Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm
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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-04-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fped.2021.651356/full |
| _version_ | 1818419659772264448 |
|---|---|
| author | Ahnjili ZhuParris Matthijs D. Kruizinga Matthijs D. Kruizinga Matthijs D. Kruizinga Max van Gent Max van Gent Eva Dessing Eva Dessing Vasileios Exadaktylos Robert Jan Doll Frederik E. Stuurman Frederik E. Stuurman Gertjan A. Driessen Gertjan A. Driessen Adam F. Cohen Adam F. Cohen |
| author_facet | Ahnjili ZhuParris Matthijs D. Kruizinga Matthijs D. Kruizinga Matthijs D. Kruizinga Max van Gent Max van Gent Eva Dessing Eva Dessing Vasileios Exadaktylos Robert Jan Doll Frederik E. Stuurman Frederik E. Stuurman Gertjan A. Driessen Gertjan A. Driessen Adam F. Cohen Adam F. Cohen |
| author_sort | Ahnjili ZhuParris |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-14T12:42:05Z |
| format | Article |
| id | doaj.art-92ada131bdd64d0396f1b07f430f173a |
| institution | Directory Open Access Journal |
| issn | 2296-2360 |
| language | English |
| last_indexed | 2024-12-14T12:42:05Z |
| publishDate | 2021-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj.art-92ada131bdd64d0396f1b07f430f173a2022-12-21T23:00:52ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602021-04-01910.3389/fped.2021.651356651356Development and Technical Validation of a Smartphone-Based Cry Detection AlgorithmAhnjili ZhuParris0Matthijs D. Kruizinga1Matthijs D. Kruizinga2Matthijs D. Kruizinga3Max van Gent4Max van Gent5Eva Dessing6Eva Dessing7Vasileios Exadaktylos8Robert Jan Doll9Frederik E. Stuurman10Frederik E. Stuurman11Gertjan A. Driessen12Gertjan A. Driessen13Adam F. Cohen14Adam F. Cohen15Centre for Human Drug Research, Leiden, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsJuliana Children's Hospital, Haga Teaching Hospital, Hague, NetherlandsLeiden University Medical Centre, Leiden, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsJuliana Children's Hospital, Haga Teaching Hospital, Hague, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsJuliana Children's Hospital, Haga Teaching Hospital, Hague, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsLeiden University Medical Centre, Leiden, NetherlandsJuliana Children's Hospital, Haga Teaching Hospital, Hague, NetherlandsDepartment of Pediatrics, Maastricht University Medical Centre, Maastricht, NetherlandsCentre for Human Drug Research, Leiden, NetherlandsLeiden University Medical Centre, Leiden, NetherlandsIntroduction: 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.https://www.frontiersin.org/articles/10.3389/fped.2021.651356/fullcryinginfanthome-monitoringhospital-monitoringsmartphonemachine learning |
| spellingShingle | Ahnjili ZhuParris Matthijs D. Kruizinga Matthijs D. Kruizinga Matthijs D. Kruizinga Max van Gent Max van Gent Eva Dessing Eva Dessing Vasileios Exadaktylos Robert Jan Doll Frederik E. Stuurman Frederik E. Stuurman Gertjan A. Driessen Gertjan A. Driessen Adam F. Cohen Adam F. Cohen Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm Frontiers in Pediatrics crying infant home-monitoring hospital-monitoring smartphone machine learning |
| title | Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm |
| title_full | Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm |
| title_fullStr | Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm |
| title_full_unstemmed | Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm |
| title_short | Development and Technical Validation of a Smartphone-Based Cry Detection Algorithm |
| title_sort | development and technical validation of a smartphone based cry detection algorithm |
| topic | crying infant home-monitoring hospital-monitoring smartphone machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fped.2021.651356/full |
| work_keys_str_mv | AT ahnjilizhuparris developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT matthijsdkruizinga developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT matthijsdkruizinga developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT matthijsdkruizinga developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT maxvangent developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT maxvangent developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT evadessing developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT evadessing developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT vasileiosexadaktylos developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT robertjandoll developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT frederikestuurman developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT frederikestuurman developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT gertjanadriessen developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT gertjanadriessen developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT adamfcohen developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm AT adamfcohen developmentandtechnicalvalidationofasmartphonebasedcrydetectionalgorithm |