Please use this identifier to cite or link to this item: http://hdl.handle.net/11328/4086
Title: The selection of an optimal segmentation region in physiological signals
Authors: Oliveira, Jorge
Margarida, Carvalho
Nogueira, Diogo
Coimbra, Miguel
Keywords: Physiological signals
Deep neural networks
Integer programming
Optimal region selection
Issue Date: 31-Mar-2022
Publisher: Wiley
Citation: Oliveira, J., Carvalho, M., Nogueira, D., & Coimbra, M. (2022). The selection of an optimal segmentation region in physiological signals. International Transactions in Operational Research, 0, 1-18. https//doi.org/10.1111/itor.13138. Repositório Institucional UPT. http://hdl.handle.net/11328/4086
Abstract: Physiological signals are often corrupted by noisy sources. Usually, artificial intelligence algorithms analyze the whole signal, regardless of its varying quality. Instead, experienced cardiologists search for a high-quality signal segment, where more accurate conclusions can be draw. We propose a methodology that simultaneously selects the optimal processing region of a physiological signal and determines its decoding into a state sequence of physiologically meaningful events. Our approach comprises two phases. First, the training of a neural network that then enables the estimation of the state probability distribution of a signal sample. Second, the use of the neural network output within an integer program. The latter models the problem of finding a time window by maximizing a likelihood function defined by the user. Our method was tested and validated in two types of signals, the phonocardiogram and the electrocardiogram. In phonocardiogram and electrocardiogram segmentation tasks, the system’s sensitivity increased on average from 95.1% to 97.5% and from 78.9% to 83.8%, respectively, when compared to standard approaches found in the literature.
URI: http://hdl.handle.net/11328/4086
ISSN: 0969-6016 (Print)
1475-399 (Electronic)
Appears in Collections:REMIT – Artigos em Revistas Internacionais / Papers in International Journals



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