Statistics Blocks

The Statistics library provides fundamental statistical operations such as minimum, maximum, mean, variance, and standard deviation. Most blocks in the Statistics library support two types of operations; basic and running.

The blocks listed below toggle between basic and running modes using the Running check box in the parameter dialog box:

An unselected Running check box means that the block is operating in basic mode, while a selected Running box means that the block is operating in running mode.

The Maximum and Minimum blocks are slightly different from the blocks above, and provide a Mode parameter in the block dialog box to select the type of operation. The Value and Index, Value, and Index options in the Mode menu all specify basic operation, in each case enabling a different set of output ports on the block. The Running option in the Mode menu selects running operation.

Basic Operations

A basic operation is one that processes each input independently of previous and subsequent inputs. For example, in basic mode (with Value and Index selected, for example) the Maximum block finds the maximum value in each column of the current input, and returns this result at the top output (Val). Each consecutive Val output therefore has the same number of columns as the input, but only one row. Furthermore, the values in a given output only depend on the values in the corresponding input. The block repeats this operation for each successive input.

This type of operation is exactly equivalent to the MATLAB® command

val = max(u)					% Equivalent MATLAB code

which computes the maximum of each column in input u.

The next section is an example of a basic statistical operation.

Create a Sliding Window

You can use the basic statistics operations in conjunction with the Buffer block to implement basic sliding window statistics operations. A sliding window is like a stencil that you move along a data stream, exposing only a set number of data points at one time.

For example, you may want to process data in 128-sample frames, moving the window along by one sample point for each operation. One way to implement such a sliding window is shown in the following ex_mean_tut model.

The Buffer block's Buffer size (Mo) parameter determines the size of the window. The Buffer overlap (L) parameter defines the "slide factor" for the window. At each sample instant, the window slides by Mo-L points. The Buffer overlap is often Mo-1, so that a new statistic is computed for every new signal sample.

Running Operations

A running operation is one that processes successive inputs, and computes a result that reflects both current and past inputs. In this mode, you must use the Input processing parameter to specify whether the block performs sample- or frame-based processing on the inputs. A reset port enables you to restart this tracking at any time. The running statistic is computed for each input channel independently, so the block's output is the same size as the input.

For example, in running mode (Running selected from the Mode parameter) the Maximum block outputs a record of the input's maximum value over time.

The following figure illustrates how a Maximum block in running mode operates on a 3-by-2 matrix input, u, when the Input processing parameter is set to Columns as channels (frame based). The running maximum is reset at t=2 by an impulse to the block's optional Rst port.

Was this topic helpful?