The PHD evidential filter (PHD-EF) is able to accept and process hard data as well as specific type of human-generated soft data, i.e., fuzzy Dempster-Shafer measurements. The PHD-EF can be considered as the generalization of popular GM-PHD filter in the sense that the GM-PHD filter is only able to process hard data.

The PHD-EF is implemented by modifying GM-PHD codes. The attached file provides the algorithmic representation of the PHD-EF, which follows the algorithmic procedure of GM-PHD filter.

Aug 25 '20 14:08 SohSalari

@SohSalari Would it be possible to provide an example as part of the documentation. Maybe just adapting one of the existing tutorials or examples, with some soft data?

If you haven't already, you'll need to install the documentation dependencies for Stone Soup which you can find in the README (or can be done easily from the base directory with python -m pip install -e .[dev]). Then from base of the repo run python -m sphinx docs/source docs/build. This will build the documentation and execute the examples, outputting documentation into the docs/build/ directory.

Oct 07 '20 09:10 sdhiscocks

Codecov Report

Merging #295 into master will decrease coverage by 2.04%. The diff coverage is 14.72%.

@@            Coverage Diff             @@
##           master     #295      +/-   ##
==========================================
- Coverage   93.69%   91.65%   -2.05%     
==========================================
  Files         124      125       +1     
  Lines        4887     5009     +122     
  Branches      704      729      +25     
==========================================
+ Hits         4579     4591      +12     
- Misses        220      328     +108     
- Partials       88       90       +2

Flag	Coverage Δ
#integration	`69.15% <11.62%> (-1.44%)`	:arrow_down:
#unittests	`89.57% <14.72%> (-2.00%)`	:arrow_down:

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
stonesoup/updater/wrapper.py	`0.00% <0.00%> (ø)`
stonesoup/updater/pointprocess.py	`55.03% <5.08%> (-42.11%)`	:arrow_down:
stonesoup/updater/kalman.py	`80.15% <12.50%> (-15.92%)`	:arrow_down:
stonesoup/hypothesiser/distance.py	`80.64% <45.45%> (-19.36%)`	:arrow_down:
stonesoup/hypothesiser/gaussianmixture.py	`82.92% <55.55%> (-8.25%)`	:arrow_down:
stonesoup/types/detection.py	`100.00% <100.00%> (ø)`

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 28cfde0...e3d0c28. Read the comment docs.

Oct 07 '20 19:10 codecov[bot]

@SohSalari Would it be possible to provide an example as part of the documentation. Maybe just adapting one of the existing tutorials or examples, with some soft data?

@sdhiscocks : Sure. I will provide an example as part of the Stone Soup's documentation as soon as the review process of the PHD-EF will be completed. (I have already provided a running example at https://gist.github.com/SohSalari/6cbc44eaacd93e3939e43f2042455e25, which requires modification/improvement.)

Oct 07 '20 21:10 SohSalari