An official website of the United States government
Abstract Classroom engagement plays a crucial role in preschoolers' development, yet the correlates of engagement, especially among children with autism spectrum disorder (ASD) and developmental delays (DD), remains unknown. This study examines levels of engagement with classroom social partners and tasks among children in three groups ASD, DD, and typical development (TD). Here, we asked whether children's vocal interactions (vocalizations to and from peers and teachers) were associated with their classroom engagement with social partners (peers and teachers) and with tasks, and whether the association between classroom engagement and vocal interactions differed between children in the ASD group and their peers in the DD and TD groups. Automated measures of vocalizations and location quantified children's vocal interactions with peers and teachers over the course of the school year. Automated location and vocalization data were used to capture both (1) children's vocal output to specific peers and teachers, and (2) the vocal input they received from those peers and teachers. Participants were 72 3–5‐year‐olds (Mage = 48.6 months, SD = 7.0, 43% girls) and their teachers. Children in the ASD group displayed lower engagement with peers, teachers, and tasks than children in the TD group; they also showed lower engagement with peers than children in the DD group. Overall, children's own vocalizations were positively associated with engagement with social partners. Thus, although children in the ASD group tend to have lower engagement scores than children in the TD group, active participation in vocal interactions appears to support their classroom engagement with teachers and peers.
more »
« less
Towards Forecasting Engagement in Children with Autism Spectrum Disorder using Social Robots and Deep Learning
The personalization of therapy for children with Autism Spectrum Disorder (ASD) has been found to be crucial in comparison to a universal approach. This personalization in therapy demands the ability to adapt to the individual’s needs and engagement levels to avoid disinterest or meltdowns. This paper proposes the first step towards forecasting engagement of children with ASD during therapy sessions using Blood Volume Pulse (BVP). The BVP data is collected from an interactive session between two children with ASD in the presence of a NAO robot, and the forecast is made using a Deep Learning architecture combining Convolutional Neural Networks (CNNs) and Long-short term Memory (LSTM). Out of the three networks tested: LSTM, CNN and CNN+LSTM, the latter was found to outperform the others and gave a coefficient of determination of 0.955. The forecast was done using less than 3 minutes of prior BVP data to forecast 3 minutes into the future time steps.
more »
« less
- Award ID(s):
- 1838808
- PAR ID:
- 10464882
- Date Published:
- Journal Name:
- Towards Forecasting Engagement in Children with Autism Spectrum Disorder using Social Robots and Deep Learning
- Page Range / eLocation ID:
- 838 to 843
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Robot-mediated interventions have been investigated for the treatment of social skill deficits amongst children with Autism Spectrum Disorder (ASD). Does the use of a Nao robot as a mediator increase vocal interaction between children with ASD? The present study examined the vocalization and turn-taking rate in six children with ASD (mean age = 11.4 years, SD = 0.86 years) interacting with and without a Nao robot for 10 sessions, order counterbalanced. Each session lasted nine minutes. In the Robot condition, the robot provided vocal prompts; in the No Robot condition, children interacted freely. Child vocalization and turn-taking rate defined as the number of utterances/turns per second were measured. Results demonstrated that three children produced higher vocalization and turn-taking rates when a robot was present, and two when it was absent. One participant produced higher vocalization rates when the robot was not present, but more conversational turns when the robot was present. The findings suggest that the use of a Nao robot as a social mediator increases vocalization and turn-taking rates among children with ASD, but large individual variability is observed. The effect of the robot as a mediator on lexical diversity of child speech will also be investigated.more » « less
-
Many coastal cities are facing frequent flooding from storm events that are made worse by sea level rise and climate change. The groundwater table level in these low relief coastal cities is an important, but often overlooked, factor in the recurrent flooding these locations face. Infiltration of stormwater and water intrusion due to tidal forcing can cause already shallow groundwater tables to quickly rise toward the land surface. This decreases available storage which increases runoff, stormwater system loads, and flooding. Groundwater table forecasts, which could help inform the modeling and management of coastal flooding, are generally unavailable. This study explores two machine learning models, Long Short-term Memory (LSTM) networks and Recurrent Neural Networks (RNN), to model and forecast groundwater table response to storm events in the flood prone coastal city of Norfolk, Virginia. To determine the effect of training data type on model accuracy, two types of datasets (i) the continuous time series and (ii) a dataset of only storm events, created from observed groundwater table, rainfall, and sea level data from 2010–2018 are used to train and test the models. Additionally, a real-time groundwater table forecasting scenario was carried out to compare the models’ abilities to predict groundwater table levels given forecast rainfall and sea level as input data. When modeling the groundwater table with observed data, LSTM networks were found to have more predictive skill than RNNs (root mean squared error (RMSE) of 0.09 m versus 0.14 m, respectively). The real-time forecast scenario showed that models trained only on storm event data outperformed models trained on the continuous time series data (RMSE of 0.07 m versus 0.66 m, respectively) and that LSTM outperformed RNN models. Because models trained with the continuous time series data had much higher RMSE values, they were not suitable for predicting the groundwater table in the real-time scenario when using forecast input data. These results demonstrate the first use of LSTM networks to create hourly forecasts of groundwater table in a coastal city and show they are well suited for creating operational forecasts in real-time. As groundwater table levels increase due to sea level rise, forecasts of groundwater table will become an increasingly valuable part of coastal flood modeling and management.more » « less
-
Robot-mediated therapy is an emerging field of research seeking to improve therapy for children with Autism Spectrum Disorder (ASD). Current approaches to autonomous robot-mediated therapy often focus on having a robot teach a single skill to children with ASD and lack a personalized approach to each individual. More recently, Learning from Demonstration (LfD) approaches are being explored to teach socially assistive robots to deliver personalized interventions after they have been deployed but these approaches require large amounts of demonstrations and utilize learning models that cannot be easily interpreted. In this work, we present a LfD system capable of learning the delivery of autism therapies in a data-efficient manner utilizing learning models that are inherently interpretable. The LfD system learns a behavioral model of the task with minimal supervision via hierarchical clustering and then learns an interpretable policy to determine when to execute the learned behaviors. The system is able to learn from less than an hour of demonstrations and for each of its predictions can identify demonstrated instances that contributed to its decision. The system performs well under unsupervised conditions and achieves even better performance with a low-effort human correction process that is enabled by the interpretable model.more » « less
-
Autism Spectrum Disorder (ASD) is a neurodevelopmental condition often associated with delayed motor skills. The Motor Assessment Battery for Children – Second Edition (MABC-2) is a standardized motor assessment for identifying motor delays pertaining to ASD. It evaluates fine and gross motor tasks across three domains: Manual Dexterity, Aiming & Catching, and Balance. These tasks are categorized into three age bands: 3-6, 7-10, and 11-16. Virtual Reality (VR) has emerged as a promising intervention in the ASD realm. This study aimed to investigate the potential of VR to assist children with ASD in performing the gross motor skills (i.e., ball skills and balance) in the MABC-2. The children who participated in the study were attendees of a local Autism Summer Camp. Our research focused on adapting motor tasks for ages 7-10 (i.e., Age Band 2) to VR, as most campers fell in this age range. Within the VR environment, children could observe avatar demonstrations and practice motor skills in a highly immersive setting. The VR environment featured avatars demonstrating ball skills and balancing tasks. Developed with the Unity game engine, 3D software Blender, C# scripting, and mixed reality toolkits, this environment was tested on the Meta Quest 2 Oculus. The children's gross motor skill performance was scored before and after VR interactions. The test standard scores were categorized through a traffic-light scoring system comprising red, amber, and green zones. A standard score ≤4 is classified in the red zone, indicating a significant movement difficulty; a standard score >4 and ≤7 is classified in the amber zone, indicating a risk for movement difficulty; and a standard score >7 is classified in the green zone, indicating no movement difficulty detected. Following the VR intervention, we observed a notable improvement in the balance score (p < 0.05). Furthermore, using the Random Forest machine learning model, we analyzed a combined dataset of MABC-2 scores from 250 children across all age bands from the Autism Summer Camp in previous years and the MABC-2 scores from the 18 children in the present study. Our analysis revealed that Balance was crucial in classifying children with ASD with motor delays, with an importance score of 0.195, nearly double that of Manual Dexterity and Aiming & Catching. When the model was exclusively applied to the Balance component score, it achieved an impressive accuracy rate of 91% in identifying children with ASD. In summary, our findings underscore the promise of VR in enhancing balance among children with ASD. The Random Forest analysis reaffirmed the significant role of balance in identifying children with ASD. Given its precision in detecting children with ASD based on their balance performance, we anticipate the potential of future machine learning advancements in this field. Our research validates the effectiveness of a VR-based approach and emphasizes the significance of collaborative research in providing valuable support to the underserved ASD population.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/SoutheastCon51012.2023.10115150
