|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Related Data for: A Machine Learning Approach For The Automatic Estimation Of Fixation-Time Data Signals’ Quality |
|
Identification Number: |
doi:10.21979/N9/0FU9ZG |
|
Distributor: |
DR-NTU (Data) |
|
Date of Distribution: |
2020-10-13 |
|
Version: |
2 |
|
Bibliographic Citation: |
Gabrieli, Giulio; Zhang, Lijun; Setoh, Peipei, 2020, "Related Data for: A Machine Learning Approach For The Automatic Estimation Of Fixation-Time Data Signals’ Quality", https://doi.org/10.21979/N9/0FU9ZG, DR-NTU (Data), V2, UNF:6:kPNKAuB3E6Sk9elIDziVzA== [fileUNF] |
|
Citation |
|
|
Title: |
Related Data for: A Machine Learning Approach For The Automatic Estimation Of Fixation-Time Data Signals’ Quality |
|
Identification Number: |
doi:10.21979/N9/0FU9ZG |
|
Authoring Entity: |
Gabrieli, Giulio (Nanyang Technological University) |
|
Zhang, Lijun (Nanyang Technological University) |
|
|
Setoh, Peipei (Nanyang Technological University) |
|
|
Software used in Production: |
Python |
|
Grant Number: |
020158-00001 |
|
Distributor: |
DR-NTU (Data) |
|
Access Authority: |
Gabrieli Giulio |
|
Depositor: |
Gabrieli Giulio |
|
Date of Deposit: |
2020-10-09 |
|
Holdings Information: |
https://doi.org/10.21979/N9/0FU9ZG |
|
Study Scope |
|
|
Keywords: |
Social Sciences, Social Sciences, Pupillometry, Infants, Fixation Time, Machine Learning |
|
Abstract: |
Fixation time measures have been widely adopted in infants' and young children's studies, because they can successfully tap on infants' meaningful nonverbal behaviors. While recording preverbal children's behavior is relatively simple, the analysis of collected signals requires extensive manual preprocessing. In this paper, we investigate the possibility of using different Machine Learning (ML) — a Linear SVC, a Non-Linear SVC, and K-Neighbors— classifiers to automatically discriminate between Usable and Unusable eye fixation recordings. Results of our models show an accuracy of up to the 80%, suggesting that ML tools can help human researchers during the preprocessing phase of collected data. |
|
Country: |
Singapore |
|
Unit of Analysis: |
Individual toddlers |
|
Universe: |
18- to 33-month-old toddlers |
|
Kind of Data: |
Behavioral Data |
|
Methodology and Processing |
|
|
Data Collector: |
Zhang, Lijun |
|
Frequency of Data Collection: |
Single visit |
|
Mode of Data Collection: |
Laboratory session |
|
Sources Statement |
|
|
Data Access |
|
|
Notes: |
Please contact giulio001@e.ntu.edu.sg or psetoh@ntu.edu.sg to get access to the original database. |
|
Other Study Description Materials |
|
|
Related Materials |
|
|
Zhang, L. (2017). Infants’ moral expectations about authority figures. Master's thesis, Nanyang Technological University, Singapore. <a href="https://hdl.handle.net/10356/70904">https://hdl.handle.net/10356/70904</a> |
|
|
Related Publications |
|
|
Citation |
|
|
Identification Number: |
10.3390/s20236775 |
|
Bibliographic Citation: |
Gabrieli, G., Balagtas, J. P. M., Esposito, G., & Setoh, P. (2020). A Machine Learning Approach for the Automatic Estimation of Fixation-Time Data Signals’ Quality. Sensors, 20(23), 6775. |
|
Citation |
|
|
Identification Number: |
10356/145869 |
|
Bibliographic Citation: |
Gabrieli, G., Balagtas, J. P. M., Esposito, G., & Setoh, P. (2020). A Machine Learning Approach for the Automatic Estimation of Fixation-Time Data Signals’ Quality. Sensors, 20(23), 6775. |
|
File Description--f54871 |
|
|
File: db.tab |
|
|
|
|
Notes: |
UNF:6:Ilgsr+/po2mt0okcjiWeRQ== |
|
File Description--f54870 |
|
|
File: scores.tab |
|
|
|
|
Notes: |
UNF:6:urkJqTSw8q/YhkhNmar/Sw== |
|
List of Variables: | |
|
Variables |
|
|
f54870 Location: |
Variable Format: character Notes: UNF:6:V4s1rxnh7yyr1MTtHi4dxg== |
|
f54870 Location: |
Summary Statistics: Min. 0.2072317716656497; Mean 0.4104991989833661; StDev 0.17727196834261355; Max. 0.5330402200679127; Valid 3.0; Variable Format: numeric Notes: UNF:6:dxnULIjyMWuZQO4V73hBOQ== |
|
f54870 Location: |
Summary Statistics: Max. 0.8102409638554217; Mean 0.7409638554216867; Min. 0.6024096385542169; StDev 0.11999147160868724; Valid 3.0 Variable Format: numeric Notes: UNF:6:MDIGvuRU2t3Qw0bZaM814g== |
|
f54870 Location: |
Summary Statistics: Max. 0.803921568627451; Mean 0.6928104575163399; Min. 0.5686274509803921; Valid 3.0; StDev 0.11819046614395509 Variable Format: numeric Notes: UNF:6:5zAlcy6SbxcJoM2i6P+w7Q== |
|
f54870 Location: |
Summary Statistics: Min. 0.9583333333333334; Valid 3.0; Max. 1.0; Mean 0.9768518518518519; StDev 0.021215628217388132 Variable Format: numeric Notes: UNF:6:4dKGOTJgr5y6AycmbeTm3Q== |
|
f54870 Location: |
Summary Statistics: Mean 0.6590909090909091; Max. 0.7954545454545454; StDev 0.13636363636363635; Min. 0.5227272727272727; Valid 3.0 Variable Format: numeric Notes: UNF:6:Kv89eruuBeIk7+BNpUijPg== |
|
f54870 Location: |
Summary Statistics: Max. 0.875; Valid 3.0; StDev 0.09985544762821888; Min. 0.6764705882352942; Mean 0.7819970453934999 Variable Format: numeric Notes: UNF:6:5ezFXRmtCR3z/z0cwatg+Q== |
|
f54870 Location: |
Summary Statistics: Valid 3.0; Mean 0.4042315331566124; Max. 0.4928602798068185; Min. 0.2618924633082486; StDev 0.1244995268186477; Variable Format: numeric Notes: UNF:6:ckjKsuzVsUGQ5h0ZSlyIXQ== |
|
Label: |
kNN.joblib |
|
Text: |
Dump of the trained classifier |
|
Notes: |
application/octet-stream |
|
Label: |
LinearSVC.joblib |
|
Text: |
Dump of the trained classifier |
|
Notes: |
application/octet-stream |
|
Label: |
ml.py |
|
Text: |
Script used to train and test the classifiers on NTU's HPC Gekko cluster |
|
Notes: |
text/x-python |
|
Label: |
NonLinearSVC.joblib |
|
Text: |
Dump of the trained classifier |
|
Notes: |
application/octet-stream |
|
Label: |
output_1605001925.txt |
|
Text: |
Timestamped output file. |
|
Notes: |
text/plain |