Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Neurable Technology (neurable.com)
56 points by boredgamer2 on May 11, 2020 | hide | past | favorite | 20 comments



OpenBCI ?


I wouldn't really call them a consumer-oriented startup. I left Kernel, OpenBCI, Intheon, g.tec, etc off the list.


I got to try their VR demo a little while ago - its amazing, I played the entire thing only using my thoughts to trigger actions. Training was really quick and it was weird how natural it was.


I've met the Neurable guys a couple years ago at a pitch event. I recall seeing a presentation where Ramses controlled a vehicle using the headset as a basic directional input method. I believe they have a unique approach to signal processing which allows them to get good signal:noise compared to most other scalp EEG headsets. It'll be interesting to see what kind of applications they end up heading towards!


Does anyone know how this hardware stacks up (price/performance) with nuerosity's headset?

I'd be interested in code running on events but would like to know how many different event types are these headsets are capable of handling.

https://neurosity.co/


So... can anyone here say that these EEG headsets actually work and do something practical? How does it compare to OpenBCI, which has 2 times the number of sensors?


Running a PCA on data from 64 node (wet contact, shaved head, lab environment), shows that you basically get one channel of data, there’s virtually zero useful information other than the main wave; you can tell whether the subject is asleep, awake or having a fit with high degree of accuracy, you can accurately classify whether the awake subject is relaxed vs aroused but that’s about it. The claims made for these systems are way beyond anything supported by the data. Would love to be proved wrong by standard, verifiable sourced data and a Jupyter notebook, but I won’t hold my breath.


Please, someone, please refute this. Please, please let the situation be better than this.


While it is difficult to get a useful signal out of EEG, a PCA doesn't show that there is only one 'channel'. A lot of interesting signals have very low power. With multiple EEG sensors, one can focus on smaller spatial regions.


I have 0 brain HCI experience but can’t you take that 2 or 3 bits of information and then use time multiplexing to encode more signals? Eg if I can reliably switch between relaxed and angry at a rate of 100ms I get 2x the bandwidth every 200ms


Was this data you collected, or heard about from friends, or ?


@Tduhbro A quick google scholar can point you to a ton of material. I recommend https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3304110/ PubMed Central (PMC)PubMed Central (PMC) Brain Computer Interfaces, a Review - A review that covers different BCI modalities and their performances.

Also I’d recommend using ICA and Loretta through EEG lab to help with any analysis. It will help you identify far more significant signals. https://sccn.ucsd.edu/eeglab/index.php sccn.ucsd.edusccn.ucsd.edu

If you want more information, check out Neurable (feel free to reach out!) on social media (#selflessplug) and the NeuroTechX organization :)


> If you want more information, check out Neurable (feel free to reach out!)

What capabilities on top of what GP said are possible?


Neurable is known for their ERP detection, especially with the p300 as well as cognitive state measures.


I am sorry, but I don't know what that means. Does it mean it is able to determine emotions? Or how focused a person is? Can I control a computer with it somehow, perhaps more than very simple motion? Can it determine words I though of? What are the differences compared to OpenBCI and why is less (sensors) more? I am a practical guy interested in practical things.


In regards to human-computer interaction (how we interact and communicate with computers), check out this presentation: https://events.technologyreview.com/video/watch/ramses-alcai...

Emotion is a tricky term because there are so many things that affect and shape one's "emotional state." At Neurable, we measure aspects of emotional spectrum (i.e. specific cognitive states, like focus). More information to come in the near future :)

Re sensors, more sensors add the possibility for more data, which is often used to take higher quality measurements. Neurable uses high quality sensors combined with special algorithms to make sense of the "not so good" data to do what others might need more data to get as clear, or even, a more clear picture.


I can't speak for this one, I gave the OCZ NIA a spin when it was released probably more than a decade ago now, and what I found was that mostly it picked up the electrical interference from all the low quality DC transformer plugpacks that powered all my monitors and chargers etc.

I'm not sure that "machine learning driven signal processing" is going to be enough to screen out the dirty EM environment you're gonna find in most peoples houses and offices.

I do wish these guys best of luck though, it's an interesting field.


Is there any work on long-term implantable technology? Not necessarily cranial, just in general as a precursor.

As far as I'm aware, the body eventually rejects or forms limiting scar tissue around pretty much all foreign bodies, with only a few exceptions. Because while I am not going to be signing up for sub-cranial implants any time soon, I could possibly be willing to try sub-dermal if there were promising results.


Wow, I did my undergrad EE with Ramses at UW! Good to see his company seems to be doing well!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: