SharpBCI
A multi-threaded brain control interface (BCI) library in C#
 All Classes Namespaces Files Functions Variables Enumerations Enumerator Properties Pages
Public Member Functions | Public Attributes | List of all members
SharpBCI.ARArtifactDetector Class Reference

A detector which uses an underlying AR model to detect artifacts. More...

Inheritance diagram for SharpBCI.ARArtifactDetector:
SharpBCI.IArtifactDetector

Public Member Functions

 ARArtifactDetector (ARModel model)
 
double Error ()
 Inform the caller of the current confusion of this implementation The returned value should be a double greater than or equal to zero Otherwise no range is assumed, but lower values should indicate lower confusion For example, a detector that perfectly models the signal with no artifacts should have an error of zero Pragmatically, error will generally be non-zero due to presence of artifacts and noise. More...
 
bool Detect (double next)
 Update artifact detector using next. More...
 

Public Attributes

const double ARTIFACT_THRESHOLD = 2
 

Detailed Description

A detector which uses an underlying AR model to detect artifacts.

The difference between the observed data and the predicted data is known internally as error. This error is distributed normally and if the observed error is more than the 95% CI interval, the observed data is assumed to be an artifact and is not added to the error distribution. In this IArtifactDetector, Error is equal to the variance of another (unfiltered) distribution of error.

Constructor & Destructor Documentation

SharpBCI.ARArtifactDetector.ARArtifactDetector ( ARModel  model)

Member Function Documentation

bool SharpBCI.ARArtifactDetector.Detect ( double  next)

Update artifact detector using next.

Returns
true iff next is an artifact, false otherwise

Implements SharpBCI.IArtifactDetector.

double SharpBCI.ARArtifactDetector.Error ( )

Inform the caller of the current confusion of this implementation The returned value should be a double greater than or equal to zero Otherwise no range is assumed, but lower values should indicate lower confusion For example, a detector that perfectly models the signal with no artifacts should have an error of zero Pragmatically, error will generally be non-zero due to presence of artifacts and noise.

Returns
the internal confusion metric of this implementation

Implements SharpBCI.IArtifactDetector.

Member Data Documentation

const double SharpBCI.ARArtifactDetector.ARTIFACT_THRESHOLD = 2
The documentation for this class was generated from the following file: