Facebook PixelA system that uses machine learning to identify bad habits and alerts the user
Create newCreate new

A system that uses machine learning to identify bad habits and alerts the user

Image credit: Getty Images

Darko Savic
Darko Savic Dec 03, 2021
Please leave the feedback on this idea

Is it original or innovative?


Is it feasible?


Is it targeting an unsolved problem?


Is it concisely described?

Bounty for the best solution

Provide a bounty for the best solution

Bounties attract serious brainpower to the challenge.

Currency *
Who gets the Bounty *
Using machine learning to alert the person of their bad habits, tics, repetitive movements, etc. A system that annoys the person with alerts or even mild electric shocks until they stop the habit.
  • Become aware of the annoying/damaging things you do subconsciously.
  • The alert system never gets tired. Stopping the bad habit is the only way to stop it from annoying you.
  • One bad habit is often replaced by another. The system's flexibility keeps the focus on the person's need for "something". Maybe the root cause can be uncovered/addressed after a while.
How it works
Cover your home with high-quality cameras that are connected to an AI-powered pattern recognition system.
First, gather a lot of video footage. While reviewing it, mark the frames and highlight the section that shows the habit you are trying to stop. For example, nail-biting is shown in the header image.
Give the system plenty of examples to learn from. Do this enough and the ML algorithm should be able to identify the pattern without a human pointing it out.
This system should be able to work with any habit that is visible on camera. Even tics or annoying repetitive movements that people are trying to stop (touching your face or hair all the time, etc).
Whenever the system detects an undesirable habit/movement the person gets alerted in any of the prefered ways:
  • Have a voice come on via bult in speakers: "Are you biting your nails again?" or "You've gone 2 minutes, 24 seconds without biting your nails. Congratulations, you are doing better." Spice it up a bit. Use humor.
  • Vibrate the person's phone (triggered via an app that runs in the background).
  • Unobtrusive notification sound - just audible enough to keep the person aware of their actions.
  • Electric jolt notifications. If you want fast results, wear an electric shocker that gives you a slight jolt as soon as the system detects you giving into the bad habit.
Creative contributions

Bad posture and out of house remedy

Miloš Stanković
Miloš Stanković Dec 04, 2021
This would work wonders for solving bad posture! Having a camera pointed at you where you work.
A quick screencap from the camera of what you look like slouched could pop on the computer screen for a split second as a powerful visual aid to remind you of how bad you look.
For when you're out of the home where your cameras aren't there, I'm pretty certain that most new phone's front cameras can measure the tilt of your head compared to the phone and alert you to change the forward head posture. The front camera can also solve the ticks and nail-biting, often done when consuming content like videos.
Please leave the feedback on this idea

Add your creative contribution

0 / 200

Added via the text editor

Sign up or


Guest sign up

* Indicates a required field

By using this platform you agree to our terms of service and privacy policy.

General comments

jnikola2 years ago
I find the idea good, but a bit scary. Anything that requires equipping your home with a bunch of high-quality cameras feels intimidating and would scare off many buyers. Is there another way how this can be tracked, without recording a live video of you?
Please leave the feedback on this idea
Shubhankar Kulkarni
Shubhankar Kulkarni2 years ago
J. Nikola Create an X-ray style image using heat sensors? It clearly shows the body structure and location but not the details like the clothes worn by the user.
Please leave the feedback on this idea
Darko Savic
Darko Savic2 years ago
thermal cameras

Please leave the feedback on this idea