0
$\begingroup$

I have gps format dataset lat, lon. I want to detection anomaly using python.

I tested knn, smv, cof, iforest using pycaret. But i did not.

These colors anomlay because the

  • angle change is too much
  • the changes of the points are deviated too much to the right and left
  • distance more two points between

but since the other colors go in a row, they are not anomaly because the heading values are reasonable.

also i grouped according to sequnceUUID

heading(bearing) is angle of north.

My dataset image

I want to detect and extract purple, green and brown datasets that are out of the way.

my dataset geojson format

$\endgroup$
0
$\begingroup$

GPS data includes positional and time data. If the n+1 position at t+1 is too far away from the n position at t (i.e. d>0.5m for instance), you should be able to detect an anomaly.

Same topic about the angle: if the angle between d1 and d2 is grater than a normal value (ex: 2 degree) then it should be considered as an anomaly.

You should consider the number of abnormal values in a row: if there are more than 3 for example, you should consider them as an anomaly.

$\endgroup$
1
  • $\begingroup$ I understand and will try. $\endgroup$
    – ai-mcv
    Jan 12 at 11:50

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.