The Experts below are selected from a list of 21810 Experts worldwide ranked by ideXlab platform
Jhing-fa Wang - One of the best experts on this subject based on the ideXlab platform.
-
Notice of Violation of IEEE Publication Principles: Acoustic and Phoneme Modeling Based on Confusion Matrix for Ubiquitous Mixed-Language Speech Recognition
2008 IEEE International Conference on Sensor Networks Ubiquitous and Trustworthy Computing (sutc 2008), 2008Co-Authors: Po-yi Shih, Jhing-fa WangAbstract:This work presents a novel approach to acoustic and phoneme modeling in order to recognize ubiquitous mixed-language speech. The conventional approaches to perform multilingual speech recognition are the usage of a multilingual phone set. A Confusion Matrix combining acoustic between every two phonetic is built for phonetic unit clustering. In this work, we are interested in speaker independent voice command recognition. The IPA representation is adapted for phonetic unit modeling. The EAT is applied to construct speaker independent acoustic models. The experimental results show that the proposed method can perform 70-80% lexicon recognition accuracy.
-
SUTC - Notice of Violation of IEEE Publication Principles Acoustic and Phoneme Modeling Based on Confusion Matrix for Ubiquitous Mixed-Language Speech Recognition
2008 IEEE International Conference on Sensor Networks Ubiquitous and Trustworthy Computing (sutc 2008), 2008Co-Authors: Po-yi Shih, Jhing-fa WangAbstract:This work presents a novel approach to acoustic and phoneme modeling in order to recognize ubiquitous mixed-language speech. The conventional approaches to perform multilingual speech recognition are the usage of a multilingual phone set. A Confusion Matrix combining acoustic between every two phonetic is built for phonetic unit clustering. In this work, we are interested in speaker independent voice command recognition. The IPA representation is adapted for phonetic unit modeling. The EAT is applied to construct speaker independent acoustic models. The experimental results show that the proposed method can perform 70-80% lexicon recognition accuracy.
David E Hornung - One of the best experts on this subject based on the ideXlab platform.
-
odorant Confusion Matrix the influence of patient history on patterns of odorant identification and misidentification in hyposmia
Physiology & Behavior, 2001Co-Authors: Daniel B Kurtz, David E Hornung, Theresa L White, Paul R Sheehe, Paul F KentAbstract:The odorant Confusion Matrix (OCM) is an odorant identification test in which the number of correct odorant identifications quantifies the level of olfactory function. As with other Confusion matrices, the OCM reflects distortions of sensory perception as errors in identification. Previous work with the OCM suggests that, within an individual, hyposmia is associated with a stable shift in odorant perception. The current study examined whether consistent shifts in odorant perception are also characteristic of the various pathologies that lead to an olfactory loss. In a retrospective study, OCM response patterns for 135 hyposmic patients were fit into a five-dimensional space in which the distances between subjects reflected the dissimilarities between their OCM response patterns. Multivariate regression was performed relating position in the five-dimensional space to each of 11 factors representing 33 demographic and medical history variables. One factor, named congestion (gathering the variables of past polyposis, current polyposis, and current nasal obstruction due to swelling), was significantly indicative of patterns of responses on the OCM, independent of the level of hyposmia. These data suggest that conductive olfactory loss may be associated with alterations in odorant perception, which are reflected in consistent odorant Confusions. Such alterations in perception may eventually serve as a basis for a clinical test to provide differential diagnoses as to the sources of olfactory losses.
-
a method for establishing a five odorant identification Confusion Matrix task in rats
Physiology & Behavior, 1990Co-Authors: Steven L Youngentob, Lisa M Markert, Maxwell M Mozell, David E HornungAbstract:Abstract Using a cross-modal association paradigm, rats were trained to associate a particular tunnel and response location with one of five different odorants (isoamyl acetate, propyl acetate, acetic acid, phenethyl alcohol, and anethole). Each of the five tunnels differed with respect to: 1) the illuminated pattern on the response key; 2) the brightness of the illuminated pattern; and 3) the somesthetic quality of the tunnel floor. Standard operant techniques were used to train trial initiating and sampling behavior at a central odorant presentation point. Following acquisition training, the animals were tested using a standard 5 × 5 Confusion Matrix design. The results showed for the first time that rats are capable of performing, with a high degree of accuracy, an odorant identification Confusion Matrix task analogous to humans. Furthermore, using multidimensional scaling techniques, these data represent the first instance in which the perceptual odor space of an animal can be determined. With the animal model in hand, we can begin to examine how, in the presence of neural dysfunction, one odorant may be incorrectly identified as another.
Andrew C Morris - One of the best experts on this subject based on the ideXlab platform.
-
INTERSPEECH - Confusion Matrix Based Entropy Correction in Multi-stream Combination
2020Co-Authors: Hemant Misra, Andrew C MorrisAbstract:An MLP classifier outputs a posterior probability for each class. With noisy data, classification becomes less certain, and the entropy of the posteriors distribution tends to increase providing a measure of classification confidence. However, at high noise levels, entropy can give a misleading indication of classification certainty. Very noisy data vectors may be classified systematically into classes which happen to be most noise-like and the resulting Confusion Matrix shows a dense column for each noise-like class. In this article we show how this pattern of misclassification in the Confusion Matrix can be used to derive a linear correction to the MLP posteriors estimate. We test the ability of this correction to reduce the problem of misleading confidence estimates and to enhance the performance of entropy based full-combination multi-stream approach. Better word-error-rates are achieved for Numbers95 database at different levels of added noise. The correction performs significantly better at high SNRs.
-
Confusion Matrix based entropy correction in multi stream combination
Conference of the International Speech Communication Association, 2003Co-Authors: Hemant Misra, Andrew C MorrisAbstract:An MLP classifier outputs a posterior probability for each class. With noisy data, classification becomes less certain, and the entropy of the posteriors distribution tends to increase providing a measure of classification confidence. However, at high noise levels, entropy can give a misleading indication of classification certainty. Very noisy data vectors may be classified systematically into classes which happen to be most noise-like and the resulting Confusion Matrix shows a dense column for each noise-like class. In this article we show how this pattern of misclassification in the Confusion Matrix can be used to derive a linear correction to the MLP posteriors estimate. We test the ability of this correction to reduce the problem of misleading confidence estimates and to enhance the performance of entropy based full-combination multi-stream approach. Better word-error-rates are achieved for Numbers95 database at different levels of added noise. The correction performs significantly better at high SNRs.
-
Confusion Matrix based posterior probabilities correction
2002Co-Authors: Andrew C Morris, Hemant MisraAbstract:An MLP classifier outputs a posterior probability for each class. With noisy data classification becomes less certain and the entropy of the posteriors distribution tends to increase, therefore providing a measure of classification confidence. However, at high noise levels entropy can give a misleading indication of classification certainty because very noisy data vectors may be classified systematically into whichever classes happen to be most noise-like. When this happens the resulting Confusion Matrix shows a dense column for each noise-like class. In this article we show how this pattern of misclassification in the Confusion Matrix can be used to derive a linear correction to the MLP posteriors estimate. We test the ability of this correction to reduce the problem of misleading confidence estimates and to increase the performance of individual MLP classifiers. Word and frame level classification results are compared with baseline results for the Numbers95 database of free format telephone numbers, in different levels of added noise.
B Nagarajan - One of the best experts on this subject based on the ideXlab platform.
-
An Optimized WebDocument Clustering UsingRecurrent Set IGA & Confusion Matrix For FactRetrieval
International Journal of Innovative Research in Computer and Communication Engineering, 2020Co-Authors: C. Josephine Christy, B NagarajanAbstract:Initially the first phase derives the Genetic Algorithm for global clustering process to resolve the optimization solution in both clustering and feature selection. The second phase follows a concept of Confusion Matrix for derivative works and improved GA is included for the final classification. The third phase presents the optimization technique to evaluate the cluster optimality for proficient document clustering based on the optimized conceptual feature words. Final phase introduce a join approach to cluster the web pages which primarily finds the recurrent sets and then clusters the documents. These recurrent sets are generated by using recurrent pattern expansion technique. Then by applying Fuzzy K-Means algorithm on Optimized Web document clustering using Recurrent Set founds clusters having documents which are extremely related and have related features. Experimental results show that our approach is more efficient then the above two join approach and can handle more efficiently in robust nature. Performance evaluation show benefits in terms of cluster optimality, true negative rate and information retrieval on real and UCI repository bag of words dataset.
-
an optimized webdocument clustering usingrecurrent set iga Confusion Matrix for factretrieval
International Journal of Innovative Research in Computer and Communication Engineering, 2013Co-Authors: Josephine C Christy, B NagarajanAbstract:Initially the first phase derives the Genetic Algorithm for global clustering process to resolve the optimization solution in both clustering and feature selection. The second phase follows a concept of Confusion Matrix for derivative works and improved GA is included for the final classification. The third phase presents the optimization technique to evaluate the cluster optimality for proficient document clustering based on the optimized conceptual feature words. Final phase introduce a join approach to cluster the web pages which primarily finds the recurrent sets and then clusters the documents. These recurrent sets are generated by using recurrent pattern expansion technique. Then by applying Fuzzy K-Means algorithm on Optimized Web document clustering using Recurrent Set founds clusters having documents which are extremely related and have related features. Experimental results show that our approach is more efficient then the above two join approach and can handle more efficiently in robust nature. Performance evaluation show benefits in terms of cluster optimality, true negative rate and information retrieval on real and UCI repository bag of words dataset.
Pawel Trajdos - One of the best experts on this subject based on the ideXlab platform.
-
IDEAL - An Extension of Multi-label Binary Relevance Models Based on Randomized Reference Classifier and Local Fuzzy Confusion Matrix
Intelligent Data Engineering and Automated Learning – IDEAL 2015, 2020Co-Authors: Pawel Trajdos, Marek KurzynskiAbstract:In this paper we addressed the issue of applying a stochastic classifier and a local, fuzzy Confusion Matrix under the framework of multi-label classification. We proposed a novel solution to the problem of correcting Binary Relevance ensembles. The main step of the correction procedure is to compute label-wise competence and cross-competence measures, which model error pattern of the underlying classifier. The method was evaluated using 20 benchmark datasets. In order to assess the efficiency of the introduced model, it was compared against 3 state-of-the-art approaches. The comparison was performed using 4 different evaluation measures. Although the introduced algorithm, as its base algorithm – Binary Relevance, is insensitive to dependencies between labels, the conducted experimental study reveals that the proposed algorithm outperform other methods in terms of Hamming-loss and False Discovery Rate.
-
bayes metaclassifier and soft Confusion Matrix classifier in the task of multi label classification
arXiv: Learning, 2019Co-Authors: Pawel Trajdos, Marcin MajakAbstract:The aim of this paper was to compare soft Confusion Matrix approach and Bayes metaclassifier under the multi-label classification framework. Although the methods were successfully applied under the multi-label classification framework, they have not been compared directly thus far. Such comparison is of vital importance because both methods are quite similar as they are both based on the concept of randomized reference classifier. Since both algorithms were designed to deal with single-label problems, they are combined with the problem-transformation approach to multi-label classification. Present study included 29 benchmark datasets and four different base classifiers. The algorithms were compared in terms of 11 quality criteria and the results were subjected to statistical analysis.
-
weighting scheme for a pairwise multi label classifier based on the fuzzy Confusion Matrix
Pattern Recognition Letters, 2018Co-Authors: Pawel Trajdos, Marek KurzynskiAbstract:Abstract In this work, we addressed the issue of improving the classification quality of label pairwise ensembles. Our goal is to improve the classification quality achieved by the ensemble via modification of the base classifiers that constitute the ensemble. To achieve this goal, a correction procedure that computes the measures of competence and cross-competence of a single classifier is proposed. These measures are used to modify the prediction of a base classifier. The measures are calculated using a dynamic Confusion Matrix. Additionally, we provide a weighting scheme that promotes the base classifiers that are the most susceptible to the correction based on the fuzzy Confusion Matrix. During the experimental study, the proposed approach was compared to two reference methods. The comparison was made in terms of eight different quality criteria. The result shows that the proposed method is able to improve classification quality when compared to baseline methods.
-
weighting scheme for a pairwise multi label classifier based on the fuzzy Confusion Matrix
arXiv: Learning, 2017Co-Authors: Pawel Trajdos, Marek KurzynskiAbstract:In this work we addressed the issue of applying a stochastic classifier and a local, fuzzy Confusion Matrix under the framework of multi-label classification. We proposed a novel solution to the problem of correcting label pairwise ensembles. The main step of the correction procedure is to compute classifier-specific competence and cross-competence measures, which estimates error pattern of the underlying classifier. At the fusion phase we employed two weighting approaches based on information theory. The classifier weights promote base classifiers which are the most susceptible to the correction based on the fuzzy Confusion Matrix. During the experimental study, the proposed approach was compared against two reference methods. The comparison was made in terms of six different quality criteria. The conducted experiments reveals that the proposed approach eliminates one of main drawbacks of the original FCM-based approach i.e. the original approach is vulnerable to the imbalanced class/label distribution. What is more, the obtained results shows that the introduced method achieves satisfying classification quality under all considered quality criteria. Additionally, the impact of fluctuations of data set characteristics is reduced.
-
an extension of multi label binary relevance models based on randomized reference classifier and local fuzzy Confusion Matrix
Intelligent Data Engineering and Automated Learning, 2015Co-Authors: Pawel Trajdos, Marek KurzynskiAbstract:In this paper we addressed the issue of applying a stochastic classifier and a local, fuzzy Confusion Matrix under the framework of multi-label classification. We proposed a novel solution to the problem of correcting Binary Relevance ensembles. The main step of the correction procedure is to compute label-wise competence and cross-competence measures, which model error pattern of the underlying classifier. The method was evaluated using 20 benchmark datasets. In order to assess the efficiency of the introduced model, it was compared against 3 state-of-the-art approaches. The comparison was performed using 4 different evaluation measures. Although the introduced algorithm, as its base algorithm – Binary Relevance, is insensitive to dependencies between labels, the conducted experimental study reveals that the proposed algorithm outperform other methods in terms of Hamming-loss and False Discovery Rate.