• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.85-94
• /
• 2017

Conventional speaker verification systems using time delay neural network, identity vector and probabilistic linear discriminant analysis (TDNN-Ivector-PLDA) are known to be very effective for verifying long-duration speech utterances. However, when test utterances are of short duration, duration mismatch between enrollment and test utterances significantly degrades the performance of TDNN-Ivector-PLDA systems. To compensate for the I-vector mismatch between long and short utterances, this paper proposes to use probabilistic linear discriminant analysis (PLDA) model adaptation with augmented data. A PLDA model is trained on vast amount of speech data, most of which have long duration. Then, the PLDA model is adapted with the I-vectors obtained from short-utterance data which are augmented by using vocal tract length perturbation (VTLP). In computer experiments using the NIST SRE 2008 database, the proposed method is shown to achieve significantly better performance than the conventional TDNN-Ivector-PLDA systems when there exists duration mismatch between enrollment and test utterances.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.55 no.7
• /
• pp.306-312
• /
• 2006

Support Vector Machine(SVM), of which the foundations have been developed by Vapnik (1995), is gaining popularity thanks to many attractive features and promising empirical performance. In this paper, we propose a new short-term load forecasting technique based on SVM. We discuss the input vector selection of SVM for load forecasting and analyze the prediction performance for various SVM parameters such as kernel function, cost coefficient C, and $\varepsilon$ (the width of 8 $\varepsilon-tube$). The computer simulation shows that the prediction performance of the proposed method is superior to that of the conventional neural networks.

• Journal of Korean Port Research
• /
• v.12 no.2
• /
• pp.291-302
• /
• 1998

A digital image processing technique which is able to be used for getting the velocity vector distribution of a surface of the spilt oil in the ocean without contacting the flow itself. This technique is based upon the PIV(Particle Imaging Velocimetry) technique and its system mainly consists of a high sensitive camera, a CCD camera, an image grabber, and a host computer in which an image processing algorithm is adopted for velocity vector acquisition. For the acquisition of the advective velocity vector of floating matters on the ocean, a new multi-frame tracking algorithm is proposed, and for the acquisition of the diffusion velocity vector distribution of the spilt oil onto the water surface, a high sensitive gray-level cross-correlation algorithm is proposed.

• Proceedings of the KIPE Conference
• /
• 2002.11a
• /
• pp.21-24
• /
• 2002

The vector control system of an induction motor is the high performance drive system to achieve the instantaneous torque control. The vector control system is greatly divided into the direct control, and the indirect control that the most widely is used, The indirect vector control needs the rotor time constant, which changes widely according to the temperature, frequency, and current amplitude. The incorrect time constant leads to the saturation of magnetic flux or under-excitation phenomena. As a result, that deteriorate the control performance. Therefore, in this paper, the effect of time constant variation is investigated and its on-line tuning algorithm is proposed. The time constant using the torque angles was calculated and that of the validity of algorithm proposed was proved through the computer simulation and the experiment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.12
• /
• pp.1732-1739
• /
• 2017

This paper presents a sensorless vector control algorithm of closed loop Gopinath flux observer to enhance the robustness at low speed by switching P/PI mode. Closed loop Gopinath flux observer has the problem in sensorless vector control of induction motor at low speed. This paper solves the problem using the characteristic function of closed loop Gopinath flux observer. P mode shows better performance than PI mode under the cut-off frequency of observer. But P mode always has a flux error due to DC offset, so this paper combines P mode and PI mode. This algorithm shows good performance over wide speed range. The performance has been confirmed through computer simulations using MATLAB SIMULINK and experiments.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.7
• /
• pp.1204-1210
• /
• 2016

The phase currents must be accurately measured to achieve the instantaneous torque control of AC motors. In general, those are measured using the current sensors. However, the measured current signals can include the offset errors and scaling errors by several components such as current sensors, analog amplifiers, noise filter circuits, and analog-to-digital converters. Therefore, the torque-controlled performance can be deteriorated by the current measurement errors. In this paper we have analyzed the influence caused by vector control of 2-phase induction motor when two errors are included in measured phase currents. Based on analyzed results, the compensation method is proposed without additional hardware. The proposed compensation method was applied vector-controlled inverter for 2-phase induction motor of 360[W] class and verified through computer simulations and experiments.

• Proceedings of the KIEE Conference
• /
• 1998.11a
• /
• pp.171-175
• /
• 1998

This paper proposes a speed sensorless vector control of induction motor using a minimum-order EKF(extended kalman filter). Minimum-order EKF has the advantage of reducing the computational estimation cost because the stator current is not estimated. EKF does not deteriorate the performance of the overall speed control system, even though the measurements are relatively noisy. The estimated rotor speed is used for vector control and overall speed control. Computer simulations of the speed sensorless vector control are carried out to test the usefulness of the minimum-order EKF algorithm.

• Communications for Statistical Applications and Methods
• /
• v.15 no.3
• /
• pp.441-450
• /
• 2008

In this paper we propose a new method for solving multiclass problem with least squares support vector machine(LS-SVM) regression. This method implements one-against-all scheme which is as accurate as any other approach. We also propose cross validation(CV) method to select effectively the optimal values of hyper-parameters which affect the performance of the proposed multiclass method. Experimental results are then presented which indicate the performance of the proposed multiclass method.

• International Journal of Contents
• /
• v.1 no.2
• /
• pp.26-30
• /
• 2005

According to the fast growth of information on the Internet, it is becoming increasingly difficult to find and organize useful information. To reduce information overload, it needs to exploit automatic text classification for handling enormous documents. Support Vector Machine (SVM) is a model that is calculated as a weighted sum of kernel function outputs. This paper describes a document classifier for web documents in the fields of Information Technology and uses SVM to learn a model, which is constructed from the training sets and its representative terms. The basic idea is to exploit the representative terms meaning distribution in coherent thematic texts of each category by simple statistics methods. Vector-space model is applied to represent documents in the categories by using feature selection scheme based on TFiDF. We apply a category factor which represents effects in category of any term to the feature selection. Experiments show the results of categorization and the correlation of vector length.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.652-654
• /
• 2015

최근 ICT융합 기술의 비약적인 발전에 따라 소형 휴대가 가능한 다양한 종류의 생체신호 측정센서의 출현으로 유헬스케어 관련 기술이 비약적으로 발전하게 되면서, 실시간으로 발생하는 생체데이터에 대한 효율적인 처리가 중요하게 되었다. 따라서 본 논문에서는 M2M기반에서 발생되는 생체데이터의 효율적인 전송을 위해 LZW(Lempel-Ziv-Welch) 압축 알고리즘과, BitVector압축 알고리즘을 결합한 LZW-BitVector 압축 알고리즘을 제안한다.