[Note for Numb3rs]101:Pilot

Key words: Rossmo’s formula

[from Wikipedia]

\displaystyle p_{i,j}=k \sum_{n=1}^{\text{total crimes}}[\frac{\phi}{(|X_i-x_n|+|Y_j-y_n|)^f}+\frac{(1-\phi)B^{g-f}}{(2B-|X_i-x_n|-|Y_j-y_n|)^g}]

where X_i\neq x_n and Y_j\neq y_n.

and \phi=1,\quad\text{if } (|X_i-x_n|+|Y_j-y_n|)>B, otherwise \phi=0.

The summation in the formula consists of two terms. The first term describes the idea of decreasing probability with increasing distance. The second term deals with the concept of a buffer zone. The variable \phi is used to put more weight on one of the two ideas. The variable B describes the radius of the buffer zone. The constant k is empirically determined.

The main idea of the formula is that the probability of crimes first increases as one moves through the buffer zone away from the hotzone, but decreases afterwards. The variable f can be chosen so that it works best on data of past crimes. The same idea goes for the variable g.

The distance is calculated with the Manhattan distance formula.


About YiMin

This is just a nerd PhD student of Math@UT Austin.

One thought on “[Note for Numb3rs]101:Pilot

Comments are closed.