Patents by Inventor Andrzej Toroj

Andrzej Toroj 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).

  • Patent number: 8200454
    Abstract: Method, apparatus, and system, including computer program products, implementing and using techniques for time series analysis, wherein the time series exhibit trend and/or seasonality. Model parameters of the time series data are determined by selecting and/or suggesting a most appropriate combination of trend and seasonality of the time series data based on analysis of variances of transformed time series data.
    Type: Grant
    Filed: May 13, 2008
    Date of Patent: June 12, 2012
    Assignee: International Business Machines Corporation
    Inventors: Ansgar Dorneich, Maik Goergens, Andrzej Toroj
  • Patent number: 8055465
    Abstract: Method, apparatus, and system, including computer program products, implementing and using techniques for determining a periodic cycle of time series data. A frequency spectrum of the data is provided. The frequency spectrum is processed using at least one of the following steps, resulting in a processed frequency spectrum: filtering the frequency spectrum for reducing noise of the data, truncating the frequency spectrum at low frequencies, and weighting high frequency contributions over low frequency contributions of the frequency spectrum. A periodic cycle is extracted based on the processed frequency spectrum.
    Type: Grant
    Filed: May 13, 2008
    Date of Patent: November 8, 2011
    Assignee: International Business Machines Corporation
    Inventors: Ansgar Dorneich, Maik Goergens, Andrzej Toroj
  • Publication number: 20090018798
    Abstract: Method, apparatus, and system, including computer program products, implementing and using techniques for time series analysis, wherein the time series exhibit trend and/or seasonality. Model parameters of the time series data are determined by selecting and/or suggesting a most appropriate combination of trend and seasonality of the time series data based on analysis of variances of transformed time series data.
    Type: Application
    Filed: May 13, 2008
    Publication date: January 15, 2009
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ansgar Dorneich, Maik Goergens, Andrzej Toroj
  • Publication number: 20090017758
    Abstract: Method, apparatus, and system, including computer program products, implementing and using techniques for determining a periodic cycle of time series data. A frequency spectrum of the data is provided. The frequency spectrum is processed using at least one of the following steps, resulting in a processed frequency spectrum: filtering the frequency spectrum for reducing noise of the data, truncating the frequency spectrum at low frequencies, and weighting high frequency contributions over low frequency contributions of the frequency spectrum. A periodic cycle is extracted based on the processed frequency spectrum.
    Type: Application
    Filed: May 13, 2008
    Publication date: January 15, 2009
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Ansgar Dorneich, Maik Goergens, Andrzej Toroj