Wyniki wyszukiwania - Biblioteka Nauki

1

Using the one-versus-rest strategy with samples balancing to improve pairwise coupling classification

100%

Chmielnicki W. , Stąpor K.

|

tom Vol. 26, no. 1

191--201

EN

The simplest classification task is to divide a set of objects into two classes, but most of the problems we find in real life applications are multi-class. There are many methods of decomposing such a task into a set of smaller classification problems involving two classes only. Among the methods, pairwise coupling proposed by Hastie and Tibshirani (1998) is one of the best known. Its principle is to separate each pair of classes ignoring the remaining ones. Then all objects are tested against these classifiers and a voting scheme is applied using pairwise class probability estimates in a joint probability estimate for all classes. A closer look at the pairwise strategy shows the problem which impacts the final result. Each binary classifier votes for each object even if it does not belong to one of the two classes which it is trained on. This problem is addressed in our strategy. We propose to use additional classifiers to select the objects which will be considered by the pairwise classifiers. A similar solution was proposed by Moreira and Mayoraz (1998), but they use classifiers which are biased according to imbalance in the number of samples representing classes.

2

Improving the accuracy of detecting steroid abuse in cattle by pairwise learning of serum samples

100%

Xia X. L.

|

2017

|

tom Vol. 37, no. 3

510--519

EN

Issues surrounding the misuse of illegal drugs in animals destined for food production have be an enormous challenge to regulatory authorities charged with enforcing their control. A method has been proposed recently which compared the bovine blood biochemistry profiles between control and treated animals, using the support vector machine (SVM) as the classification tool. Whether an animal has been treated is determined by the classification outcome of the SVM on an individual serum sample taken off the animal. However, the acquisition time of the serum sample is essential in the classification performance of the SVM. Thus, the paper proposed to collect and analyze a pair of samples, in order to obtain at least one sample whose acquisition time resulted in an SVM with the highest sensitivity. The power of the strategy in improving sensitivity was theoretically proven to be up to 0.25 and empirically confirmed on a bovine blood biochemistry data. Furthermore, classification rules of the SVM were proposed to be adapted to meet higher levels of demands on sensitivity. Schemes were described which optimized the time apart between the collection of the two samples and the impact of the proposed strategy on specificity was also investigated.

3

Klasyfikacja tekstur za pomocą SVM - Maszyny Wektorów Wspierających

84%

Goszczyński J.

Inżynieria Rolnicza

|

2006

|

tom R. 10, nr 13(88)

119-126

PL

Motywacją do badań był pomysł wytworzenia robota-kosiarki wyposażonego w system komputerowego widzenia. Rozpoznawanie obrazu może zostać zrealizowane za pomocą klasyfikacji tekstur obiektów, które otaczają robota. Artykuł przedstawia przykład klasyfikacji tekstur za pomocą Maszyny wektorów wspierających SVM (ang. Support Vector Machine) Do badań wykorzystano oprogramowanie LIBSVM.

EN

Motivation for research was idea to create mower robot with computer vision system. Image recognition can be done by textures classification of objects that robot is surrounded. This article has reviewed example of texture classification by SVM Support vector machine. For research was used LIBSVM software.

4

Automatic parametric fault detection in complex analog systems based on a method of minimum node selection

84%

Bilski A. , Wojciechowski J.

|

2016

|

tom Vol. 26, no. 3

655--668

EN

The aim of this paper is to introduce a strategy to find a minimal set of test nodes for diagnostics of complex analog systems with single parametric faults using the support vector machine (SVM) classifier as a fault locator. The results of diagnostics of a video amplifier and a low-pass filter using tabu search along with genetic algorithms (GAs) as node selectors in conjunction with the SVM fault classifier are presented. General principles of the diagnostic procedure are first introduced, and then the proposed approach is discussed in detail. Diagnostic results confirm the usefulness of the method and its computational requirements. Conclusions on its wider applicability are provided as well.

5

Comparison of speaker dependent and speaker independent emotion recognition

84%

Rybka J. , Janicki A.

|

2013

|

tom Vol. 23, no. 4

797--808

EN

This paper describes a study of emotion recognition based on speech analysis. The introduction to the theory contains a review of emotion inventories used in various studies of emotion recognition as well as the speech corpora applied, methods of speech parametrization, and the most commonly employed classification algorithms. In the current study the EMO-DB speech corpus and three selected classifiers, the k-Nearest Neighbor (k-NN), the Artificial Neural Network (ANN) and Support Vector Machines (SVMs), were used in experiments. SVMs turned out to provide the best classification accuracy of 75.44% in the speaker dependent mode, that is, when speech samples from the same speaker were included in the training corpus. Various speaker dependent and speaker independent configurations were analyzed and compared. Emotion recognition in speaker dependent conditions usually yielded higher accuracy results than a similar but speaker independent configuration. The improvement was especially well observed if the base recognition ratio of a given speaker was low. Happiness and anger, as well as boredom and neutrality, proved to be the pairs of emotions most often confused.

6

Classification of speech intelligibility in Parkinson's disease

84%

Khan T. , Westin J. , Dougherty M.

|

2014

|

tom Vol. 34, no. 1

35--45

EN

A problem in the clinical assessment of running speech in Parkinson's disease (PD) is to track underlying deficits in a number of speech components including respiration, phonation, articulation and prosody, each of which disturbs the speech intelligibility. A set of 13 features, including the cepstral separation difference and Mel-frequency cepstral coefficients were computed to represent deficits in each individual speech component. These features were then used in training a support vector machine (SVM) using n-fold cross validation. The dataset used for method development and evaluation consisted of 240 running speech samples recorded from 60 PD patients and 20 healthy controls. These speech samples were clinically rated using the Unified Parkinson's Disease Rating Scale Motor Examination of Speech (UPDRS-S). The classification accuracy of SVM was 85% in 3 levels of UPDRS-S scale and 92% in 2 levels with the average area under the ROC (receiver operating characteristic) curves of around 91%. The strong classification ability of selected features and the SVM model supports suitability of this scheme to monitor speech symptoms in PD.

7

Lung cancer detection using an integration of fuzzy K-Means clustering and deep learning techniques for CT lung images

84%

Prasad J. M. N. , Chakravarty S. , Krishna M. V.

|

tom Vol. 70, nr 3

art. no. e139006

EN

Computer aided detection systems are used for the provision of second opinion during lung cancer diagnosis. For early-stage detection and treatment false positive reduction stage also plays a vital role. The main motive of this research is to propose a method for lung cancer segmentation. In recent years, lung cancer detection and segmentation of tumors is considered one of the most important steps in the surgical planning and medication preparations. It is very difficult for the researchers to detect the tumor area from the CT (computed tomography) images. The proposed system segments lungs and classify the images into normal and abnormal and consists of two phases, The first phase will be made up of various stages like pre-processing, feature extraction, feature selection, classification and finally, segmentation of the tumor. Input CT image is sent through the pre-processing phase where noise removal will be taken care of and then texture features are extracted from the pre-processed image, and in the next stage features will be selected by making use of crow search optimization algorithm, later artificial neural network is used for the classification of the normal lung images from abnormal images. Finally, abnormal images will be processed through the fuzzy K-means algorithm for segmenting the tumors separately. In the second phase, SVM classifier is used for the reduction of false positives. The proposed system delivers accuracy of 96%, 100% specificity and sensitivity of 99% and it reduces false positives. Experimental results shows that the system outperforms many other systems in the literature in terms of sensitivity, specificity, and accuracy. There is a great tradeoff between effectiveness and efficiency and the proposed system also saves computation time. The work shows that the proposed system which is formed by the integration of fuzzy K-means clustering and deep learning technique is simple yet powerful and was effective in reducing false positives and segments tumors and perform classification and delivers better performance when compared to other strategies in the literature, and this system is giving accurate decision when compared to human doctor’s decision.