GestureRecognitionToolkit  Version: 0.1.0
The Gesture Recognition Toolkit (GRT) is a cross-platform, open-source, c++ machine learning library for real-time gesture recognition.
ClassLabelTimeoutFilter Class Reference
Inheritance diagram for ClassLabelTimeoutFilter:
PostProcessing MLBase GRTBase Observer< TrainingResult > Observer< TestInstanceResult >

Public Types

enum  FilterModes { ALL_CLASS_LABELS =0, INDEPENDENT_CLASS_LABELS }
 
- Public Types inherited from PostProcessing
enum  PostprocessingInputModes { INPUT_MODE_NOT_SET =0, INPUT_MODE_PREDICTED_CLASS_LABEL, INPUT_MODE_CLASS_LIKELIHOODS }
 
enum  PostprocessingOutputModes { OUTPUT_MODE_NOT_SET =0, OUTPUT_MODE_PREDICTED_CLASS_LABEL, OUTPUT_MODE_CLASS_LIKELIHOODS }
 
typedef std::map< std::string, PostProcessing *(*)() > StringPostProcessingMap
 
- Public Types inherited from MLBase
enum  BaseTypes { BASE_TYPE_NOT_SET =0, CLASSIFIER, REGRESSIFIER, CLUSTERER }
 

Public Member Functions

 ClassLabelTimeoutFilter (unsigned long timeoutDuration=1000, UINT filterMode=ALL_CLASS_LABELS)
 
 ClassLabelTimeoutFilter (const ClassLabelTimeoutFilter &rhs)
 
virtual ~ClassLabelTimeoutFilter ()
 
ClassLabelTimeoutFilteroperator= (const ClassLabelTimeoutFilter &rhs)
 
virtual bool deepCopyFrom (const PostProcessing *postProcessing)
 
virtual bool process (const VectorDouble &inputVector)
 
virtual bool reset ()
 
virtual bool saveModelToFile (std::string filename) const
 
virtual bool saveModelToFile (std::fstream &file) const
 
virtual bool loadModelFromFile (std::string filename)
 
virtual bool loadModelFromFile (std::fstream &file)
 
bool init (unsigned long timeoutDuration, UINT filterMode=ALL_CLASS_LABELS)
 
UINT filter (UINT predictedClassLabel)
 
UINT getFilteredClassLabel ()
 
bool isTimeoutActive ()
 
bool setTimeoutDuration (unsigned long timeoutDuration)
 
bool setFilterMode (UINT filterMode)
 
- Public Member Functions inherited from PostProcessing
 PostProcessing (void)
 
virtual ~PostProcessing (void)
 
bool copyBaseVariables (const PostProcessing *postProcessingModule)
 
std::string getPostProcessingType () const
 
UINT getPostProcessingInputMode () const
 
UINT getPostProcessingOutputMode () const
 
UINT getNumInputDimensions () const
 
UINT getNumOutputDimensions () const
 
bool getInitialized () const
 
bool getIsPostProcessingInputModePredictedClassLabel () const
 
bool getIsPostProcessingInputModeClassLikelihoods () const
 
bool getIsPostProcessingOutputModePredictedClassLabel () const
 
bool getIsPostProcessingOutputModeClassLikelihoods () const
 
VectorFloat getProcessedData () const
 
PostProcessingcreateNewInstance () const
 
- Public Member Functions inherited from MLBase
 MLBase (void)
 
virtual ~MLBase (void)
 
bool copyMLBaseVariables (const MLBase *mlBase)
 
virtual bool train (ClassificationData trainingData)
 
virtual bool train_ (ClassificationData &trainingData)
 
virtual bool train (RegressionData trainingData)
 
virtual bool train_ (RegressionData &trainingData)
 
virtual bool train (TimeSeriesClassificationData trainingData)
 
virtual bool train_ (TimeSeriesClassificationData &trainingData)
 
virtual bool train (ClassificationDataStream trainingData)
 
virtual bool train_ (ClassificationDataStream &trainingData)
 
virtual bool train (UnlabelledData trainingData)
 
virtual bool train_ (UnlabelledData &trainingData)
 
virtual bool train (MatrixFloat data)
 
virtual bool train_ (MatrixFloat &data)
 
virtual bool predict (VectorFloat inputVector)
 
virtual bool predict_ (VectorFloat &inputVector)
 
virtual bool predict (MatrixFloat inputMatrix)
 
virtual bool predict_ (MatrixFloat &inputMatrix)
 
virtual bool map (VectorFloat inputVector)
 
virtual bool map_ (VectorFloat &inputVector)
 
virtual bool clear ()
 
virtual bool print () const
 
virtual bool save (const std::string filename) const
 
virtual bool load (const std::string filename)
 
virtual bool getModel (std::ostream &stream) const
 
Float scale (const Float &x, const Float &minSource, const Float &maxSource, const Float &minTarget, const Float &maxTarget, const bool constrain=false)
 
virtual std::string getModelAsString () const
 
DataType getInputType () const
 
DataType getOutputType () const
 
UINT getBaseType () const
 
UINT getNumInputFeatures () const
 
UINT getNumInputDimensions () const
 
UINT getNumOutputDimensions () const
 
UINT getMinNumEpochs () const
 
UINT getMaxNumEpochs () const
 
UINT getValidationSetSize () const
 
UINT getNumTrainingIterationsToConverge () const
 
Float getMinChange () const
 
Float getLearningRate () const
 
Float getRootMeanSquaredTrainingError () const
 
Float getTotalSquaredTrainingError () const
 
Float getValidationSetAccuracy () const
 
VectorFloat getValidationSetPrecision () const
 
VectorFloat getValidationSetRecall () const
 
bool getUseValidationSet () const
 
bool getRandomiseTrainingOrder () const
 
bool getTrained () const
 
bool getModelTrained () const
 
bool getScalingEnabled () const
 
bool getIsBaseTypeClassifier () const
 
bool getIsBaseTypeRegressifier () const
 
bool getIsBaseTypeClusterer () const
 
bool enableScaling (const bool useScaling)
 
bool setMaxNumEpochs (const UINT maxNumEpochs)
 
bool setMinNumEpochs (const UINT minNumEpochs)
 
bool setMinChange (const Float minChange)
 
bool setLearningRate (const Float learningRate)
 
bool setUseValidationSet (const bool useValidationSet)
 
bool setValidationSetSize (const UINT validationSetSize)
 
bool setRandomiseTrainingOrder (const bool randomiseTrainingOrder)
 
bool setTrainingLoggingEnabled (const bool loggingEnabled)
 
bool registerTrainingResultsObserver (Observer< TrainingResult > &observer)
 
bool registerTestResultsObserver (Observer< TestInstanceResult > &observer)
 
bool removeTrainingResultsObserver (const Observer< TrainingResult > &observer)
 
bool removeTestResultsObserver (const Observer< TestInstanceResult > &observer)
 
bool removeAllTrainingObservers ()
 
bool removeAllTestObservers ()
 
bool notifyTrainingResultsObservers (const TrainingResult &data)
 
bool notifyTestResultsObservers (const TestInstanceResult &data)
 
MLBasegetMLBasePointer ()
 
const MLBasegetMLBasePointer () const
 
Vector< TrainingResult > getTrainingResults () const
 
- Public Member Functions inherited from GRTBase
 GRTBase (void)
 
virtual ~GRTBase (void)
 
bool copyGRTBaseVariables (const GRTBase *GRTBase)
 
std::string getClassType () const
 
std::string getLastWarningMessage () const
 
std::string getLastErrorMessage () const
 
std::string getLastInfoMessage () const
 
bool setInfoLoggingEnabled (const bool loggingEnabled)
 
bool setWarningLoggingEnabled (const bool loggingEnabled)
 
bool setErrorLoggingEnabled (const bool loggingEnabled)
 
GRTBasegetGRTBasePointer ()
 
const GRTBasegetGRTBasePointer () const
 
- Public Member Functions inherited from Observer< TrainingResult >
virtual void notify (const TrainingResult &data)
 
- Public Member Functions inherited from Observer< TestInstanceResult >
virtual void notify (const TestInstanceResult &data)
 

Protected Attributes

UINT filteredClassLabel
 
UINT filterMode
 
unsigned long timeoutDuration
 
Vector< ClassLabelAndTimerclassLabelTimers
 
- Protected Attributes inherited from PostProcessing
std::string postProcessingType
 
bool initialized
 
UINT postProcessingInputMode
 
UINT postProcessingOutputMode
 
VectorFloat processedData
 
- Protected Attributes inherited from MLBase
bool trained
 
bool useScaling
 
DataType inputType
 
DataType outputType
 
UINT baseType
 
UINT numInputDimensions
 
UINT numOutputDimensions
 
UINT numTrainingIterationsToConverge
 
UINT minNumEpochs
 
UINT maxNumEpochs
 
UINT validationSetSize
 
Float learningRate
 
Float minChange
 
Float rootMeanSquaredTrainingError
 
Float totalSquaredTrainingError
 
Float validationSetAccuracy
 
bool useValidationSet
 
bool randomiseTrainingOrder
 
VectorFloat validationSetPrecision
 
VectorFloat validationSetRecall
 
Random random
 
std::vector< TrainingResult > trainingResults
 
TrainingResultsObserverManager trainingResultsObserverManager
 
TestResultsObserverManager testResultsObserverManager
 
- Protected Attributes inherited from GRTBase
std::string classType
 
DebugLog debugLog
 
ErrorLog errorLog
 
InfoLog infoLog
 
TrainingLog trainingLog
 
TestingLog testingLog
 
WarningLog warningLog
 

Static Protected Attributes

static RegisterPostProcessingModule< ClassLabelTimeoutFilterregisterModule
 

Additional Inherited Members

- Static Public Member Functions inherited from PostProcessing
static PostProcessingcreateInstanceFromString (std::string const &postProcessingType)
 
- Static Public Member Functions inherited from GRTBase
static std::string getGRTVersion (bool returnRevision=true)
 
static std::string getGRTRevison ()
 
- Protected Member Functions inherited from PostProcessing
bool init ()
 
bool savePostProcessingSettingsToFile (std::fstream &file) const
 
bool loadPostProcessingSettingsFromFile (std::fstream &file)
 
- Protected Member Functions inherited from MLBase
bool saveBaseSettingsToFile (std::fstream &file) const
 
bool loadBaseSettingsFromFile (std::fstream &file)
 
- Protected Member Functions inherited from GRTBase
Float SQR (const Float &x) const
 
- Static Protected Member Functions inherited from PostProcessing
static StringPostProcessingMapgetMap ()
 

Detailed Description

Definition at line 73 of file ClassLabelTimeoutFilter.h.

Constructor & Destructor Documentation

ClassLabelTimeoutFilter::ClassLabelTimeoutFilter ( unsigned long  timeoutDuration = 1000,
UINT  filterMode = ALL_CLASS_LABELS 
)

Default Constructor. Sets the timeoutDuration and filterMode parameters.

The timeoutDuration sets how long (in milliseconds) the Class Label Timeout Filter will debounce valid predicted class labels for, after it has viewed the first valid predicted class label which triggers the debounce mode to be activated. A valid predicted class label is simply a predicted class label that is not the default null rejection class label (i.e. a label with the class value of 0). The filterMode parameter sets how the Class Label Timeout Filter reacts to different predicted class labels (different from the predicted class label that triggers the debounce mode to be activated). There are two options for the filterMode: ALL_CLASS_LABELS or INDEPENDENT_CLASS_LABELS. In the ALL_CLASS_LABELS filterMode, after the debounce mode has been activated, all class labels will be ignored until the current timeoutDuration period has elapsed, regardless of which class actually triggered the timeout. Alternatively, in the INDEPENDENT_CLASS_LABELS mode, the debounce mode will be reset if a different predicted class label is detected that is different from the predicted class label that initially triggered the debounce mode to be activated. For instance, if the debounce mode was activated with the class label of 1, and then class 2 was input into the class label filter, then the debounce mode would be reset to class 2, even if the timeoutDuration for class 1 had not expired.

Parameters
timeoutDurationsets the timeoutDuration value (in milliseconds). Default value timeoutDuration=1000
filterModesets the filterMode parameter. Default value filterMode=ALL_CLASS_LABELS

Definition at line 28 of file ClassLabelTimeoutFilter.cpp.

ClassLabelTimeoutFilter::ClassLabelTimeoutFilter ( const ClassLabelTimeoutFilter rhs)

Copy Constructor.

Copies the values from the rhs ClassLabelTimeoutFilter to this instance of the ClassLabelTimeoutFilter.

Parameters
rhsthe rhs from which the values will be copied to this this instance of the ClassLabelTimeoutFilter

Definition at line 39 of file ClassLabelTimeoutFilter.cpp.

ClassLabelTimeoutFilter::~ClassLabelTimeoutFilter ( )
virtual

Default Destructor

Definition at line 59 of file ClassLabelTimeoutFilter.cpp.

Member Function Documentation

bool ClassLabelTimeoutFilter::deepCopyFrom ( const PostProcessing postProcessing)
virtual

Sets the PostProcessing deepCopyFrom function, overwriting the base PostProcessing function. This function is used to deep copy the values from the input pointer to this instance of the PostProcessing module. This function is called by the GestureRecognitionPipeline when the user adds a new PostProcessing module to the pipeline.

Parameters
postProcessinga pointer to another instance of a ClassLabelTimeoutFilter, the values of that instance will be cloned to this instance
Returns
true if the deep copy was successful, false otherwise

Reimplemented from PostProcessing.

Definition at line 78 of file ClassLabelTimeoutFilter.cpp.

UINT ClassLabelTimeoutFilter::filter ( UINT  predictedClassLabel)

This is the main filter function which filters the input predictedClassLabel.

Parameters
predictedClassLabelthe predictedClassLabel which should be filtered return returns the filtered class label

Definition at line 142 of file ClassLabelTimeoutFilter.cpp.

UINT ClassLabelTimeoutFilter::getFilteredClassLabel ( )
inline

Get the most recently filtered class label value.

Returns
returns the filtered class label

Definition at line 206 of file ClassLabelTimeoutFilter.h.

bool ClassLabelTimeoutFilter::init ( unsigned long  timeoutDuration,
UINT  filterMode = ALL_CLASS_LABELS 
)

This function initializes the ClassLabelTimeoutFilter.

Parameters
timeoutDurationsets the timeoutDuration value (in milliseconds)
filterModesets the filterMode parameter
Returns
returns true if the ClassLabelTimeoutFilter was initialized, false otherwise

Definition at line 125 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::isTimeoutActive ( )

Get if the filter is currently ignorning new inputs because the timeout is active.

Returns
returns true if the timeout mode is active, false otherwise

Definition at line 220 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::loadModelFromFile ( std::string  filename)
virtual

This loads the post processing settings from a file. This overrides the loadSettingsFromFile function in the PostProcessing base class.

Parameters
filenamethe name of the file to load the settings from
Returns
returns true if the settings were loaded successfully, false otherwise

Reimplemented from PostProcessing.

Definition at line 267 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::loadModelFromFile ( std::fstream &  file)
virtual

This loads the post processing settings from a file. This overrides the loadSettingsFromFile function in the PostProcessing base class.

Parameters
filenamethe name of the file to load the settings from
Returns
returns true if the settings were loaded successfully, false otherwise

Reimplemented from PostProcessing.

Definition at line 283 of file ClassLabelTimeoutFilter.cpp.

ClassLabelTimeoutFilter & ClassLabelTimeoutFilter::operator= ( const ClassLabelTimeoutFilter rhs)

Assigns the equals operator setting how the values from the rhs instance will be copied to this instance.

Parameters
rhsthe rhs instance from which the values will be copied to this this instance of the ClassLabelTimeoutFilter
Returns
returns a reference to this instance of the ClassLabelTimeoutFilter

Definition at line 63 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::process ( const VectorDouble inputVector)
virtual

Sets the PostProcessing process function, overwriting the base PostProcessing function. This function is called by the GestureRecognitionPipeline when any new input data needs to be processed (during the prediction phase for example). This function calls the ClassLabelTimeoutFilter's filter(...) function.

Parameters
inputVectorthe inputVector that should be processed. This should be a 1-dimensional vector containing a predicted class label
Returns
true if the data was processed, false otherwise

Reimplemented from PostProcessing.

Definition at line 98 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::reset ( )
virtual

Sets the PostProcessing reset function, overwriting the base PostProcessing function. This function is called by the GestureRecognitionPipeline when the pipelines main reset() function is called. This function resets the ClassLabelTimeoutFilter by re-initiliazing the instance.

Returns
true if the ClassLabelTimeoutFilter was reset, false otherwise

Reimplemented from PostProcessing.

Definition at line 117 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::saveModelToFile ( std::string  filename) const
virtual

This saves the post processing settings to a file. This overrides the saveSettingsToFile function in the PostProcessing base class.

Parameters
filenamethe name of the file to save the settings to
Returns
returns true if the settings were saved successfully, false otherwise

Reimplemented from PostProcessing.

Definition at line 231 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::saveModelToFile ( std::fstream &  file) const
virtual

This saves the post processing settings to a file. This overrides the saveSettingsToFile function in the PostProcessing base class.

Parameters
filenamethe name of the file to save the settings to
Returns
returns true if the settings were saved successfully, false otherwise

Reimplemented from PostProcessing.

Definition at line 251 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::setFilterMode ( UINT  filterMode)

Sets the filterMode parameter, must be a value greater than 0.

The filterMode parameter sets how the Class Label Timeout Filter reacts to different predicted class labels (different from the predicted class label that triggers the debounce mode to be activated). There are two options for the filterMode: ALL_CLASS_LABELS or INDEPENDENT_CLASS_LABELS. In the ALL_CLASS_LABELS filterMode, after the debounce mode has been activated, all class labels will be ignored until the current timeoutDuration period has elapsed, regardless of which class actually triggered the timeout. Alternatively, in the INDEPENDENT_CLASS_LABELS mode, the debounce mode will be reset if a different predicted class label is detected that is different from the predicted class label that initially triggered the debounce mode to be activated.

For instance, if the debounce mode was activated with the class label of 1, and then class 2 was input into the class label filter, then the debounce mode would be reset to class 2, even if the timeoutDuration for class 1 had not expired. If the Class Label Filter has been initialized then the module will be reset.

Parameters
filterModethe new filterMode parameter
Returns
returns true if the filterMode parameter was updated, false otherwise

Definition at line 342 of file ClassLabelTimeoutFilter.cpp.

bool ClassLabelTimeoutFilter::setTimeoutDuration ( unsigned long  timeoutDuration)

Sets the timeoutDuration parameter, must be a value greater than 0.

The timeoutDuration sets how long (in milliseconds) the Class Label Timeout Filter will debounce valid predicted class labels for, after it has viewed the first valid predicted class label which triggers the debounce mode to be activated. A valid predicted class label is simply a predicted class label that is not the default null rejection class label (i.e. a label with the class value of 0). If the Class Label Filter has been initialized then the module will be reset.

Parameters
timeoutDurationthe new timeoutDuration parameter
Returns
returns true if the timeoutDuration parameter was updated, false otherwise

Definition at line 334 of file ClassLabelTimeoutFilter.cpp.


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