Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/7218
Title: A conditional random field-based model for joint sequence segmentation and classification
Authors: Kosmopoulos, Dimitrios 
Doliotis, Paul 
Chatzis, Sotirios P. 
Kosmopoulos, Dimitrios 
Doliotis, Paul 
Keywords: Computer science
Pattern recognition
Signal processing
Issue Date: 2013
Publisher: Elsevier
Source: Pattern recognition, 2013, Volume 46, Issue 6, Pages 1569–1578
Abstract: In this paper, we consider the problem of joint segmentation and classification of sequences in the framework of conditional random field (CRF) models. To effect this goal, we introduce a novel dual-functionality CRF model: on the first level, the proposed model conducts sequence segmentation, whereas, on the second level, the whole observed sequences are classified into one of the available learned classes. These two procedures are conducted in a joint, synergetic fashion, thus optimally exploiting the information contained in the used model training sequences. Model training is conducted by means of an efficient likelihood maximization algorithm, and inference is based on the familiar Viterbi algorithm. We evaluate the efficacy of our approach considering a real-world application, and we compare its performance to popular alternatives
URI: http://ktisis.cut.ac.cy/handle/10488/7218
ISSN: 0031-3203
10.1016/j.patcog.2012.11.028
DOI: 10.1016/j.patcog.2012.11.028
Rights: © 2012 Elsevier Ltd
Appears in Collections:Άρθρα/Articles

Show full item record

SCOPUSTM   
Citations 20

13
checked on Jul 29, 2017

WEB OF SCIENCETM
Citations 20

9
Last Week
0
Last month
checked on Jul 27, 2017

Page view(s) 50

25
Last Week
0
Last month
3
checked on Aug 21, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.