Application of Pattern Recognition Techniques to the Classification of Full-Term and Preterm Infant Cry.

OBJECTIVES Scientific and clinical advances in perinatology and neonatology have enhanced the chances of survival of preterm and very low weight neonates. Infant cry analysis is a suitable noninvasive complementary tool to assess the neurologic state of infants particularly important in the case of preterm neonates. This article aims at exploiting differences between full-term and preterm infant cry with robust automatic acoustical analysis and data mining techniques. STUDY DESIGN Twenty-two acoustical parameters are estimated in more than 3000 cry units from cry recordings of 28 full-term and 10 preterm newborns. METHODS Feature extraction is performed through the BioVoice dedicated software tool, developed at the Biomedical Engineering Lab, University of Firenze, Italy. Classification and pattern recognition is based on genetic algorithms for the selection of the best attributes. Training is performed comparing four classifiers: Logistic Curve, Multilayer Perceptron, Support Vector Machine, and Random Forest and three different testing options: full training set, 10-fold cross-validation, and 66% split. RESULTS Results show that the best feature set is made up by 10 parameters capable to assess differences between preterm and full-term newborns with about 87% of accuracy. Best results are obtained with the Random Forest method (receiver operating characteristic area, 0.94). CONCLUSIONS These 10 cry features might convey important additional information to assist the clinical specialist in the diagnosis and follow-up of possible delays or disorders in the neurologic development due to premature birth in this extremely vulnerable population of patients. The proposed approach is a first step toward an automatic infant cry recognition system for fast and proper identification of risk in preterm babies.

[1]  Dror Lederman,et al.  Classification of cries of infants with cleft-palate using parallel hidden Markov models , 2008, Medical & Biological Engineering & Computing.

[2]  S Van Huffel,et al.  Assessment of Pain Expression in Infant Cry Signals Using Empirical Mode Decomposition , 2010, Methods of Information in Medicine.

[3]  Sazali Yaacob,et al.  Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network , 2012, Comput. Methods Programs Biomed..

[4]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[5]  I. M. Yassin,et al.  Optimization of MFCC parameters using Particle Swarm Optimization for diagnosis of infant hypothyroidism using Multi- Layer Perceptron , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[6]  Chakib Tadj,et al.  Cry-based classification of healthy and sick infants using adapted boosting mixture learning method for gaussian mixture models , 2012 .

[7]  A Fort,et al.  Acoustic analysis of newborn infant cry signals. , 1998, Medical engineering & physics.

[8]  Sergio Daniel Cano-Ortiz,et al.  A Combined Classifier of Cry Units with New Acoustic Attributes , 2006, CIARP.

[9]  B. Lester,et al.  Atypical Cry Acoustics in 6‐Month‐Old Infants at Risk for Autism Spectrum Disorder , 2012, Autism research : official journal of the International Society for Autism Research.

[10]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[11]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[12]  Carlos A. Reyes García,et al.  Applying Statistical Vectors of Acoustic Characteristics for the Automatic Classification of Infant Cry , 2007, ICIC.

[13]  Peter Wermke,et al.  Cry Melody in 2-Month-Old Infants with and without Clefts , 2011, The Cleft palate-craniofacial journal : official publication of the American Cleft Palate-Craniofacial Association.

[14]  Qiang Shen,et al.  Computational Intelligence and Feature Selection - Rough and Fuzzy Approaches , 2008, IEEE Press series on computational intelligence.

[15]  Claudia Manfredi,et al.  Effective pre-processing of long term noisy audio recordings: An aid to clinical monitoring , 2013, Biomed. Signal Process. Control..

[16]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[17]  B. Fuller.  Acoustic Discrimination of Three Types of Infant Cries , 1991, Nursing research.

[18]  K. Michelsson,et al.  Sound-spectrographic cry analysis of normal and abnormal newborn infants. A review and a recommendation for standardization of the cry characteristics. , 1976, Folia phoniatrica.

[19]  Chakib Tadj,et al.  Resonance frequencies behavior in pathologic cries of newborns. , 2015, Journal of voice : official journal of the Voice Foundation.

[20]  L. Lagasse,et al.  Assessment of infant cry: acoustic cry analysis and parental perception. , 2005, Mental retardation and developmental disabilities research reviews.

[21]  Michael P Robb,et al.  Sudden infant death syndrome: cry characteristics. , 2013, International journal of pediatric otorhinolaryngology.

[22]  B. Lester,et al.  Developmental outcome prediction from acoustic cry analysis in term and preterm infants. , 1987, Pediatrics.

[23]  A. Zabidi,et al.  Performance of Combined Support Vector Machine and Principal Component Analysis in recognizing infant cry with asphyxia , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[24]  Jayanta Mukhopadhyay,et al.  Classification of Infant Cries Using Dynamics of Epoch Features , 2013, J. Intell. Syst..

[25]  Xiaoxue Li,et al.  A flexible analysis tool for the quantitative acoustic assessment of infant cry. , 2013, Journal of speech, language, and hearing research : JSLHR.

[26]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[27]  A T Cacace,et al.  An acoustic template of newborn infant crying. , 1997, Folia phoniatrica et logopaedica : official organ of the International Association of Logopedics and Phoniatrics.

[28]  M. Linhares,et al.  Early neurobehavioral development of preterm infants , 2013 .

[29]  Carlo V Bellieni,et al.  Cry Features Reflect Pain Intensity in Term Newborns: An Alarm Threshold , 2004, Pediatric Research.

[30]  Michael P. Robb,et al.  Acoustic estimates of respiration in the pain cries of newborns. , 2011, International journal of pediatric otorhinolaryngology.

[31]  Robert P. W. Duin,et al.  Bagging, Boosting and the Random Subspace Method for Linear Classifiers , 2002, Pattern Analysis & Applications.

[32]  A Fort,et al.  Parametric and non-parametric estimation of speech formants: application to infant cry. , 1996, Medical engineering & physics.

[33]  K. Michelsson,et al.  Phonation in the newborn, infant cry. , 1999, International journal of pediatric otorhinolaryngology.

[34]  Sazali Yaacob,et al.  Analysis of Infant Cry Through Weighted Linear Prediction Cepstral Coefficients and Probabilistic Neural Network , 2012, Journal of Medical Systems.

[35]  Huan Liu,et al.  Book review: Machine Learning, Neural and Statistical Classification Edited by D. Michie, D.J. Spiegelhalter and C.C. Taylor (Ellis Horwood Limited, 1994) , 1996, SGAR.

[36]  Carlos A. Reyes García,et al.  Automatic infant cry analysis for the identification of qualitative features to help opportune diagnosis , 2012, Biomed. Signal Process. Control..

[37]  Carlos A. Reyes García,et al.  Classification of Infant Crying to Identify Pathologies in Recently Born Babies with ANFIS , 2004, ICCHP.

[38]  Mannes Poel,et al.  Analyzing Infant Cries Using a Committee of Neural Networks in Order to Detect Hypoxia Related Disorder , 2006, Int. J. Artif. Intell. Tools.

[39]  K. Michelsson,et al.  Cry Characteristics of 172 Healthy 1- to 7-Day-Old Infants , 2002, Folia Phoniatrica et Logopaedica.

[40]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[41]  Claudia Manfredi,et al.  Testing software tools with synthesized deviant voices for medicolegal assessment of occupational dysphonia , 2014, Biomed. Signal Process. Control..

[42]  Yoshiyuki Horii,et al.  Fundamental frequency characteristics of infant non-distress vocalization during the first twenty-four weeks , 1977, Journal of Child Language.

[43]  Henning Reetz,et al.  A Classification Model for Infant Cries with Hearing Impairment and Unilateral Cleft Lip and Palate , 2012, Folia Phoniatrica et Logopaedica.

[44]  K. Michelsson,et al.  Sound spectrographic analysis of pain cry in preterm infants. , 1983, Early human development.

[45]  M Robb,et al.  Acoustic examination of preterm and full-term infant cries: the long-time average spectrum. , 1999, Journal of speech, language, and hearing research : JSLHR.

[46]  C Manfredi,et al.  High-resolution cry analysis in preterm newborn infants. , 2009, Medical engineering & physics.

[47]  Kazuo Okanoya,et al.  Segmentation of expiratory and inspiratory sounds in baby cry audio recordings using hidden Markov models. , 2011, The Journal of the Acoustical Society of America.