Breakpoints / Clusters with a Line

Context: I want to create an interactive heating map with areas separated by zip code. I did not find a way to show it directly (i.e. using Google Maps or OSM), so I want to create curves or lines that separate these areas and visualize them on maps.

I have a set of points represented by their coordinates and their class (zip code). I want to get a curve separating them. The problem is that these points are not linearly separable.

I tried using softmax regression, but this does not work with nonlinearly shared classes. The only methods that I know that can be separated nonlinearly are closest neighbors and neural networks. But such classifiers only classify, they do not tell me the boundaries between classes.
Is there a way to get the borders in some way?

+4
source share
1 answer

If you have a dense cloud of known points in each Zip code with coordinates [latitude. longitude, zip code] using machine learning to find the boundary spanning these points sounds like redundant.

, , , Zip- , Matlab

K = convhull(X,Y)

K , X, Y , .

, , (lat, lon) map (x, y). Matlab Mapping Toolbox, M_Map M_Map, .

: Zip- , , , . , .

+3

Source: https://habr.com/ru/post/1693163/


All Articles