Patents by Inventor Janna SAARELA

Janna SAARELA has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Compatible anonymization of data sets of different sources
    Patent number: 11972023
    Abstract: Creating compatible anonymized data sets by performing with machine learning equipment that operates a machine learning model by defining data types of variables of a data set; identifying quasi-identifiers for the data set; defining reidentification sensitivity of all or any targeted subset of the individual variables and quasi-identifiers; defining missing data handling rules for the individual variables; defining allowed data transformations including generalization and use of synthesized data; optimizing quasi-identifier selection, use of synthesized data and a choice of data transformations to minimize information loss and maximize privacy metrics based on the data set; the allowed data transformations; and the missing data handling rules; training the machine learning model using the data set according to the defined data types; the optimized quasi-identifier selection; the optimized use of synthesized data; and the choice of data transformations; and anonymizing the data set using the training of the m
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: April 30, 2024
    Assignee: University of Helsinki
    Inventors: Timo A. Miettinen, Janna Saarela, Teemu J. Perheentupa, Robert Mills, Mehreen Ali, Tuomo Pentikäinen
  • COMPATIBLE ANONYMIZATION OF DATA SETS OF DIFFERENT SOURCES
    Publication number: 20220237323
    Abstract: Creating compatible anonymized data sets by performing with machine learning equipment that operates a machine learning model by defining data types of variables of a data set; identifying quasi-identifiers for the data set; defining reidentification sensitivity of all or any targeted subset of the individual variables and quasi-identifiers; defining missing data handling rules for the individual variables; defining allowed data transformations including generalization and use of synthesized data; optimizing quasi-identifier selection, use of synthesized data and a choice of data transformations to minimize information loss and maximize privacy metrics based on the data set; the allowed data transformations; and the missing data handling rules; training the machine learning model using the data set according to the defined data types; the optimized quasi-identifier selection; the optimized use of synthesized data; and the choice of data transformations; and anonymizing the data set using the training of the m
    Type: Application
    Filed: May 20, 2020
    Publication date: July 28, 2022
    Applicant: University of Helsinki
    Inventors: Timo A. MIETTINEN, Janna SAARELA, Teemu J. PERHEENTUPA, Robert MILLS, Mehreen ALI, Tuomo PENTIKÄINEN