[aceraven777]

I'm working on a traffic flow prediction where I can predict that a place has heavy or light traffic. I have classified each traffic as 1-5, 1 being the lightest traffic and 5 being the heaviest traffic.

I came across to this website http://www.waset.org.../v25/v25-36.pdf, adaboost algorithm, and I'm really having a difficulty learning this algorithm. Specially in the part where S is the set ((xi,yi),i=(1,2,…,m)). where Y={-1,+1}. what is x and y? and the constant L? what is the value of L?

Can someone explain me this algorithm?

[sepp2k]

The set S is one of the parameters of the algorithm. It's a set that contains m 2-tuples. x₁ through x_m and y₁ through y_m respectively are the first and second elements of each of those 2-tuples.

The constant L is another parameter of the algorithm.

[aceraven777]

sepp2k, on 06 August 2012 - 03:38 AM, said:

The set S is one of the parameters of the algorithm. It's a set that contains m 2-tuples. x₁ through x_m and y₁ through y_m respectively are the first and second elements of each of those 2-tuples.

The constant L is another parameter of the algorithm.

yes I know that, what i'm asking is what is the use of x and y? and what must be the value of L?

[sepp2k]

S is your sample set. Each x is an element to be classified and each y is what the element should be classified as. The note about Y being {-1,1} for the purposes of this paper, means that the paper only considers problems where each element is either classified as "matches conditions" or "doesn't match conditions". That's not quite what you want because, as I understood it, you want to classify your elements into groups from 1 to 5, but that should be okay. The paper didn't say that the algorithm doesn't work for non-binary classification, just that it doesn't focus on it.

The value of L can be any integer. It's the limit that describes how much steps the algorithm will perform at most. The higher L, the better the results and the longer the potential running time.