Processing

Please wait...

Settings

Settings

Goto Application

1. WO2006094002 - HIERARCHICAL DETERMINATION OF FEATURE RELEVANCY FOR MIXED DATA TYPES

Publication Number WO/2006/094002
Publication Date 08.09.2006
International Application No. PCT/US2006/007158
International Filing Date 28.02.2006
IPC
G06K 9/62 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/623
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6228Selecting the most significant subset of features
623by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
G06K 9/6282
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6279relating to the number of classes
628Multiple classes
6281Piecewise classification, i.e. whereby each classification requires several discriminant rules
6282Tree-organised sequential classifiers
Applicants
  • COMPUTER ASSOCIATES THINK, INC. [US]/[US] (AE, AG, AL, AM, AT, AU, AZ, BA, BB, BE, BF, BG, BJ, BR, BW, BY, BZ, CA, CF, CG, CH, CI, CM, CN, CO, CR, CU, CY, CZ, DE, DK, DM, DZ, EC, EE, EG, ES, FI, FR, GA, GB, GD, GE, GH, GM, GN, GQ, GR, GW, HR, HU, ID, IE, IL, IN, IS, IT, JP, KE, KG, KM, KN, KP, KR, KZ, LC, LK, LR, LS, LT, LU, LV, LY, MA, MC, MD, MG, MK, ML, MN, MR, MW, MX, MZ, NA, NE, NG, NI, NL, NO, NZ, OM, PG, PH, PL, PT, RO, RU, SC, SD, SE, SG, SI, SK, SL, SM, SN, SY, SZ, TD, TG, TJ, TM, TN, TR, TT, TZ, UA, UG, UZ, VC, VN, YU, ZA, ZM, ZW)
  • DUAN, Baofu [CN]/[US] (UsOnly)
  • MENG, Zhuo [CN]/[US] (UsOnly)
  • PAO, Yoh-Han [US]/[US] (UsOnly)
Inventors
  • DUAN, Baofu
  • MENG, Zhuo
  • PAO, Yoh-Han
Agents
  • PEDERSEN, Luke, K.
Priority Data
11/068,18528.02.2005US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) HIERARCHICAL DETERMINATION OF FEATURE RELEVANCY FOR MIXED DATA TYPES
(FR) DETERMINATION HIERARCHIQUE DE LA PERTINENCE DE CARACTERISTIQUES POUR DES TYPES DE DONNEES MIXTES
Abstract
(EN)
A method for feature selection based on hierarchical local-region analysis of feature characteristics in a data set of mixed data type is provided. A data space associated with a mixed- type data set is partitioned into a hierarchy of plural local regions. A relationship metric (for example, a similarity correlation metric) is used to evaluate for each local region a relationship measure between input features and a target. One or more relevant features is identified, by using the relationship measure for each local region.
(FR)
L'invention concerne un procédé de sélection de caractéristiques basé sur l'analyse hiérarchique de régions locales des caractéristiques d'un ensemble de données du type mixte. Le procédé comporte les étapes consistant à: découper un espace de données associé à un ensemble de données du type mixte en une hiérarchie de plusieurs régions locales; utiliser une mesure de relation (par exemple, mesure de corrélation de similitudes) pour évaluer, pour chaque région locale, une mesure de relation entre les caractéristiques d'entrée et une cible; identifier une ou plusieurs caractéristiques pertinentes à l'aide de la mesure de relation, pour chaque région locale.
Also published as
EP6736469
Latest bibliographic data on file with the International Bureau