Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics

Diego Martín-Martínez; Pablo Casaseca-de-la-Higuera; Gonzalo Vegas-Sánchez-Ferrero; Lucilio Cordero Grande; José María Andrés-de-Llano; José Ramón Garmendia-Leiza; Julio Ardura-Fernández

doi:10.1109/IEMBS.2010.5627206

Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics

Diego Martín-Martínez, Pablo Casaseca-de-la-Higuera, Gonzalo Vegas-Sánchez-Ferrero, Lucilio Cordero Grande, José María Andrés-de-Llano, José Ramón Garmendia-Leiza, Julio Ardura-Fernández

Universidad de Valladolid

Research output: Contribution to journal › Conference paper › peer-review

5 Citations (Scopus)

Abstract

The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.

Original language	English
Pages (from-to)	2383-2386
Number of pages	4
Journal	IEEE Proceedings on EMBS
Volume	32
DOIs	https://doi.org/10.1109/IEMBS.2010.5627206
Publication status	Published - 4 Sept 2010

Keywords

actimetry
activity/rest analysis
symbolic dynamics
wavelet

Access to Document

10.1109/IEMBS.2010.5627206

http://dx.doi.org/10.1109/IEMBS.2010.5627206

Cite this

Martín-Martínez, D., Casaseca-de-la-Higuera, P., Vegas-Sánchez-Ferrero, G., Cordero Grande, L., Andrés-de-Llano, J. M., Garmendia-Leiza, J. R., & Ardura-Fernández, J. (2010). Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics. IEEE Proceedings on EMBS, 32, 2383-2386. https://doi.org/10.1109/IEMBS.2010.5627206

@article{5630295d77bc46ca8dfddcb6a3bbec39,

title = "Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics",

abstract = "The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.",

keywords = "actimetry, activity/rest analysis, symbolic dynamics, wavelet",

author = "Diego Mart{\'i}n-Mart{\'i}nez and Pablo Casaseca-de-la-Higuera and Gonzalo Vegas-S{\'a}nchez-Ferrero and {Cordero Grande}, Lucilio and Andr{\'e}s-de-Llano, {Jos{\'e} Mar{\'i}a} and Garmendia-Leiza, {Jos{\'e} Ram{\'o}n} and Julio Ardura-Fern{\'a}ndez",

year = "2010",

month = sep,

day = "4",

doi = "10.1109/IEMBS.2010.5627206",

language = "English",

volume = "32",

pages = "2383--2386",

journal = "IEEE Proceedings on EMBS",

}

Martín-Martínez, D, Casaseca-de-la-Higuera, P, Vegas-Sánchez-Ferrero, G, Cordero Grande, L, Andrés-de-Llano, JM, Garmendia-Leiza, JR & Ardura-Fernández, J 2010, 'Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics', IEEE Proceedings on EMBS, vol. 32, pp. 2383-2386. https://doi.org/10.1109/IEMBS.2010.5627206

Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics. / Martín-Martínez, Diego; Casaseca-de-la-Higuera, Pablo; Vegas-Sánchez-Ferrero, Gonzalo et al.
In: IEEE Proceedings on EMBS, Vol. 32, 04.09.2010, p. 2383-2386.

Research output: Contribution to journal › Conference paper › peer-review

TY - JOUR

T1 - Characterization of activity epochs in actimetric registries for infantile colic diagnosis

T2 - Identification and feature extraction based on wavelets and symbolic dynamics

AU - Martín-Martínez, Diego

AU - Casaseca-de-la-Higuera, Pablo

AU - Vegas-Sánchez-Ferrero, Gonzalo

AU - Cordero Grande, Lucilio

AU - Andrés-de-Llano, José María

AU - Garmendia-Leiza, José Ramón

AU - Ardura-Fernández, Julio

PY - 2010/9/4

Y1 - 2010/9/4

N2 - The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.

AB - The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.

KW - actimetry

KW - activity/rest analysis

KW - symbolic dynamics

KW - wavelet

U2 - 10.1109/IEMBS.2010.5627206

DO - 10.1109/IEMBS.2010.5627206

M3 - Conference paper

VL - 32

SP - 2383

EP - 2386

JO - IEEE Proceedings on EMBS

JF - IEEE Proceedings on EMBS

ER -

Martín-Martínez D, Casaseca-de-la-Higuera P, Vegas-Sánchez-Ferrero G, Cordero Grande L, Andrés-de-Llano JM, Garmendia-Leiza JR et al. Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics. IEEE Proceedings on EMBS. 2010 Sept 4;32:2383-2386. doi: 10.1109/IEMBS.2010.5627206

Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics

Abstract

Keywords

Access to Document

Fingerprint

Cite this