research-article

Using Auto-Encoder Neural Networks for Memory Fault Tolerance in Gesture Recognition System

Authors:

Yan WANGAuthors Info & Claims

ICMAI '21: Proceedings of the 2021 6th International Conference on Mathematics and Artificial Intelligence

Pages 25 - 33

https://doi.org/10.1145/3460569.3460571

Published: 31 August 2021 Publication History

Abstract

Data faults and retention characteristics in memories induce inaccuracy and failure in conventional electronic systems. While intelligent hardware which using AI algorithms can tolerate these faults with the advantage of neural network. This paper proposes using auto-encoder (AE) neural networks for memory fault tolerance in gesture recognition system based on RF sensors. This paper models the data faults of memories with defects or operating in ultra-low power state by a binary-type noise distribution. Then the model is used to test the effect of AE neural network in gesture recognition algorithm. Experimental results show AE neural network compress and extract useful features from noisy RF images, and higher gesture recognition accuracy is achieved based on these features. The algorithm achieves a recognition accuracy of 93% considering 20% bit level faults in RF images. The purpose of this method is to reduce the power consumption and improve the yield of the embedded RF based gesture recognition chip.

References

[1]

Yoshua Bengio. 2009. Learning deep architectures for AI. Foundations and trends® in Machine Learning 2, 1 (2009), 1–127.

Digital Library

[2]

Yoshua Bengio, Li Yao, Guillaume Alain, and Pascal Vincent. 2013. Generalized denoising auto-encoders as generative models. In Advances in neural information processing systems. 899–907.

[3]

Chin-Long Chen and MY Hsiao. 1984. Error-correcting codes for semiconductor memory applications: A state-of-the-art review. IBM Journal of Research and development 28, 2 (1984), 124–134.

[4]

Minmin Chen, Kilian Weinberger, Fei Sha, and Yoshua Bengio. 2014. Marginalized denoising auto-encoders for nonlinear representations. In International Conference on Machine Learning. 1476–1484.

[5]

Bo Du, Wei Xiong, Jia Wu, Lefei Zhang, Liangpei Zhang, and Dacheng Tao. 2016. Stacked convolutional denoising auto-encoders for feature representation. IEEE transactions on cybernetics 47, 4 (2016), 1017–1027.

[6]

Young-Ho Gong and Sung Woo Chung. 2015. Exploiting refresh effect of DRAM read operations: A practical approach to low-power refresh. IEEE Trans. Comput. 65, 5 (2015), 1507–1517.

Digital Library

[7]

Ruiqi Guo, Yonggang Liu, Shixuan Zheng, Ssu-Yen Wu, Peng Ouyang, Win-San Khwa, Xi Chen, Jia-Jing Chen, Xiudong Li, Leibo Liu, 2019. A 5.1 pJ/neuron 127.3 us/inference RNN-based speech recognition processor using 16 computing-in-memory SRAM macros in 65nm CMOS. In 2019 Symposium on VLSI Circuits. IEEE, C120–C121.

[8]

G. B. Hacene, F. Leduc-Primeau, A. B. Soussia, V. Gripon, and F. Gagnon. 2019. Training Modern Deep Neural Networks for Memory-Fault Robustness. In 2019 IEEE International Symposium on Circuits and Systems (ISCAS). 1–5. https://doi.org/10.1109/ISCAS.2019.8702382

[9]

J Alex Halderman, Seth D Schoen, Nadia Heninger, William Clarkson, William Paul, Joseph A Calandrino, Ariel J Feldman, Jacob Appelbaum, and Edward W Felten. 2009. Lest we remember: cold-boot attacks on encryption keys. Commun. ACM 52, 5 (2009), 91–98.

Digital Library

[10]

Souvik Hazra and Avik Santra. 2018. Robust gesture recognition using millimetric-wave radar system. IEEE sensors letters 2, 4 (2018), 1–4.

[11]

Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. science 313, 5786 (2006), 504–507.

[12]

Vayyar Imaging. Apr. 24 2016. Walabot - technical brief. (Apr. 24 2016).

[13]

Kiyoo Itoh. 1990. Trends in megabit DRAM circuit design. IEEE Journal of Solid-State Circuits 25, 3 (1990), 778–789.

[14]

Sascha Lange and Martin Riedmiller. 2010. Deep auto-encoder neural networks in reinforcement learning. In The 2010 International Joint Conference on Neural Networks (IJCNN). IEEE, 1–8.

[15]

Jonathan Masci, Ueli Meier, Dan Cireşan, and Jürgen Schmidhuber. 2011. Stacked convolutional auto-encoders for hierarchical feature extraction. In International conference on artificial neural networks. Springer, 52–59.

[16]

Duy Thanh Nguyen, Hyuk-Jae Lee, Hyun Kim, and Ik-Joon Chang. 2020. An approximate DRAM with efficient refresh schemes for low power deep learning applications. In 2020 International Conference on Electronics, Information, and Communication (ICEIC). IEEE, 1–2.

[17]

R. R. Some, W. S. Kim, G. Khanoyan, L. Callum, A. Agrawal, and J. J. Beahan. 2001. A software-implemented fault injection methodology for design and validation of system fault tolerance. In 2001 International Conference on Dependable Systems and Networks. 501–506.

[18]

F. Tu, W. Wu, S. Yin, L. Liu, and S. Wei. 2018. RANA: Towards Efficient Neural Acceleration with Refresh-Optimized Embedded DRAM. In 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 340–352. https://doi.org/10.1109/ISCA.2018.00037

Digital Library

[19]

Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning. 1096–1103.

Digital Library

[20]

Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, and Pierre-Antoine Manzagol. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research 11, Dec (2010), 3371–3408.

Digital Library

[21]

Saiwen Wang, Jie Song, Jaime Lien, Ivan Poupyrev, and Otmar Hilliges. 2016. Interacting with soli: Exploring fine- grained dynamic gesture recognition in the radio-frequency spectrum. In Proceedings of the 29th Annual Symposium on User Interface Software and Technology. 851–860.

Digital Library

[22]

Shouyi Yin, Peng Ouyang, Shibin Tang, Fengbin Tu, Xiudong Li, Shixuan Zheng, Tianyi Lu, Jiangyuan Gu, Leibo Liu, and Shaojun Wei. 2017. A high energy efficient reconfigurable hybrid neural network processor for deep learning applications. IEEE Journal of Solid-State Circuits 53, 4 (2017), 968–982.

[23]

Zhaofeng Zhang, Longbiao Wang, Atsuhiko Kai, Takanori Yamada, Weifeng Li, and Masahiro Iwahashi. 2015. Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification. EURASIP Journal on Audio, Speech, and Music Processing 2015, 1 (2015), 12.

[24]

Haitao Zhao, Zhihui Lai, Henry Leung, and Xianyi Zhang. 2020. Neural-Network-Based Feature Learning: Auto-Encoder. In Feature Learning and Understanding. Springer, 195–217.

[25]

Guangming Zhu, Liang Zhang, Peiyi Shen, and Juan Song. 2017. Multimodal gesture recognition using 3-D convolution and convolutional LSTM. Ieee Access 5 (2017), 4517–4524.

Cited By

Čopič Pucihar KMeneghello FSalami DSluÿters AVatavu R(2024)Beyond Radar Waves: The First Workshop on Radar-Based Human-Computer InteractionCompanion Proceedings of the 16th ACM SIGCHI Symposium on Engineering Interactive Computing Systems10.1145/3660515.3662836(97-102)Online publication date: 24-Jun-2024
https://dl.acm.org/doi/10.1145/3660515.3662836

Index Terms

Using Auto-Encoder Neural Networks for Memory Fault Tolerance in Gesture Recognition System

Index terms have been assigned to the content through auto-classification.

Recommendations

A fault tolerance technique for feedforward neural networks
Fault Tolerance Small-World Cellular Neural Networks for Inttermitted Faults
WAINA '09: Proceedings of the 2009 International Conference on Advanced Information Networking and Applications Workshops

A Cellular Neural Network (CNN) is a neural network model in which cells are linked only to neighboring cells. In image processing, a CNN can be used for noise reduction and edge detection. Small-World Cellular Neural Networks (SWCNN) are CNNs extended ...
Characterizing and improving the fault tolerance of artificial neural networks

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMAI '21: Proceedings of the 2021 6th International Conference on Mathematics and Artificial Intelligence

March 2021

142 pages

ISBN:9781450389464

DOI:10.1145/3460569

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 31 August 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICMAI 2021

ICMAI 2021: 2021 6th International Conference on Mathematics and Artificial Intelligence

March 19 - 21, 2021

Chengdu, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
44
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)1

Reflects downloads up to 26 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Čopič Pucihar KMeneghello FSalami DSluÿters AVatavu R(2024)Beyond Radar Waves: The First Workshop on Radar-Based Human-Computer InteractionCompanion Proceedings of the 16th ACM SIGCHI Symposium on Engineering Interactive Computing Systems10.1145/3660515.3662836(97-102)Online publication date: 24-Jun-2024
https://dl.acm.org/doi/10.1145/3660515.3662836

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents