¯ classifier that incorporates an update rule, while, in the SVM scheme, the ANN was considered as the kernel function of the classifier. Bayes¡¯ approach performed slightly better than SVM on both the training set (91.4% versus 90.7%) and the testing set (84.2% versus 76.0%), favoring the proposed Bayes¡¯ scheme as more suitable than the proposed SVM in distinguishing among the different monitored activities. 1. Introduction With the evolution of wireless communication technology, it is now possible to use inertial sensors (Inertial Measurement Units (IMU)) to gather and transmit over the air patterns associated with different activities performed by people moving in unconstrained environments [1]. IMUs allow to collect kinematic data through miniaturized accelerometers [2], gyroscopes [3], and possibly magnetometers [4]. Restricting the analysis to accelerometers, they are popular as fall detectors [5], as means to monitor physical activity [6], and also as tools to classify among different motor activities [7, 8]. They have also been shown as good predictors of the functional capacity in healthy adults [9] and elderly people [10] and of the level of energy expenditure [11, 12]. In these specific regards, since the accuracy in the prediction strongly depends on the kind of activity [13], classification of activities is often necessary as a preliminary step for energy expenditure estimation [14]. The utility of distinguishing between activities is also apparent when, for long term monitoring, the wearable device needs to transmit data in a compact way. Following this perspective, the general communication model of having raw data to be sent continuously from the sensing devices over the air,
%U http://www.hindawi.com/journals/cmmm/2013/343084/