A Machine Learning Approach for the Automatic Estimation of Fixation-Time Data Signals’ Quality

Fixation time measures have been widely adopted in studies with infants and young children because they can successfully tap on their meaningful nonverbal behaviors. While recording preverbal children’s behavior is relatively simple, 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 and labelling phase of collected data.

[1]  E. Spelke,et al.  Origins of knowledge. , 1992, Psychological review.

[2]  Amos J. Storkey,et al.  Data Augmentation Generative Adversarial Networks , 2017, ICLR 2018.

[3]  Mohamed Bekkar,et al.  Evaluation Measures for Models Assessment over Imbalanced Data Sets , 2013 .

[4]  Munirah Bangee,et al.  Loneliness and attention to social threat in young adults: Findings from an eye tracker study , 2014 .

[5]  Jan Gorodkin,et al.  Comparing two K-category assignments by a K-category correlation coefficient , 2004, Comput. Biol. Chem..

[6]  Richard N Aslin,et al.  Automated Corneal-reflection Eye Tracking in Infancy: Methodological Developments and Applications to Cognition Calibration of Eye-tracking Systems , 2022 .

[7]  M. Bornstein,et al.  Assessing Mothers’ Postpartum Depression From Their Infants’ Cry Vocalizations , 2020, Behavioral sciences.

[8]  Gari D. Clifford,et al.  A machine learning approach to multi-level ECG signal quality classification , 2014, Comput. Methods Programs Biomed..

[9]  J. Deloache,et al.  An examination of interference effects in infants' memory for faces. , 1977, Child development.

[10]  A. Premack,et al.  Infants Attribute Value to the Goal-Directed Actions of Self-propelled Objects , 1997, Journal of Cognitive Neuroscience.

[11]  B. Sodian,et al.  Do infants apply the principle of rational action to human agents , 2004 .

[12]  Cara H. Cashon,et al.  Eight-Month-Old Infants' Perception of Possible and Impossible Events. , 2000, Infancy : the official journal of the International Society on Infant Studies.

[13]  Juraj Kacur,et al.  Eye Tracking and KNN Based Detection of Schizophrenia , 2019, 2019 International Symposium ELMAR.

[14]  Lijun Zhang.  Infants’ moral expectations about authority figures , 2017 .

[15]  Esben Jannik Bjerrum,et al.  Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics , 2017, ArXiv.

[16]  R. Baillargeon,et al.  Infants expect leaders to right wrongs , 2019, Proceedings of the National Academy of Sciences.

[17]  Wes McKinney,et al.  pandas: a Foundational Python Library for Data Analysis and Statistics , 2011 .

[18]  Leo Pauly,et al.  Detection of drowsiness based on HOG features and SVM classifiers , 2015, 2015 IEEE International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN).

[19]  Paula Rubio-Fernández.  Publication standards in infancy research: Three ways to make Violation-of-Expectation studies more reliable. , 2019, Infant behavior & development.

[20]  Daniel P. Kennedy,et al.  Atypical Visual Saliency in Autism Spectrum Disorder Quantified through Model-Based Eye Tracking , 2015, Neuron.

[21]  Giulio Gabrieli,et al.  PySiology: A Python Package for Physiological Feature Extraction , 2020, Neural Approaches to Dynamics of Signal Exchanges.

[22]  Glenn I. Roisman,et al.  Young infants expect an unfamiliar adult to comfort a crying baby: Evidence from a standard violation-of-expectation task and a novel infant-triggered-video task , 2018, Cognitive Psychology.

[23]  Stan Szpakowicz,et al.  Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation , 2006, Australian Conference on Artificial Intelligence.

[24]  Maayan Stavans,et al.  Children Hold Leaders Primarily Responsible, Not Entitled. , 2020, Child development.

[25]  Karen Wynn,et al.  Young infants prefer prosocial to antisocial others. , 2011, Cognitive development.

[26]  Jing Zhong,et al.  Data Augmentation for Mixed Spectral Signatures Coupled with Convolutional Neural Networks , 2019, 2019 9th International Conference on Information Science and Technology (ICIST).

[27]  K. Hiraki,et al.  Baby arithmetic: one object plus one tone , 2004, Cognition.

[28]  B. C. Lacey,et al.  Pupillary and cardiac activity during visual attention. , 1973, Psychophysiology.

[29]  A. Pickering.  The mangle of practice : time, agency, and science , 1997 .

[30]  K. Moeller,et al.  Insights into numerical cognition: considering eye-fixations in number processing and arithmetic , 2016, Psychological Research.

[31]  Rochel Gelman,et al.  Young infants have biological expectations about animals , 2013, Proceedings of the National Academy of Sciences.

[32]  G. Westermann,et al.  Pupillometry in Infancy Research , 2016 .

[33]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[34]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[35]  Cesare Furlanello,et al.  pyphysio: A physiological signal processing library for data science approaches in physiology , 2019, SoftwareX.

[36]  Xiaoli Li,et al.  The identification of children with autism spectrum disorder by SVM approach on EEG and eye-tracking data , 2020, Comput. Biol. Medicine.

[37]  D. Chicco,et al.  The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation , 2020, BMC Genomics.

[38]  Dana Kulic,et al.  Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks , 2017, ICMI.

[39]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[40]  A. Woodward.  Infants selectively encode the goal object of an actor's reach , 1998, Cognition.

[41]  R. L. Fantz.  Visual Experience in Infants: Decreased Attention to Familiar Patterns Relative to Novel Ones , 1964, Science.

[42]  P. Vernon.  THE RORSCHACH INK‐BLOT TEST. III , 1933 .

[43]  Yanxia Zhang,et al.  Discrimination of gaze directions using low-level eye image features , 2011, PETMEI '11.

[44]  J. Hamlin,et al.  Social evaluation by preverbal infants , 2007, Nature.

[45]  Andrew Pickering,et al.  The mangle of practice : time, agency, and science , 1997 .

[46]  Q Li,et al.  Dynamic time warping and machine learning for signal quality assessment of pulsatile signals , 2012, Physiological measurement.

[47]  L. Harris,et al.  Developmental Changes in Infants’ Categorization of Anger and Disgust Facial Expressions , 2017, Developmental psychology.

[48]  Christian Graff,et al.  Four-Day-Old Human Neonates Look Longer at Non-Biological Motions of a Single Point-of-Light , 2007, PloS one.

[49]  Renee L Baillargeon,et al.  Psychological and Sociomoral Reasoning in Infancy , 2014 .

[50]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[51]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[52]  R. Baillargeon,et al.  Young infants’ reasoning about physical events involving inert and self-propelled objects , 2009, Cognitive Psychology.

[53]  Sunny Shin,et al.  Do 15-Month-Old Infants Understand False Beliefs ? , 2005 .

[54]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[55]  S. R. Mahadeva Prasanna,et al.  Robust Mizo digit recognition using data augmentation and tonal information , 2018, Speech Prosody 2018.

[56]  T. Racine,et al.  An Analysis of the Conceptual Foundations of the Infant Preferential Looking Paradigm , 2014, Human Development.

[57]  Ming Jiang,et al.  Machine learning accurately classifies age of toddlers based on eye tracking , 2019, Scientific Reports.