Quantification and Visualization of Interpersonal Synchrony Using Wearable Sensors: A Case Study on Autistic and Neurotypical Children.

Researchers created a new way to automatically measure how well autistic and neurotypical children sync up during social interactions using wearable sensors. Instead of manually watching and coding videos (which takes a long time), this system can automatically detect when children are moving and interacting in sync with each other. The technology showed good results in telling the difference between high and low levels of social connection during classroom activities.

This study developed an automated sensor-based system to measure interpersonal synchrony (IS) in classroom interactions between autistic and neurotypical children using wearable sensors. The researchers compared time series analysis methods (Cross-correlation, Dynamic Time Warping, Cross-Wavelet Analysis) with traditional statistical features for machine learning classification of interaction levels. Results demonstrated that similarity-based features outperformed conventional approaches in distinguishing high and low interpersonal synchrony using ensemble classifiers. The study also evaluated two approaches for identifying pseudosynchrony and developed visualization tools for dynamic tracking of interaction patterns.

This framework offers a scalable, objective alternative to time-consuming manual video coding methods.

This technology could revolutionize social interaction assessment by providing objective, real-time measurement of interpersonal synchrony. May support intervention monitoring, social skills assessment, and research into social interaction patterns in autism, though further validation studies are needed.

Sample size not reported. Single case study limits generalizability. Validation relied on video-coded motor coordination as proxy measure rather than direct social interaction assessment. Unclear how findings translate to broader autism populations or other settings.

Interpersonal synchrony (IS), a key indicator of social interactions, is traditionally assessed through video data and manual coding methods, a process that is time-consuming and subjective. This study presents an automated sensor-based framework for quantifying and visualizing IS using time series data collected from wearable sensors, demonstrated through a case study of interactions between autistic and neurotypical children in classroom settings. We evaluated time series similarity measures, including Cross-correlation (CC), Dynamic Time Warping (DTW), and Cross-Wavelet Analysis (XWA), as features for machine learning (ML) models that classify interaction levels, where ground truth labels are derived from video-coded motor coordination as a behavioral proxy for IS. Results show that these similarity-based features outperform conventional statistical features in distinguishing high and low IS using ensemble classifiers.

We further compare two approaches for identifying pseudosynchrony: a surrogate data analysis for threshold estimation and a supervised learning approach for direct prediction, providing a systematic evaluation of their methodological trade-offs that has been largely overlooked in prior synchrony research. The developed visualization tools enable dynamic tracking of interaction patterns while filtering out pseudosynchrony. The proposed workflow offers a scalable, objective, and reproducible alternative to manual coding, addressing a key gap in the current literature and supporting broader applications in social, developmental, and rehabilitation research.