A smart sensing platform for the discrimination of human movement

This thesis documents the design, implementation and testing of a smart sensing platform that is able to discriminate between differences or small changes in a persons walking. The distributive tactile sensing method is used to monitor the deflection of the platform surface using just a small number of sensors and, through the use of neural networks, infer the characteristics of the object in contact with the surface. The thesis first describes the development of a mathematical model which uses a novel method to track the position of a moving load as it passes over the smart sensing surface. Experimental methods are then described for using the platform to track the position of swinging pendulum in three dimensions. It is demonstrated that the method can be extended to that of real-time measurement of balance and sway of a person during quiet standing. Current classification methods are then investigated for use in the classification of different gait patterns, in particular to identify individuals by their unique gait pattern. Based on these observations, a novel algorithm is developed that is able to discriminate between abnormal and affected gait. This algorithm, using the distributive tactile sensing method, was found to have greater accuracy than other methods investigated and was designed to be able to cope with any type of gait variation. The system developed in this thesis has applications in the area of medical diagnostics, either as an initial screening tool for detecting walking disorders or to be able to automatically detect changes in gait over time. The system could also be used as a discrete biometric identification method, for example identifying office workers as they pass over the surface.

Non-invasive respiratory monitoring using long-period fiber grating sensors

In non-invasive ventilation, continuous monitoring of respiratory volumes is essential. Here, we present a method for the measurement of respiratory volumes by a single fiber-grating sensor of bending and provide the proof-of-principle by applying a calibration-test measurement procedure on a set of 18 healthy volunteers. Results establish a linear correlation between a change in lung volume and the corresponding change in a local thorax curvature. They also show good sensor accuracy in measurements of tidal and minute respiratory volumes for different types of breathing. The proposed technique does not rely on the air flow through an oronasal mask or the observation of chest movement by a clinician, which distinguishes it from the current clinical practice. © 2014 Optical Society of America.

Rib-cage-movement measurements as a potential new trigger signal in non-invasive mechanical ventilation

Non-invasive ventilation performed through an oronasal mask is a standard in clinical and homecare mechanical ventilation. Besides all its advantages, inevitable leaks through the mask cause errors in the feedback information provided by the airflow sensor and, hence, patient-ventilator asynchrony with multiple negative consequences. Here we investigate a new way to provide a trigger to the ventilator. The method is based on the measurement of rib cage movement at the onset of inspiration and during breathing by fibre-optic sensors. In a series of simultaneous measurements by a long-period fibre grating sensor and pneumotachograph we provide the statistical evidence of the 200 ms lag of the pneumo with respect the fibre-optic signal. The lag is registered consistently across three independent delay metrics. Further, we discuss exceptions from this trend and identify the needed improvements to the proposed fibre-sensing scheme.