Skip to main content
SpringerLink
Log in

Disaggregated Power System Signal Recognition Using Capsule Network

  • Conference paper
  • First Online:
Neural Computing for Advanced Applications (NCAA 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1265))

Included in the following conference series:

Abstract

Non-intrusive-load-monitoring (NILM) is normally based on power series analysis. In the load classification stage we use an image based deep convolutional neural network (DCNN) which is modelled on the biological visual cortex thereby achieving extremely high levels of object recognition and classification. However, the downsize to the DCNN is the requirement of a large image training dataset, translational invariance and loss during max pooling of information captured in small signal perturbations. In this paper to reduce the training dataset, provide appliance signature equivariance recognition and replace max pooling with routing by agreement for improved NILM recognition and classification we use Hinton’s capsule network (CapsNet). Disaggregated appliance current, real power and power factor signals are converted to two-dimensional (2D) images and then complementary fused together for increased recognition accuracy before final input into the CapsNet. We implement the Discrete Wavelet Transform (DWT) since it is able to transform within a large frequency band portfolio and fuses well low pixel images. By using image fusion technique we show that for only fifteen images per appliance and with no data augmentation we are able to achieve average prediction accuracies of up to 93.75% and hence consolidate the validity of the CapsNet in the NILM recognition and classification scheme for limited data memory and improved recognition.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Esa, N.F., Abdullah, M.P., Hassan, M.Y.: A review disaggregation method in non-intrusive appliance load monitoring. Renew. Sustain. Energy Rev. 66, 163–173 (2016)

    Article  Google Scholar 

  2. De Baets, L., Ruyssinck, J., Develder, C., Dhaene, T., Deschrijver, D.: Appliance classification using VI trajectories and convolutional neural networks. Energy Build. 158, 32–36 (2018)

    Article  Google Scholar 

  3. Yamashita, R., Nishio, M., Do, R.K.G., Togashi, K.: Convolutional networks: an overview and application in radiology. Insights Imaging 9(4), 611–629 (2018)

    Article  Google Scholar 

  4. Damaševicius, R., Maskeliunas, R., Wozniak, M., Polap, D.: Visualization of physiologic signals based on Hjorth parameters and Gramian angular fields. In: IEE 16th World Symposium of Applied Machine Intelligence and Informatics, pp. 000091–000096 (2018)

    Google Scholar 

  5. Wang, Z., Oates, T.: Imaging time-series to improve classification and imputation. In: International Joint Conference on Artificial Intelligence, pp. 3939–3945 (2015)

    Google Scholar 

  6. Ha, K.W., Jeong, J.W.F.: Decoding two-class motor imagery EEG with capsule networks. In: IEEE International Conference on Big Data and Smart Computing (Big Comp) (2019). https://doi.org/10.1109/BIGCOMP.2019.8678917

  7. Hatami, N., Gavet, Y., Debayle, J.: Classification of time-series images using deep convolutional neural networks. In: Tenth International Conference on Machine Vision (ICMV), Vienna, Austria (2017). https://doi.org/10.1117/12.2309486

  8. Yang, C.L., Yang, C.Y., Chen, Z.X., Lo, N.W.: Multivariate time series data transformation for convolutional neural network. In: Proceeding of the IEEE/SICE International Symposium on System Integration, pp. 188–192 (2019)

    Google Scholar 

  9. Properties of Functions. http://www.math.fsu.edu/~pkirby/mad2104/SlideShow/s4-2.pdf. Accessed 4 Aug 2019

  10. Alofi, A., et al.: A review of data fusion techniques. Int. J. Comput. Appl. 167(7), 0975–8887 (2017)

    Google Scholar 

  11. Shi-tong, Y.: An effective image fusion rule based on consistency checking. In: International Conference on Computer Science and Network Technology, pp. 2443–2446 (2011)

    Google Scholar 

  12. Chacko, B., Agrwal, S.L., et al.: Performance of image fusion technique using 4x4 block wavelet cosine transformation contribution title. In: 7th International Conference on Cloud Computing, Data Science and Engineering - Confluence, pp. 618–622 (2017)

    Google Scholar 

  13. Hamid, I., Nawaz, Q., Zia, M.A., Mumtaz, I.: Pixel-level multi-focus image fusion algorithm based on 2DPCA. In: IEEE 11th International Conference on Communication Software and Networks, pp. 362–365 (2019)

    Google Scholar 

  14. Katarya, R., Arora, Y.: Study on text classification using capsule networks. In: 5th International Conference on Advanced computing and Communication Systems (ICACCS), pp. 501–505 (2019)

    Google Scholar 

  15. Gumusbas, D., Yildrim, T.: Offline signature identification and verification using capsule network. In: IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) (2019). https://doi.org/10.1109/INISTA.2019.8778228

  16. Dombetzki, L.A.: An overview over capsule networks. In: Seminar Innovative Internet Technologies and Mobile Communications, September 2018, pp. 89–95 (2018). https://doi.org/10.2313/NET-2018-11-1_12

  17. Sabour, S., Frost, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing, pp. 3856–3866 (2017)

    Google Scholar 

  18. Sreelaksmi, K., Akarsh, S., Vinayakumar, R., Soman, K.P.: Capsule neural networks and visualization for segregation of plastic and non-plastic wastes. In: 5th International Conference on Advanced Computing & Communication Systems (ICACCS), pp. 631–636 (2019)

    Google Scholar 

  19. Tektronix. https://download.tek.com/manual/PA1000-Power-Analyzer-077091201.pdf. Accessed 25 Feb 2020

  20. Rosenfeld, M., Graham, R.L., et al. (eds.): In Praise of the Gram Matrix. The Mathematics of Paul Erdos I, pp. 551–557 (2013). https://doi.org/10.1007/978-3-642-60406-5

  21. Marttinez-Arellano, G., Terrazas, G., Ratchev, S.: Tool wear classification using time series imaging and deep learning. Int. J. Adv. Manuf. Technol. 104, 3647–3662 (2019)

    Article  Google Scholar 

  22. ScienceDirect Wavelet Analysis. https://www.sciencedirect.com/topics/earth-and-planetary-sciences/wavelet-analysis/. Accessed 26 Feb 2020

  23. Pajares, G., Manuel, J.: A wavelet-based image fusion tutorial. Pattern Recogn. 37(9), 1855–1872 (2004)

    Article  Google Scholar 

  24. Wang, H., Zhang, C., Song, Y., Pang, B.: Information-fusion methods based simultaneous localization and mapping for robot adapting to search and rescue postdisaster environments. J. Robot. 2018, 1–13 (2018)

    Google Scholar 

  25. Youtube. https://www.youtube.com/watch?v=0YYdo3vJnzU/. Accessed 19 Sep 2019

  26. The AIlearner. https://theailearner.com/tag/capsule-network/. Accessed 1 Dec 2019

  27. Stackoverflow. https://stackoverflow.com/questions/7370801/measure-time-elapsed-in-python/. Accessed 5 Mar 2020

  28. Wang, Z., Oates, T.: 3D capsule networks for object classification from 3D model data. In: IEEE 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC, pp. 2225–2229 (2018)

    Google Scholar 

Download references

Acknowledgment

This research is supported partially by South African National Research Foundation Grants (Nos. 112108 and 112142), and South African National Research Foundation Incentive Grant (No. 95687 and 114911), Eskom Tertiary Education Support Programme Grants, Research grant from URC of University of Johannesburg.

Author information

Authors and Affiliations

  1. Department of Electrical and Electronic Engineering Science, University of Johannesburg, Auckland Park, 2006, South Africa

    Liston Matindife & Yanxia Sun

  2. Department of Electrical and Mining Engineering, University of South Africa, Florida, 1710, South Africa

    Zenghui Wang

Authors
  1. Liston Matindife
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanxia Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zenghui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zenghui Wang .

Editor information

Editors and Affiliations

  1. Harbin Institute of Technology, Shenzhen, China

    Haijun Zhang

  2. Hefei University of Technology, Hefei, China

    Zhao Zhang

  3. Chongqing University, Chongqing, China

    Zhou Wu

  4. South China Normal University, Guangzhou, China

    Tianyong Hao

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Matindife, L., Sun, Y., Wang, Z. (2020). Disaggregated Power System Signal Recognition Using Capsule Network. In: Zhang, H., Zhang, Z., Wu, Z., Hao, T. (eds) Neural Computing for Advanced Applications. NCAA 2020. Communications in Computer and Information Science, vol 1265. Springer, Singapore. https://doi.org/10.1007/978-981-15-7670-6_29

Download citation

  • DOI: https://doi.org/10.1007/978-981-15-7670-6_29

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-15-7669-0

  • Online ISBN: 978-981-15-7670-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation