Gait detection and step counting using smartphone

The focus of this thesis is the detection of walking and running, followed by a step count. Testing is performed on signals of regular daily human activity that involve sections of running, walking or no activity. Those signals are logged using accelerometer in smartphone. The exact type of physical activity performed is distinguished by an average, variation coefficient and wave transformation methods. Basics statistic methods are used to quantify the number of steps taken during either walking or running. Algorithm for activity detection and algorithm for step counting are optimized and tested by a set of signals