# Getting started with time series sensor data analytics in Elasticsearch

**URL:** <https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626>\
**Category:** Elasticsearch\
**Created:** [January 14, 2017, 11:01pm UTC](https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626 "2017-01-14T23:01:25Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![iotify](https://avatars.discourse-cdn.com/v4/letter/i/7c8e57/32.png) [@iotify](https://discuss.elastic.co/u/iotify)\
**Post date:** [January 14, 2017, 11:01pm UTC](https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626/1 "2017-01-14T23:01:25Z")

</div>

Dear users,

We have published a guide where we have explored the possibility of using Elasticsearch to visualize your sensor data for IoT.  
[https://help.iotify.io/database-generator/analyzing-time-series-sensor-data-with-elasticsearch](https://help.iotify.io/database-generator/analyzing-time-series-sensor-data-with-elasticsearch)

My question is what kind of anomaly detection algorithm could we write on top of such sensor data. Do you have any experience dealing with such data in the past? Couple of ideas which we have

- Show the instances when Sensor value remains abnormally high for a longer time.
- Filter out the spurious values in sensor (which do not fit into a pattern)
- Correlate two sensor values to predict a condition (e.g. high humidity and low temperature indicates rain)

Any other input will be highly appreciated.

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [January 15, 2017, 12:47am UTC](https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626/2 "2017-01-15T00:47:09Z")

</div>

Machine Learning (aka Prelert) will be perfect for this!

You can also do some degree of this with Timelion and holt winters, but it's not as accurate.

---

<div class="post-metadata">

**Author:** ![iotify](https://avatars.discourse-cdn.com/v4/letter/i/7c8e57/32.png) [@iotify](https://discuss.elastic.co/u/iotify)\
**Post date:** [January 15, 2017, 1:08pm UTC](https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626/3 "2017-01-15T13:08:44Z")

</div>

Prelert looks awesome Mark,  
We are definitely gonna give it a try!

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [February 12, 2017, 1:08pm UTC](https://discuss.elastic.co/t/getting-started-with-time-series-sensor-data-analytics-in-elasticsearch/71626/4 "2017-02-12T13:08:45Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.