Patents by Inventor Gabriele Alexe

Gabriele Alexe 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).

  • Method and system for robust classification strategy for cancer detection from mass spectrometry data
    Patent number: 8731839
    Abstract: A robust classification method for cancer detection from mass spectrometry data includes inputting the mass spectrometry data, preprocessing the spectrometry data, conducting robust feature selection, generating predictions for the test data sets using multiple data classifiers, the multiple data classifiers including artificial neural networks, support vector machines, weighted voting on data patterns, classification and regression trees, k-nearest neighbor classification, and logistic regression, and constructing and validating a meta-classifier by combining individual predictions of the multiple data classifiers to generate a robust prediction of a phenotype. The test data sets are used exclusively for validation of the meta-classifier.
    Type: Grant
    Filed: April 4, 2008
    Date of Patent: May 20, 2014
    Assignee: International Business Machines Corporation
    Inventors: Gyan Vatsaraja Bhanot, Gabriele Alexe, Arnold J. Levine, Babu Venkataraghavan
  • Method and system for robust classification strategy for cancer detection from mass spectrometry data
    Patent number: 7899625
    Abstract: A robust classification method for cancer detection from mass spectrometry data includes inputting the mass spectrometry data, preprocessing the spectrometry data, conducting robust feature selection, generating predictions for the test data sets using multiple data classifiers, the multiple data classifiers including artificial neural networks, support vector machines, weighted voting on data patterns, classification and regression trees, k-nearest neighbor classification, and logistic regression, and constructing and validating a meta-classifier by combining individual predictions of the multiple data classifiers to generate a robust prediction of a phenotype. The test data sets are used exclusively for validation of the meta-classifier.
    Type: Grant
    Filed: July 27, 2006
    Date of Patent: March 1, 2011
    Assignee: International Business Machines Corporation
    Inventors: Gyan Vatsaraja Bhanot, Gabriele Alexe, Arnold J. Levine, Babu Venkataraghavan
  • METHOD AND SYSTEM FOR ROBUST CLASSIFICATION STRATEGY FOR CANCER DETECTION FROM MASS SPECTROMETRY DATA
    Publication number: 20080187207
    Abstract: A robust classification method for cancer detection from mass spectrometry data includes inputting the mass spectrometry data, preprocessing the spectrometry data, conducting robust feature selection, generating predictions for the test data sets using multiple data classifiers, the multiple data classifiers including artificial neural networks, support vector machines, weighted voting on data patterns, classification and regression trees, k-nearest neighbor classification, and logistic regression, and constructing and validating a meta-classifier by combining individual predictions of the multiple data classifiers to generate a robust prediction of a phenotype. The test data sets are used exclusively for validation of the meta-classifier.
    Type: Application
    Filed: April 4, 2008
    Publication date: August 7, 2008
    Applicant: International Business Machines Corporation
    Inventors: Gyan Vatsaraja Bhanot, Gabriele Alexe, Arnold J. Levine, Badu Venkataraghavan
  • Method and system for robust classification strategy for cancer detection from mass spectrometry data
    Publication number: 20080025591
    Abstract: A robust classification method for cancer detection from mass spectrometry data includes inputting the mass spectrometry data, preprocessing the spectrometry data, conducting robust feature selection, generating predictions for the test data sets using multiple data classifiers, the multiple data classifiers including artificial neural networks, support vector machines, weighted voting on data patterns, classification and regression trees, k-nearest neighbor classification, and logistic regression, and constructing and validating a meta-classifier by combining individual predictions of the multiple data classifiers to generate a robust prediction of a phenotype. The test data sets are used exclusively for validation of the meta-classifier.
    Type: Application
    Filed: July 27, 2006
    Publication date: January 31, 2008
    Inventors: Gyan Vatsaraja Bhanot, Gabriele Alexe, Arnold J. Levine, Babu Venkataraghavan