deepSignalAnomalyDetectorLSTM

Detect signal anomalies using LSTM autoencoder

Since R2023a

Description

The deepSignalAnomalyDetectorLSTM object uses a long short-term memory (LSTM) autoencoder model to detect signal anomalies.

Creation

Create a deepSignalAnomalyDetectorLSTM object using deepSignalAnomalyDetector and specifying "lstmautoencoder" as the model type.

Properties

General

IsTrained — Training status

0 (false) | 1 (true)

This property is read-only.

Training status, returned as 0 (false) or 1 (true). Once you train the detector, IsTrained is equal to 1.

Data Types: logical

NumChannels — Number of channels

positive integer

This property is read-only.

Number of channels in each input signal, returned as a positive integer.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Model

ModelType — Type of deep learning model

"lstmautoencoder"

This property is read-only.

Type of deep learning model implemented by the detector, returned as "lstmautoencoder".

EncoderHiddenUnits — Number of hidden units in encoder

[32 16] (default) | vector of positive integers

This property is read-only.

Number of hidden units for each layer in the encoder, returned as a vector of positive integers. The ith element of the vector sets the number of hidden units in the ith layer.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

DecoderHiddenUnits — Number of hidden units in decoder

[32 16] (default) | vector of positive integers

This property is read-only.

Number of hidden units in each layer of the decoder, returned as a vector of positive integers. The ith element of the vector sets the number of hidden units in the ith layer.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Window

WindowLength — Window length

1 (default) | positive integer | "fullSignal"

This property is read-only.

Window length of each signal segment, returned as a positive integer or as "fullSignal".

• If WindowLength is an integer, the detector divides each input signal into segments. The length of each segment is equal to the WindowLength value in samples.

• If WindowLength is "fullSignal", the detector treats each input signal as a single segment.

Use updateDetector to modify this and other window properties.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

OverlapLength — Number of overlapped samples

"auto" (default) | positive integer

This property is read-only.

Number of overlapped samples between window segments, returned as a positive integer or as "auto".

• If OverlapLength is a positive integer, the detector sets the number of overlapped samples equal to the OverlapLength value.

• If OverlapLength is "auto", the detector sets the number of overlapped samples equal to WindowLength – 1.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

WindowLossAggregation — Method to aggregate sample loss

"mean" (default) | "max" | "min" | "median"

This property is read-only.

Method to aggregate sample loss within each window segment, returned as one of these:

• "max" — Compute the aggregated window loss as the maximum value of all the sample losses within the window.

• "mean" — Compute the aggregated window loss as the mean value of all the sample losses within the window.

• "median" — Compute the aggregated window loss as the median value of all the sample losses within the window.

• "min" — Compute the aggregated window loss as the minimum value of all the sample losses within the window.

Data Types: char | string

Threshold

ThresholdMethod — Method to compute detection threshold

"contaminationFraction" (default) | "max" | "median" | "mean" | "manual" | "customFunction"

This property is read-only.

Method to compute the detection threshold, returned as one of these:

• "contaminationFraction" — Value corresponding to the detection of anomalies within a specified fraction of windows. The fraction value is specified by ThresholdParameter.

• "max" — Maximum window loss measured over the entire training data set and multiplied by ThresholdParameter.

• "median" — Median window loss measured over the entire training data set and multiplied by ThresholdParameter.

• "mean" — Mean window loss measured over the entire training data set and multiplied by ThresholdParameter.

• "manual" — Manual detection threshold value based on Threshold.

• "customFunction" — Custom detection threshold value based on ThresholdFunction.

Use updateDetector to modify this and other threshold properties.

Data Types: char | string

ThresholdParameter — Detection threshold

real scalar

This property is read-only.

Detection threshold, returned as a nonnegative scalar when you set ThresholdMethod to "contaminationFraction", and as positive scalar when you set ThresholdMethod to "max", "median", or "mean".

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Threshold — Manual detection threshold

positive scalar

This property is read-only.

Manual detection threshold, retuned as a positive scalar. This property applies only when you set ThresholdMethod to "manual".

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

ThresholdFunction — Function to compute custom detection threshold

function handle

This property is read-only.

Function to compute custom detection threshold, returned as a function handle. This property applies only when you set ThresholdMethod to "customFunction".

Data Types: function_handle

Object Functions

detect	Detect anomalies in signals
getModel	Get underlying neural network model of signal anomaly detector
plotAnomalies	Plot signal anomalies
plotLoss	Plot window reconstruction loss
plotLossDistribution	Plot CDF and histogram of aggregated window loss distribution
saveModel	Save detector network and parameters
trainDetector	Train signal anomaly detector
updateDetector	Update settings of trained detector and recompute detection threshold

Examples

Neural Network Model of LSTM Anomaly Detector

Create an object that uses a long short-term memory (LSTM) autoencoder model to detect anomalies in four-channel signals. Use deepSignalAnomalyDetector with default property values.

D = deepSignalAnomalyDetector(4,"lstmautoencoder");

Get the underlying neural network model of the LSTM anomaly detector. Use the analyzeNetwork (Deep Learning Toolbox) function to inspect the model.

M = getModel(D);
analyzeNetwork(M)

Extended Capabilities

GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

Usage notes and limitations:

• The ExecutionEnvironment option must be "gpu" or "auto" when the input data is:

  • A gpuArray

  • A cell array containing gpuArray objects

  • A datastore that outputs cell arrays containing gpuArray objects

For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

Version History

Introduced in R2023a