Ανάπτυξη αλγόριθμου αναγνώρισης χειρονομιών σε χαμηλής κατανάλωσης Bluetooth τσιπ για εφαρμογές Internet-Of-Things
Development of gesture recognition algorithm in low-power Bluetooth chip for Internet-Of-Things applications
The current dissertation deals with the selection and modification of a pattern recognition algorithm that will be able to be used in devices with low power cpu and limited resources. As a demonstration vehicle, we choose the Dialog Semiconductors System-on-Chip SmartBond DA14580 that supports Bluetooth Low Energy and enables the development of Bluetooth 4.1 applications. The use of such an algorithm as it is, was impossible using the Smartbond DA14580 chip from Dialog Semiconductor. For this reason, we present in this paper all the modifications that were chosen and the techniques that were used in order to reduce the size of the code, the memory used and also to improve the execution time of the algorithm. Even though there are some restrictions in the recognition system, such as the fact that it is user- depended, we proved that there is a way to implement pattern recognition algorithms in such devices, leading the way for a new generation of devices that will provide the users with more capabilities.