Package jline.api.infer
Class InferLqnOptions
java.lang.Object
jline.api.infer.InferLqnOptions
Options for LQN parameter identification via the Extended Kalman Filter
(
InferLqn).
The tuning factors follow Zheng, Yang, Woodside, Litoiu, Iszlai, "Tracking Time-Varying Parameters in Software Systems with Extended Kalman Filters", CASCON 2005: the drift covariance is Q_ii = (QFac*a0_i*cvA)^2 (eq 9a) and the measurement covariance is R_ii = ((RFac*zbar_i)/1.96)^2/gammaT (eq 9b), with gammaT = T/Tstar. Explicit Q, R, P0, a0 override the constructed values.
Copyright (c) 2012-2026, Imperial College London. All rights reserved.-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic interfaceObservation model: solve the LQN and return its per-element average table. -
Field Summary
FieldsModifier and TypeFieldDescriptionbooleandoubledoubledoubledoubledoubleObservation-model solver; when null a silent SolverLN is used.boolean -
Constructor Summary
Constructors -
Method Summary
-
Field Details
-
solver
Observation-model solver; when null a silent SolverLN is used. -
QFac
public double QFac -
RFac
public double RFac -
cvA
public double cvA -
gammaT
-
T
-
Tstar
-
Q
-
R
-
P0
-
a0
-
aTrue
-
fdStep
public double fdStep -
fdFloor
public double fdFloor -
clampPositive
public boolean clampPositive -
verbose
public boolean verbose
-
-
Constructor Details
-
InferLqnOptions
public InferLqnOptions()
-