February 25, 2015 at 5:15 PM

These guys have a very interesting modelled-after-brain thing for just these
types of things...

Anomaly detection, autonomous temporal sequence learning, you name it ;)

https://github.com/numenta/htm.java

_______________________________________________
hawkular-dev mailing list
hawkular-dev@lists.jboss.org
https://lists.jboss.org/mailman/listinfo/hawkular-dev

Matt Wringe

February 25, 2015 at 4:23 PM

Does it only have to be about forecasting/projecting 'bad' things :)

With more historical data, it could get more interesting than a just an estimated straight line.

Say if it was able to know that you have a large increase in power at a particular time of day (eg a 30 minute commute on the train at 17:30 where you stream video). The forecasted chart in this case could have a dip in battery reserves at about this time.

But maybe you don't always stream video during your commute. So in this case it could give you an estimated range instead of a particular time.

Although, bringing in historical data analysis and estimated ranges tend to make things more complicated and the charts more confusing.

On 25/02/15 03:04 PM, Heiko W. Rupp wrote:

_______________________________________________
hawkular-dev mailing list
hawkular-dev@lists.jboss.org
https://lists.jboss.org/mailman/listinfo/hawkular-dev

Heiko W. Rupp

February 25, 2015 at 3:04 PM

Something I was talking about for a while ...

I saw this today in Android 5 - they give you (when the device is running on battery) not only a

chart about past battery consumption (dark green), but also about estimated future depletion (grey-green)

and on top of the chart the current state (40%) + an estimate that the battery will last ~4 more days at the

same usage level.

--
Heiko Rupp hwr@pilhuhn.de
Blog: http://pilhuhn.blogspot.com @pilhuhn

_______________________________________________
hawkular-dev mailing list
hawkular-dev@lists.jboss.org
https://lists.jboss.org/mailman/listinfo/hawkular-dev