The Experts below are selected from a list of 303 Experts worldwide ranked by ideXlab platform
Anton Bryl - One of the best experts on this subject based on the ideXlab platform.
-
CEAS - Evaluation of the Highest Probability SVM Nearest Neighbor Classifier with Variable Relative Error Cost
2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor (HP-SVM-NN) classifier, which combines the ideas of the SVM and k-NN classifiers, on the task of spam filtering, using the pure SVM classifier as a quality baseline. To classify a sample the HP-SVM-NN classifier does the following: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labeled samples, uses this model to classify the given sample, and transforms the output of SVM into posterior probabilities of the two classes using sigmoid approximation; than it selects that of the 2×N resulting answers which has the Highest Probability. The experimental evaluation shows, that in terms of ROC curves the algorithm is able to achieve higher accuracy than the pure SVM classifier.
-
evaluation of the Highest Probability svm nearest neighbor classifier with variable relative error cost
Conference on Email and Anti-Spam, 2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor (HP-SVM-NN) classifier, which combines the ideas of the SVM and k-NN classifiers, on the task of spam filtering, using the pure SVM classifier as a quality baseline. To classify a sample the HP-SVM-NN classifier does the following: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labeled samples, uses this model to classify the given sample, and transforms the output of SVM into posterior probabilities of the two classes using sigmoid approximation; than it selects that of the 2×N resulting answers which has the Highest Probability. The experimental evaluation shows, that in terms of ROC curves the algorithm is able to achieve higher accuracy than the pure SVM classifier.
-
Highest Probability SVM Nearest Neighbor Classifier for Spam Filtering
2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor classifier, which is a combination of the SVM and k-NN classifiers, on a corpus of email messages. To classify a sample the algorithm performs the following actions: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labelled samples, and uses this model to classify the given sample, then fits a sigmoid approximation of the probabilistic output for the SVM model, and computes the probabilities of the positive and the negative answers; than it selects that of the 2 × N resulting answers which has the Highest Probability. The experimental evaluation shows, that this algorithm is able to achieve higher accuracy than the pure SVM classifier at least in the case of equal error costs.
Enrico Blanzieri - One of the best experts on this subject based on the ideXlab platform.
-
CEAS - Evaluation of the Highest Probability SVM Nearest Neighbor Classifier with Variable Relative Error Cost
2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor (HP-SVM-NN) classifier, which combines the ideas of the SVM and k-NN classifiers, on the task of spam filtering, using the pure SVM classifier as a quality baseline. To classify a sample the HP-SVM-NN classifier does the following: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labeled samples, uses this model to classify the given sample, and transforms the output of SVM into posterior probabilities of the two classes using sigmoid approximation; than it selects that of the 2×N resulting answers which has the Highest Probability. The experimental evaluation shows, that in terms of ROC curves the algorithm is able to achieve higher accuracy than the pure SVM classifier.
-
evaluation of the Highest Probability svm nearest neighbor classifier with variable relative error cost
Conference on Email and Anti-Spam, 2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor (HP-SVM-NN) classifier, which combines the ideas of the SVM and k-NN classifiers, on the task of spam filtering, using the pure SVM classifier as a quality baseline. To classify a sample the HP-SVM-NN classifier does the following: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labeled samples, uses this model to classify the given sample, and transforms the output of SVM into posterior probabilities of the two classes using sigmoid approximation; than it selects that of the 2×N resulting answers which has the Highest Probability. The experimental evaluation shows, that in terms of ROC curves the algorithm is able to achieve higher accuracy than the pure SVM classifier.
-
Highest Probability SVM Nearest Neighbor Classifier for Spam Filtering
2007Co-Authors: Enrico Blanzieri, Anton BrylAbstract:In this paper we evaluate the performance of the Highest Probability SVM nearest neighbor classifier, which is a combination of the SVM and k-NN classifiers, on a corpus of email messages. To classify a sample the algorithm performs the following actions: for each k in a predefined set {k1, ..., kN} it trains an SVM model on k nearest labelled samples, and uses this model to classify the given sample, then fits a sigmoid approximation of the probabilistic output for the SVM model, and computes the probabilities of the positive and the negative answers; than it selects that of the 2 × N resulting answers which has the Highest Probability. The experimental evaluation shows, that this algorithm is able to achieve higher accuracy than the pure SVM classifier at least in the case of equal error costs.
André Monin - One of the best experts on this subject based on the ideXlab platform.
-
Modal Trajectory Estimation using Maximum Gaussian Mixture
IEEE Transactions on Automatic Control, 2013Co-Authors: André MoninAbstract:This paper deals with the estimation of the whole trajectory of a stochastic dynamic system with Highest Probability , conditionally upon the past observation process, using a maximum Gaussian mixture. We first recall the Gaussian sum technique applied to minimum variance filtering. It is then shown that the same concept of Gaussian mixture can be applied in that context, provided we replace the Sum operator by the Max operator.
-
Modal Trajectory Estimation Using Maximum Gaussian Mixture
IEEE Transactions on Automatic Control, 2013Co-Authors: André MoninAbstract:This technical note deals with the estimation of the whole trajectory of a stochastic dynamic system with Highest Probability, conditionally upon the past observation process, using a maximum Gaussian mixture. We first recall the Gaussian sum technique applied to minimum variance filtering. It is then shown that the same concept of Gaussian mixture can be applied in that context, provided we replace the Sum operator by the Max operator.
Taek Lyul Song - One of the best experts on this subject based on the ideXlab platform.
-
Highest Probability Data Association for Multi-Target Particle Filtering with Nonlinear Measurements
IEICE Transactions on Communications, 2013Co-Authors: Da Sol Kim, Taek Lyul Song, Darko MuŠickiAbstract:In this paper, we propose a new data association method termed the Highest Probability data association (HPDA) and apply it to real-time recursive nonlinear tracking in heavy clutter. The proposed method combines the probabilistic nearest neighbor (PNN) with a modified probabilistic strongest neighbor (PSN) approach. The modified PSN approach uses only the rank of the measurement amplitudes. This approach is robust as exact shape of amplitude Probability density function is not used. In this paper, the HPDA is combined with particle filtering for nonlinear target tracking in clutter. The measurement with the Highest measurement-to-track data association Probability is selected for track update. The HPDA provides the track quality information which can be used in for the false track termination and the true track confirmation. It can be easily extended to multi-target tracking with nonlinear particle filtering. The simulation studies demonstrate the HPDA functionality in a hostile environment with high clutter density and low target detection Probability.This work was supported by Defense Acquisition Program Administration and Agency for Defense Development under the contract UD100002KD
-
a study of automatic multi target detection and tracking algorithm using Highest Probability data association in a cluttered environment
The Transactions of the Korean Institute of Electrical Engineers, 2007Co-Authors: Dasoul Kim, Taek Lyul SongAbstract:In this paper, we present a new approach for automatic detection and tracking for multiple targets. We combine a Highest Probability data association(HPDA) algorithm for target detection with a particle filter for multiple target tracking. The proposed approach evaluates the probabilities of one-to-one assignments of measurement-to-track and the measurement with the Highest Probability is selected to be target- originated, and the measurement is used for probabilistic weight update of particle filtering. The performance of the proposed algorithm for target tracking in clutter is compared with the existing clustering algorithm and the sequential monte carlo method for Probability hypothesis density(SMC PHD) algorithm for multi-target detection and tracking. Computer simulation studies demonstrate that the HPDA algorithm is robust in performing automatic detection and tracking for multiple targets even though the environment is hostile in terms of high clutter density and low target detection Probability.
-
Highest Probability data association for active sonar tracking
International Conference on Information Fusion, 2006Co-Authors: Taek Lyul Song, Da Sol KimAbstract:We propose a new method of data association called Highest Probability data association (HPDA) combined with particle filtering and applied to active sonar tracking in clutter. The proposed HPDA method is a unification of probabilistic nearest neighbor and probabilistic strongest neighbor approaches. It evaluates the probabilities of one-to-one assignments of measurement-to-track. All of the measurements at the present sampling instance are lined up in the order of signal strength. The measurement with the Highest Probability is selected to be target-originated and the measurement is used for probabilistic weight update of particle filtering. The HPDA algorithm can be used in Automatic target detection for track confirmation and estimation of the number of the targets. The proposed HPDA algorithm is easily extended to multi-target tracking problems. It can be used to avoid track coalescence phenomenon that prevails when several tracks move very close.
-
FUSION - Highest Probability Data Association for Active Sonar Tracking
2006 9th International Conference on Information Fusion, 2006Co-Authors: Taek Lyul Song, Da Sol KimAbstract:We propose a new method of data association called Highest Probability data association (HPDA) combined with particle filtering and applied to active sonar tracking in clutter. The proposed HPDA method is a unification of probabilistic nearest neighbor and probabilistic strongest neighbor approaches. It evaluates the probabilities of one-to-one assignments of measurement-to-track. All of the measurements at the present sampling instance are lined up in the order of signal strength. The measurement with the Highest Probability is selected to be target-originated and the measurement is used for probabilistic weight update of particle filtering. The HPDA algorithm can be used in Automatic target detection for track confirmation and estimation of the number of the targets. The proposed HPDA algorithm is easily extended to multi-target tracking problems. It can be used to avoid track coalescence phenomenon that prevails when several tracks move very close.
-
Highest Probability data association and particle filtering for target tracking in clutter
ICMIT 2005: Information Systems and Signal Processing, 2005Co-Authors: Taek Lyul Song, Da Sol KimAbstract:There proposed a new method of data association called Highest Probability data association (HPDA) combined with particle filtering and applied to passive sonar tracking in clutter. The HPDA method evaluated the probabilities of one-to-one assignments of measurement-to-track. All of the bearing measurements at the present sampling instance were lined up in the order of signal strength. The measurement with the Highest Probability was selected to be target-originated and the measurement was used for probabilistic weight update of particle filtering. The proposed HPDA algorithm can be easily extended to multi-target tracking problems. It can be used to avoid track coalescence phenomenon that prevails when several tracks move very close together.
Ramón Artiaga - One of the best experts on this subject based on the ideXlab platform.
-
Functional nonparametric classification of wood species from thermal data
Journal of Thermal Analysis and Calorimetry, 2010Co-Authors: Javier Tarrío-saavedra, Salvador Naya, Mario Francisco-fernández, Jorge López-beceiro, Ramón ArtiagaAbstract:In this study, thermogravimetric (TG) and differential scanning calorimetry (DSC) curves, obtained by means of a simultaneous TG/DSC analyzer, and statistical functional nonparametric methods are used to classify different wood species. The temperature ranges, where the Highest Probability of correct classification is reached, are also computed. As each observation is a curve, a nonparametric functional discriminant technique based on the Bayes rule and the Nadaraya–Watson regression estimator is used. It assigns a future observation to the Highest Probability predefined class (supervised classification). The smoothing parameter needed in this nonparametric method is selected according to the cross-validation technique. The method proposed is applied to a sample of 49 wood items (7 per wood class) and also to classify between hardwoods and softwoods. In all the cases, the samples have been successfully classified, obtaining better results with the TG curves. The results are compared with those obtained with other nonparametric methods based on boosting algorithm. A discussion about the relation of the obtained results with the referenced wood component degradation temperature ranks is presented.
