• MALSORI
• /
• no.49
• /
• pp.145-158
• /
• 2004

This paper is aiming at implementation of real-time speaker verification system using DSP board. Dialog/4, which is based on microprocessor and DSP processor, is selected to easily control telephone signals and to process audio/voice signals. Speaker verification system performs signal processing and feature extraction after receiving voice and its ID. Then through computing the likelihood ratio of claimed speaker model to the background model, it makes real-time decision on acceptance or rejection. For the verification experiments, total 15 speaker models and 6 background models are adopted. The experimental results show that verification accuracy rates are 99.5% for using telephone speech-based speaker models.

• MALSORI
• /
• no.49
• /
• pp.159-174
• /
• 2004

The development of the durational component of prosody modelling was overviewed and discussed in text-to-speech conversion of spoken English and Korean, showing the strengths and weaknesses of each approach. The possibility of integrating linguistic feature effects into the duration modelling of TTS systems was also investigated. This paper claims that current approaches to language timing synthesis still require an understanding of how segmental duration is affected by context. Three modelling approaches were discussed: sequential rule systems, Classification and Regression Tree (CART) models and Sums-of-Products (SoP) models. The CART and SoP models show good performance results in predicting segment duration in English, while it is not the case in the SoP modelling of spoken Korean.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2036-2039
• /
• 2003

This paper focuses on the study of the robustness of face authentication methods under illumination changes. Four different face authentication methods are tried. These methods are as follows; Principal Component Analysis, Gaussian Mixture Models, 1-Dimensional Hidden Markov Models, 2-Dimensional Hidden Markov Models. Experiment results involving an artificial illumination change to face images are compared with each others. Face feature vector extraction method based on the 2-Dimensional Discrete Cosine Transform is used. Experiments to evaluate the above four different face authentication methods are carried out on the Olivetti Research Laboratory(ORL) face database. For the pseudo 2D HMM, the best EER (Equal Error Rate) performance is observed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.3 s.246
• /
• pp.219-230
• /
• 2006

Digital CAD models are one of the most important assets the manufacturer holds. The trend toward concurrent engineering and outsourcing in the distributed development and manufacturing environment has elevated the importance of high quality CAD model and its efficient exchange. But designers have spent a great deal of their time repairing CAD model errors. Most of those poor quality models may be due to designer errors caused by poor or incorrect CAD data generation practices. In this paper, we propose a rule-based approach for healing CAD model errors. The proposed approach focuses on the design history data representation from a commercial CAD model, and the procedural method for building knowledge base to heal CAD model. Through the use of rule-based approach, a CAD model healing system can be implemented, and experiments are carried out on automobile part models.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.20 no.2
• /
• pp.123-135
• /
• 2016

This article deals with the pricing of Asian options under a constant elasticity of variance (CEV) model as well as a stochastic elasticity of variance (SEV) model. The CEV and SEV models are underlying asset price models proposed to overcome shortcomings of the constant volatility model. In particular, the SEV model is attractive because it can characterize the feature of volatility in risky situation such as the global financial crisis both quantitatively and qualitatively. We use an asymptotic expansion method to approximate the no-arbitrage price of an arithmetic average Asian option under both CEV and SEV models. Subsequently, the zero and non-zero constant leverage effects as well as stochastic leverage effects are compared with each other. Lastly, we investigate the SEV correction effects to the CEV model for the price of Asian options.

• Communications for Statistical Applications and Methods
• /
• v.22 no.5
• /
• pp.415-434
• /
• 2015

In this paper we overview the literature on common features analysis of economic time series. Starting from the seminal contributions by Engle and Kozicki (1993) and Vahid and Engle (1993), we present and discuss the various notions that have been proposed to detect and model common cyclical features in macroeconometrics. In particular, we analyze in details the link between common cyclical features and the reduced-rank regression model. We also illustrate similarities and differences between the common features methodology and other popular types of multivariate time series modelling. Finally, we discuss some recent developments in this area, such as the implications of common features for univariate time series models and the analysis of common autocorrelation in medium-large dimensional systems.

• Korean Journal of Remote Sensing
• /
• v.23 no.3
• /
• pp.199-209
• /
• 2007

Traditionally, aerial images have been used as main sources for compiling topographic maps. In recent years, lidar data has been exploited as another type of mapping data. Regarding their performances, aerial imagery has the ability to delineate object boundaries but omits much of these boundaries during feature extraction. Lidar provides direct information about heights of object surfaces but have limitations with respect to boundary localization. Considering the characteristics of the sensors, this paper proposes an approach to extracting buildings from lidar and aerial imagery, which is based on the complementary characteristics of optical and range sensors. For detecting building regions, relationships among elevation contours are represented into directional graphs and searched for the contours corresponding to external boundaries of buildings. For generating building models, a wing model is proposed to assemble roof surface patches into a complete building model. Then, building models are projected and checked with features in aerial images. Experimental results show that the proposed approach provides an efficient and accurate way to extract building models.

• Smart Structures and Systems
• /
• v.23 no.4
• /
• pp.393-403
• /
• 2019

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.75-88
• /
• 2021

Automobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.