medigraphic.com
ISSN 1684-1859 (Print)

2022, Number 1

Next >>

Revista Cubana de Informática Médica 2022; 14 (1)

How to classify newborn cry through a supervised neural network

Escobedo BDI, Benitez LGJ, Cano OSD, Capdevila BL, Delgado GGM

Language: Spanish
References: 46
Page:
PDF size: 793.27 Kb.


ABSTRACT

Cry from newborn (0-28 days) is a way of communication for the interaction with surrounding world. Infant cry researches provide information that correlate among cries acoustic features with pathologies. It has been demonstrated that the infant cry is able to reflect child neurophysiology integrity and give meaning from newborn interaction with environment, also cognitive and social development from child. This contribution shows how to classify the cry of neonates with hypoxia and of a control group, into normal or pathological, through a supervised artificial neural network. Network implementation makes use of MATLAB® platform possibilities. Design and structuring of network take into consideration aspects as training algorithm, iterations, tests and classification intervals. All these referred aspects give as result an architectural, topology and functionalities from neural network able to classify cry in generalization stage offering good outcome. Different methods are applied in this paper as selection of cases, acoustic methods in order to obtain quantitative parameters from cry signals (in time, intensity and frequency domain). Methods related with design, implementation and validation (diagnostic test) of an artificial neural network able to carry out the goal of this paper (classification of cry) are used. With accuracy results in cry classification about 90 %, authors get ready conditions for an informatic solution (with addition of interface for data base interaction) for help as a non-invasive complement to medical diagnosis using cry from neonate induced by pain.


REFERENCES

  1. Wasz-Höckert O, Lind J, Vuorenkoski V, Partanen T, Valanne E. The infant cry a spectrographic and auditory analysis. Clinics in Devel Medicine. 1968; 29:1-42.

  2. Escobedo Beceiro DI. Análisis acústico del llanto del niño recién nacido orientado al diagnóstico de patología en su neurodesarrollo debido a Hipoxia [Tesis de Doctorado (Registro: 1015-2010)]. Santiago de Cuba: Universidad de Oriente, 2006.

  3. Escobedo Beceiro DI. Análisis acústico del llanto del niño recién nacido: Una metodología. Riga, Letonia: Editorial Académica Española. OmniScriptum Publishing Group, 2018.

  4. Vuorenkoski V, Lind J, Partanen TJ, Lejeune J, Lafourcade J, Wasz-Höckert O. Spectrographic analysis of cries from children with Maladie du Cri du Chat. Annls Paediat Fenn. 1966;12:174-80.

  5. Lind J, Vuorenkoski V, Rosberg G, Partanen T, Wasz-Höckert O. Spectrographic analysis of vocal response to pain stimuli in infants with Down´s Syndrome. Devel Med Child Neurol. 1970;12:478-86.

  6. Koivisto M, Wasz-Höckert O, Vuorenkoski V, Partanen T, Lind J. Cry studies in neonatal hyperbilirubinaemia. Acta Paediatr Scand Suppl. 1970;206:26-7.

  7. Michelsson K, Sirviö P. Cry analysis in herpes encephalitis. En: Proceedings of the 5th Scand Congr Perinat Med; 1975.

  8. Michelsson K. Cry analysis of symptomless low birth weight neonates and of asphyxiated newborn infants. Acta Paediatr Scand. 1971.

  9. Michelsson K, Sirviö P, Wasz-Höckert O. Pain cry in full-term asphyxiated newborn infants correlated with late findings. Acta Paediatr Scand. 1977;66(5): 611-16.

  10. Karelitz S, Fisichelli VR. The cry thresholds of normal infants and those with brain damage. J Pediat. 1962;61:679-85.

  11. Lind J, Wasz-Höckert O, Vuorenkoski V, Valanne E. The vocalization of a newborn, brain-damaged child. Annals Paediat Fenn. 1965;11:32-7.

  12. Sirviö P, Michelsson K. Sound-spectrographic cry analysis of normal and abnormal newborn infants. Folia phoniat. 1976; 28:161-73.

  13. Michelsson K, Wasz-Höckert O. The value of cry analysis in neonatology and early infancy. En: Murry T, Murry J, eds. Infant Communication: Cry and Early Speech. Houston: College-Hill Press, 1980:152-82.

  14. Wasz-Höckert O, Michelsson K, Lind J. Twenty-five years of scandinavian cry research. En: Lester BM, Boukydis CFZ, eds. Infant Crying: Theoretical and Research Perspectives. New York: Plenum Publishing Corporation, 1985:83-104.

  15. Pinyerd BJ. Infant cries: physiology and assessment. Neonatal Network, 1994; 13(4):15-20.

  16. Escobedo BDI, Cano OSD, Coello FE, Regüeiferos PL, Capdevila BL. Rising shift of pitch frequency in the infant cry of some pathologic cases. En: 2nd Int. Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications; Firenze: Firenze University Press, 2001:84-90.

  17. Escobedo BDI, Sanabria MF, Cano OSD, Marañón REJ. Adaptación del diagrama de bloques de un algoritmo para la extracción de la frecuencia fundamental en el llanto infantil. Revista Electrónica Ciencia en su PC. 2009;(2):50-60.

  18. Murry T. Perceptual and acoustic characteristics of infant cry types. En: Murry T, Murry J, eds. Infant Communication: Cry and Early Speech. Houston: College-Hill Press, 1980:251-71.

  19. Lester BM. Developmental outcome prediction from acoustic cry analysis in term and preterm infants. Pediatrics. 1987;80(4):529-34.

  20. Mende W, Wermke K, Schindler S, Wilzopolski K, Höck S. Variability of the cry melody and the melody spectrum as indicators for certain CNS disorders. En: Evans R, Kirkland J, Maclean B, eds. Early Child Development and Care. 1990: 95-107.

  21. Petroni M, Malowany AS, Johnston CC, Stevens BJ. Classification of infant cry vocalizations using Artificial Neural Networks (ANNs). En: Int Conf on Acoustic, Speech and Signal Processing. ICASSP-95; IEEE, 1995:3475-78.

  22. Schönweiler R, Kaese S, Möller S, Rinscheid A, Ptok M. Neuronal networks and self-organizing maps: new computer techniques in the acoustic evaluation of the infant cry. Int J Pediatr Otorhinolaryngol. 1996;38(1):1-11.

  23. Cano OSD, Escobedo BDI. Clasificación de unidades de llanto infantil mediante el mapa auto-organizado de Kohonen. En: Alonso L, ed. Reconocimiento de Patrones con Redes Neuronales. Salamanca: Imprenta Catedral, 2001:137-48.

  24. Lederman D, Cohen A, Zmora E, Wermke K, Hauschildt S, Stellzig-Eisenhauer A. On the use of hidden Markov models in infants´cry classification. En: The 22nd Convention of Electrical and Electronics Engineers; Israel: IEEE, 2002:350-52.

  25. Orozco GJ, Reyes GCA. Mel-frequency cepstrum coefficients extraction from infant cry for classification of normal and pathological cry with feed-forward neural networks. En: Int Joint Conf on Neural Networks. Proc of the 2003; Portland: 2003:3140-45.

  26. Orozco GJ, Reyes GCA. Detecting pathologies from infant cry applying scaled conjugate gradient neural networks. En: European Symposium on ANNs. ESANN 2003; Bruges: 2003:349-54.

  27. Cano OSD, Escobedo BDI, Ekkel T. A radial basis function network oriented for infant cry classification. En: Lecture Notes in Computer Science. Springer-Verlag Heidelberg, 2004:374-80.

  28. Cano OSD, Escobedo BDI, Reyes GCA, Regüeiferos PL, Capdevila BL. El enfoque multilateral para el problema de la clasificación del llanto infantil con fines diagnósticos. Revista Electrónica Ciencia en su PC. 2010;(3):96-108.

  29. Reyes GCA, Reyes GO, Cano OSD, Escobedo BDI, Zatarain R, Barrón EL. Soft computing approaches to the problem of infant cry classification with diagnostic purposes. En: Melin P, et al, eds. Studies in Computational Intelligence: Soft Computing for Recognition Based on Biometrics. Berlin: Springer-Verlag Berlin Heidelberg, 2010:3-18.

  30. Escobedo BDI, Sanabria MF, Marañón REJ, Cano OSD, Zamora ML, Regüeiferos PL, et al. Preclasificación de llanto infantil y pruebas preliminares de validez. En: I Congr Integr de las Ciencias y las Tecnologías Informáticas. Informática 2013; Santiago de Cuba: 2013.

  31. Cano OSD, Reyes GCA, Reyes GO, Escobedo BDI, Cano OJD. Emergence of a new alternative on cry analysis: the fuzzy approach. En: Folgueras J, et al, editors. V Latin Am Congr on Biomed Eng. IFMBE Proc; Berlin: Springer Berlin Heidelberg, 2013:846-49.

  32. Escobedo BDI, Sanabria MF, Marañón REJ, Cano OSD, Zamora ML, Regüeiferos PL, et al. Clasificación del llanto del recién nacido según la frecuencia fundamental. En: XIV Simp Int de Com Soc. Comunicación Social: Retos y Perspectivas; Santiago de Cuba: Ediciones Centro de Lingüística Aplicada, 2015:635-40.

  33. Gámez De La Rosa R, Escobedo BDI, Sanabria MF. A software version for getting frequency shifts on infant cry pitch. En: Braidot A, Hadad A, editors. VI Latin Am Congr on Biomed Eng. IFMBE Proc; Paraná: Springer International Publishing, 2015:611-14.

  34. James LS. Emergencias en la sala de partos. En: Fanaroff AA, Martin RJ, Merkatz IR, eds. Enfermedades del Feto y del Recién Nacido: Perinatología-Neonatología. La Habana: Editorial Científico-Técnica, 1977:230-50.

  35. Kliegman R, Stanton B, StGemeIII J, Schor N, Behrman R. Nelson. Tratado de pediatría. 20ª ed. Barcelona: Elsevier España, 2016.

  36. Enríquez EV, Berrojo MA. PCVOX, Manual de Usuario. Madrid: Escuela Técnica Superior de Ingenieros de Telecomunicación de la Universidad Politécnica de Madrid, 1992.

  37. Aguilera S, Santos A, Muñoz E. El visualizador del habla (VISHA). INFODIDAC. 1991;(13):35-43.

  38. Cano OSD, Escobedo BDI, Socarrás RM. BPVoz, sistema computarizado para el procesamiento de la voz. Santiago de Cuba: VIII Fórum de Ciencia y Técnica de la Universidad de Oriente, 1993.

  39. Soto LJE, Escobedo BDI, Cano OSD, Madrazo RR. BDLLANTO: base de datos de llanto (versión 1.0). En: V Simp Int de Com Soc; Santiago de Cuba: Impreso Universidad de Twente, 1997:228-33.

  40. Escobedo BDI, Sanabria MF, Cano OSD, Marañón REJ. Manual de Usuario Anavoz 1.0 (Registro: 1846-2008). Santiago de Cuba: Universidad de Oriente, 2008.

  41. Escobedo BDI, Sanabria MF, Marañón REJ, Cano OSD. Manual de Usuario Preclasificador de Llanto Infantil 1.0 (Registro: 2143-2009). Santiago de Cuba: Universidad de Oriente, 2009.

  42. Martín Del Brío B, Sanz MA. Redes Neuronales y Sistemas Difusos. Zaragoza: Ra-Ma, 2002.

  43. Altman DG, Bland JM. Statistics Notes: Diagnostic tests 1, sensitivity and specificity. BMJ. 1994;308:1552.

  44. Molinero L. Valoración de pruebas diagnósticas. En: Asociación de la Sociedad Española de Hipertensión; 2002:1-7.

  45. Newman TB, Kohn MA. Evidence-Based Diagnosis. N.York: Cambridge University Press, 2009.

  46. Torres MA, Miyar FI, Diez RH, Cano OSD, Escobedo BDI, Regüeiferos PL, et al. Una aproximación al diagnóstico del llanto infantil basado en redes neuronales supervisadas. En: I Taller AIRENE sobre Reconocimiento de Patrones con Redes Neuronales; Antofagasta: Universidad Católica del Norte, 1999:20-3.




2020     |     www.medigraphic.com