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

Großekathöfer, Ulf; Manyakov, Nikolay V.; Mihajlović, Vojkan; Pandina, Gahan; Skalkin, Andrew; Ness, Seth; Bangerter, Abigail; Goodwin, Matthew S.

doi:10.3389/fninf.2017.00009

Cited by 47 publications

(48 citation statements)

References 37 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the parameter transfer learning capability besides the possibility of incremental training of the proposed deep architecture facilitates the online adaptation of an automatic SMM detector in real-time scenarios. This finding overlooks the subject specific [73], and monolithic [74,35] activity recognition systems opening new frontiers toward adaptable activity recognition systems which are more appropriate for realtime usages. At the end, the high detection performance on unbalanced training sets achieved in the dynamic feature space facilitates the application of our method on the realistic data when the incoming data samples are highly skewed.…”

Section: Toward Real-time Automatic Smm Detectionmentioning

confidence: 99%

“…Most of these studies tried to extract time and frequency domain features such as mean, standard deviation, skewness, and FFT peaks from raw signals to feed them to a classifier for activity identification [21,22]. According to the achieved results in human activity recognition systems, applying pattern recognition on the collected data by IMU sensors can reliably and accurately detect physical activities which are an evidence for the possibility of applying such techniques to automatically detect SMMs in ASD children [23,24,25,26,27,28,29,30,31,32,33,34,35,36]. Despite meaningful amount of research in this direction, few challenges for automatic SMM detection using wearable sensors still remain unsolved especially in real-time applications.…”

Section: Introductionmentioning

confidence: 99%

“…Another challenge toward developing a real-time SMM detection system is personalization due to the intra and inter-subject variability [33,35]. This challenge, despite its crucial importance, has been undervalued [33].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

et al. 2018

View full text Add to dashboard Cite

Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multiaxis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.

show abstract

Section: Toward Real-time Automatic Smm Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

et al. 2018

View full text Add to dashboard Cite

show abstract

“…This motor learning process is viewed by the improvements in speed, accuracy, or precision which the given motor movement (or sequence of movements) is performed. Over time with extensive repetition, movements can also become automated and no longer requiring over attention control for the execution [12]. Individuals with ASD are able to execute an aimed motor movement with accuracy comparable to that individual development.…”

Section: Motor Learning and Technologymentioning

confidence: 99%

Analysis and Design of Rehabilitation Device in Sensory Integration Therapy for Autism Children

Ghazali

Zulkifly²,

Hanafi

2019

Int. J. Robot. Autom. Technol.

View full text Add to dashboard Cite

A group of complex disorders in terms of brain development is known as Autism Spectrum Disorder (ASD). The rehabilitation device playing vital roles in this institute which provide crucial assistance in the process of helping the autism people. Nowadays, the development of the technologies has led to the integration of the rehabilitation device with technology to sophisticating the function of the device. In this study, the integration of the electrical and the electronic technologies will be implemented for the purpose of attracting the learning desire of the autism children. The performance of autism children in the aspect of 'attention' will be identified and discussed. Overall data that had been collected showed an improvement in the performance of both of the autism children. Hence, autism children showed that they had improved their performance by paying attention on the task that had been given and less doing unnecessary things that can keep their attention away.

show abstract

“…In psychology, it has become an attractive tool revealing the complexity of human behavior across multiple timescales. It has been applied to measure the coupling of two behavioral signals from different interacting actors (e.g., Shockley, Santana, & Fowler, 2003;Richardson & Dale, 2005;Shockley & Turvey, 2005), behavioral coupling in parent-child interactions (López Pérez et al, 2017), including gaze coupling (Nomikou, Leonardi, Rohlfing, & Raczaszek-Leonardi, 2016) or stereotypical motor behavior of individuals with autism spectrum disorder (Romero, Fitzpatrick, Schmidt, & Richardson, 2016;Großekathöfer et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Beyond fixation durations: Recurrence quantification analysis reveals spatiotemporal dynamics of infant visual scanning

et al. 2018

View full text Add to dashboard Cite

Standard looking-duration measures in eye-tracking data provide only general quantitative indices, while details of the spatiotemporal structuring of fixation sequences are lost. To overcome this, various tools have been developed to measure the dynamics of fixations. However, these analyses are only useful when stimuli have high perceptual similarity and they require the previous definition of areas of interest (AOIs). Although these methods have been widely applied in adult studies, relatively little is known about the temporal structuring of infant gaze-foraging behaviors such as variability of scanning over time or individual scanning patterns. Thus, to shed more light on the spatiotemporal characteristics of infant fixation sequences we apply for the first time a new methodology for nonlinear time-series analysis-the recurrence quantification analysis (RQA). We present how the dynamics of infant scanning varies depending on the scene content during a ''pop-out'' search task. Moreover, we show how the normalization of RQA measures with average fixation durations provides a more detailed account of the dynamics of fixation sequences. Finally, we link the RQA measures of temporal dynamics of scanning with the spatial information about the stimuli using heat maps of recurrences without the need for defining a priori AOIs and present how infants' foraging strategies are driven by the image content. We conclude from our findings that the RQA methodology has potential applications in the analysis of the temporal dynamics of infant visual foraging offering advantages over existing methods.

show abstract

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

Cited by 47 publications

References 37 publications

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

Analysis and Design of Rehabilitation Device in Sensory Integration Therapy for Autism Children

Beyond fixation durations: Recurrence quantification analysis reveals spatiotemporal dynamics of infant visual scanning

Contact Info

Product

Resources

About