Hacker News Reader

Comment by gregsadetsky | Hacker News Reader

Fascinating! A few questions:

- once the LED has slowed down to 60 bpm, do you keep it at that tempo for the rest of the day? for a few hours? do you ever go back to 120 bpm and then go back down?

- generally speaking, how did you come up with the idea?

- do you think that a software version (i.e. some blinking pixels in the top right corner of a monitor) would work, or is the intensity of the LED (i.e. the fact that it's not part of the monitor) part of the reason why it works?

- could you also talk about the heart-rate sensor - how do you use it / how does it affect the bpm algorithm?

Thanks!

View on HN

Sure,

Here is what I did to my current v.3+

- Once it reaches the lowest rate, the LED goes off after a 30min timer set, it fades the light over that time under the same blinking rate. So I won't notice. - The Idea comes from desperation really, mostly curiosity on why sound beats from upbeat music had a effect to improve mood, i.e. work more at gym. Also the idea that your brain will take patterns and try to synch with. Check PubMed (few articles about) - I started with a software version (v.1 and v2) and then a hardware one. No idea why, but hardware (as a side device) works really good. I 3D printed a tiny case and it is discreetly below my iMac screen powered by the USB. Look like an old modem but tiny.

Finally...

- I added the heart monitor (a cheap cable and wrist sensor) to see if I could shorten the time to achieve the lowest rate of blink based on my heart response instead of waiting the time or trying to read brainwave pattern (I try measuring voltage and electric wave form, from a headband I bought and returned after a rapid test) but the signal would mix with the work in front of me, so useless and expensive.

Using heart rate looks cheap, non-intrusive and effective to shorten the time, it goes 1/3 of time to get lowest, could use an apple watch vs cable and sensor but I'm cheap.

; )

Thanks, super interesting!

There was research some time ago (jeez, 10 years ago...) [0] [1] that used video and... computer vision algorithms to detect a person's heart rate without any devices. Wondering if it could be used here i.e. use your webcam instead of an external hardware sensor?

Other thing - would you be open to publishing/sharing your algorithm / esp32 code (on Github or as a blog article)?

[0] https://news.mit.edu/2012/amplifying-invisible-video-0622

[1] https://people.csail.mit.edu/mrub/vidmag/

We use this approach of video heartbeat detection on a real product (recruiting tool) but not for my hack ADHD device,

You can't really do video detection it in real time and properly, without overheating the cheap device. On the SaaS we did we use a recorded segment of video so we can analyse it afterwards, check the colour changes in the face of the subject and try estimate heartbeat with loose accuracy. More like high, Normal, Low after taking a few seconds as base.

The idea of the ADHD device was just a cheap hack done in a day for myself.

Not a product or commercial as I don't feel claiming it can do to others what I looks like does to me.

Happy to share here FREE ; )

I assume you are measuring the pulse/stress level of a candidate. Is this a proxy measurement for a lie detector?

Dear Lord, hope not.

Sounds a bit like a Voigt-Kampf machine to see if they’re a replicant to me.

Greedo shouldn’t have asked about Han’s mother!

We use on video-applications when pre processing them, the idea is to sense stress levels when the applicant is introducing themselves at the start of the video and then not reducing their scores or points when the same person gets shy of being on video or forget something due to stress when talking about something else.

We try estimate a "confidence" level when saying something, but NOT able to guess if a lie. An actor can easily have full confidence in a script, but still be a lie.

We intended for roles that are client facing and where personal skills are key. Things like retail, costumer service, sales.... not technically or education based, temporary work and alike. Not that Orwellian yet ; )

Example: You need 40 people for an event to work a few hours as guides or hosts, from 100 applying the system can suggest a score and list them all in order so you can start watching or calling for interviews from somewhere.

Thanks, I appreciate the reply.

I'm definitely NOT attending an interview where this kind of tech is used. My heart rate is irrelevant to whether someone should hire me - and I say that as someone who doesn't even get anxious or nervous during interviews.

Not for interviews, video-applications, is used to sense stress and give extra points (not deducting them) if a person is indeed just too shy of being on video vs talking about something ; )

I've developed an experimental ESP32 project that simulates a heartbeat pattern. But I don't have a heart rate sensor, I used my normal resting heart rate as a basis for the simulation. The project utilizes an ESP32 to create a LED blink pattern that represents a heartbeat, starting at a faster rate and gradually slowing down to a resting rate.

Here's the link to the project: https://github.com/Qiaogun/ADHD_Blink

That's the idea! Looks good ; )

Reply on news.ycombinator.com