没有合适的资源?快使用搜索试试~ 我知道了~
首页关于泊松点过程的生成方法-Report1_POISSON_Prog.pdf
关于泊松点过程的生成方法-Report1_POISSON_Prog.pdf
需积分: 49 28 下载量 112 浏览量
更新于2023-03-16
评论 3
收藏 1.95MB PDF 举报
关于泊松点过程的生成方法-Report1_POISSON_Prog.pdf 在百度上看很多人问平面内泊松点怎么生成,以前我也迷茫的很久,刚好今天找到一个很有用的方法,分享给大家! Report1_POISSON_Prog.pdf 泊松点生成
资源详情
资源评论
资源推荐
POISSON
A program for spatial point generation using Poisson processes
Department of Mining and Mineral Engineering
The University of Leeds
September 2002
Stochastic Modelling of Fractures in Rock Masses, 2002
2
1. Introduction
The purpose of the program is to generate spatial points in R
2
as realisations of user-
defined Poisson processes. The type of processes implemented by the program are:
homogeneous Poisson process, non-homogeneous Poisson process, Poisson cluster
process, simple Cox process and simple Boolean model.
The realisation is to be constructed in a rectangular area, A=[x
1
,x
2
]×[y
1
,y
2
], where x
1
,
x
2
, y
1
and y
2
can be specified. A is divided into quadrate cells with each individual
cell being treated as an all bounded Borel set. The number of cells in X and Y can also
be specified by the user of the program. For this arrangement, all cells are disjoint
and therefore the simulation of Poisson points for each cell can be done
independently.
The commands to be used are all listed under the master menu of “SpatialPattern”.
Select the corresponding command will bring up the related parameter specification
window. Closing the window will activate the simulation and the generated points
will be displayed once the process finishes.
2. Homogeneous Poisson process
Homogeneous process is the simplest possible stochastic mechanism representing the
spatial point patterns. It generates realisations of stationary and isotropic
characteristics which resemble complete spatial randomness (CSR) in applications.
The process defines a spatial points pattern which bears the following properties
(characteristics):
• For any bounded Borel set A in the region of consideration ℜ, the number of
points falling inside A, N(A), follows a Poisson distribution with mean λ⋅ν(A),
where ν(A) is the measure of A. λ is referred to as the density of the
distribution. In two-dimensional case, A is a planar sub-region of ℜ and ν(A)
is the area of the sub-region.
• Conditioned on N(A) = n, the n event points are uniformly distributed inside
the sub-region A. In two-dimensional case, the events follow bi-variate
uniform distribution.
• For any disjoint sub-regions B
1
, B
2
, …, B
k
within the region ℜ, N(B
1
), N(B
2
),
…, N(B
k
) are independent random variables.
Two distinct ways can be used to generate realisations of homogeneous Poisson
process. One is to use the property that the spatial differences (areas in 2D case)
between successive point events follow an exponential distribution with parameter λ
(the density of the Poisson process). Different implementations can be derived to
explore this property in 2D and 3D cases. The other way is to simulate the Poisson
variable N(A) directly. Simulation of N(A) may sometimes be time-consuming, the
implementation nevertheless is simpler and less error prone. In the current exercise,
direct Poisson variable simulation is used.
The procedures for the realisation of homogeneous Poisson process in a two
dimensional region ℜ are given as:
• 1). Sub-divide the region ℜ into m sub-regions, A
1
, A
2
, …, A
m
. In most of the
cases, region ℜ is a rectangle and A
1
, A
2
, …, A
m
are disjoint rectangular
Stochastic Modelling of Fractures in Rock Masses, 2002
3
quadrates with
U
i
i
A=ℜ . Work out the mean of the Poisson distribution for
each quadrate as )(
iii
Aνλµ ⋅= , where λ
i
is the density for quadrate i. For
homogeneous case, λ
1
=λ
2
= … =λ
m
= λ.
• 2). For each of the m sub-regions A
i
, generate a random variable N
i
based on
the Poisson distribution function:
!
)(
n
enNP
n
i
i
i
µ
µ−
==
• 3). For each of the n events for quadrate A
i
, generate two random variables
according to the uniform distribution and use them as the locations inside the
sub-region.
• 4). Repeat procedures 2 and 3 until all quadrates in ℜ are visited.
In step 2, the simulation of Poisson variable is from Ross [5]. To simulate a Poisson
random variable with mean µ, generate a sequence of independent random variables
uniformly distributed within (0,1), U
1
, U
2
, …, stopping when the following condition
is reached:
∏
=
−
<
k
i
i
eU
1
µ
then the variable n=k has the desired distribution. An alternative to the above
condition is by taking the logarithms and the condition becomes:
∑ ∑
= =
>−−<
k
i
k
i
ii
UorU
1 1
)log()log( µµ
Figure 1 Parameters for homogeneous Poisson process
Based on our experience, the alternative form is preferred although it takes longer
computation time due to the logarithmic transformation involved in each step of the
Stochastic Modelling of Fractures in Rock Masses, 2002
4
simulation. The reason is simple. When µ→∝, e
-µ
→0, so for large µ value, e
-µ
is
small. As U
i
∈(0,1) so a large number of uniform variables U
i
are needed to reach the
condition. Computers are always problematic when dealing with small numbers and
therefore as k increases, the rounding error soon renders ∏U
i
inaccurate or even
meaningless. By using logarithms, this rounding error problem is avoided.
Figure 1 is the dialogue window for specifying the parameters to be used to generate a
realisation of a homogeneous Poisson process. The region of simulation ℜ is a
rectangle and ℜ is sub-divided into rectangular sub-regions by specifying the number
of cells required in both axis directions. Density λ is specified directly by typing the
value in the data box provided.
Figure 2 Example of a realisation of a homogeneous Poisson process
Figure 2 shows an example of a realisation of a homogeneous Poisson process defined
in Figure 1. Homogeneity of the point pattern is obvious just by way of visual
inspection.
QUESTION: How can we control the number of events to be an exact value?
剩余18页未读,继续阅读
weixin_39840914
- 粉丝: 435
- 资源: 1万+
上传资源 快速赚钱
- 我的内容管理 收起
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
会员权益专享
最新资源
- stc12c5a60s2 例程
- Android通过全局变量传递数据
- c++校园超市商品信息管理系统课程设计说明书(含源代码) (2).pdf
- 建筑供配电系统相关课件.pptx
- 企业管理规章制度及管理模式.doc
- vb打开摄像头.doc
- 云计算-可信计算中认证协议改进方案.pdf
- [详细完整版]单片机编程4.ppt
- c语言常用算法.pdf
- c++经典程序代码大全.pdf
- 单片机数字时钟资料.doc
- 11项目管理前沿1.0.pptx
- 基于ssm的“魅力”繁峙宣传网站的设计与实现论文.doc
- 智慧交通综合解决方案.pptx
- 建筑防潮设计-PowerPointPresentati.pptx
- SPC统计过程控制程序.pptx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0