View profile

CWI#95 - The Be-MOMO Project & more

I should write an intro here but all I got is this lousy thing called the alphabet, emoji and in best
CWI#95 - The Be-MOMO Project & more
By Dries Bultynck • Issue #95 • View online
I should write an intro here but all I got is this lousy thing called the alphabet, emoji and in best case animated gifs. So I’ll stick to the be-MOMO project for this update with some extra things that passed my radar.

It's complicated, because it's connected
Over 50°C. We can’t even imagine, can we? With the crying help for more and clean water, this heath is literally wiping out mankind.
India weather: Temperature passes 50C Celsius in northern India
Yeah yeah.. It’s happening over there. Not our concern. I hear you. Yet, in Belgium, researchers have been studying the impact of environmental risk factors on the mortality rate in Belgium, called the Be-MOMO project:
In Belgium, surveillance of all-cause mortality is carried out on a weekly basis by theInfectious Diseases Epidemiology Unit of Sciensano. The mortality monitoring model is designed to serve as a tool for rapid detection and quantification of unusual mortality which might result from disease epidemics such as influenza or from extreme environmental conditions such as heat waves. A timely assessment of the impact on mortality may be useful to guide or reinforce new or existing public health measures, e.g. vaccinations for influenza and the national heat action plan. Moreover, mortality monitoring can be used to evaluate possible effects of public health measures by comparing periods before and after the implementation of the intervention.
As water is connected to thirst, heat is connected to ... ? mortality?
As water is connected to thirst, heat is connected to ... ? mortality?
Some think abouts that pop into my head ...
  • Can we use mortality rate to anticipate hospital bed, nurturing personnel and more?
  • Can we use heat rate to alert people to drink more water, in real-time?
  • Can we get insights on where mortality rates are going up during peak heat moments? In cities? In rural areas?
  • Is mortality a post- or pre-heat occurrence? and is it connected to effort?
  • How do we get better information, as a society?
  • How do we get the message out?
  • How do we encourage people to change?
  • How do we change behaviour?
that’s it for now.
d - out.
Niche tv needs online distribution
The man behind Discovery Channel launched a streaming service, aka repackaging content, at a $2,99/month. It’s called Curiosity Stream. Pretty niche & an interesting distribution opportunity to find more of these types of personas, as niches aren’t a great match for TV distribution (think GRP’s).
Erase and they won't use it?
Nothing to add. Quite bold to do so though. Or was it just procedure, like they do after academic research: delete the data. Headline readers brand-lifting for sure :)
Microsoft discreetly wiped its massive facial recognition database
Bag of words ... excuse-me: bag of salt
Quite shocking, yet… read through the article; The costs for training models with a few hundred parameters versus 65 mio + is quite a different challenge, and thus energy consumption. How relates AI to energy, as time relates to ‘progress’ or 'return’ I wonder?
Personal stuff
I’m 3 months married today and that called for a celebration yesterday! So we had a beer at Sinksenfeesten Kortrijk 🎉 , danced a bit and had a lazy sunday morning with ‘koffiekoeken’, slow coffee and 'in oezne piejama zitn tot njin" :D
And with that huge news (marriage), 2019-2020 is a quite a big year: we’re selling the house and building a new one as we speak. Busy year, good times ahead.
On the other hand, i’m fairly bored-out at work and so, maybe I already mentioned it before, got myself in some mess 9 months ago by following a course in Machine learning & Deep learning. In Python. I didn’t knew shit about Python. I found energy there and paused the record label for now. Missing lots of energy, slowly getting it back by writing this newsletter.
Short: Building the machine learning models is doable but how to make it actionable and above all economical interesting is extremely hard. Deep learning is even harder. And you need lots of data. Half of current industries need an analytical translator to source the data first & help them turn it into a proof of concept before to dive into machine or deep learning. The things you read are a lie.
I’ve learned so much in the last few months, which made me think about how only a few people really make things actionable & economically interesting. I think it’s fair to say that we’re often waste our time thinking about non important stuff. Efficient leverage over time vs effective effort.
Example: Training a neural network to find context in sentences & words
Example: Training a neural network to find context in sentences & words
That’s it for this week.
d - out.
Did you enjoy this issue?
Dries Bultynck

Remarkable reads, spotted momentum & behavioral patterns in media, digital, retail, economics, health, climate, etc.
Often hollistic, sometimes very specific.

I'm Dries & the internet is the best thing that ever happened to me. more about me here:

If you don't want these updates anymore, please unsubscribe here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue