NonDEvidence Class Reference

Class for the Dempster-Shafer Evidence Theory methods within DAKOTA/UQ. More...

Inheritance diagram for NonDEvidence:

List of all members.

Public Member Functions
	NonDEvidence (Model &model)
	constructor
	~NonDEvidence ()
	destructor
void	quantify_uncertainty ()
	for cumulative distribution functions of belief and plausibility
void	print_results (ostream &s)
	print the cumulative distribution functions for belief and plausibility
Protected Member Functions
void	initialize_final_statistics ()
	initialize finalStatistics for belief/plausibility results sets
void	compute_statistics ()
	or vice-versa
Private Member Functions
void	calculate_basic_prob_intervals ()
	basic probability assignments for input interval combinations
void	calculate_maxmin_per_interval (const size_t &func_num)
	maximum and minimum values within each input interval combination (cell).
void	calculate_cum_belief_plaus (const size_t &func_num)
	per interval cell
Private Attributes
Iterator	lhsSampler
	the LHS sampler instance
const int	originalSeed
	the user seed specification (default is 0)
int	numSamples
	the number of samples used in the surrogate
int	NV
	Size variable for DDS arrays.
int	NCMB
	Size variable for DDS arrays.
int	MAXINTVLS
	Size variable for DDS arrays.
Real	Y
	Temporary output variable.
Real *	BPA
	Internal DDS array.
Real *	VMIN
	Internal DDS array.
Real *	VMAX
	Internal DDS array.
Real *	BPAC
	Internal DDS array.
Real *	CMIN
	Internal DDS Array.
Real *	CMAX
	Internal DDS Array.
Real *	X
	Internal DDS Array.
int *	NI
	Internal DDS array.
int *	IP
	Internal DDS array.
int *	IPBEL
	Internal DDS array.
int *	IPPLA
	Internal DDS array.
RealVectorArray	cc_bel_fn
	Storage array to hold CCBF values.
RealVectorArray	cc_plaus_fn
	Storage array to hold CCPF values.
RealVectorArray	cc_bel_val
	Storage array to hold CCB response values.
RealVectorArray	cc_plaus_val
	Storage array to hold CCP response values.
VariablesArray	all_vars
	Storage array to hold variables.
ResponseArray	all_responses
	Storage array to hold responses.

---

Detailed Description

Class for the Dempster-Shafer Evidence Theory methods within DAKOTA/UQ.

The NonDEvidence class implements the propagation of epistemic uncertainty using Dempster-Shafer theory of evidence. In this approach, one assigns a set of basic probability assignments (BPA) to intervals defined for the uncertain variables. Input interval combinations are calculated, along with their BPA. Currently, the response function is evaluated at a set of sample points, then a response surface is constructed which is sampled extensively to find the minimum and maximum within each input interval cell, corresponding to the belief and plausibility within that cell, respectively. This data is then aggregated to calculate cumulative distribution functions for belief and plausibility.

---

Member Data Documentation

int NV [private]

Size variable for DDS arrays.

NV = number of interval variables

int NCMB [private]

Size variable for DDS arrays.

NCMB = number of cell combinations

int MAXINTVLS [private]

Size variable for DDS arrays.

MAXINTVLS = maximum number of intervals per individual interval var

Real Y [private]

Temporary output variable.

Y = current output to be placed in cell

Real* BPA [private]

Internal DDS array.

Basic Probability Assignments

Real* VMIN [private]

Internal DDS array.

Minimum ends of intervals.

Real* VMAX [private]

Internal DDS array.

Maximum ends of intervals.

Real* BPAC [private]

Internal DDS array.

Basic Probability Combinations.

Real* CMIN [private]

Internal DDS Array.

Minimum per cell combination.

Real* CMAX [private]

Internal DDS Array.

Maximum per cell combination.

Real* X [private]

Internal DDS Array.

X per cell combination.

int* NI [private]

Internal DDS array.

Number of intervals per interval variable

int* IP [private]

Internal DDS array.

Sort order for combinations

int* IPBEL [private]

Internal DDS array.

Sort order for belief values

int* IPPLA [private]

Internal DDS array.

Sort order for belief values

---

The documentation for this class was generated from the following files:

• NonDEvidence.H
• NonDEvidence.C

---