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
-
-
Abstract In inclusive preschools, children with autism spectrum disorder (ASD) and other developmental disabilities (DD) are less socially engaged with peers than are typically developing (TD) children. However, there is limited objective information describing how children with ASD engage with teachers, or how teacher engagement compares to engagement with peers. We tracked over 750 hours' worth of children's (N = 77;NASD = 24,NDD = 23,NTD = 30;Mage = 43.98 months) and teachers' (N = 12) locations and orientations across eight inclusion preschool classrooms to quantify child‐teacher and child‐peer social preference. Social approach velocity and time in social contact were computed for each child and compared across social partners to index children's preference for teachers over peers. Children with ASD approached teachers–‐but not peers—more quickly than children with TD, and children with ASD were approached more quickly by teachers and more slowly by peers than children with TD. Children with ASD spent less time in social contact with peers and did not differ from children with TD in their time in social contact with teachers. Overall, children with ASD showed a greater preference for approaching, being approached by, and being in social contact with teachers (relative to peers) than children with TD. No significant differences emerged between children with DD and children with TD. In conclusion, children with ASD exhibited a stronger preference for engaging with teachers over peers, re‐emphasizing the need for classroom‐based interventions that support the peer interactions of children with ASD.more » « less
-
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
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/SoutheastCon51012.2023.10115150
