• Journal of KIISE
• /
• v.42 no.2
• /
• pp.220-226
• /
• 2015

Semantic role labeling (SRL) systems determine the semantic role labels of the arguments of predicates in natural language text. An SRL system usually needs to perform four tasks in sequence: Predicate Identification (PI), Predicate Classification (PC), Argument Identification (AI), and Argument Classification (AC). In this paper, we use the Korean Propbank to develop our Korean semantic role labeling system. We describe our Korean semantic role labeling system that uses sequence labeling with structured Support Vector Machine (SVM). The results of our experiments on the Korean Propbank dataset reveal that our method obtains a 97.13% F1 score on Predicate Identification and Classification (PIC), and a 76.96% F1 score on Argument Identification and Classification (AIC).

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2020

Effective jamming in electronic warfare depends on proper jamming technique selection and jamming parameter estimation. For this purpose, this paper proposes a new method of estimating jamming parameters using Gaussian kernel function networks. In the proposed approach, a new method of determining the optimal structure and parameters of Gaussian kernel function networks is proposed. As a result, the proposed approach estimates the jamming parameters in a reliable manner and outperforms other methods such as the DNN(Deep Neural Network) and SVM(Support Vector Machine) estimation models.

• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.53-61
• /
• 2017

The preferred feature selection methods for text classification are filter-based. In a common filter-based feature selection scheme, unique scores are assigned to features; then, these features are sorted according to their scores. The last step is to add the top-N features to the feature set. In this paper, we propose an improved global feature selection scheme wherein its last step is modified to obtain a more representative feature set. The proposed method aims to improve the classification performance of global feature selection methods by creating a feature set representing all classes almost equally. For this purpose, a local feature selection method is used in the proposed method to label features according to their discriminative power on classes; these labels are used while producing the feature sets. Experimental results obtained using the well-known 20 Newsgroups and Reuters-21578 datasets with the k-nearest neighbor algorithm and a support vector machine indicate that the proposed method improves the classification performance in terms of a widely known metric ($F_1$).

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1977-1978
• /
• 2006

This paper discusses the method of vision based sensor fusion system for biped robot walking. Most researches on biped walking robot have mostly focused on walking algorithm itself. However, developing vision systems for biped walking robot is an important and urgent issue since biped walking robots are ultimately developed not only for researches but to be utilized in real life. In the research, systems for environment recognition and tele-operation have been developed for task assignment and execution of biped robot as well as for human robot interaction (HRI) system. For carrying out certain tasks, an object tracking system using modified optical flow algorithm and obstacle recognition system using enhanced template matching and hierarchical support vector machine algorithm by wireless vision camera are implemented with sensor fusion system using other sensors installed in a biped walking robot. Also systems for robot manipulating and communication with user have been developed for robot.

• Journal of Integrative Natural Science
• /
• v.4 no.3
• /
• pp.238-242
• /
• 2011

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. The system that uses the artificial neural network(ANN) falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the SVM/ANN hybrid algorithm is proposed in this paper. The proposed algorithm is the method that ANN learns selectively after clustering the SNR data by SVM, then more improved performance estimation can be obtained than using ANN only and The proposed algorithm can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure. Experimental results indicate that the proposed SVM/ANN hybrid algorithm generally outperforms ANN algorithm.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1038-1047
• /
• 2013

Augmented reality (AR) is currently being applied actively to commercial products, and various types of intelligent AR systems combining both the Global Positioning System and computer-vision technologies are being developed and commercialized. This paper suggests an in-vehicle head-up display (HUD) system that is combined with AR technology. The proposed system recognizes driving-safety information and offers it to the driver. Unlike existing HUD systems, the system displays information registered to the driver's view and is developed for the robust recognition of obstacles under bad weather conditions. The system is composed of four modules: a ground obstacle detection module, an object decision module, an object recognition module, and a display module. The recognition ratio of the driving-safety information obtained by the proposed AR-HUD system is about 73%, and the system has a recognition speed of about 15 fps for both vehicles and pedestrians.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.4
• /
• pp.364-371
• /
• 2013

Emotion Recognition is one of the important part to develop in human-human and human computer interaction. In this paper, we have focused on the performance of multi-class SVM (Support Vector Machine) with Gaussian RFB (Radial Basis function) kernel, which has been used to solve the problem of emotion recognition from physiological signals and to improve the accuracy of emotion recognition. The experimental paradigm for data acquisition, visual-stimuli of IAPS (International Affective Picture System) are used to induce emotional states, such as fear, disgust, joy, and neutral for each subject. The raw signals of acquisited data are splitted in the trial from each session to pre-process the data. The mean value and standard deviation are employed to extract the data for feature extraction and preparing in the next step of classification. The experimental results are proving that the proposed approach of multi-class SVM with Gaussian RBF kernel with OVO (One-Versus-One) method provided the successful performance, accuracies of classification, which has been performed over these four emotions.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.330-336
• /
• 2011

In this paper, we propose a new method to improve the performance of supervector linear kernel SVM (Support Vector Machine) for speaker identification. This method is based on splitting one training datum into several pieces of utterances. We use four different databases for evaluating performance and use PCA (Principal Component Analysis), GKPCA (Greedy Kernel PCA) and KMDA (Kernel Multimodal Discriminant Analysis) for feature enhancement. As a result, the proposed method shows improved performance for speaker identification using supervector linear kernel SVM.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.249-255
• /
• 2014

Recently, creation and sharing of information make progress actively through the SNS(Social Network Service) such as twitter, facebook and so on. It is necessary to extract the knowledge from aggregated information and data mining is one of the knowledge based approach. Especially, emotion analysis is a recent subdiscipline of text classification, which is concerned with massive collective intelligence from an opinion, policy, propensity and sentiment. In this paper, We propose the emotion prediction method, which extracts the significant key words and related key words from SNS paragraph, then predicts the emotion using these extracted emotion features.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.111-118
• /
• 2014

This paper presents an efficient Markov feature extraction method for detecting splicing forged images. The Markov states used in our method are composed of the difference between DCT coefficients in the adjacent blocks. Various first-order Markov state transition probabilities are extracted as features for splicing detection. In addition, we propose a feature reduction algorithm by analysing the distribution of the Markov probability. After training the extracted feature vectors using the SVM classifier, we determine whether the presence of the image splicing forgery. Experimental results verify that the proposed method shows good detection performance with a smaller number of features compared to existing methods.