Logo réduit OCTOPIZE - pictogramme

Systolic Blood Pressure

The data captured in this use case covers the very specific context of time series anonymization.

Data type

In the Systolic Blood Pressure case, the data used are artificial systolic blood pressure data. All the measurements are performed on 20 patients on about 50 timepoints and form a time series. This is a specific type of data involving a dependence between the different values. Time series are frequently used, especially in the health field. Their temporal characteristic makes them subject to re-identification by individualization.
  • 20 patients
  • 25 measurements / patient

Objectives of anonymization

  1. First, the goal is to make it impossible to re-identify the individuals in the dataset: personal data protection objective.
  2. Secondly, the anonymization of systolic blood pressure data will have to preserve the usefulness of the data by preserving the trends, patterns and possible seasonality of the time series.
The reference data produced were purposely separated in a bimodal fashion to ensure that this information would be retained after the transformation into avatarized time series.
After transformation into an avatar, the generated time series are superimposed on the reference series. This representation allows to visualize the quality of the information kept in terms of clustering and trend.

Other use cases

New York Taxi

The "New York Taxi" use case presents a context of anonymization of spatio-temporal data. The difficulty lies in the particular nature of this data, where the combination of spatial and temporal dimensions accentuates the risk of re-identification.

Body Fat

This use case illustrates a supervised learning problem: the prediction of a continuous value, here the percentage of fat mass, according to the other parameters of the data set.

Heart Disease

This use case corresponds to a classification exercise. The goal is to predict a bimodal value, here the presence of cardiac disease in the patient, according to the other parameters entered in the dataset.
© Octopize 2021