Sensor Selection for Tidal Volume Determination via Linear Regression-Impact of Lasso versus Ridge Regression.

The measurement of respiratory volume based on upper body movements by means of a smart shirt is increasingly requested in medical applications. This research used upper body surface motions obtained by a motion capture system, and two regression methods to determine the optimal selection and placement of sensors on a smart shirt to recover respiratory parameters from benchmark spirometry values. The results of the two regression methods (Ridge regression and the least absolute shrinkage and selection operator (Lasso)) were compared. This work shows that the Lasso method offers advantages compared to the Ridge regression, as it provides sparse solutions and is more robust to outliers. However, both methods can be used in this application since they lead to a similar sensor subset with lower computational demand (from exponential effort for full exhaustive search down to the order of O (n2)). A smart shirt for respiratory volume estimation could replace spirometry in some cases and would allow for a more convenient measurement of respiratory parameters in home care or hospital settings.

Characterisation and Quantification of Upper Body Surface Motions for Tidal Volume Determination in Lung-Healthy Individuals.

Measurement of accurate tidal volumes based on respiration-induced surface movements of the upper body would be valuable in clinical and sports monitoring applications, but most current methods lack the precision, ease of use, or cost effectiveness required for wide-scale uptake. In this paper, the theoretical ability of different sensors, such as inertial measurement units, strain gauges, or circumference measurement devices to determine tidal volumes were investigated, scrutinised and evaluated. Sixteen subjects performed different breathing patterns of different tidal volumes, while using a motion capture system to record surface motions and a spirometer as a reference to obtain tidal volumes. Subsequently, the motion-capture data were used to determine upper-body circumferences, tilt angles, distance changes, movements and accelerations-such data could potentially be measured using optical encoders, inertial measurement units, or strain gauges. From these parameters, the measurement range and correlation with the volume signal of the spirometer were determined. The highest correlations were found between the spirometer volume and upper body circumferences; surface deflection was also well correlated, while accelerations carried minor respiratory information. The ranges of thorax motion parameters measurable with common sensors and the values and correlations to respiratory volume are presented. This article thus provides a novel tool for sensor selection for a smart shirt analysis of respiration.

Acoustic Indoor Localization Augmentation by Self-Calibration and Machine Learning.

An acoustic transmitter can be located by having multiple static microphones. These microphones are synchronized and measure the time differences of arrival (TDoA). Usually, the positions of the microphones are assumed to be known in advance. However, in practice, this means they have to be manually measured, which is a cumbersome job and is prone to errors. In this paper, we present two novel approaches which do not require manual measurement of the receiver positions. The first method uses an inertial measurement unit (IMU), in addition to the acoustic transmitter, to estimate the positions of the receivers. By using an IMU as an additional source of information, the non-convex optimizers are less likely to fall into local minima. Consequently, the success rate is increased and measurements with large errors have less influence on the final estimation. The second method we present in this paper consists of using machine learning to learn the TDoA signatures of certain regions of the localization area. By doing this, the target can be located without knowing where the microphones are and whether the received signals are in line-of-sight or not. We use an artificial neural network and random forest classification for this purpose.