I’ll try this out

Thanks

On 20 Oct 2015, at 1:04 AM, Chetan Surpur 
<[email protected]<mailto:[email protected]>> wrote:

Zvika,

On Oct 19, 2015, at 7:06 AM, Zvika Ashani 
<[email protected]<mailto:[email protected]>> wrote:

- Any suggestions on the scaling of the radius parameter ? It can be measured 
relative to the previous sample or relative to a sample from a few seconds ago, 
how will that change the outcome?

You can use the GeospatialCoordinateEncoder as an analogy. It computes a radius 
for a given speed, such that the encodings of consecutive readings to be 
adjacent with some overlap (specially an overlap of 50%) [1].

You can try the same logic for your application.

[1] 
https://github.com/numenta/nupic/blob/master/src/nupic/encoders/geospatial_coordinate.py#L113

- Chetan


On 19 Oct 2015, at 4:33 PM, Matthew Taylor 
<[email protected]<mailto:[email protected]>> wrote:

Zvika,

Before you try a different encoder, you should attempt to use the
CoordinateEncoder directly. It can accept X,Y coordinates and a
"radius" which can represent speed. That is what I used to get NuPIC
to do anomaly detection on Minecraft XYZ coordinates:
https://github.com/nupic-community/mine-hack/blob/master/python/nupic_client.py#L71-L79

And for an anomaly detection model on coordinates, you won't need to
swarm because we already have model params that work well detection
these types of anomalies here:
https://github.com/nupic-community/mine-hack/blob/master/python/model_params/model_params.py.
You should be able to re-use those model params (maybe with a few
string replacements).
---------
Matt Taylor
OS Community Flag-Bearer
Numenta


On Mon, Oct 19, 2015 at 5:05 AM, Zvika Ashani 
<[email protected]<mailto:[email protected]>> wrote:
Hi Nupic,

I am trying to see if I can do anomaly detection over a data set that 
represents object tracks. Each object track is a list of data points that have 
the following information:

- timestamp
- position (x,y between 0 and 1)
- speed

I want to learn a large number for such tracks and then look for anomalies in 
new tracks.
This is kind of like the nupic.geospatial example but the position data is in a 
different coordinate system.
I am looking at using a vector encoder with each sample being [x,y,speed] and 
then feeding each track as a separate sequence into the model.

Questions:

- is this the correct approach or is there some better way of encoding the data?
- is it possible to swarm over this to find the best model?

Thanks,
Zvika




Reply via email to