“A Homespun Decentralised DIY Data Science Analysis Pipeline for the Net of *Your* Items”
So numerous buzzwords so small time.
What do information science, electronic signal processing, machine learning, databases, mobile platforms, devops, containers, sensors, and micro-controllers have in prevalent?
You have heard it a million moments, it is so easy to collect your have details with points these as Arduino sensor shields, wristbands, and even mobile telephones. You can monitor your sleep, the time you expend in the pub, depend how several steps you took last Sunday, and how lots of periods you listened to Taylor Swift last week, even even though your twitter bio reads that your favourite band is Radiohead.
But when you use industrial solutions, what transpires to your information? where by does it all go? and additional importantly, how is it used? There is no final solution to all those inquiries but some of that details can be utilised to derive a good deal of your particular data, as Liccardi et al. demonstrate in I know the place you dwell: Inferring aspects of people’s lives by visualizing publicly shared locale details, ACM SIGCHI 2016.
This communicate is about how to construct your own info pipeline, from selection, to signal processing, to storage, and to aggregated assessment and visualisation. Via a series of illustrations, a range of simple information science ideas will be defined, demonstrating what can be reached with information, and certain problems that it delivers in terms of privacy. A range of absolutely free and open source resources will be used all over the illustrations, with a emphasis on tools that adhere to Close Person Improvement (EUD) principles, from details accumulating with a drag and fall, blocks based mostly, mobile application improvement device, to routing information by way of a movement dependent program, and to displaying charts and graphs in an interactive notebook.