The Experts below are selected from a list of 6675 Experts worldwide ranked by ideXlab platform

Carlos A Escobar - One of the best experts on this subject based on the ideXlab platform.

  • process monitoring for quality a Model Selection Criterion for shallow neural networks
    Proceedings of the Annual Conference of the PHM Society, 2019
    Co-Authors: Carlos A Escobar, Ruben Moralesmenendez
    Abstract:

    Since most manufacturing systems generate only a fewdefects per million of opportunities, rare quality eventdetection is one of the main applications of process monitoringfor quality. Single-hidden-layer feed-forwardneural networks have been successfully applied to performthis task. However, since the best network structureis not known in advance, many Models need to be learnedand tested to select a final Model with the right numberof hidden neurons. A new three-dimension 3D

  • Process-Monitoring-for- Quality — A Model Selection Criterion for Shallow Neural Networks
    2019
    Co-Authors: Carlos A Escobar, Ruben Morales-menendez
    Abstract:

    Since most manufacturing systems generate only a fewdefects per million of opportunities, rare quality eventdetection is one of the main applications of process monitoringfor quality. Single-hidden-layer feed-forwardneural networks have been successfully applied to performthis task. However, since the best network structureis not known in advance, many Models need to be learnedand tested to select a final Model with the right numberof hidden neurons. A new three-dimension 3D

  • Process-monitoring-for-quality—A robust Model Selection Criterion for the logistic regression algorithm
    Manufacturing letters, 2019
    Co-Authors: Carlos A Escobar, Ruben Morales-menendez
    Abstract:

    Abstract Process Monitoring for Quality is a big data-driven quality philosophy aimed at defect detection through binary classification. The l 1 -regularized Logistic Regression learning algorithm has been successfully applied in manufacturing systems for rare quality event detection. Since the optimal value of the regularization parameter is not known in advance, many Models should be created and tested to find the final Model to be deployed at the plant. In this context, Model Selection becomes a critical step in the process of developing a manufacturing functional Model. Since most mature organizations generate only a few Defects Per Million of Opportunities, a three-dimensional Model Selection Criterion ( 3 D - LR ) was initially introduced aimed at analyzing highly/ultra unbalanced binary data structures. The 3 D - LR Criterion combines three of the most important attributes – prediction, separability, complexity – of each candidate Model and map them into a three dimensional space to select the best one. In this letter, the 3 D - LR is improved; the fit attribute is replaced by a novel separability index that takes into consideration the classification threshold to reward for robustness of predictions. Updated Criterion, 3 D - LRI , is an improved version of the initial concept.

  • process monitoring for quality a Model Selection Criterion for genetic programming
    International Conference on Evolutionary Multi-criterion Optimization, 2019
    Co-Authors: Carlos A Escobar, Diana M Wegner, Abhinav Gaur, Ruben Moralesmenendez
    Abstract:

    Process Monitoring for Quality is a manufacturing quality philosophy aimed at defect detection through binary classification that is founded on big data and big Models. Genetic Programming (GP) algorithms have been successfully applied by following the big Models learning paradigm for rare quality event detection (classification). Since it is a bias-free technique unmarred by human preconceptions, it can potentially generate better solutions (Models) compared with the best human efforts. However, since GP uses random search methods based on Darwinian philosophy of “survival of the fittest”, hundreds, or even thousands of Models need to be created to find a good solution. In this context, Model Selection becomes a critical step in the process of finding the final Model to be deployed at the plant. A three-objective optimization Model Selection Criterion (\(3D-GP\)) is introduced for analyzing highly/ultra unbalanced data structures. It uses three competing attributes – prediction, separability, complexity – to project candidate Models into a three-dimensional space to select the final Model that solves the posed tradeoff between them the best.

  • EMO - Process-Monitoring-for-Quality—A Model Selection Criterion for Genetic Programming
    Lecture Notes in Computer Science, 2019
    Co-Authors: Carlos A Escobar, Diana M Wegner, Abhinav Gaur, Ruben Morales-menendez
    Abstract:

    Process Monitoring for Quality is a manufacturing quality philosophy aimed at defect detection through binary classification that is founded on big data and big Models. Genetic Programming (GP) algorithms have been successfully applied by following the big Models learning paradigm for rare quality event detection (classification). Since it is a bias-free technique unmarred by human preconceptions, it can potentially generate better solutions (Models) compared with the best human efforts. However, since GP uses random search methods based on Darwinian philosophy of “survival of the fittest”, hundreds, or even thousands of Models need to be created to find a good solution. In this context, Model Selection becomes a critical step in the process of finding the final Model to be deployed at the plant. A three-objective optimization Model Selection Criterion (\(3D-GP\)) is introduced for analyzing highly/ultra unbalanced data structures. It uses three competing attributes – prediction, separability, complexity – to project candidate Models into a three-dimensional space to select the final Model that solves the posed tradeoff between them the best.

Abd‐krim Seghouane - One of the best experts on this subject based on the ideXlab platform.

  • a small sample Model Selection Criterion based on kullback s symmetric divergence
    IEEE Transactions on Signal Processing, 2004
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection. KIC serves as an asymptotically unbiased estimator of a variant (within a constant) of the Kullback symmetric divergence, known also as J-divergence between the generating Model and the fitted candidate Model. In this paper, a bias correction to KIC is derived for linear regression Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is a moderate to large fraction of the sample size. For linear regression Models, the corrected Criterion, called KICc is an exactly unbiased estimator of the variant of the Kullback symmetric divergence, assuming that the true Model is correctly specified or overfitted. Furthermore, when applied to polynomial regression and autoregressive time-series Modeling, KICc is found to estimate the Model order more accurately than any other asymptotically efficient method. Finally, KICc is tested on real data to forecast foreign currency exchange rate; the result is very interesting in comparison to classical techniques.

  • A linear vector Model Selection Criterion based on Kullback’s‐Leibler divergence
    AIP Conference Proceedings, 2004
    Co-Authors: Abd‐krim Seghouane
    Abstract:

    The Kullback Information Criterion, KIC and its univariate bias‐corrected version, KICc are two recently developed criteria for Model Selection. The two criteria may be viewed as estimators of the expected Kullback symmetric divergence and have a fixed bias corrected term. In this paper, a small sample Model Selection Criterion for selecting linear vector Models is proposed. This Criterion adjusts the Kullback Information Criterion, KIC, to be an exact unbiased estimator for a variant (within a constant) of the expected Kullback symmetric divergence. The proposed Criterion is named KICvc, where the notation “vc” stands for vector correction. Simulation results shows that the proposed Criterion estimates the Model order more accurately than any other asymptotically efficient method when applied to linear vector Model Selection in small samples. As a result, KICvc serves as an effective tool for selecting a linear vector Model of appropriate order. A theoretical justification of the proposed Criterion is pr...

  • a small sample Model Selection Criterion based on kullback s symmetric divergence
    International Conference on Acoustics Speech and Signal Processing, 2003
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara, Gilles Fleury
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection (Cavanaugh, J.E., Statistics and Probability Letters, vol.42, p.333-43, 1999). KIC serves as an asymptotically unbiased estimator of a variant of the Kullback symmetric divergence, known also as J-divergence. A bias correction of the Kullback symmetric information Criterion is derived for linear Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is of a moderate to large fraction of the sample size. For linear regression Models, the corrected method, called KICc, is an exactly unbiased estimator of a variant of the Kullback symmetric divergence between the true unknown Model and the candidate fitted Model. Furthermore, KICc is found to provide better Model order choice than any other asymptotically efficient methods when applied to autoregressive time series Models.

  • ICASSP (6) - A small sample Model Selection Criterion based on Kullback's symmetric divergence
    2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003. Proceedings. (ICASSP '03)., 2003
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara, Gilles Fleury
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection (Cavanaugh, J.E., Statistics and Probability Letters, vol.42, p.333-43, 1999). KIC serves as an asymptotically unbiased estimator of a variant of the Kullback symmetric divergence, known also as J-divergence. A bias correction of the Kullback symmetric information Criterion is derived for linear Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is of a moderate to large fraction of the sample size. For linear regression Models, the corrected method, called KICc, is an exactly unbiased estimator of a variant of the Kullback symmetric divergence between the true unknown Model and the candidate fitted Model. Furthermore, KICc is found to provide better Model order choice than any other asymptotically efficient methods when applied to autoregressive time series Models.

  • a bootstrap Model Selection Criterion based on kullback s symmetric divergence
    IEEE Signal Processing Workshop on Statistical Signal Processing, 2003
    Co-Authors: Abd‐krim Seghouane, L De Lathauwer
    Abstract:

    Following in the recent work of J. Cavanaugh (1999) and A.K. Seghouane (2002), a new corrected variant of KIC develop for the purpose of sources separation is proposed in this paper. The variant utilizes bootstrapping to provide an estimate of the expected Kullback-Leibler symmetric divergence between the Model generating the data and a fitted approximating Model. Simulation results that illustrate the performance of the new proposed Criterion for the detection of the number of signals received by a sensor array are presented. As a result, the KIC variant serves as an effective tool for estimating the number of sources compared to other well known criteria.

Maiza Bekara - One of the best experts on this subject based on the ideXlab platform.

  • a small sample Model Selection Criterion based on kullback s symmetric divergence
    IEEE Transactions on Signal Processing, 2004
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection. KIC serves as an asymptotically unbiased estimator of a variant (within a constant) of the Kullback symmetric divergence, known also as J-divergence between the generating Model and the fitted candidate Model. In this paper, a bias correction to KIC is derived for linear regression Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is a moderate to large fraction of the sample size. For linear regression Models, the corrected Criterion, called KICc is an exactly unbiased estimator of the variant of the Kullback symmetric divergence, assuming that the true Model is correctly specified or overfitted. Furthermore, when applied to polynomial regression and autoregressive time-series Modeling, KICc is found to estimate the Model order more accurately than any other asymptotically efficient method. Finally, KICc is tested on real data to forecast foreign currency exchange rate; the result is very interesting in comparison to classical techniques.

  • a small sample Model Selection Criterion based on kullback s symmetric divergence
    International Conference on Acoustics Speech and Signal Processing, 2003
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara, Gilles Fleury
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection (Cavanaugh, J.E., Statistics and Probability Letters, vol.42, p.333-43, 1999). KIC serves as an asymptotically unbiased estimator of a variant of the Kullback symmetric divergence, known also as J-divergence. A bias correction of the Kullback symmetric information Criterion is derived for linear Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is of a moderate to large fraction of the sample size. For linear regression Models, the corrected method, called KICc, is an exactly unbiased estimator of a variant of the Kullback symmetric divergence between the true unknown Model and the candidate fitted Model. Furthermore, KICc is found to provide better Model order choice than any other asymptotically efficient methods when applied to autoregressive time series Models.

  • ICASSP (6) - A small sample Model Selection Criterion based on Kullback's symmetric divergence
    2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003. Proceedings. (ICASSP '03)., 2003
    Co-Authors: Abd‐krim Seghouane, Maiza Bekara, Gilles Fleury
    Abstract:

    The Kullback information Criterion (KIC) is a recently developed tool for statistical Model Selection (Cavanaugh, J.E., Statistics and Probability Letters, vol.42, p.333-43, 1999). KIC serves as an asymptotically unbiased estimator of a variant of the Kullback symmetric divergence, known also as J-divergence. A bias correction of the Kullback symmetric information Criterion is derived for linear Models. The correction is of particular use when the sample size is small or when the number of fitted parameters is of a moderate to large fraction of the sample size. For linear regression Models, the corrected method, called KICc, is an exactly unbiased estimator of a variant of the Kullback symmetric divergence between the true unknown Model and the candidate fitted Model. Furthermore, KICc is found to provide better Model order choice than any other asymptotically efficient methods when applied to autoregressive time series Models.

A Biem - One of the best experts on this subject based on the ideXlab platform.

  • a Model Selection Criterion for classification application to hmm topology optimization
    International Conference on Document Analysis and Recognition, 2003
    Co-Authors: A Biem
    Abstract:

    This paper proposes a Model Selection Criterion for classification problems. The Criterion focuses on selecting Models that are discriminant instead of Models based on the Occam's razor principle of parsimony between accurate Modeling and complexity. The Criterion, dubbed discriminative information Criterion (DIC), is applied to the optimization of hidden Markov Model topology aimed at the recognition of cursively-handwritten digits. The results show that DIC-generated Models achieve 18% relative improvement in performance from a baseline system generated by the Bayesian information Criterion (BIC).

  • ICDAR - A Model Selection Criterion for classification: application to HMM topology optimization
    Seventh International Conference on Document Analysis and Recognition 2003. Proceedings., 2003
    Co-Authors: A Biem
    Abstract:

    This paper proposes a Model Selection Criterion for classification problems. The Criterion focuses on selecting Models that are discriminant instead of Models based on the Occam's razor principle of parsimony between accurate Modeling and complexity. The Criterion, dubbed discriminative information Criterion (DIC), is applied to the optimization of hidden Markov Model topology aimed at the recognition of cursively-handwritten digits. The results show that DIC-generated Models achieve 18% relative improvement in performance from a baseline system generated by the Bayesian information Criterion (BIC).

  • a bayesian Model Selection Criterion for hmm topology optimization
    International Conference on Acoustics Speech and Signal Processing, 2002
    Co-Authors: A Biem, Jin-young Ha, Jayashree Subrahmonia
    Abstract:

    This paper addresses the problem of estimating the optimal Hidden Markov Model (HMM) topology. The optimal topology is defined as the one that gives the smallest error-rate with the minimal number of parameters. The paper introduces a Bayesian Model Selection Criterion that is suitable for Continuous Hidden Markov Models topology optimization. The Criterion is derived from the Laplacian approximation of the posterior of a Model structure, and shares the algorithmic simplicity of conventional Bayesian Selection criteria, such as Schwarz's Bayesian Information Criterion (BIC). Unlike, BIC, which uses a multivariate Normal distribution assumption for the prior of all parameters of the Model, the proposed HMM-oriented Bayesian Information Criterion (HBIC), Models each parameter by a different distribution, one more appropriate for that parameter The results on an handwriting recognition task shows that the HBIC realizes a much smaller and efficient system than a system generated through the BIC.

  • ICASSP - A Bayesian Model Selection Criterion for HMM topology optimization
    IEEE International Conference on Acoustics Speech and Signal Processing, 2002
    Co-Authors: A Biem, Jin-young Ha, Jayashree Subrahmonia
    Abstract:

    This paper addresses the problem of estimating the optimal Hidden Markov Model (HMM) topology. The optimal topology is defined as the one that gives the smallest error-rate with the minimal number of parameters. The paper introduces a Bayesian Model Selection Criterion that is suitable for Continuous Hidden Markov Models topology optimization. The Criterion is derived from the Laplacian approximation of the posterior of a Model structure, and shares the algorithmic simplicity of conventional Bayesian Selection criteria, such as Schwarz's Bayesian Information Criterion (BIC). Unlike, BIC, which uses a multivariate Normal distribution assumption for the prior of all parameters of the Model, the proposed HMM-oriented Bayesian Information Criterion (HBIC), Models each parameter by a different distribution, one more appropriate for that parameter The results on an handwriting recognition task shows that the HBIC realizes a much smaller and efficient system than a system generated through the BIC.

Amaury Lendasse - One of the best experts on this subject based on the ideXlab platform.

  • a faster Model Selection Criterion for op elm and op knn hannan quinn Criterion
    The European Symposium on Artificial Neural Networks, 2009
    Co-Authors: Yoan Miche, Amaury Lendasse
    Abstract:

    The Optimally Pruned Extreme Learning Machine (OP- ELM) and Optimally Pruned K-Nearest Neighbors (OP-KNN) algorithms use the a similar methodology based on random initialization (OP-ELM) or KNN initialization (OP-KNN) of a Feedforward Neural Network fol- lowed by ranking of the neurons; ranking is used to determine the best combination to retain. This is achieved by Leave-One-Out (LOO) cross- validation. In this article is proposed to use the Hannan-Quinn (HQ) Criterion as a Model Selection Criterion, instead of LOO. It proved to be efficient and as good as the LOO one for both OP-ELM and OP-KNN, while decreasing computations by factors of four to five for OP-ELM and up to 24 for OP-KNN.

  • ESANN - A faster Model Selection Criterion for OP-ELM and OP-KNN: Hannan-Quinn Criterion
    2009
    Co-Authors: Yoan Miche, Amaury Lendasse
    Abstract:

    The Optimally Pruned Extreme Learning Machine (OP- ELM) and Optimally Pruned K-Nearest Neighbors (OP-KNN) algorithms use the a similar methodology based on random initialization (OP-ELM) or KNN initialization (OP-KNN) of a Feedforward Neural Network fol- lowed by ranking of the neurons; ranking is used to determine the best combination to retain. This is achieved by Leave-One-Out (LOO) cross- validation. In this article is proposed to use the Hannan-Quinn (HQ) Criterion as a Model Selection Criterion, instead of LOO. It proved to be efficient and as good as the LOO one for both OP-ELM and OP-KNN, while decreasing computations by factors of four to five for OP-ELM and up to 24 for OP-KNN.