An efficient visibility graph similarity algorithm and its application for sleep stages classification
Paper
Paper/Presentation Title | An efficient visibility graph similarity algorithm and its application for sleep stages classification |
---|---|
Presentation Type | Paper |
Authors | Zhu, Guohun (Author), Li, Yan (Author) and Wen, Peng Paul (Author) |
Editors | Zanzotto, Fabio Massimo, Tsumoto, Shusaku, Taatgen, Niels and Yao, Yiyu |
Journal or Proceedings Title | Brain Informatics |
Journal Citation | 7670, pp. 185-195 |
Number of Pages | 11 |
Year | 2012 |
Publisher | Springer |
Place of Publication | Heidelberg, Germany |
ISSN | 2198-4018 |
2198-4026 | |
ISBN | 9783642351389 |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-642-35139-6_18 |
Web Address (URL) of Paper | http://link.springer.com/chapter/10.1007%2F978-3-642-35139-6_18 |
Conference/Event | 2012 International Conference on Brain Informatics (BI 2012) |
Event Details | 2012 International Conference on Brain Informatics (BI 2012) Parent International Conference on Brain Informatics (BI) Event Date 04 to end of 07 Dec 2012 Event Location Macau, China |
Abstract | This paper presents an efficient horizontal visibility directed graph similarity algorithm (HVDS) by taking the advantages of two synchronization measuring methods in graph theory: phase locking value (PLV) and visibility graph similarity (VGS). It develops a new linear horizontal visibility graph constructing algorithm, analyzes its constructing complexity, and tests its feature performance via the sleep stages identification application. Six features are extracted, separately, from HVDS, PLV and VGS as the input to a support vector machine to classify the seven sleep stages. 11,120 data segments are used for the experiments with each segment lasts 30 seconds. The training sets are selected from a single subject and the testing sets are selected from multiple subjects. 10-cross-validation is employed to evaluate the performances of the PLV, VGS and HVDS methods. The experimental results show that the PLV, VGS and HVDS algorithms produce an average classification accuracy of 72.3%, 81.5% and 82.6%, respectively. The speed of the HVDS is 39 times faster than the VGS algorithm. |
Keywords | computational complexity, phase locking value, horizontal visibility; directed graph similarity, classification sleep stage, synchronization |
ANZSRC Field of Research 2020 | 429999. Other health sciences not elsewhere classified |
490102. Biological mathematics | |
400399. Biomedical engineering not elsewhere classified | |
460103. Applications in life sciences | |
420313. Mental health services | |
Public Notes | Published as Lecture Notes in Computer Science, Vol. 7670. Permanent restricted access to published version due to publisher copyright policy. |
Byline Affiliations | Department of Mathematics and Computing |
Department of Electrical, Electronic and Computer Engineering | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q1w52/an-efficient-visibility-graph-similarity-algorithm-and-its-application-for-sleep-stages-classification
2101
total views11
total downloads5
views this month0
downloads this month