Novel pattern detection in children with Autism Spectrum Disorder using Iterative Subspace Identification

Min, Cheol-Hong; Tewfik, A.H.

doi:10.1109/icassp.2010.5495885

Cited by 19 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, our study is the first to use artificial intelligence algorithms to measure the duration of vocal stereotypy during sessions. Our results replicate and extend prior studies that have used machine learning to measure motor and vocal forms of stereotypy (Goodwin et al, 2011;Min & Tewfik, 2010;Rad & Furlanello, 2016;Westeyn et al, 2005). We also extend research on artificial intelligence as we studied how we can program computers to perform a task at which humans are currently better at.…”

Section: Discussionsupporting

confidence: 82%

Artificial Intelligence for the Measurement of Vocal Stereotypy

Dufour¹,

Lanovaz²,

Cardinal³

2020

Preprint

View full text Add to dashboard Cite

Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observations using human observers increases the costs of conducting research and monitoring interventions in practice. To address this issue, we conducted a proof of concept examining whether artificial intelligence could measure vocal stereotypy in individuals with autism. More specifically, we used an artificial neural network with over 1,500 minutes of audio data from eight different individuals to train and test models to measure vocal stereotypy. Our results showed that our artificial neural network performed adequately (i.e., session-by-session correlation near or above .80 with a human observer) in measuring engagement in vocal stereotypy for six of eight participants. That said, researchers need to conduct additional research to further improve the generalizability of the approach.

show abstract

Section: Discussionsupporting

confidence: 82%

Artificial Intelligence for the Measurement of Vocal Stereotypy

Dufour¹,

Lanovaz²,

Cardinal³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…One approach is to use a single accelerometer to detect one type of SMM, such as hand flapping when a sensor is worn on the wrist (Gonçalves et al, 2012a ; Rodrigues et al, 2013 ). The second approach is to use multiple accelerometers to detect multiple SMM, such as hand flapping from sensors worn on the wrist, and body rocking with a sensor worn on the torso (Min et al, 2009 ; Min and Tewfik, 2010a , b , 2011 ; Min, 2014 ). Other studies have done the same, but included a detection class where hand flapping and body rocking occur simultaneously in time (i.e., “flap-rock,” see Albinali et al, 2009 , 2012 ; Goodwin et al, 2011 , 2014 ).…”

Section: Related Workmentioning

confidence: 99%

Automated Detection of Stereotypical Motor Movements in Autism Spectrum Disorder Using Recurrence Quantification Analysis

Großekathöfer

Manyakov

Mihajlović

et al. 2017

Front. Neuroinform.

View full text Add to dashboard Cite

A number of recent studies using accelerometer features as input to machine learning classifiers show promising results for automatically detecting stereotypical motor movements (SMM) in individuals with Autism Spectrum Disorder (ASD). However, replicating these results across different types of accelerometers and their position on the body still remains a challenge. We introduce a new set of features in this domain based on recurrence plot and quantification analyses that are orientation invariant and able to capture non-linear dynamics of SMM. Applying these features to an existing published data set containing acceleration data, we achieve up to 9% average increase in accuracy compared to current state-of-the-art published results. Furthermore, we provide evidence that a single torso sensor can automatically detect multiple types of SMM in ASD, and that our approach allows recognition of SMM with high accuracy in individuals when using a person-independent classifier.

show abstract

“…To date, several automated systems of behavioral measurement have been developed. For example, studies have evaluated the use of accelerometers in the measurement of stereotypic behavior in individuals with ASD with very good results (Goodwin, Intille, Velicer, & Groden, 2011; Min & Tewfik, 2010). More recently, Kuroda (2018) has presented a system for tracking operant behavior in real‐time using a three‐dimensional camera, with implications for the automated measurement of continuous behavior such as in a learning task.…”

Section: Automated Measurement Of Behavior Using the Microsoft Kinectmentioning

confidence: 99%

Automated measurement of repetitive behavior using the Microsoft Kinect: a proof of concept

Maharaj

Gutierrez

Cueto

et al. 2020

Behavioral Interventions

View full text Add to dashboard Cite

show abstract

Novel pattern detection in children with Autism Spectrum Disorder using Iterative Subspace Identification

Cited by 19 publications

References 8 publications

Artificial Intelligence for the Measurement of Vocal Stereotypy

Artificial Intelligence for the Measurement of Vocal Stereotypy

Automated Detection of Stereotypical Motor Movements in Autism Spectrum Disorder Using Recurrence Quantification Analysis

Automated measurement of repetitive behavior using the Microsoft Kinect: a proof of concept

Contact Info

Product

Resources

About