Machine learning workflow

(409829), Andrée-Anne Grosset; (9243070), Frédérick Dallaire; (230714), Tien Nguyen; (9243073), Mirela Birlea; (9243076), Jahg Wong; (9243079), François Daoust; (3427007), Noémi Roy; (6633050), André Kougioumoutzakis; (9243082), Feryel Azzi; (502991), Kelly Aubertin; (9243085), Samuel Kadoury; (5735126), Mathieu Latour; (9243088), Roula Albadine; (9243091), Susan Prendeville; (196570), Paul Boutros; (522709), Michael Fraser; (9243094), Rob G. Bristow; (373992), Theodorus van der Kwast; (4395118), Michèle Orain; (9243097), Hervé Brisson; (6633038), Nazim Benzerdjeb; (6633056), Hélène Hovington; (5735102), Alain Bergeron; (6633062), Yves Fradet; (65374), Bernard Têtu; (243995), Fred Saad; (3954290), Frédéric Leblond; (65380), Dominique Trudel

doi:10.1371/journal.pmed.1003281.s002

Public

Machine learning workflow.

Published in Figshare • Aug 14, 2020

NobleIDNI8P301W342R057S803

Authors:

Andrée-Anne Grosset (409829)

,

Frédérick Dallaire (9243070)

,

Tien Nguyen (230714)

Abstract

The workflow of the classification is read from top to bottom. In our analysis, features are spectral wavelengths (e.g., 1,004 cm−1, 1,477 cm−1) with a corresponding value (Raman intensity) different for each Raman spectrum. The feature selection algorithm is a linear SVM wi...

Subject

Artificial intelligence

Decision boundary

Computer science

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!