F_VN_GetSampleClusterExp

F_VN_GetSampleClusterExp 1:

Get the ID of the best-matching cluster of a single sample. (expert function)

Syntax

Definition:

FUNCTION F_VN_GetSampleClusterExp : HRESULT
VAR_INPUT
    ipClusterer : ITcVnMlModel;
    ipSample    : ITcUnknown;
END_VAR
VAR_IN_OUT
    nCluster    : DINT;
END_VAR
VAR_INPUT
    fNovelty    : Reference To REAL;
    hrPrev      : HRESULT;
END_VAR

F_VN_GetSampleClusterExp 2: Inputs

Name

Type

Description

ipClusterer

ITcVnMlModel

Clusterer to be used

ipSample

ITcUnknown

Container holding a single input sample (ContainerType_Vector_REAL or ContainerType_Vector_LREAL)

fNovelty

Reference To REAL

Returns the degree of novelty (0.0 if a sample is completely known; > 0.0 otherwise) of the presented sample (optional, set to 0 if not required)

hrPrev

HRESULT

HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.)

F_VN_GetSampleClusterExp 3: In/Outputs

Name

Type

Description

nCluster

DINT

Returns the ID of the cluster the sample has been assigned to

F_VN_GetSampleClusterExp 4: Return value

HRESULT

Further information

The function F_VN_GetSampleClusterExp is the expert variant of F_VN_GetSampleCluster. It contains additional parameters.

Parameter

Clusterer model

A previously trained model must be transferred to ipClusterer for assignment to clusters.

Sample

A container with a sample is transferred to ipSample. The type of container must be ContainerType_Vector_REAL or ContainerType_Vector_LREAL.

Cluster ID

The ID determined is returned via nCluster.

Degree of novelty

The degree of novelty of the sample is returned via the reference fNovelty. The degree of novelty indicates how strongly a sample differs from the clusters. A degree of novelty of 0 indicates that a sample is known to the model.

Application

The calculation of the cluster and the degree of novelty of a sample can be calculated as follows:

hr := F_VN_GetSampleClusterExp(
    ipClusterer := ipClusterer,
    ipSample    := ipSample,
    nCluster    := nCluster,
    fNovelty    := fNovelty,
    hrPrev      := hr);

Related functions

Required License

TC3 Vision Machine Learning

System Requirements

Development environment

Target platform

PLC libraries to include

TwinCAT V3.1.4024.54 or later

PC or CX (x64) with PL50, e.g. Intel 4-core Atom CPU

Tc3_Vision