Application of Random Forest Classifier for Automatic Sleep Spindle Detection

Patti, C, Salary Shahrbabaki, S, Dissanayaka Manamperi, P and Cvetkovic, D 2015, 'Application of Random Forest Classifier for Automatic Sleep Spindle Detection', in 2015 IEEE BioCAS Proceedings, Atlanta, United States, 22-24 October 2015, pp. 350-353.

Document type: Conference Paper
Collection: Conference Papers

Title Application of Random Forest Classifier for Automatic Sleep Spindle Detection
Author(s) Patti, C
Salary Shahrbabaki, S
Dissanayaka Manamperi, P
Cvetkovic, D
Year 2015
Conference name 11th Annual IEEE Biomedical Circuits and Systems Conference (BioCAS'15)
Conference location Atlanta, United States
Conference dates 22-24 October 2015
Proceedings title 2015 IEEE BioCAS Proceedings
Publisher IEEE
Place of publication United States
Start page 350
End page 353
Total pages 4
Abstract Sleep spindle detection using supervised learning methods such as Artificial Neural Networks and Support Vector Machines had been researched in the past. Supervised learning methods such as the above are prone to overfitting problems. In this research paper, we explore the detection of sleep spindles using the Random Forest classifier which is known to over fit data to a much lower extent when compared to other supervised classifiers. The classifier was developed using data from 3 subjects and it was tested on data from 12 subjects from the MASS database. A sensitivity of 71.2% and a specificity of 96.73% was achieved using the random forest classifier.
Subjects Biomedical Instrumentation
Biomedical Engineering not elsewhere classified
Keyword(s) Sleep Spindles
Random Forest
Automatic Detection
Supervised Learning
DOI - identifier 10.1109/BioCAS.2015.7348373
Copyright notice © 2015 IEEE
ISBN 9781479972340
Version Filter Type
Altmetric details:
Access Statistics: 107 Abstract Views  -  Detailed Statistics
Created: Thu, 25 Feb 2016, 10:45:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us