Predicting

hi,

note: after re-reading post see looks school question, assure it's not.

i'm trying program prediction algorithm if may.

i have data in 2-d array 7 "cells" wide  14 "cells" high so:
the 7 wide cells week days (mon-sun)
the 14 high cells times (7-21)
the data people passed per minute.

code: [select]



float ppl [14][7] ={
{4.6, 4.7, 2.3, 3.6, 0.5, 4.5, 0.2},
{3.6, 2.2, 4.6, 3.7, 4.6, 4.9, 4.3},
{2.4, 4.4, 4.4, 2.2, 3.8, 1.8, 0.9},
{3.8, 6.6, 3.3, 4.4, 3.6, 3.8, 0.4},
{3.5, 4.4, 2.3, 1.4, 1.5, 2.2, 0.3},
{1.7, 2.6, 3.1, 4.7, 3.3, 0.5, 4.5},
{0.5, 2.7, 2.1, 2.9, 2.1, 4.2, 3.5},
{2.2, 3.2, 4.9, 2.1, 3.8, 2.2, 1.4},
{0.6, 0.6, 4.5, 0.9, 1.1, 0.3, 4.6},
{1.9, 0.9, 1.9, 4.3, 2.4, 1.3, 2.2},
{4.9, 4.3, 4.5, 4.9, 4.5, 1.5, 1.5},
{0.1, 0.4, 1.6, 3.8, 2.2, 2.6, 4.7},
{4.6, 0.3, 3.3, 2.2, 0.3, 3.3, 2.2},
{3.1, 4.8, 0.7, 0.1, 0.8, 2.5, 3.1},
};



now i'm trying wrap head around how calculate for-coming of people based on history data.

example: if time tue 10:00 (6.6 people/minute pass @ time) @ time (when) 2846 people pass?

here how think math:

first find out people/minute needed reach 2846 (2846 / 60 = 47.4)
then note time now, , in chronological order array , add next hours people/minute figures until reach 47.4

that right answer it's kind of awkward.  i start changing table 'people per hour' instead of 'people per minute'.  then not need divide number of people 60.

Arduino Forum > Using Arduino > Programming Questions > Predicting

arduino