2009년 11월 25일 수요일

Poisson process에 관한 내용(Wiki)

Homogeneous

Sample Poisson process N(t)

The homogeneous Poisson process is one of the most well-known Lévy processes. This process is characterized by a rate parameter λ, also known as intensity, such that the number of events in timeinterval (t, t + τ] follows a Poisson distribution with associated parameter λτ. This relation is given as

 P [(N(t+ \tau) - N(t)) = k] = \frac{e^{-\lambda \tau} (\lambda \tau)^k}{k!} \qquad k= 0,1,\ldots,

where N(t + τ) − N(t) is the number of events in time interval (t, t + τ].

Just as a Poisson random variable is characterized by its scalar parameter λ, a homogeneous Poisson process is characterized by its rate parameter λ, which is the expected number of "events" or "arrivals" that occur per unit time.

N(t) is a sample homogeneous Poisson process, not to be confused with a density or distribution function.

[edit]Non-homogeneous

In general, the rate parameter may change over time; such a process is called a non-homogeneous Poisson process or inhomogeneous Poisson process. In this case, the generalized rate function is given as λ(t). Now the expected number of events between time a and time b is

\lambda_{a,b} = \int_a^b \lambda(t)\,dt.

Thus, the number of arrivals in the time interval (a, b], given as N(b) − N(a), follows a Poisson distribution with associated parameter λa,b

 P [(N(b) - N(a)) = k] = \frac{e^{-\lambda_{a,b}} (\lambda_{a,b})^k}{k!} \qquad k= 0,1,\ldots.

A homogeneous Poisson process may be viewed as a special case when λ(t) = λ, a constant rate.

[edit]Spatial

A further variation on the Poisson process, called the spatial Poisson process, introduces a spatial dependence on the rate function and is given as \lambda(\vec{x},t) where \vec{x} \in Vfor some vector space V (e.g. R2 or R3). For any set S \subset V (e.g. a spatial region) with finite measure, the number of events occurring inside this region can be modelled as a Poisson process with associated rate function λS(t) such that

\lambda_S(t) = \int_S \lambda(\vec{x},t)\,d\vec{x}.

In the special case that this generalized rate function is a separable function of time and space, we have:

\lambda(\vec{x},t) = f(\vec{x}) \lambda(t)

for some function f(\vec{x}). Without loss of generality, let

\int_V f(\vec{x}) \, d\vec{x}=1.

(If this is not the case, λ(t) can be scaled appropriately.) Now, f(\vec{x}) represents the spatial probability density function of these random events in the following sense. The act of sampling this spatial Poisson process is equivalent to sampling a Poisson process with rate function λ(t), and associating with each event a random vector \vec{X}sampled from the probability density function f(\vec{x}). A similar result can be shown for the general (non-separable) case.

댓글 없음:

댓글 쓰기