Main Content

Preprocess Data

Clean and label data in preparation for more advanced signal processing

In algorithm design for predictive maintenance, basic data preprocessing is often necessary to clean the data and perform other preliminary operations such as signal labeling prior to applying more specialized feature-focused processing. You can perform data preprocessing on arrays or tables of measured or simulated data that you manage with Predictive Maintenance Toolbox™ ensemble datastores. For an overview of some common types of data preprocessing, see Data Preprocessing for Condition Monitoring and Predictive Maintenance.


Data CleanerPreprocess and organize column-oriented data (Since R2022a)
Signal LabelerLabel signal attributes, regions, and points of interest, and extract features


expand all

fillmissingFill missing entries
filloutliersDetect and replace outliers in data
smoothdataSmooth noisy data
movmeanMoving mean
detrendRemove polynomial trend
rescaleScale range of array elements