Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm
Open Access
- 13 April 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Pediatrics
Abstract
Introduction: The duration and frequency of crying of an infant can be indicative of its health. Manual tracking and labeling of crying is laborious, subjective, and sometimes inaccurate. The aim of this study was to develop and technically validate a smartphone-based algorithm able to automatically detect crying. Methods: For the development of the algorithm a training dataset containing 897 5-s clips of crying infants and 1,263 clips of non-crying infants and common domestic sounds was assembled from various online sources. OpenSMILE software was used to extract 1,591 audio features per audio clip. A random forest classifying algorithm was fitted to identify crying from non-crying in each audio clip. For the validation of the algorithm, an independent dataset consisting of real-life recordings of 15 infants was used. A 29-min audio clip was analyzed repeatedly and under differing circumstances to determine the intra- and inter- device repeatability and robustness of the algorithm. Results: The algorithm obtained an accuracy of 94% in the training dataset and 99% in the validation dataset. The sensitivity in the validation dataset was 83%, with a specificity of 99% and a positive- and negative predictive value of 75 and 100%, respectively. Reliability of the algorithm appeared to be robust within- and across devices, and the performance was robust to distance from the sound source and barriers between the sound source and the microphone. Conclusion: The algorithm was accurate in detecting cry duration and was robust to various changes in ambient settings.This publication has 26 references indexed in Scilit:
- Application of Pattern Recognition Techniques to the Classification of Full-Term and Preterm Infant CryJournal of Voice, 2016
- Comparing Random Forest with Logistic Regression for Predicting Class-Imbalanced Civil War Onset DataPolitical Analysis, 2016
- Audio Pattern Recognition of Baby Crying Sound EventsJournal of the Audio Engineering Society, 2015
- openSMILE:)ACM SIGMultimedia Records, 2015
- Automatic classification of infant cry: A reviewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- The Crying Infant: Diagnostic Testing and Frequency of Serious Underlying DiseasePEDIATRICS, 2009
- Clinical Response to 2 Commonly Used Switch Formulas Occurs within 1 DayClinical Pediatrics, 2008
- Assessment of infant cry: Acoustic cry analysis and parental perceptionMental Retardation and Developmental Disabilities Research Reviews, 2005
- Double-blind placebo-controlled trial of omeprazole in irritable infants with gastroesophageal refluxThe Journal of Pediatrics, 2003
- Parental diary of infant cry and fuss behaviour.Archives of Disease in Childhood, 1988