Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

SpringerLink
Log in

Hyper-parameter optimization of deep learning model for prediction of Parkinson’s disease

  • Special Issue Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Neurodegenerative disorder such as Parkinson’s disease (PD) is among the severe health problems in our aging society. It is a neural disorder that affects people socially as well as economically. It occurs due to the failure of the brain’s dopamine-producing cells to produce enough dopamine to enable the motor movement of the body. This disease primarily affects vision, speech, movement problems, and excretion activity, followed by depression, nervousness, sleeping problems, and panic attacks. The onset of Parkinson’s disease is diagnosed with the help of speech disorders, which are the earliest symptoms of it. The essential goal of this paper is to build up a viable clinical decision-making system that helps the doctor in diagnosing the PD influenced patients. In this paper, a specific framework based on grid search optimization is proposed to develop an optimized deep learning Model to predict the early onset of Parkinson’s disease whereby multiple hyperparameters are to be set and tuned for evaluation of the deep learning model. The grid search optimization consists of three main stages, i.e., the optimization of the deep learning model topology, the hyperparameters, and its performance. An evaluation of the proposed approach is done on the speech samples of PD patients and healthy individuals. The results of the approach proposed are finally analyzed, which shows that the fine-tuning of the deep learning model parameters result in the overall test accuracy of 89.23% and the average classification accuracy of 91.69%.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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. Cai, Z., Gu, J., Wen, C., Zhao, D., Huang, C.: An intelligent Parkinson’s disease diagnostic system based on a chaotic bacterial foraging optimization enhanced fuzzy KNN approach, Hindawi Computational and Mathematical Methods in Medicine, pp. 1–24 (2018)

  2. Rinaldi, S., Trompetto, C.: Balance dysfunction in Parkinson’s Disease. In: Hindawi BioMed Research Journal, pp. 1–10 (2015)

  3. Colony, B., Maabreh, M., AlFuqaha, A.: Parameters optimization of deep learning models using Particle swarm optimization. In: International Conference of Wireless Communications, and Mobile Computing (2017)

  4. Harel, B., Cannizzaro, M., Snyder, P.: Variability in fundamental frequency during a speech in prodromal and incipient Parkinson’s disease: a longitudinal case study. Brain Cogn. 56, 24–29 (2004)

    Article  Google Scholar 

  5. Wang, X., Gong, G.: Detection analysis of epileptic EEG using a novel random forest model combined with grid search optimization. Front. Hum. Neurosci. 13, 1–13 (2019)

    Google Scholar 

  6. Zhang, Y. N.: Can a smartphone diagnose Parkinson disease? A Deep Learning Model Method and Telediagnosis System Implementation, Hindawi Parkinson’s disease, pp. 1–11 (2017)

  7. Bind, S., Tiwari, A., Sahani, A.: A survey of machine learning-based approaches for Parkinson disease prediction. Int. J. Inf. Technol. Comput. Sci. 6, 1648–1655 (2015)

    Google Scholar 

  8. Singh, R., Srivastava, S.: Stock prediction using deep learning. Multimed. Tools Appl. 76, 18569–18584 (2016)

    Article  Google Scholar 

  9. Fatawa, A. H., Jahardi, M. H., Ling, S. H.: Efficient diagnosis system for Parkinson’s disease using deep belief network, pp. 1324–1330 (2016)

  10. Sairam, N., Mandal, I.: New machine-learning algorithms for prediction of Parkinson’s disease. Taylor&Francis Int. J. Syst. Sci. 45, 647–666 (2014)

    Article  MathSciNet  Google Scholar 

  11. Tahmassebi, A., Gandomi, A., Fong, S.: Multi-stage optimization of a deep model: a case study on ground motion modeling. Plos One. 3, 1–23 (2018)

    Google Scholar 

  12. Koutsoukas, A., Monaghan, K.J., Li, X., Jun, H.: Deep-learning: investigating Deep Learning Models hyperparameters and performance comparison of shallow methods for modeling bioactivity data, Springer. J. Cheminf. 3, 1–13 (2017)

    Google Scholar 

  13. Lee, S., Zokhirova, M., Nguyen, T.: Effect of hyper-parameters on deep learning networks in structural engineering, pp. 537–544 (2018)

  14. Yaseen, M., Anjum, A., Rana, O., Antonopoulos, N.: Hyper-parameter optimization of deep learning for video analytics in clouds. In: IEEE Transactions on Systems, Man, and Cybernetics: Systems, pp. 2168–2216 (2018)

  15. www.uci-repository.com

  16. Madrigal, F., Maurice, C., Lerasle, F.: Hyper-parameter optimization tools comparison for multiple object tracking applications. J. Mach. Vis. Appl. 3, 1–12 (2018)

    Google Scholar 

  17. Das, R.: A comparison of multiple classification methods for the diagnosis of Parkinson’s disease. Expert Syst. Appl. 37, 568 (2010)

    Google Scholar 

  18. Yadav, G., Kumar, Y., Sahoo, G.: Prediction of Parkinson’s disease using data mining methods: a comparative analysis of tree, statistical, and support vector machine classifiers. Indian J. Med. Sci. 65(6), 231–242 (2011). https://doi.org/10.4103/0019-5359.107023

    Article  Google Scholar 

  19. Lorenzo, P. R., Nalepa, J.: Hyper-parameter selection in deep learning models using parallel particle swarm optimization. In: GECCO Companion, pp. 1864–1887 (2017)

  20. Little, M.A., McSharry, P.E., Roberts, S.J., Costello, D.A., Moroz, I.M.: Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection. J. Biomed. Eng. 6, 1–23 (2007)

    Google Scholar 

  21. Khemphila, A., Boonjing, V.: Parkinson’s disease classification using neural network and feature selection, world academy of science, engineering, and technology. Int. J. Math. Comput. Phys. Electr. Comput. Eng. 6, 377 (2012)

    Google Scholar 

  22. Rustempasic, I., Can, M.: Diagnosis of Parkinson’s disease using principal component analysis and boosting committee machines. Southeast Eur. J. Soft Comput. 102, 10 (2013)

    Google Scholar 

  23. Shahbakhi, M., Taheri, D.: Speech analysis for diagnosis of Parkinson’s disease using genetic algorithm and support vector machine. J. Biomed. Sci. Eng. Sci. Res. 7, 147 (2014)

    Article  Google Scholar 

  24. Suganya, P., Sumathi, C.P.: A novel metaheuristic data mining algorithm for the detection and classification of Parkinson’s disease. Indian J. Sci. Technol. 8, 1 (2015)

    Google Scholar 

  25. Hassan, M., Sabar, N., Song, A.: Optimizing deep learning by hyper-heuristic approach for classifying good quality images, pp. 528–539 (2018)

  26. Wang, L., Zhou, B., Xiang, B., Mahadevan, S.: Efficient hyperparameter optimization for NLP applications. In: International Conference on Natural Language Processing in Empirical Methods, pp. 2112–2117 (2015)

  27. Gracia, N., Castaneda, A. L.: Effect of dataset sampling on the hyperparameter optimization phase over the Efficiency of a machine learning algorithm, Wiley Hindawi, pp. 1–16 (2019)

  28. Zeng, X., Luo, G.: Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection. Springer Health Inf. Sci. Syst. 3, 1–21 (2017)

    Google Scholar 

  29. Yaseen, M., Anjum, A., Rana, O., Antonopoulos, N.: Deep Learning hyperparameter optimization for video analytics in clouds. IEEE Trans. Man Cybern. Syst. Oper. 3, 2168–2216 (2018)

    Google Scholar 

  30. Gnana, S. K., Deepa, S. N.: Review on methods to fix number of hidden neurons in neural networks. In: Hindawi Mathematical Problems in Engineering, pp. 1–12 (2013)

  31. Wang, P., Ge, R., Xiao, X., Cai, X., Wang, G.: Rectified linear unit based deep learning for biomedical multi-label data. J. Comput. Life Sci. 9, 419–422 (2016)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Punjabi University, Patiala, 147002, India

    Sukhpal Kaur & Himanshu Aggarwal

  2. Computer Science and Engineering Department, Thapar Institute of Engineering and Technology, Patiala, 147004, India

    Rinkle Rani

Authors
  1. Sukhpal Kaur
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Himanshu Aggarwal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rinkle Rani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sukhpal Kaur.

Ethics declarations

Disclosure

There are no money related or different relations that could prompt an adverse circumstance.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kaur, S., Aggarwal, H. & Rani, R. Hyper-parameter optimization of deep learning model for prediction of Parkinson’s disease. Machine Vision and Applications 31, 32 (2020). https://doi.org/10.1007/s00138-020-01078-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-020-01078-1

Keywords

Search

Navigation