Vital Signs Monitoring and Gesture Recognition through IR-UWB Radar Sensors

Abstract

In this dissertation, we have focused on the application of IR-UWB technology in vital signs monitoring, gestures recognition for vehicular applications and mobile phone usage detection by the driver to avoid accidents due to the distraction of driver from the road while texting during driving. Non-invasive monitoring of the vital signs such as breathing and heart rate is very important in medical engineering. Non-invasive monitoring is extremely necessary in situations where it is difficult to use complicated wired connections, such as ECG monitoring for infants, burn victims or people buried during building collisions. The previous work regarding vital sign measurements through IR UWB has certain limitations i.e., the effect of random body motion on the vital signs has not been studied quantitatively and an algorithm for heart rate detection in the presence of strong breathing harmonics located close to the heart rate was missing. Therefore, we studied various random body movements (RBM) to investigate its effect on vital sign measurements. Our proposed algorithm is robust and it shown 6.67% improvements in avoiding the invalid estimates in the heart rate readings. Another application of the IR-UWB is the gesture recognition that gives better performance irrespective of lighting conditions and that do not evade the privacy of users unlike the camera. In this work, a real-time version of gesture recognition using only one radar sensor is implemented. In this study, we proposed a new hand-based gesture recognition algorithm that works robustly against changes in distance or direction while responding only to defined gestures by ignoring meaningless motions. The hand-based gesture recognition proposed in this work would be a key technology of future automobile user interfaces. In this dissertation, an algorithm is developed for detection of a mobile phone usage during driving. As texting on a mobile phone during driving may cause visual, manual or cognitive distraction of a driver. In order to reduce accidents caused by a distracted driver, we proposed an algorithm that can detect perfectly a driver's mobile phone usage even if there are various motions of the driver in the car or changes in background objects. This novel technique, which detect phone usage before a driver makes a mistake, may be very helpful in developing techniques for avoiding a car crash. Mobile phone detection algorithm showed 100 percent accuracy of detection inside the car.