Projekte sind ein essenzieller Bestandteil des Curriculums von Mobile Computing. Die Studierenden bekommen die Möglichkeit, das im Zuge ihres Studiums erworbene theoretische Wissen selbst praktisch umzusetzen. Ein sowohl für StudentInnen als auch für Lehrende immer wieder spannendes Unterrichtskonzept, in dem schon erfolgreiche Startups wie z.B. runtastic und Butleroy ihre Anfänge gefunden haben.
Character Recognition with STABILO ErgoPen
The aspect of this project is to recognize handwritten characters which are written with a ballpoint-like digital pen in real-time. Characters which should be recognized are restricted to lowercase letters. The character recognition should be accomplished by utilizing machine learning models such as the Hidden Markov Model. HMMs are especially known for their application in reinforcement learning and temporal pattern recognition such as speech, handwriting, gesture recognition. Another option is the utilization of artificial neuronal networks such as LSTM (Long Short Term Memory) networks which are currently on everyone’s lips and provide better results compared to classical machine learning.
The system consists of two parts whereby the hardware (ErgoPen) is provided by CDE (Communication Data Engineering). The pen system allows the recording and analysis of handwritings, drawings and gesture movements on a solid ground. The pen is used to gather data while the user is writing with it. Motion data are transmitted via a Bluetooth Low Energy (BLE) wireless connection to a connected android device. When connected, the pen sends data every 60ms in byte stream format. From the gathered data distinct features are extracted and used to train machine learning models which are later used to recognize the written characters in real-time. The result is shown on the smartphone in the respective app.