0
$\begingroup$

I am a newbie to data science. I was reading this blog

When I was half way through, I came into this sentence

Further, each series of data has been partitioned into overlapping windows of 2.56 seconds of data, or 128 time steps. These windows of data correspond to the windows of engineered features (rows) in the previous section.

What does 'series' means here and what is window partitioning?

Further I would like to ask all the data science enthusiasts there,What do I lack here.Is it comprehension or logical skills needed .What can I do to improve upon this.I encounter such doubts often and what I do is search for the terms I dont understand or leave it and get ahead.When I search for the terms I get broad answers leaving me more confused.If i leave it like that I dont understand the rest.What should I do here?I cant post every small doubts in stack exchange.It would be great If you could share some light on this as well.

$\endgroup$
0
$\begingroup$

I think, with "series", the authors refer to time series data in their dataset. In this case, it should be x, y, z, angular velocity and maybe other features for each participant.

"Splitting data into fixed windows of 2.56 seconds (128 data points) with 50% overlap." I would translate to: Every 2.56 seconds aggregate each series of the data over the next 5.12 seconds.

You can imagine windowing basically as a timestamp-based data aggregation technique that is often used for stream data processing to reduce data and fix granularity of the data. The stream analytics windowing function documentation contains visualizations, which should help you to understand what is meant. I think, in the blog, the authors mean what Microsoft calls "hopping windows".

I read that windowing is a time series feature engineering topic. So maybe, it might help, if you learn more about feature engineering.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.