Research

Dr. Patel’s research focuses on understanding movement development and motor skill acquisition across entire lifespan, with an emphasis on using state-of-the-art sensor technology and machine learning techniques to measure and analyse biomechanics of movement patterns in naturalistic settings. Her work has implications for early identification of developmental differences, intervention strategies, and understanding fundamental principles of human motor learning.

Current Research Projects

Spontaneous Movement in Infancy

Infants move constantly in their first year of life, but how much and what influences this movement remain open questions. In this study, we use lightweight wearable sensors to capture infants’ natural, everyday movements in their home environments. By quantifying the amount of spontaneous movement and examining factors such as age, environment, and caregiving practices, we aim to shed light on the role of early movement in motor and cognitive development.

Key Methods: Wearable IMU sensors, home-based data collection, machine learning analysis

Automated Posture Classification in Infancy

Naturalistic video recordings provide a rich window into infant behavior, but analyzing these videos is time-consuming and subjective. This project leverages advances in artificial intelligence to automate the classification of infant postures (e.g., sitting, crawling, standing) from video data collected in the home. By building and validating posture recognition models, we aim to create scalable tools for studying motor development across diverse populations and environments.

Key Methods: Machine learning classification, longitudinal assessment

Virtual Reality and Motor Learning

This project explores how immersive virtual reality can be used as a tool for studying motor learning and adaptation. Using the Meta Quest headset and the VR puzzle game, we are testing how different practice schedules—such as adaptive versus random difficulty—affect performance and skill acquisition. Our goal is to better understand the potential of VR as both a research platform and a rehabilitation tool for enhancing motor learning in children and adults.

Key Methods: VR-based motor tasks, kinematic analysis, learning curve modeling

Exploratory Behavior in Early Childhood

Exploration is a key driver of learning in early childhood. In this laboratory-based study, we measure both the quantity and the kinematic patterns of exploratory behaviors in young children as they interact with different tasks and environments. Using a combination of sensor technology and behavioral analysis, we investigate how factors such as task demands, developmental stage, and individual differences shape exploration, ultimately aiming to connect patterns of exploration with broader outcomes in learning and development.

Key Methods: Motor skill assessment, kinematic analysis, longitudinal outcomes