Skip to content

efficomp/Celestine

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Celestine

Celestine is a Python-based procedure to solve classification problems through five Machine Learning methods:

  • K-NN
  • SVM
  • Naive Bayes
  • Random Forest
  • Convolutional Neural Network (CNN)

Requirements

Celestine requires Python 3. It also depends on the following Python packages:

Documentation

Celestine is fully documented in its github-pages. You can also generate its docs from the source code. Simply change directory to the doc subfolder and type in make html, the documentation will be under build/html. You will need Sphinx to build the documentation.

Usage

There are two files to perform the classification:

  • cnn.py - Script to run only the CNN.
  • classfiers.py - Script to run the rest of classifiers.

The command to execute each script is as follows:

$ python3 script data_train.npy labels_train.npy data_test.npy labels_test.npy MRMR.csv

where:

  • script is cnn.py or classifiers.py.
  • data_train.npy is the file with the training dataset data (in .npy format).
  • labels_train.npy is the file with the training dataset labels (in .npy format).
  • data_test.npy is the file with the test dataset data (in .npy format).
  • labels_test.npy is the file with the test dataset labels (in .npy format).
  • MRMR.csv is the file with mRMR features ranking (in .csv format).

Finally, once the script is finished, the accuracy of each method will be saved in a local database using the PyMongo library.

Publications

  • J. C. Gómez-López, J. J. Escobar, J. González, F. Gil-Montoya, J. Ortega, M. Burmester, M. Damas. Energy-Time Profiling for Machine Learning Methods to EEG Classification. In: International Conference on Bioengineering and Biomedical Signal and Image Processing. BIOMESIP 2021, pp. 311-322. https://doi.org/10.1007/978-3-030-88163-4_27

Acknowledgments

This work was supported by project New Computing Paradigms and Heterogeneous Parallel Architectures for High-Performance and Energy Efficiency of Classification and Optimization Tasks on Biomedical Engineering Applications (HPEE-COBE), with reference PGC2018-098813-B-C31, funded by the Spanish Ministerio de Ciencia, Innovación y Universidades, and by the European Regional Development Fund (ERDF).

Ministerio de Economía y Competitividad                   European Regional Development Fund (ERDF)

License

GNU GPLv3.

Copyright

Celestine © 2015 EFFICOMP.

About

Celestine is a Python-based procedure to solve classification problems.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages