Newborn cry nonlinear features extraction and classification

Issue title: Intelligent and Fuzzy Systems applied to Language & Knowledge Engineering

Guest editors: David Pinto, Vivek Kumar Singh, Aline Villavicencio, Philipp Mayr-Schlegel and Efstathios Stamatatos

Article type: Research Article

Authors: Peralta-Malváez, Lizbeth | López-Rincón, Omar | Rojas-Velázquez, David | Valencia-Rosado, Luis Oswaldo | Rosas-Romero, Roberto | Etcheverry, Gibran^{; *}

Affiliations: Departamento de Computación, Electrónica y Mecatrónica, Escuela de Ingeniería, Universidad de las Américas Puebla, Ex Hacienda Santa Catarina Mártir SN, Cholula, Puebla, México

Correspondence: [*] Corresponding author. Gibran Etcheverry, Departamento de Computación, Electrónica y Mecatrónica, Escuela de Ingeniería, Universidad de las Américas Puebla, Ex Hacienda Santa Catarina Mártir SN, Cholula, Puebla, CP. 72810, México. E-mail: [email protected].

Abstract: Newborn cry features extraction for affections detection and classification has been intensively developed during the last ten to fifteen years. In this work, methods from the system identification area have been implemented in order to obtain ten Linear Predictive Coefficients (LPCs) plus a nonlinear one stated as Bilinear Intermittent Factor (BIF) per 20 ms analysis window for 40 normal and loss hearing (deaf) newborn cries each. In order to show the contribution of the nonlinear feature, a Kernel Discriminant Analysis (KDA) is performed and afterwards, two classifications tests employing Supported Vector machines (SVMs) as a standard and the Expectation Maximization (EM) algorithm over a Mixture of Experts (ME) operation, considering the BIF as an expert or parent of the LPCs, allows to obtain a 99.84% classification.

Keywords: Newborn cry classification, nonlinear features, Mixture of Experts, KDA, SVMs, EM

DOI: 10.3233/JIFS-169510

Journal: Journal of Intelligent & Fuzzy Systems, vol. 34, no. 5, pp. 3281-3289, 2018