One page · Nov 2026

Emotional Zoo

A meltdown should never be the first sign.

Studies find a signal in the body of autistic children minutes before an episode. Emozu tests if a soft band with a little friend on top can warn a parent in time, at home.

Concept photo of a ladybug friend on a soft blue band on a 6-year-old's wrist, real size
Concept image, not a real photo
  1. Problem
  2. Idea
  3. Evidence
  4. Why now
  5. Plan
  6. Next

01 · The problem

Today a parent finds out by watching it happen.

The child often cannot say what is wrong. The parent looks for a trigger after the fact, and the next one comes without warning.

02 · The idea

A soft band. A little friend on top. Serious sensing inside.

Exploded render: friend with a battery cavity, battery in a tray with hooks, latch and contacts, thin cover with locks, board with sensors underneath, base with holes for them, frame and woven band
Render · design targets
Render from above of three friends: hedgehog, ladybug, turtle

03 · The evidence

The signal is real. Nobody has tested it at home.

99children in all published studies
0of them followed at home
1–10 minhow far ahead models warn
0.71–0.87AUROC. 0.5 is a coin flip

Goodwin 2019 (20 children, 1 min), Imbiriba 2023 (70 children, 4 hospitals, 3 min), Kartha 2026 preprint (9, classroom, 10 min). All four studies

The hard part

About 2 of 3 alerts were false in the one study that counts them. A parent pulled away for nothing stops listening. So we start silent: record, label, look back. Live alerts come only if the numbers hold.

04 · Why now

The models arrived. The devices left the market.

  1. Q-Sensor stopped
  2. First model, 20 children
  3. 70 children, 4 hospitals
  4. Empatica E4 retired
  5. No family device gives raw signal and home data. That is the gap.

05 · The plan

6 to 9 months to a study and a paper.

  1. Now · closed pilot, one childAt home, an off-the-shelf device, worn all day. About 15 episodes. Can we warn ahead?
  2. Step 2 · closed beta, six familiesReady, from a parent community of 135 families.
  3. Step 3 · protocol and regulatorEthics, consent, data rights. FDA Pre-Sub before any claim.
  4. Step 4 · our own prototypesA small batch of bands that give raw signal and that children keep on.
  5. Goal · study and paperWith clinical psychiatrists, on 30 to 50 children, by protocol.

This is a plan, not traction. Open questions: who pays, medical device or wellness, the alert threshold.

06 · What's next

Our own band, a real study, the FDA.

In 6 to 9 months: our own prototypes, a study with clinical psychiatrists on 30 to 50 children, and an FDA Pre-Submission. We are looking for people who can turn a pilot into science and a product:

Write to us

Yury Sakhonchyk, founder · Yerevan, Armenia · [email protected]

Write to us