Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 4

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
w słowach kluczowych:  support vectors machine
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22% ± 0.01 accuracy on the MEEI database and 94.7% ± 0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.
Content available remote Performance of the Support Vector Machines for medical classification problems
In the Support Vector Machines classification technique the best possible discriminating hyperplane between two populations is looked for by maximizing of margin between the populations' closest points. This idea is also applied for obtaining nonlinear discriminant boundaries by using different kernels for transformations, thus obtaining a nonlinear Support Vector Machines method. The nonlinear Support Vector Machines method is based on pre-processing of data to represent patterns in high dimension- usually much higher than the original variable feature space. In the presented work the dependency of Support Vector Machines performance on the kind of kernel and Support Vector Machines parameters is presented. The performance was assessed by resubstitution, 10- fold cross-validation, leave-one-out error, learning curves and Receiver Operating Characteristic curves. The kind and shape of the kernel is more important than regularization constant allowing different levels of overlapping classes. Combining boosting and Support Vector Machines did not improved performance in comparison to Support Vector Machines method alone, because both Support Vector Machines procedure and boosting are focused on observations difficult to classify.
Content available remote Ocena rzeczywistej wydajności wybranych regresorów
Poniższa praca porusza temat nieparametrycznej estymacji funkcji regresji oraz jej efektywności czasowej. Autorzy porównują dokładność regresji, ale i czas potrzebny na wyznaczenie wartości dla obiektu testowego. Czas ten uwzględnia nie tylko samo wyznaczanie wartości, ale i etap tworzenia regresora. Eksperymenty zostały przeprowadzone na wielowymiarowych danych rzeczywistych.
This paper raises a problem of nonparametric estimation of the regression function and its time efficiency. Authors compare the regression accuracy but considers also the time that is needed to evaluate the value for the test object. That time takes into consideration the evaluation time, but also the time of regressor creating. Experiments were conducted with the usage of multidimensional real data.
Content available remote Application of SVM in computer aided gastric diagnostic system
In the paper computer aided stomach diagnosis problems are presented. The subject of the study is electrical signal generated by human stomach and called electrogastrographic (EGG) signal. The non-invasively measured signals were subjected to parametrization, which was performed with one of the time series modelling methods, with linear autoregressive models (AR). Then the obtained sets of numbers were classified with the Support Vector Machine (SVM), which is a relatively new pattern recognition technique and is based on the idea of structural risk minimization, The structure and parameters of algorithm used for classification of the parameterized EGG data are described. The finally obtained effectiveness of the whole system (SVM with the parametrization method applied), amounting to 81%, is promising and, according to the authors' analysis can be improved. The ways of improving of the effectiveness are also outlined in the conclusions.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.