|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Related Data for: Assessing mothers’ post-partum depression from their infants’ cry vocalizations |
|
Identification Number: |
doi:10.21979/N9/IU0UOB |
|
Distributor: |
DR-NTU (Data) |
|
Date of Distribution: |
2019-12-17 |
|
Version: |
2 |
|
Bibliographic Citation: |
Gabrieli, Giulio; Esposito, Gianluca, 2019, "Related Data for: Assessing mothers’ post-partum depression from their infants’ cry vocalizations", https://doi.org/10.21979/N9/IU0UOB, DR-NTU (Data), V2, UNF:6:u+hovzOvW18kdhs7ZDyIOg== [fileUNF] |
|
Citation |
|
|
Title: |
Related Data for: Assessing mothers’ post-partum depression from their infants’ cry vocalizations |
|
Identification Number: |
doi:10.21979/N9/IU0UOB |
|
Authoring Entity: |
Gabrieli, Giulio (Nanyang Technological University) |
|
Esposito, Gianluca (Nanyang Technological University) |
|
|
Software used in Production: |
Google Cloud - AutoML Tables |
|
Grant Number: |
GA-2013-630166 |
|
Grant Number: |
GA-2013-630166 |
|
Distributor: |
DR-NTU (Data) |
|
Access Authority: |
Gabrieli Giulio |
|
Depositor: |
Gabrieli Giulio |
|
Date of Deposit: |
2019-12-17 |
|
Holdings Information: |
https://doi.org/10.21979/N9/IU0UOB |
|
Study Scope |
|
|
Keywords: |
Social Sciences, Social Sciences, acoustic analysis, infant cry, post-partum depression |
|
Abstract: |
Postpartum depression (PPD) is a condition that affects up to the 15% of mothers in high-income countries, reduces attention toward the needs of the child, which is among the first causes of infanticide. PPD is usually identified using self-report measures and therefore the diagnosis may not always be valid. Previous studies highlighted the presence of significant differences in the acoustical properties of the vocalizations of children of depressed and healthy mothers. In this study, cry episodes of infants of depressed and non-depressed mothers are analyzed to investigate the possibility that a machine learning model can identify PPD from the acoustical properties of infants' vocalizations. Acoustic features are first extracted from recordings of crying infants, then novel cloud-based artificial intelligence models are employed to identify maternal depression versus non depression from those features. Trained model shows that commonly adopted acoustical features to individuate Post-Partum Depressed mothers with very high accuracy (89.5%). |
|
Kind of Data: |
Estimated acoustic features (f0, f1,f2,f3,f4, Intensity, Sex, Mother's age) |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Notes: |
Please contact giulio001@e.ntu.edu.sg or gianluca.esposito@ntu.edu.sg to get access to the dataset. |
|
Other Study Description Materials |
|
|
Related Publications |
|
|
Citation |
|
|
Identification Number: |
10.1371/journal.pone.0169066 |
|
Bibliographic Citation: |
Esposito, G., Manian, N., Truzzi, A., & Bornstein, M. H. (2017). Response to infant cry in clinically depressed and non-depressed mothers. PloS one, 12(1), e0169066. |
|
Citation |
|
|
Identification Number: |
10356/84821 |
|
Bibliographic Citation: |
Esposito, G., Manian, N., Truzzi, A., & Bornstein, M. H. (2017). Response to infant cry in clinically depressed and non-depressed mothers. PloS one, 12(1), e0169066. |
|
File Description--f18141 |
|
|
File: ProcessedData.tab |
|
|
|
|
Notes: |
UNF:6:u+hovzOvW18kdhs7ZDyIOg== |
|
Label: |
Praat_Script.txt |
|
Notes: |
text/plain |
|
Label: |
README.txt |
|
Notes: |
text/plain |