A Machine-Learning-Based Touch Orientation Detection Method for Piezoelectric Touch Sensing in Noisy Environment
- 10 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (23) , 26373-26381
Abstract
Touch orientation detection is important for piezoelectric touch panels to stabilize force-voltage responsivities. Current touch orientation estimation techniques utilize machine learning algorithms for orientation classification. However, environmental noise could weaken the data quality which will result in a lowered detection accuracy. To address this issue, in this article, we present a noise robustness technique, in which different levels of noise data are injected into the training data. The performance of “dirty” data trained model exhibits a good performance (average mean absolute error (MAE) of 7.8 degrees) among signal-to-noise ratio (SNR) from 3 dB to 40 dB, indicating that an improved user experience can be obtained.Keywords
Funding Information
- National Natural Science Foundation (61803017, 61827802)
- Beihang University (KG12090401, ZG216S19C8)
This publication has 41 references indexed in Scilit:
- Stream water temperature prediction based on Gaussian process regressionExpert Systems with Applications, 2013
- Graphene-P(VDF-TrFE) Multilayer Film for Flexible ApplicationsACS Nano, 2013
- Short term wind speed prediction based on evolutionary support vector regression algorithmsExpert Systems with Applications, 2011
- An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests.Psychological Methods, 2009
- Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological PredictionEcosystems, 2006
- Classification and Regression Trees, Bagging, and Boosting2005
- Travel-Time Prediction With Support Vector RegressionIEEE Transactions on Intelligent Transportation Systems, 2004
- Accurate On-line Support Vector RegressionNeural Computation, 2003
- Analyzing baggingThe Annals of Statistics, 2002
- Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond1998