plotHistogram

Plot histogram of anomaly scores and detection threshold for trained deep learning anomaly detector

Since R2025a

Syntax

plotHistogram(detector,data1)

plotHistogram(detector,data1,data2)

plotHistogram(___,Name=Value)

Description

Add-On Required: This feature requires the Time Series Anomaly Detection for MATLAB add-on.

plotHistogram(detector,data1) plots computes the anomaly scores for the trained deep learning detector detector using the data in data1, and plots a histogram of the scores along with the threshold in detector.threshold.

Use this syntax, for example, when you have trained a detector using the normal data in data1, and you want to examine the score distribution and the threshold placement.

For an example of using plotHistogram as part of the detector development workflow, see Train and Test TCN Anomaly Detector.

This function requires Deep Learning Toolbox™.

plotHistogram(detector,data1,data2) plots the histograms for two sets of data, data1 and data2, together in the same figure.

Use this syntax, for example, when you have both normal data and test data and you want to view the histogram of the associated anomaly scores together. You can use this syntax without running detect first.

plotHistogram(___,Name=Value) sets additional options using one or more name-value arguments.

Input Arguments

detector — Trained deep learning anomaly detector

TcnDetector object | DeepantDetector object | UsadDetector object | VaelstmDetector object

Trained anomaly detector model, specified as a TcnDetector, DeepantDetector, UsadDetector, or VaelstmDetector object.

data1 — Time series data for computing first or only set of anomaly scores

matrix | timetable | cell array

Time series data for computing the first or only set of anomaly scores to plot, specified as a matrix, a cell array, or a timetable. Typically, data1 contains the training data that was used for training the anomaly detector and consists of only normal data, with no known anomalies or abnormal data.

When data1 contains m sets of signals, each of which contain n = detector.NumChannels channels, the possible formats are these:

• n-column matrix that consists of a single multichannel signal (m=1).

• Cell array with m cells that each contain a matrix that has NumChannels columns.

• Timetable that contains a single multichannel signal , arranged in one of two possible ways.

  • The n channels are distributed in the columns of a matrix that the timetable contains in a single variable

  • The n channels are represented by n timetable variables that each contain a vector.

  In either case, the timetable must contain finite, increasing, and uniformly sampled time values.

data2 — Time series data for computing second set of anomaly scores

matrix | timetable | cell array

Time series data for computing the second set of anomaly scores to plot, specified as a matrix, a cell array, or a timetable. Typically, data2 consists of test data, and can contain a mix of abnormal and normal data.

When data2 contains m sets of signals, each of which contain n = detector.NumChannels channels, the possible formats are these:

• n-column matrix that consists of a single multichannel signal (m=1).

• Cell array with m cells that each contain a matrix that has NumChannels columns.

• Timetable that contains a single multichannel signal , arranged in one of two possible ways.

  • The n channels are distributed in the columns of a matrix that the timetable contains in a single variable

  • The n channels are represented by n timetable variables that each contain a vector.

  In either case, the timetable must contain finite, increasing, and uniformly sampled time values.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Example: plotHistogram(detectortcn,data,MiniBatchSize=64) plots a histogram of data for the TCN detector detectortcn and specifies a mini-batch size of 64 for detection.

All Detectors

ExecutionEnvironment — Execution environment

"auto" (default) | "cpu" | "gpu" | "multi-gpu"

Execution environment that determines what hardware resources the software uses to run the network, specified as "auto", "cpu", "gpu", or "multi-gpu".

• "auto" — Use the GPU if one is available, or if not, the CPU.

• "cpu" — Use the CPU.

• "gpu" — Use the GPU.

• "multi-gpu" — Use the GPU array.

Example: plot(detectorUsad,data,ExecutionEnvironment="auto") uses a GPU for histogram plotting if one is available or the CPU if a GPU is not available.

TCN, DeepAnt, and VAELSTM Detectors Only

MiniBatchSize — Mini-batch size

128 (default) | positive integer scalar

Mini-batch size that is used in detect, specified as a positive integer scalar.

You must set this argument if detect uses a MiniBatchSize value of anything other than default size of 128.

Extended Capabilities

GPU Arrays

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

The plotHistogram function supports GPU arrays when you use plotHistogram on any detector model. To specify GPU processing, see ExecutionEnvironment.

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

Version History

Introduced in R2025a

R2026a: GPU capability available for all anomaly detector models

GPU capability added for UsadDetector and VaelstmDetector detectors.

R2026a: Functionality moved to support package

Functionality moved to Time Series Anomaly Detection for MATLAB^® support package.