Machine Learning for Touch Localization on an Ultrasonic Lamb Wave Touchscreen

• Main Authors: Bahrami, S. (Author), Grondin, F. (Author), Masson, P. (Author), Moriot, J. (Author)
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: Access control; Computing time; Deep neural networks; Guided electromagnetic wave propagation; Human Machine Interface; human–machine interface; Localisation; machine earning; Machine earning; Machine-learning; Mean square error; signal processing; Signal processing; Signal-processing; Simple++; Surface waves; Touch technologies; touch technology; Ultrasonic guided wave; Ultrasonic lamb waves; ultrasonic wave; Ultrasonic waves
• Online Access: View Fulltext in Publisher

 Classification and regression employing a simple Deep Neural Network (DNN) are investigated to perform touch localization on a tactile surface using ultrasonic guided waves. A robotic finger first simulates the touch action and captures the data to train a model. The model is then validated with data from experiments conducted with human fingers. The localization root mean square errors (RMSE) in time and frequency domains are presented. The proposed method provides satisfactory localization results for most human–machine interactions, with a mean error of 0.47 cm and standard deviation of 0.18 cm and a computing time of 0.44 ms. The classification approach is also adapted to identify touches on an access control keypad layout, which leads to an accuracy of 97% with a computing time of 0.28 ms. These results demonstrate that DNN-based methods are a viable alternative to signal processing-based approaches for accurate and robust touch localization using ultrasonic guided waves. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.