Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 10.12 MB
Add to list
  1. Search results
  2. A light-weight CNN model for efficien...

A light-weight CNN model for efficient Parkinson's disease diagnostics

Xuechao Wang (UGent) , Junqing Huang (UGent) , Marianna Chatzakou (UGent) , Kadri Medijainen, Pille Taba, Aaro Toomela, Sven Nomm and Michael Ruzhansky (UGent)
(2023) Computer-Based Medical Systems, 36th IEEE International symposium, Proceedings. In IEEE International Symposium on Computer-Based Medical Systems p.616-621
Author
Organization
Project
Abstract
In recent years, deep learning methods have achieved great success in various fields due to their strong performance in practical applications. In this paper, we present a light-weight neural network for Parkinson's disease diagnostics, in which a series of hand-drawn data are collected to distinguish Parkinson's disease patients from healthy control subjects. The proposed model consists of a convolution neural network (CNN) cascading to long-short-term memory (LSTM) to adapt the characteristics of collected time-series signals. To make full use of their advantages, a multilayered LSTM model is firstly used to enrich features which are then concatenated with raw data and fed into a shallow one-dimensional (1D) CNN model for efficient classification. Experimental results show that the proposed model achieves a high-quality diagnostic result over multiple evaluation metrics with much fewer parameters and operations, outperforming conventional methods such as support vector machine (SVM), random forest (RF), lightgbm (LGB) and CNN-based methods.
Keywords
Ghent Analysis & PDE center, Parkinson's disease, Deep Learning, Hand-drawn tests, CLASSIFICATION

Downloads

  • Download
    2023112829.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 10.12 MB

Citation

Please use this url to cite or link to this publication:

MLA
Wang, Xuechao, et al. “A Light-Weight CNN Model for Efficient Parkinson’s Disease Diagnostics.” Computer-Based Medical Systems, 36th IEEE International Symposium, Proceedings, IEEE, 2023, pp. 616–21, doi:10.1109/CBMS58004.2023.00117.
APA
Wang, X., Huang, J., Chatzakou, M., Medijainen, K., Taba, P., Toomela, A., … Ruzhansky, M. (2023). A light-weight CNN model for efficient Parkinson’s disease diagnostics. Computer-Based Medical Systems, 36th IEEE International Symposium, Proceedings, 616–621. https://doi.org/10.1109/CBMS58004.2023.00117
Chicago author-date
Wang, Xuechao, Junqing Huang, Marianna Chatzakou, Kadri Medijainen, Pille Taba, Aaro Toomela, Sven Nomm, and Michael Ruzhansky. 2023. “A Light-Weight CNN Model for Efficient Parkinson’s Disease Diagnostics.” In Computer-Based Medical Systems, 36th IEEE International Symposium, Proceedings, 616–21. IEEE. https://doi.org/10.1109/CBMS58004.2023.00117.
Chicago author-date (all authors)
Wang, Xuechao, Junqing Huang, Marianna Chatzakou, Kadri Medijainen, Pille Taba, Aaro Toomela, Sven Nomm, and Michael Ruzhansky. 2023. “A Light-Weight CNN Model for Efficient Parkinson’s Disease Diagnostics.” In Computer-Based Medical Systems, 36th IEEE International Symposium, Proceedings, 616–621. IEEE. doi:10.1109/CBMS58004.2023.00117.
Vancouver
1.
Wang X, Huang J, Chatzakou M, Medijainen K, Taba P, Toomela A, et al. A light-weight CNN model for efficient Parkinson’s disease diagnostics. In: Computer-Based Medical Systems, 36th IEEE International symposium, Proceedings. IEEE; 2023. p. 616–21.
IEEE
[1]
X. Wang et al., “A light-weight CNN model for efficient Parkinson’s disease diagnostics,” in Computer-Based Medical Systems, 36th IEEE International symposium, Proceedings, L’Aquila, Italy, 2023, pp. 616–621.
@inproceedings{01H04X168E57EATJGTV4TNCDNP,
  abstract     = {{In recent years, deep learning methods have achieved great success in various
fields due to their strong performance in practical applications. In this
paper, we present a light-weight neural network for Parkinson's disease
diagnostics, in which a series of hand-drawn data are collected to distinguish
Parkinson's disease patients from healthy control subjects. The proposed model
consists of a convolution neural network (CNN) cascading to long-short-term
memory (LSTM) to adapt the characteristics of collected time-series signals. To
make full use of their advantages, a multilayered LSTM model is firstly used to
enrich features which are then concatenated with raw data and fed into a
shallow one-dimensional (1D) CNN model for efficient classification.
Experimental results show that the proposed model achieves a high-quality
diagnostic result over multiple evaluation metrics with much fewer parameters
and operations, outperforming conventional methods such as support vector
machine (SVM), random forest (RF), lightgbm (LGB) and CNN-based methods.
}},
  author       = {{Wang, Xuechao and Huang, Junqing and Chatzakou, Marianna and Medijainen, Kadri and Taba, Pille and Toomela, Aaro and Nomm, Sven and Ruzhansky, Michael}},
  booktitle    = {{Computer-Based Medical Systems, 36th IEEE International symposium, Proceedings}},
  isbn         = {{9798350312249}},
  issn         = {{2372-9198}},
  keywords     = {{Ghent Analysis & PDE center,Parkinson's disease,Deep Learning,Hand-drawn tests,CLASSIFICATION}},
  language     = {{eng}},
  location     = {{L'Aquila, Italy}},
  pages        = {{616--621}},
  publisher    = {{IEEE}},
  title        = {{A light-weight CNN model for efficient Parkinson's disease diagnostics}},
  url          = {{http://doi.org/10.1109/CBMS58004.2023.00117}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: