Skip to main content
SpringerLink
Log in

DeepComp: A Hybrid Framework for Data Compression Using Attention Coupled Autoencoder

  • Research Article-Computer Engineering and Computer Science
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

Abstract

Due to the evolution of new media formats, emphasis on appropriate compression of data becomes paramount. Compression algorithms employed in real-time streaming applications must provide high compression ratio with acceptable loss. For such applications, the compression ratio of traditional compression algorithms used in Windows remains a challenge. Integrating deep learning algorithms with traditional Windows archivers can help the research objective in overcoming the challenges encountered by traditional Windows archivers. In this study, we propose a hybrid and robust compression framework named DeepComp that employs an attention-based autoencoder along with traditional Windows WinRAR archiver to compress both numerical and image data formats. Autoencoders- a well-known deep learning architecture widely used for data compression, outperform traditional archivers in terms of compression ratio but fall short in terms of reconstruction error. To minimize the reconstruction error, an attention layer is proposed in the autoencoder used in DeepComp. The attention layer accomplishes this by impeding the transition of spatial locality of the input data points during its processing in the compression and decompression phase. DeepComp is evaluated using numerical and image-type atmospheric and oceanic data obtained from the National Centers for Environmental Prediction (NCEP), which operates under National Oceanic and Atmospheric Administration (NOAA), USA. The performance analysis illustrates the robustness of DeepComp in compressing both numeric and image datatypes. In terms of compression ratio, it outperforms Windows archivers by an average of 69% and multilayer autoencoders by 48%. DeepComp also outperforms the reconstruction performance of the multilayer autoencoder.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Abirami, S.; Chitra, P.: Regional air quality forecasting using spatiotemporal deep learning. J. Clean. Prod. 283, 125341 (2021). https://doi.org/10.1016/j.jclepro.2020.125341

    Article  Google Scholar 

  2. Sivasundaram, S.; Pandian, C.: Performance analysis of classification and segmentation of cysts in panoramic dental images using convolutional neural network architecture. Int. J. Imag. Syst. Technol. https://doi.org/10.1002/ima.22625

  3. Abirami, S.; Chitra, P.: Regional spatio-temporal forecasting of particulate matter using autoencoder based generative adversarial network. Stochast Environ Res Risk Assess (2022). https://doi.org/10.1007/s00477-021-02153-3

    Article  Google Scholar 

  4. Yildirim, O.; Tan, R.S.; Acharya, U.R.: An efficient compression of ECG signals using deep convolutional autoencoders. Cogn. Syst. Res. 52, 198–211 (2018). https://doi.org/10.1016/j.cogsys.2018.07.004

    Article  Google Scholar 

  5. Wessel, P.: Compression of large data grids for internet transmission. Comput. Geosci. 29, 665–671 (2003). https://doi.org/10.1016/S0098-3004(03)00038-4

    Article  Google Scholar 

  6. Chen, M.; Shi, X.; Zhang, Y.; Wu, D.; Guizani, M.: Deep features learning for medical image analysis with convolutional autoencoder neural network. IEEE Trans. Big Data. (2017). https://doi.org/10.1109/TBDATA.2017.2717439

    Article  Google Scholar 

  7. Chen, H.; Wang, S.; Wu, L.; Wang, J.: A novel smart meter data compression method via stacked convolutional sparse auto-encoder. Int. J. Elect. Power Energy Syst. (2019). https://doi.org/10.1016/j.ijepes.2019.105761

    Article  Google Scholar 

  8. Ahmeda, S.M.; Abo-Zahhad, M.: A new hybrid algorithm for ECG signal compression based on the wavelet transformation of the linearly predicted error. Med. Eng. Phys. 23, 117–126 (2001). https://doi.org/10.1016/S1350-4533(01)00026-1

    Article  Google Scholar 

  9. Cherezov, A.; Jang, J.; Lee, D.: A PCA compression method for reactor core transient multiphysics simulation. Prog. Nucl. Energy. 128, 103441 (2020). https://doi.org/10.1016/j.pnucene.2020.103441

    Article  Google Scholar 

  10. Park, J.; Park, H.; Choi, Y.: Data compression and prediction using machine learning for industrial IoT. In: Proceedings of the 2018 international conference on information networking (ICOIN). pp. 818–820 (2018)

  11. Li, M.; Zuo, W.; Gu, S.; Zhao, D.; Zhang, D.: Learning convolutional networks for content-weighted image compression. CoRR. abs/1703.1 (2017)

  12. Yang, F.; Herranz, L.; Weijer, J.V.D.; Guitián, J.A.I.; López, A.M.; Mozerov, M.G.: Variable rate deep image compression with modulated autoencoder. IEEE Signal Process. Lett. 27, 331–335 (2020). https://doi.org/10.1109/LSP.2020.2970539

    Article  Google Scholar 

  13. Ameen Suhail, K.M.; Sankar, S.: Image compression and encryption combining autoencoder and chaotic logistic map. Iran. J. Sci. Technol. Trans. A Sci. 44, 1091–1100 (2020). https://doi.org/10.1007/s40995-020-00905-4

    Article  MathSciNet  Google Scholar 

  14. Zhang, Y.; Zhang, E.; Chen, W.: Deep neural network for halftone image classification based on sparse auto-encoder. Eng. Appl. Artif. Intell. 50, 245–255 (2016). https://doi.org/10.1016/j.engappai.2016.01.032

    Article  Google Scholar 

  15. Zeng, K.; Yu, J.; Wang, R.; Li, C.; Tao, D.: Coupled deep autoencoder for single image super-resolution. IEEE Trans. Cybern. 47, 27–37 (2017). https://doi.org/10.1109/TCYB.2015.2501373

    Article  Google Scholar 

  16. Cheng, Z.; Sun, H.; Takeuchi, M.; Katto, J.: Energy compaction-based image compression using convolutional autoencoder. IEEE Trans. Multimedia. 22, 860–873 (2020). https://doi.org/10.1109/TMM.2019.2938345

    Article  Google Scholar 

  17. Nuha, H.; Balghonaim, A.; Liu, B.; Mohandes, M.; Deriche, M.; Fekri, F.: Deep neural networks with extreme learning machine for seismic data compression. Arab. J. Sci. Eng. (2019). https://doi.org/10.1007/s13369-019-03942-3

    Article  Google Scholar 

  18. Wang, S.; Wang, H.; Xiang, S.; Yu, L.: Densely connected convolutional network block based autoencoder for panorama map compression. Sig. Process. Image Commun. 80, 115678 (2020). https://doi.org/10.1016/j.image.2019.115678

    Article  Google Scholar 

  19. Huang, X.; Hu, T.; Ye, C.; Xu, G.; Wang, X.; Chen, L.: Electric load data compression and classification based on deep stacked auto-encoders (2019)

  20. Ilkhechi, A.; Crotty, A.; Galakatos, A.; Mao, Y.; Fan, G.; Shi, X.; Cetintemel, U.: DeepSqueeze: deep semantic compression for tabular data. In: Proceedings of the 2020 ACM SIGMOD international conference on management of data. pp. 1733–1746. Association for Computing Machinery, New York, NY, USA (2020)

  21. Huffman, D.A.: A method for the construction of minimum-redundancy codes. Resonance 11, 91–99 (2006). https://doi.org/10.1007/BF02837279

    Article  Google Scholar 

  22. Al-Nashash, H.A.M.: A dynamic fourier series for the compression of ECG using FFT and adaptive coefficient estimation. Med. Eng. Phys. 17, 197–203 (1995). https://doi.org/10.1016/1350-4533(95)95710-R

    Article  Google Scholar 

  23. Wang, K.; Zhang, M.; Zhang, S.; Xu, Z.: A PQ data compression algorithm based on wavelet domain principal component analysis. In: Proceedings of the 2020 Asia energy and electrical engineering symposium (AEEES). pp. 347–350 (2020)

  24. Lu, J.L.; Verma, N.; Jha, N.K.: Convolutional autoencoder-based transfer learning for multi-task image inferences. IEEE Trans. Emerg. Top. Comput. (2021). https://doi.org/10.1109/TETC.2021.3068063

    Article  Google Scholar 

  25. Ziv, J.; Lempel, A.: A universal algorithm for sequential data compression. IEEE Trans. Inf. Theor. 23, 337–343 (2006). https://doi.org/10.1109/TIT.1977.1055714

    Article  MathSciNet  MATH  Google Scholar 

  26. Senigagliesi, L.; Baldi, M.; Gambi, E.: Physical layer authentication techniques based on machine learning with data compression (2020)

  27. Chowdhury, M.R.; Tripathi, S.; De, S.: Adaptive multivariate data compression in smart metering internet of things. IEEE Trans. Ind. Inform. 17, 1287–1297 (2021). https://doi.org/10.1109/TII.2020.2981382

    Article  Google Scholar 

  28. Sharma, N.; Sharma, R.; Jindal, N.: Machine learning and deep learning applications: a vision. Glob. Trans. Proc. 2, 24–28 (2021). https://doi.org/10.1016/j.gltp.2021.01.004

    Article  Google Scholar 

  29. Romero, J.; Olson, J.P.; Aspuru-Guzik, A.: Quantum autoencoders for efficient compression of quantum data. Quant. Sci. Technol. 2, 45001 (2017). https://doi.org/10.1088/2058-9565/aa8072

    Article  Google Scholar 

  30. Kim, J.; Choi, J.; Chang, J.; Lee, J.: Efficient deep learning-based lossy image compression via asymmetric autoencoder and pruning. In: ICASSP 2020–2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). pp. 2063–2067 (2020)

  31. Yang, Y.; Sautière, G.; Ryu, J.J.; Cohen, T.S.: Feedback recurrent autoencoder. CoRR. abs/1911.0 (2019)

  32. Weng, Z.; Zhang, W.; Dou, W.: Adversarial attention-based variational graph autoencoder. IEEE Access. 8, 152637–152645 (2020). https://doi.org/10.1109/ACCESS.2020.3018033

    Article  Google Scholar 

  33. Huang, F.; Zhang, X.; Li, C.; Li, Z.; He, Y.; Zhao, Z.: Multimodal network embedding via attention based multi-view variational autoencoder. In: Proceedings of the 2018 ACM on international conference on multimedia retrieval. pp. 108–116. Association for Computing Machinery, New York, NY, USA (2018)

  34. Polyak, A.; Wolf, L.: Attention-based Wavenet Autoencoder for Universal Voice Conversion. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). 6800–6804 (2019)

  35. Xue, Y.; Su, J.: Attention based image compression post-processing convolutional neural network (2019)

  36. Kundu, A.; Sahu, A.; Serpedin, E.; Davis, K.: A3D: attention-based auto-encoder anomaly detector for false data injection attacks. Elect. Power Syst. Res. 189, 106795 (2020). https://doi.org/10.1016/j.epsr.2020.106795

    Article  Google Scholar 

  37. Zhou, L.; Sun, Z.; Wu, X.; Wu, J.: End-to-end optimized image compression with attention mechanism. In: CVPR Workshops (2019)

  38. Zou, K.H.; Tuncali, K.; Silverman, S.G.: Correlation and simple linear regression. Radiology 227, 617–628 (2003). https://doi.org/10.1148/radiol.2273011499

    Article  Google Scholar 

  39. Ma, M.; Sun, C.; Chen, X.: Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Trans. Ind. Inform. 14, 1137–1145 (2018). https://doi.org/10.1109/TII.2018.2793246

    Article  Google Scholar 

  40. Wang, W.; Feng, C.; Zhang, B.; Gao, H.: Environmental monitoring based on fog computing paradigm and internet of things. IEEE Access. 7, 127154–127165 (2019). https://doi.org/10.1109/ACCESS.2019.2939017

    Article  Google Scholar 

  41. Ioannou, K.; Karampatzakis, D.; Amanatidis, P.; Aggelopoulos, V.; Karmiris, I.: Low-cost automatic weather stations in the internet of things (2021)

  42. Liang, Y.; Li, Y.: An efficient and robust data compression algorithm in wireless sensor networks. IEEE Commun. Lett. (2014). https://doi.org/10.1109/LCOMM.2014.011214.132319

    Article  Google Scholar 

  43. Lu, Y.; Phillips, C.A.; Langston, M.A.: A robustness metric for biological data clustering algorithms. BMC Bioinform. (2019)

  44. Armstrong, O.; Gilad-Bachrach, R.: Robust model compression using deep hypotheses (2021)

  45. Zhang, P.; Wang, X.; Wang, F.; Zeng, A.; Xiao, J.: Measuring the robustness of link prediction algorithms under noisy environment. Sci. Rep. 6, 18881 (2016). https://doi.org/10.1038/srep18881

    Article  Google Scholar 

  46. Oguz, C.; Watson, L.T.; Baumann, W.T.; Tyson, J.J.: Predicting network modules of cell cycle regulators using relative protein abundance statistics. BMC Syst. Biol. 11, 30 (2017). https://doi.org/10.1186/s12918-017-0409-1

    Article  Google Scholar 

  47. Kim, T.K.: T test as a parametric statistic. Korean J. Anesthesiol. 68, 540–546 (2015). https://doi.org/10.4097/kjae.2015.68.6.540

    Article  Google Scholar 

Download references

Acknowledgements

Authors from C-DAC are thankful to Naval Research Board (NRB) to provide funding for this research.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, India

    S. Sriram, P. Chitra, V. Vijay Sankar, S. Abirami & S. J. Rethina Durai

  2. HPC-S&EA Group, C-DAC, Pune, Maharashtra, 411008, India

    Arun K. Dwivedi, Divya Pandey & Manoj K. Khare

Authors
  1. S. Sriram
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arun K. Dwivedi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. P. Chitra
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. V. Vijay Sankar
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. S. Abirami
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. S. J. Rethina Durai
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Divya Pandey
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Manoj K. Khare
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to P. Chitra.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sriram, S., Dwivedi, A.K., Chitra, P. et al. DeepComp: A Hybrid Framework for Data Compression Using Attention Coupled Autoencoder. Arab J Sci Eng 47, 10395–10410 (2022). https://doi.org/10.1007/s13369-022-06587-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-022-06587-x

Keywords

Search

Navigation