# High Three-Dimensional Detection Accuracy in Piezoelectric-Based Touch Panel in Interactive Displays by Optimized Artificial Neural Networks

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Literature Review

_{i}is the induced polarization, and σ

_{jk}and d

_{ijk}denote the stress and piezoelectric coefficient, respectively. The coefficients remain the same for direct and inverse piezoelectric effects. The coefficients d

_{ijk}are symmetric in j and k [10]. Thus, Equation (1) can be simplified as follows:

## 3. Methodology

#### 3.1. Experimental Setup and Data Acquisition

#### 3.2. Pre-Processing and Dataset Preparation

#### 3.3. Pre-Processing Multi-Layers Neural Networks for Classification

## 4. Results and Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Gao, S.; Wu, X.; Ma, H.; Robertson, J.; Nathan, A. Ultrathin Multi-functional Graphene-pvdf Layers for Multi-dimensional Touch Interactivity for Flexible Displays. ACS Appl. Mater. Interfaces
**2017**, 9, 18410–18416. [Google Scholar] [CrossRef] [PubMed] - Gao, S.; Nathan, A. P-180: Force Sensing Technique for Capacitive Touch Panel. In SID Symposium Digest of Technical Papers; Wiley: Hoboken, NJ, USA, 2016; Volume 47, pp. 1814–1817. [Google Scholar]
- Vuorinen, T.; Zakrzewski, M.; Rajala, S.; Lupo, D.; Vanhala, J.; Palovuori, K. Printable, Transparent, and Flexible Touch Panels Working in Sunlight and Moist Environments. Adv. Funct. Mater.
**2015**, 24, 6340–6347. [Google Scholar] [CrossRef] - Park, W.; Yang, J.H.; Kang, C.G.; Lee, Y.G.; Hwang, H.J.; Cho, C. Characteristics of a Pressure Sensitive Touch Sensor Using a Piezoelectric pvdf-trfe/mos Stack. Nanotechnology
**2013**, 24, 475501. [Google Scholar] [CrossRef] [PubMed] - Bae, S.H.; Kahya, O.; Sharma, B.K.; Kwon, J.; Cho, H.J.; Ozyilmaz, B.; Ahn, J.H. Graphene-P (VDF-TrFE) Multilayer Film for Flexible Applications. ACS Nano
**2013**, 7, 3130–3138. [Google Scholar] [CrossRef] [PubMed] - Reynolds, K.; Petr, S.; Arnulf, G. Invited Paper: Touch and Display Integration with Force. In SID Symposium Digest of Technical Papers; Wiley: Hoboken, NJ, USA, 2016; Volume 47, pp. 617–620. [Google Scholar]
- Chu, X.; Liu, J.; Gao, R.; Chang, J.; Li, L. Design and Analysis of a Piezoelectric Material Based Touch Screen with Additional Pressure and Its Acceleration Measurement Functions. Smart Mater. Struct.
**2013**, 22, 125008. [Google Scholar] [CrossRef] - Gao, S.; Wu, L. Why Piezoelectric Based Force Sensing is not Successful in Interactive Displays? IEEE Consum. Electron. Mag.
**2019**, 8. in press. [Google Scholar] - Gao, S.; Duan, J.; Kitsos, V.; Selviah, D.R.; Nathan, A. User-Oriented Piezoelectric Force Sensing and Artificial Neural Networks in Interactive Displays. IEEE J. Electron. Device Soc.
**2018**, 6, 766–773. [Google Scholar] [CrossRef] - Gao, S.; Arcos, V.; Nathan, A. Piezoelectric vs. Capacitive Based Force Sensing in Capacitive Touch Panels. IEEE Access
**2016**, 4, 3769–3774. [Google Scholar] [CrossRef] - Manbachi, A.; Cobbold, R.S.C. Development and Application of Piezoelectric Materials for Ultrasound Generation and Detection. Ultrasound
**2011**, 19, 187–196. [Google Scholar] [CrossRef] - Nathan, A.; Henry, B. Microtransducer CAD: Physical and Computational Aspects (Computational Microelectronics); Springer: Vienna, Austria, 1999. [Google Scholar]
- Maseeh, F.; Schmidt, M.A.; Allen, M.G.; Senturia, S.D. Calibrated Measurements of Elastic Limit, Modulus, and the Residual Stress of Thin Films Using Micromachined Suspended Structures. In Proceedings of the IEEE Solid-State Sens and Actuator Workshop, Hilton Head Island, SC, USA, 6–9 June 1988. [Google Scholar]
- Mohammadi, B.; Yousefi, A.A.; Bellah, S.M. Effect of Tensile Strain Rate and Elongation on Crystalline Structure and Piezoelectric Properties of PVDF Thin Films. Polym. Test.
**2007**, 26, 42–50. [Google Scholar] [CrossRef] - Saketi, P.; Latifi, S.K.; Hirvonen, J.; Rajala, S.; Vehkaoja, A.; Salpavaara, T.; Lekkala, J.; Kallio, P. PVDF Microforce Sensor for the Measurement of Z-directional Strength in Paper Fiber Bonds. Sens. Actuators A Phys.
**2015**, 222, 194–203. [Google Scholar] [CrossRef] - Cain, M.G. (Ed.) Characterisation of Ferroelectric Bulk Materials and Thin Films, 2nd ed.; Springer: Dordrecht, The Netherlands, 2014. [Google Scholar]
- Dineva, P.; Gross, D.; Müller, R.; Rangelov, T. Dynamic Fracture of Piezoelectric Materials, Solid Mechanics and Its Applications; Springer International Publishing: Cham, Switzerland, 2014. [Google Scholar]
- Gao, S. A Multifunctional Touch Interface for Multidimensional Sensing. Ph.D. Thesis, University of Cambridge, Cambridge, UK, 2018. [Google Scholar]
- Gao, S.; Nathan, A. P-209: Augmenting Capacitive Touch with Piezoelectric Force Sensing. In SID Symposium Digest of Technical Papers; Wiley: Hoboken, NJ, USA, 2017; Volume 48, pp. 2068–2071. [Google Scholar]
- Jones, L.A. Perception and Control of Finger Forces. In Proceedings of the ASME Dynamic Systems and Control Division, Anaheim, CA, USA, 15–20 November 1998; Volume 5, pp. 133–137. [Google Scholar]
- Jones, L.A. The Control and Perception of Finger Forces. In The Human Hand as an Inspiration for Robot Hand Development; Springer: Cham, Switzerland, 2014. [Google Scholar]
- Chen, L.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell.
**2018**, 40, 834–848. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Kim, Y. Convolutional Neural Networks for Sentence Classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014; pp. 1746–1751. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 3–6 December 2012; pp. 1097–1105. [Google Scholar]
- Long, J.; Shelhamer, E.; Darrell, T. Fully Convolutional Networks for Semantic Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241. [Google Scholar]
- Shelhamer, E.; Long, J.; Darrell, T. Fully Convolutional Networks for Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell.
**2017**, 39, 640–651. [Google Scholar] [CrossRef] [PubMed] - Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the International Conference on Learning Representations, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going Deeper with Convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 1–9. [Google Scholar]
- Bengio, Y.; Simard, P.Y.; Frasconi, P. Learning Long-term Dependencies with Gradient Descent is Difficult. IEEE Trans. Neural Netw.
**1994**, 5, 157–166. [Google Scholar] [CrossRef] [PubMed] - Graves, A.; Jaitly, N. Towards End-To-End Speech Recognition with Recurrent Neural Networks. In Proceedings of the International Conference on Machine Learning, Beijing, China, 21–26 June 2014; pp. 1764–1772. [Google Scholar]
- Graves, A.; Mohamed, A.; Hinton, G.E. Speech Recognition with Deep Recurrent Neural Networks. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Vancouver, BC, Canada, 26–30 May 2013; pp. 6645–6649. [Google Scholar]
- Osako, K.; Singh, R.; Raj, B. Complex Recurrent Neural Networks for Denoising Speech Signals. In Proceedings of the Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, USA, 18–21 October 2015; pp. 1–5. [Google Scholar]
- Sak, H.; Senior, A.W.; Rao, K.; Beaufays, F. Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition. In Proceedings of the Conference on International Speech Communication Association, Dresden, Germany, 20 May 2015; pp. 1468–1472. [Google Scholar]
- Williams, R.J.; Zipser, D. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks. Neural Comput.
**1989**, 1, 270–280. [Google Scholar] [CrossRef] - Snyder, M.M.; Ferry, D.K. Open Loop Stability Criterion for Layered and Fully-connected Neural Networks. Neural Netw.
**1988**, 1, 133. [Google Scholar] - Wan, L.; Zeiler, M.D.; Zhang, S.; Cun, Y.L.; Fergus, R. Regularization of Neural Networks using DropConnect. In Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA, 16–21 June 2013; pp. 1058–1066. [Google Scholar]
- Xu, Q.; Zhang, M.; Gu, Z.; Pan, G. Overfitting Remedy by Sparsifying Regularization on Fully-connected Layers of CNNs. Neurocomputing
**2018**, 328, 69–74. [Google Scholar] [CrossRef] - Gajowniczek, K.; Chmielewski, L.J.; Orlowski, A.; Ząbkowski, T. Generalized Entropy Cost Function in Neural Networks. In Proceedings of the International Conference on Artificial Neural Networks, Alghero, Italy, 11–14 September 2017; pp. 128–136. [Google Scholar]
- Hampshire, J.B.; Waibel, A. A Novel Objective Function for Improved Phoneme Recognition Using Time-delay Neural Networks. IEEE Trans. Neural Netw.
**1990**, 1, 216–228. [Google Scholar] [CrossRef] - Janocha, K.; Czarnecki, W.M. On Loss Functions for Deep Neural Networks in Classification. Schedae Inform.
**2017**, 2016, 4959. [Google Scholar] [CrossRef] - Nasr, G.E.; Badr, E.A.; Joun, C. Cross Entropy Error Function in Neural Networks: Forecasting Gasoline Demand; The Florida AI Research Society: Melbourne, FL, USA, 2002; pp. 381–384. [Google Scholar]
- Xu, L. Original Contribution: Least Mean Square Error Reconstruction Principle for Self-organizing Neural-nets. Neural Netw.
**1993**, 6, 627–648. [Google Scholar] [CrossRef] - Zhang, Z.; Sabuncu, M.R. Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels. In Proceedings of the Neural Information Processing Systems, Montreal, NU, Canada, 3–8 December 2018. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Andrychowicz, M.; Denil, M.; Gomez, S.; Hoffman, M.W.; Pfau, D.; Schaul, T.; Shillingford, B.; De Freitas, N. Learning to Learn by Gradient Descent by Gradient Descent. In Proceedings of the Advances in Neural Information Processing Systems 29 (NIPS 2016), Barcelona, Spain, 5–10 December 2016; pp. 3981–3989. [Google Scholar]
- Li, Y.; Yuan, Y. Convergence Analysis of Two-layer Neural Networks with ReLU Activation. In Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 597–607. [Google Scholar]
- Nair, V.; Hinton, G.E. Rectified Linear Units Improve Restricted Boltzmann Machines. In Proceedings of the International Conference on Machine Learning, Haifa, Israel, 21–24 June 2010; pp. 807–814. [Google Scholar]
- Girosi, F.; Jones, M.J.; Poggio, T. Regularization Theory and Neural Networks Architectures. Neural Comput.
**1995**, 7, 219–269. [Google Scholar] [CrossRef] [Green Version]

**Figure 5.**Schematic diagram of a fully connected artificial neural network (ANN). F is the number of features (nine for both force level and location classification); N and M are the hidden layer number and node number; C is the number of object classes (three for force level classification and nine for location classification). Note: Each hidden layer and output layer also have a bias input, which is ignored in this figure.

**Figure 6.**Signal pre-processing results: (

**a**) original signal; (

**b**) DC offset removed signal; (

**c**) signal after envelope detection; (

**d**) signal after multi-channel noise suppression; (

**e**) detected signal peaks.

**Figure 7.**Response voltages at the same location with different force levels; (

**a**), (

**b**) and (

**c**): response voltages of force level 1, 2 and 3.

**Figure 8.**Force level estimation using different loss functions. (

**a**,

**c**,

**e**) are the accuracy during training using the mean-squared error loss, categorical cross-entropy loss, and binary cross-entropy loss, respectively. (

**b**,

**d**,

**f**) are the loss of (

**a**,

**c**,

**e**).

**Figure 9.**Location estimation using different cost functions. (

**a**,

**c**,

**e**) are accuracy during training using mean-squared error loss, categorical cross-entropy loss, and binary cross-entropy loss, respectively. (

**b**,

**d**,

**f**) are the loss of (

**a**,

**c**,

**e**).

**Figure 10.**Classification accuracy of ANNs using different layer numbers and node numbers. (

**a**): accuracy of force claasification; (

**b**): accuracy of location classification.

Volunteer No. | Gender | Height (cm) | Weight (kg) | Handedness |
---|---|---|---|---|

1 | Male | 173 | 71 | Right |

2 | Male | 182 | 90.5 | Right |

3 | Female | 167 | 65 | Left |

4 | Female | 159 | 44 | Right |

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Gao, S.; Dai, Y.; Kitsos, V.; Wan, B.; Qu, X.
High Three-Dimensional Detection Accuracy in Piezoelectric-Based Touch Panel in Interactive Displays by Optimized Artificial Neural Networks. *Sensors* **2019**, *19*, 753.
https://doi.org/10.3390/s19040753

**AMA Style**

Gao S, Dai Y, Kitsos V, Wan B, Qu X.
High Three-Dimensional Detection Accuracy in Piezoelectric-Based Touch Panel in Interactive Displays by Optimized Artificial Neural Networks. *Sensors*. 2019; 19(4):753.
https://doi.org/10.3390/s19040753

**Chicago/Turabian Style**

Gao, Shuo, Yanning Dai, Vasileios Kitsos, Bo Wan, and Xiaolei Qu.
2019. "High Three-Dimensional Detection Accuracy in Piezoelectric-Based Touch Panel in Interactive Displays by Optimized Artificial Neural Networks" *Sensors* 19, no. 4: 753.
https://doi.org/10.3390/s19040753