Updated twice, last on 21 December 2016. Notes below.

tl;dr - So, does it work?!

NeuroOn, the self-proclaimed "world's first smart sleep mask" isn't a medical grade device, but it's much better than a coin toss.

Its total accuracy in detecting sleep stages is 65%.

One of the biggest problems with NeuroOn is that when used as an alarm clock almost every third time (31.6%) it will choose the worst possible moment for waking, assuring lack of energy and grogginess¹ after awakening.

Comparing NeuroOn's sleep stage results to a professional polysomnography² scored by a human expert:

When polysomnography detects a sleep phase suitable for waking up, NeuroOn agrees in 73.8% of the cases. In the rest 26.2% it isn't a big deal, since it will just wait until the next good opportunity to wake you up.

When polysomnography says not to wake the user up, NeuroOn agrees in 68.4%. In the rest 31.6% - nearly a third of all cases - it could try to wake the user, resulting in …

Continue reading

Winding up the long-overdue NeuroOn's signal research together with Ryszard Cetnarski from Nencki Institute of Experimental Biology in Warsaw (github profile) we created a scientific poster summarizing our findings. We presented it at the 6th International Conference "Aspects of Neuroscience" (link) taking place between 25-27th of November in Warsaw, Poland.

Just as the research notebook itself is freely available on Github and licensed under MIT License, our poster is released as completely open, under a little bit more restrictive CC-BY-SA license.

Since our research wasn't criticized beyond data representation methods on the course of several months, it should be safe to assume that it's ready to present to a wider audience. On the course of the following week you may expect a full NeuroOn verification summary blogpost with results explained in simple terms, leaving no ambiguities regarding the device.

The poster is available in PDF, SVG and AI.

Note: I am still working on NeuroOn signal analysis. You can expect to see the hypnogram¹ comparisons first together with time-synchronized signal files and all the code in an open Jupyter Notebook²

Hackerspaces and biology

As a long time Citizen Science and Open Source supporter I love the idea of Hackerspaces³ - collaboration workspaces allowing individuals to work on their own technical projects, sharing tools and knowledge. I consider them a vital counterpart to Academic research labs, where people are not bound by strict rules and grants. Hackerspaces excel in very disorganized research and development of various IT and electronic projects, producing a lot of open designs and proof of concepts⁴.

Many researchers point out that it is possible only due to the nature of IT and electronics allowing rapid prototyping and near-instantaneous results - something which couldn't be replicated in more time-consuming experimental sciences such as chemistry and biology. I'd like to disagree with that point. While it is impossible to achieve the same speed of prototyping as in IT or electronics …

Continue reading

Edit 29.09.2016

The analysis and all the data files are available for peer review at my Github.

NeuroOn Today

I was intending to start a blog for a long time, kept back by the feeling that I didn't really have anything valuable to share. This changed when I found a Polish startup - NeuroOn¹ over two years ago. My first post² expressed all the hopes I had for the sleep mask and skepticism at the clear disregard for scientific standards of its creators. Since it consists mostly of quotes I don't want to risk misinterpretation of IntelClinic employees by translating it fully. I ended it with the following paragraph:

The NeuroOn sleep mask cannot work exactly as advertised - it cannot utilize a proper EEG signal. While it can detect a REM phase in sleep very roughly, it's very far from reliable sleep analysis. The majority of the population isn't able to achieve polyphasic sleep, since their brains aren't capable of that. A similar thing goes with lucid dreaming. NeuroOn at its best …

Continue reading

For some time I've been using React JS stack in my professional projects at X-Team and I decided to share some knowledge. React is just one piece piece of puzzle, requiring Redux, React-Router, Webpack and Babel to create truly interesting architecture. I've met many people having problems with grasping that, struggling to go beyond simple component state of their application. Since I had similar problems learning this modular approach, I decided to give a short presentation on the topic.

Initially given on April 27th in a wonderful Noisebridge hackerspace, I updated it a little after React Europe 2016 and presented again at MeetJS Warsaw on the 7th of June 2016.

The presented application of React + Redux is just a simple view authentication method, which nicely highlights the simplicity of the architecture. All links - including "by then you should know" are clickable, so feel free to browse sources recommended by me. All code itself is either runnable or has a pseudocode warning on the slide.

Slides are available in an iframe below or at my slides …

Continue reading