Assessment & Research

Automated detection of stereotypical motor movements.

Goodwin et al. (2011) · Journal of autism and developmental disorders 2011
★ The Verdict

A small wireless accelerometer plus pattern software catches 90% of hand flapping and body rocking so you can ditch the stopwatch.

✓ Read this if BCBAs who track stereotypy in classroom or clinic settings.
✗ Skip if Teams that only measure vocal or self-injurious behavior.

01Research in Context

01

What this study did

The team taped a tiny 3-axis accelerometer to kids with autism.

Software watched the wrist or torso for hand flapping and body rocking.

They tested the setup in a lab and in a real classroom.

02

What they found

The program caught about 90% of stereotypy episodes.

It worked as well at a desk as it did in the clinic.

No one had to click a stopwatch.

03

How this fits with other research

Gilchrist et al. (2018) later pushed the same idea to 93% accuracy without calibrating each child.

Lotfizadeh et al. (2020) swapped the target to self-injury and hit 94–99% accuracy, showing the wearables can handle harder behaviors.

Maharaj et al. (2020) traded the accelerometer for a Kinect camera and still reached 92% agreement, proving vision sensors work too.

Together the papers say: pick your gadget—wrist, torso, or camera—and you can automate motor counts.

04

Why it matters

You can stop doing 10-minute partial-interval samples by hand.

Strap on a $30 accelerometer, run free pattern software, and get clean data while you teach.

Use the extra time to plan intervention instead of tallying flaps.

Free CEUs

Want CEUs on This Topic?

The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.

Join Free →
→ Action — try this Monday

Tape an accelerometer to one learner’s wrist, open the free detector app, and compare its count with your manual tally for one session.

02At a glance

Intervention
not applicable
Design
other
Population
autism spectrum disorder
Finding
positive
Magnitude
large

03Original abstract

To overcome problems with traditional methods for measuring stereotypical motor movements in persons with Autism Spectrum Disorders (ASD), we evaluated the use of wireless three-axis accelerometers and pattern recognition algorithms to automatically detect body rocking and hand flapping in children with ASD. Findings revealed that, on average, pattern recognition algorithms correctly identified approximately 90% of stereotypical motor movements repeatedly observed in both laboratory and classroom settings. Precise and efficient recording of stereotypical motor movements could enable researchers and clinicians to systematically study what functional relations exist between these behaviors and specific antecedents and consequences. These measures could also facilitate efficacy studies of behavioral and pharmacologic interventions intended to replace or decrease the incidence or severity of stereotypical motor movements.

Journal of autism and developmental disorders, 2011 · doi:10.1007/s10803-010-1102-z