Regensburg 2022 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

O: Fachverband Oberflächenphysik

O 58: Poster Wednesday: New Methods and Developments, Frontiers of Electronic Structure Theory

O 58.2: Poster

Wednesday, September 7, 2022, 18:00–20:00, P4

Deep learning based signal processing for touch-sensitive surfaces — •Jakob Elsner, Viktor Fairuschin, and Thorsten Uphues — Institute for Sensor and Actuator Technology, Coburg, Germany

Touch-sensitive surfaces enable intuitive and efficient operation of electronic devices and eliminate the need for external peripherals and mechanical components, making touch technology increasingly important in the modern society. However, conventional touch technologies, i.e. capacitive, resistive or optical, are usually limited to non-metallic materials that hardly meet the stringent requirements for robustness and hygiene in a medical environment. Stainless steel is one of the most commonly used materials in medical fields due to its high strength, chemical resistance and excellent hygienic properties. In this work, we present a novel approach based on Lamb wave technology and deep learning analytics, and apply this new principle to design a stainless steel touch-sensitive surface. Compared to Rayleigh wave-based touch technology, our approach requires no additional reflective structures and involves only a single piezoelectric transducer used to monitor the entire surface, while position-sensitive information is extracted from raw Lamb wave signals using a trained deep neural network.