# Meaning of the Targets are Unclear

**URL:** <https://community.drivendata.org/t/meaning-of-the-targets-are-unclear/720>\
**Category:** Senior Data Science: Safe Aging with SPHERE\
**Created:** [July 20, 2016, 8:18pm UTC](https://community.drivendata.org/t/meaning-of-the-targets-are-unclear/720 "2016-07-20T20:18:27Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![fhidalgo](https://avatars.discourse-cdn.com/v4/letter/f/e19adc/32.png) [@fhidalgo](https://community.drivendata.org/u/fhidalgo)\
**Post date:** [July 20, 2016, 8:18pm UTC](https://community.drivendata.org/t/meaning-of-the-targets-are-unclear/720/1 "2016-07-20T20:18:27Z")

</div>

Hey,

Can someone clarify what the targets are?

The text states, “The mean duration of each label within this window is used as the target variable.” Does this mean that if it’s .333 for walk, .333 for stand, and .333 for turning that the participant spend a third of a second on each activity in that time window.

Or…

That a third of the annotators through that they were walking, standing, or turning?

Can someone people clarify this for me :).

Thanks!

---

<div class="post-metadata">

**Author:** ![ntwomey](https://avatars.discourse-cdn.com/v4/letter/n/e9c0ed/32.png) [@ntwomey](https://community.drivendata.org/u/ntwomey)\
**Post date:** [July 21, 2016, 8:40am UTC](https://community.drivendata.org/t/meaning-of-the-targets-are-unclear/720/2 "2016-07-21T08:40:37Z")

</div>

Hi fhidalgo,

Please refer to the FAQ under “Interpretation of targets”

> **[Senior Data Science: Safe Aging with SPHERE](https://www.drivendata.org/competitions/42/page/75/)**
>
> Contribute to open, cutting-edge research on the use of wearables in promoting health and independence for seniors.

To summarise, the data are segmented into one-second chunks, and the targets are given as the proportion of each activity that falls within each chunk. I made the image below to clarify:

 ![](https://canada1.discourse-cdn.com/flex028/uploads/drivendata1/original/1X/b81ea6e598188f74efa1d9f338f9622db54435f4.png)

The top A1 and A2 are the times over which two activities are annotated by one annotator. The lower A1 and A2 (which given hindsight when I drew this image should be P(A1) and P(A2), ie the probability of the two activities) represents the proportion of time during each one-second interval which each activity was annotated.