• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.365-368
• /
• 2005

We propose a speech act analysis method for Korean dialogue using Support Vector Machines (SVM). We use a lexical form of a word, its part of speech (POS) tags, and bigrams of POS tags as sentence features and the contexts of the previous utterance as context features. We select informative features by Chi square statistics. After training SVM with the selected features, SVM classifiers determine the speech act of each utterance. In experiment, we acquired overall $90.54\%$ of accuracy with dialogue corpus for hotel reservation domain.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.195-200
• /
• 2004

In this paper we propose effective speech recognizer through two recognition experiments. In general, SVM is classification method which classify two class set by finding voluntary nonlinear boundary in vector space and possesses high classification performance under few training data number. In this paper we compare recognition performance of HMM and SVM at training data number and investigate recognition performance of each feature parameter while changing feature space of MFCC using Independent Component Analysis(ICA) and Principal Component Analysis(PCA). As a result of experiment, recognition performance of SVM is better than 1:.um under few training data number, and feature parameter by ICA showed the highest recognition performance because of superior linear classification.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.102-108
• /
• 2011

Support vector machines are well known for their outstanding performance in pattern recognition fields. One example of their applications is music/speech classification for a standardized codec such as 3GPP2 selectable mode vocoder. In this paper, we propose a novel scheme that improves the speech/music classification of support vector machines based on the second-order conditional maximum a priori. While conventional support vector machine optimization techniques apply during training phase, the proposed technique can be adopted in classification phase. In this regard, the proposed approach can be developed and employed in parallel with conventional optimizations, resulting in synergistic boost in classification performance. According to experimental results, the proposed algorithm shows its compatibility and potential for improving the performance of support vector machines.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.315-319
• /
• 2006

Support vector machines in biped humanoid robot are presented in this paper. The trajectory of the ZMP in biped walking robot poses an important criterion for the balance of the walking robots but complex dynamics involved make robot control difficult. We are establishing empirical relationships based on the dynamic stability of motion using SVMs. SVMs and kernel method have become very popular method for learning from examples. We applied SVM to model the practical humanoid robot. Three kinds of kernels are employed also and each result has been compared. As a result, SVM based on kernel method have been found to work well. Especially SVM with RBF kernel function provides the best results. The simulation results show that the generated ZMP from the SVM can be improve the stability of the biped walking robot and it can be effectively used to model and control practical biped walking robot.

• Steel and Composite Structures
• /
• v.29 no.3
• /
• pp.309-318
• /
• 2018

Steel girders are the structural members often used for passing long spans. Mostly being subjected to patch loading, or concentrated loading, steel girders are likely to face sudden deformation or damage e.g., web breathing. Horizontal or vertical stiffeners are employed to overcome this phenomenon. This study aims at assessing the feasibility of a machine learning method, namely the support vector machines (SVM) in predicting the patch loading resistance of longitudinally stiffened webs. A database consisting of 162 test data is utilized to develop SVM models and the model with best performance is selected for further inspection. Existing formulations proposed by other researchers are also investigated for comparison. BS5400 and other existing models (model I, model II and model III) appear to yield underestimated predictions with a large scatter; i.e., mean experimental-to-predicted ratios of 1.517, 1.092, 1.155 and 1.256, respectively; whereas the selected SVM model has high prediction accuracy with significantly less scatter. Robust nature and accurate predictions of SVM confirms its feasibility of potential use in solving complex engineering problems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.2
• /
• pp.236-243
• /
• 2016

This paper presents a threat list acquisition method in an engagement area using the support vector machines (SVM). The proposed method consists of track creation, track estimation, track feature extraction, and threat list classification. To classify the threat track robustly, dynamic track estimation and pattern recognition algorithms are used. Dynamic tracks are estimated accurately by approximating a track movement using position, velocity and time. After track estimation, track features are extracted from the track information, and used to classify threat list. Experimental results showed that the threat list acquisition method in the engagement area achieved about 95 % accuracy rate for whole test tracks when using the SVM classifier. In case of improving the real-time process through further studies, it can be expected to apply the fire control systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1889-1893
• /
• 2008

This paper explores the classification performance of applying to support vector machines (SVMs) for the image classification problems. In this study, we extract the color, texture and shape features of natural images and compare the performance of image classification using each individual feature and integrated features. The experiment results show that classification accuracy on the basis of color feature is better than that based on texture and shape features and the results of the integrating features also provides a better and more robust performance than individual feature. In additions, we show that the proposed classifier of SVM based approach outperforms BPNN to corporate the image classification problems.

• East Asian mathematical journal
• /
• v.37 no.3
• /
• pp.333-354
• /
• 2021

A support vector machine (SVM) is a state-of-the-art machine learning model rooted in structural risk minimization. SVM is underestimated with regards to its application to real world problems because of the difficulties associated with its use. We aim at showing that the performance of SVM highly depends on which kernel function to use. To achieve these, after providing a summary of support vector machines and kernel function, we constructed experiments with various benchmark datasets to compare the performance of various kernel functions. For evaluating the performance of SVM, the F1-score and its Standard Deviation with 10-cross validation was used. Furthermore, we used taylor diagrams to reveal the difference between kernels. Finally, we provided Python codes for all our experiments to enable re-implementation of the experiments.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.167-175
• /
• 2006

Building accurate corporate bankruptcy prediction models has been one of the most important research issues in finance. Recently, support vector machines (SVMs) are popularly applied to bankruptcy prediction because of its many strong points. However, in order to use SVM, a modeler should determine several factors by heuristics, which hinders from obtaining accurate prediction results by using SVM. As a result, some researchers have tried to optimize these factors, especially the feature subset and kernel parameters of SVM But, there have been no studies that have attempted to determine appropriate instance subset of SVM, although it may improve the performance by eliminating distorted cases. Thus in the study, we propose the simultaneous optimization of the instance selection as well as the parameters of a kernel function of SVM by using genetic algorithms (GAs). Experimental results show that our model outperforms not only conventional SVM, but also prior approaches for optimizing SVM.

• Journal of Distribution Research
• /
• v.10 no.3
• /
• pp.1-14
• /
• 2005

It is important to control performance and a Sustainable Collaboration (SC) for the successful Supply Chain Management (SCM). This research developed a control model which analyzed SCM performances based on a Balanced Scorecard (ESC) and an SC using Support Vector Machine (SVM). 108 specialists of an SCM completed the questionnaires. We analyzed experimental data set using SVM. This research compared the forecasting accuracy of an SCMSC through four types of SVM kernels: (1) linear, (2) polynomial (3) Radial Basis Function (REF), and (4) sigmoid kernel (linear > RBF > Sigmoid > Polynomial). Then, this study compares the prediction performance of SVM linear kernel with Artificial Neural Network. (ANN). The research findings show that using SVM linear kernel to forecast an SCMSC is the most outstanding. Thus SVM linear kernel provides a promising alternative to an SC control level. A company which pursues an SCM can use the information of an SC in the SVM model.