Çevre farkındalığı tabanlı yaklaşımla taşınabilir bilgisayarlarda işaret tanıması hassasiyetinin arttırılması

Input capabilities (e.g. joystick, keypad) of handheld devices allow users to interact withthe user interface to access the information and mobile services. However, these inputcapabilities are very limited because of the mobile convenience. New input devices andinteraction techniques are needed for handheld devices. Gestural interaction with accelerometer sensor is one of the newest interaction techniques on mobile computing.In this thesis, we introduce solutions that can be used for automatically enhancing the gesturerecognition accuracy of accelerometer sensor, and as a standardized gesture library for gesturalinteraction on touch screen and accelerometer sensor.In this novel solution, we propose a framework that decides on suitable signal processingtechniques for acceleration sensor data for a given context of the user. First system recognizesthe context of the user using pattern recognition algorithm. Then, system automatically choosessignal filtering techniques for recognized context, and recognizes gestures. Gestures are alsostandardized for better usage.In this work, we also present several experiments which show the feasibility and effectivenessof our automated gesture recognition enhancement system.