An efficient feature selection method for mobile devices with application to activity recognition

This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modelled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited. An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.

FDTD analysis of close-coupled 418 MHz radiating devices for human biotelemetry

This paper describes the finite-difference time-domain (FDTD) analysis of antenna-body interaction effects occurring when chest-mounted 418 MHz radio transmitters are used for medical telemetry applications. Whole-body software models (homogeneous, layered and tissue-segmented) were developed for an adult male subject. Using an electrically small (300 mm(2)) planar loop antenna, calculated radiation efficiencies ranged between 33.5% and 39.2% for a whole-body model, and between 60.7% and 66.1% for a torso; radiation patterns were found to be largely independent of model composition. The computed radiation efficiency for a 21.5 kg phantom representing a six-year-old female was within 1.1 dB of measured results (actual body mass 28 kg) and well-correlated azimuthal radiation patterns were noted.