Recognition algorithms based on computation of estimates

Zhuravlev, Yu. I.; Nikiforov, V. V.

doi:10.1007/bf01070446

Cited by 23 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, the results of different algorithms for solving same tasks are very different. The rows of tables presents the results of recognition of different algorithms: LM -"linear machine" [9], k -neighbors -"k-nearest neighbors" [9], AEC -"estimation calculation algorithms" [7], LDF -"Fisher linear discriminator" [9], LR -"voting algorithm over sets of logical regularities of classes [10].…”

Section: The Results Of Numerical Experimentsmentioning

confidence: 99%

“…Comparison takes place on different subsets of features in the maximum feature subspace whereȳ andx λ have no gaps. This expresses the fact of existance of dependencies between features (see [7]). …”

Section: Resultsmentioning

confidence: 99%

“…For simplicity, we further denoteȳ =x i ,ȳ = (y 1 , y 2 , ..., y n ), The general algorithm consists in solving of [log 2 N ] + 1 dichotomous recognition tasks. It was used the estimation calculation algorithm, based on voting over support sets of a given power [7]. This algorithm reflects the correlation properties between features and doesn't use any training.…”

Section: Restoration Of Feature Values As the Solution Of Recognitionmentioning

confidence: 99%

“…The task of restoring the value x ij is considered to be resolved. Otherwise, the transition at point 1 and process is repeated with respect to the set a 1 < a 2 < ... < a [ To calculate estimates for the classes one can use other ways of calculating estimates [7].…”

Section: Restoration Of Feature Values As the Solution Of Recognitionmentioning

confidence: 99%

See 3 more Smart Citations

Some Imputation Algorithms for Restoration of Missing Data

Ryazanov

2011

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. The problem of reconstructing the feature values in samples of objects given in terms of numerical features is considered. The three approaches, not involving the use of probability models and a priori information, are considered. The first approach is based on the organization of the iterative procedure for successive elaboration of missing values of attributes. In this case, the analysis of local information for each object with missing data is fulfilled. The second approach is based on solving an optimization problem. We calculate such previously unknown feature values for which there is maximum correspondence of metric relations between objects in subspaces of known partial values and found full descriptions. The third approach is based on solving a series of recognition tasks for each missing value. Comparisons of these approaches on simulated and real problems are presented.

show abstract

Section: The Results Of Numerical Experimentsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Restoration Of Feature Values As the Solution Of Recognitionmentioning

confidence: 99%

Section: Restoration Of Feature Values As the Solution Of Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Some Imputation Algorithms for Restoration of Missing Data

Ryazanov

2011

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…I. Zhuravlev and his school [3][4][5]. This class of algorithms is based on the heuristic precedence principle (one can act in a similar way in similar situations).…”

Section: Introductionmentioning

confidence: 99%

An approach to solving classification problems under incomplete information

Babak

Tatarinov

2005

Cybern Syst Anal

View full text Add to dashboard Cite

show abstract

Selecting Objects for ALVOT

Medina‐Pérez

García-Borroto

Villuendas-Rey

et al. 2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

ALVOT is a model of supervised classification based on partial precedences. In this paper a new object selection method based on a voting procedure for ALVOT is proposed. The method was developed for dealing with databases having objects described by features that are not exclusively numeric or categorical. A comparative numerical experiment was performed with different algorithms of object selection. The experimental results show a good performance of the proposed method with respect to the other algorithms.

show abstract

Recognition algorithms based on computation of estimates

Cited by 23 publications

References 0 publications

Some Imputation Algorithms for Restoration of Missing Data

Some Imputation Algorithms for Restoration of Missing Data

An approach to solving classification problems under incomplete information

Selecting Objects for ALVOT

Contact Info

Product

Resources

About