JYJulia Yurkovic‐Harding

Julia Yurkovic‐Harding

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Julia Yurkovic‐Harding has a total of 13 co-authors. Here are the top co-authors by number of shared publications:

  • Jessica Bradshaw

    Department of Psychology University of South Carolina Columbia South Carolina USA

    4 shared publications
  • Chen Yu

    Department of Psychology University of Texas at Austin

    2 shared publications
  • Craig A. Erickson

    Department of Psychiatry and Behavioral Neuroscience, Cincinnati Children’s Hospital, Burnet Avenue, Cincinnati, OH 45229, USA

    2 shared publications
  • Daniel P. Kennedy

    Department of Psychological and Brain Sciences, Indiana University – Bloomington, E 10th Street, Bloomington, IN, 47405, USA

    2 shared publications
  • Ernest V. Pedapati

    Division of Psychiatry, Cincinnati Children’s Hospital Medical Center, Burnet Avenue, Cincinnati, OH 45229, USA

    2 shared publications
  • Grace Lisandrelli

    Department of Psychological and Brain Sciences, Indiana University – Bloomington, E 10th Street, Bloomington, IN, 47405, USA

    2 shared publications

Latest Publications

  • Open Access

    Social Behavior Forecasts Moment‐to‐Moment Changes in RSA in Infants With Autism

    by Julia Yurkovic‐Harding, Vignesh Narayanan, Jessica Bradshaw

    Respiratory sinus arrhythmia (RSA), an index of physiological regulation, increases during infancy, and is associated with concurrent and later social abilities. However, little is known about the moment‐by‐moment, bidirectional dynamics of RSA and social behaviors. This is particularly relevant to autism spectrum disorder (ASD), in which altered RSA may underly social deficits. The current study investigated the dynamic relationship between RSA and social behaviors in very young infants with and without ASD. Infants ( N = 74) at elevated (EL) or low (LL) familial likelihood for ASD who were later classified as typically developing (TD) or having ASD were included in analyses. These infants completed a dyadic, face‐to‐face interaction with their caregivers at 3, 4, and 6‐months. Infant social behaviors (looking and smiling) and RSA during the interaction were quantified. Granger causality analyses determined if RSA significantly “forecasted” social behaviors and vice versa. Social behavior, especially looking to the caregiver, significantly forecasted moment‐to‐moment changes RSA in more infants than the converse. Smiles forecasted RSA in more EL infants than LL infants. Looks forecasted RSA in more infants with ASD than TD infants. We found a bidirectional relationship between RSA and social behavior, with social behavior more often forecasting RSA. Infants later diagnosed with ASD showed a greater likelihood for social attention to forecast RSA than TD infants, suggesting early differences in dynamic behavior‐physiology processes. Additionally, EL infants showed a greater likelihood for smiling to forecast RSA than LL infants, suggesting that ASD likelihood may influence early physiological and social dynamics, regardless of outcome. Summary: We explored the dynamic and bidirectional relationship between social behavior and respiratory sinus arrhythmia (RSA) in infants with and without autism spectrum disorder (ASD). Infant social behavior, especially looking to the parent, significantly forecasted moment‐to‐moment changes in RSA in more infants than the converse. Smiles forecasted RSA in more infants at elevated than low likelihood for ASD, suggesting that ASD likelihood may influence early physiological and social dynamics. Looks forecasted RSA in more infants with ASD than TD infants, suggesting early differences in dynamic behavior‐physiology processes.


  • Open Access

    Making Machine Learning Accessible for Developmental Science: The Case of Automated Face Detection

    by Teodor Y. Nikolov, Julia Yurkovic‐Harding, Tamas Foldes, Jessica Bradshaw, Yu‐Kun Lai, Hana D'SOuza

    The last decade has seen rapid advancements in machine learning, significantly transforming fields like cybersecurity and healthcare. Developmental science has been slower to adopt these technologies. Yet, machine learning holds immense potential to transform this field, enabling scalable and data‐driven insights into developmental processes. Broader adoption is currently hindered by challenges in algorithm selection and technical implementation . We address these barriers by focusing on an area that has reached high sophistication from a machine learning perspective while also being of significant interest to developmental scientists: face detection . Face detection is crucial for analysing visual experiences through children's dynamic, first‐person views. Automatising this process allows efficient handling of large egocentric datasets, enabling well‐powered studies otherwise limited by labour‐intensive manual annotation. Here, we systematically evaluated 13 state‐of‐the‐art face detection algorithms (DeepFace library) using data from two increasingly common developmental methodologies involving children under 3 years of age: head‐mounted eye‐tracking in more structured settings ( N = 20; n = 10 4‐month‐olds, n = 10 8‐month‐olds) and head‐mounted cameras in naturalistic home environments ( N = 10 18–29‐month‐olds). Benchmarking these algorithms against manual annotations revealed that YOLOv11Face (M) and RetinaFace consistently outperformed others in terms of precision and recall, exhibiting strong concordance with manual ratings, lower error, reduced systematic deviation and robust rank‐order correlations with manual annotations. To facilitate broader adoption, we introduce an accessible face detection tool ( TinyExplorer Detection App ), promoting efficiency, scalability, and innovation in developmental science by widening access to machine learning.


  • The Dynamics of Looking and Smiling Differ for Young Infants at Elevated Likelihood for ASD

    by Julia Yurkovic‐Harding, Jessica Bradshaw

    Social smiling is the earliest gained social communication skill, emerging around 2 months of age. From 2 to 6‐months, infants primarily smile in response to caregivers. After 6 months, infants coordinate social smiles with other social cues to initiate interactions with the caregiver. Social smiling is reduced in older infants with autism spectrum disorder (ASD) but has rarely been studied before 6 months of life. The current study therefore aimed to understand the component parts of infant social smiles, namely look to caregiver and smile, during face‐to‐face interactions in 3 and 4‐month‐old infants at elevated (EL) and low likelihood (LL) for ASD. We found that EL and LL infants looked to their caregiver and smiled for similar amounts of time and at similar rates, suggesting that social smiling manifests similarly in both groups. A nuanced difference between groups emerged when considering temporal dynamics of looking and smiling. Specifically, 3‐month‐old EL infants demonstrated extended looking to the caregiver after smile offset. These findings suggest that social smiling is largely typical in EL infants in early infancy, with subtle differences in temporal coupling. Future research is needed to understand the full magnitude of these differences and their implications for social development.


  • Automated Detection of Faces in Infant and Parent First-Person Views During Play

    by Julia Yurkovic-Harding, Jessica Bradshaw

    Attention to faces is linked to social and communicative developmental outcomes, but questions remain about when and why infants look to faces in their everyday lives. To make answering these questions tractable, advanced methodological techniques are needed. Thirty infants played with their parent while wearing head-mounted eye trackers at 4- and 8-months-old. Computer vision automatic face detection software (RetinaFace) identified faces, including facial features, from the first-person camera views of both the infant and the parent. Additionally, emotion recognition software identified moments when the parent smiled. Automatic face detection was highly convergent with human coding. We employed a Viterbi algorithm to ameliorate moments when a face was missed (i.e., false negative) or incorrectly detected (i.e., false positive). Finally, we compared the availability of and attention to faces across age. Faces were more available to 4-month-old dyads than 8-month-old dyads, and 4-month-old infants looked at faces more than 8-month-old infants. Infants at both ages primarily looked to the eye region of the face, and parent smiling did not impact attention to the face. Implications of the current work and future directions are discussed.


  • Children with ASD establish joint attention during free-flowing toy play without face looks

    by Julia Yurkovic-Harding, Grace Lisandrelli, Rebecca C. Shaffer, Kelli C. Dominick, Ernest V. Pedapati, Craig A. Erickson, Chen Yu, Daniel P. Kennedy


  • Open Access

    Using head-mounted eye tracking to examine visual and manual exploration during naturalistic toy play in children with and without autism spectrum disorder

    by Julia R. Yurkovic, Grace Lisandrelli, Rebecca C. Shaffer, Kelli C. Dominick, Ernest V. Pedapati, Craig A. Erickson, Daniel P. Kennedy, Chen Yu

    Multimodal exploration of objects during toy play is important for a child’s development and is suggested to be abnormal in children with autism spectrum disorder (ASD) due to either atypical attention or atypical action. However, little is known about how children with ASD coordinate their visual attention and manual actions during toy play. The current study aims to understand if and in what ways children with ASD generate exploratory behaviors to toys in natural, unconstrained contexts by utilizing head-mounted eye tracking to quantify moment-by-moment attention. We found no differences in how 24- to 48-mo children with and without ASD distribute their visual attention, generate manual action, or coordinate their visual and manual behaviors during toy play with a parent. Our findings suggest an intact ability and willingness of children with ASD to explore toys and suggest that context is important when studying child behavior.