• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.163-170
• /
• 2011

This study proposed the composition of a new long-code MMSE detector using the pilot channel that demonstrated the most excellent performance under Rayleigh fading in the previous studies. It analyzed and explained how to maintain the stability of the weight vector(introduction to the course of radio waves) in the receiver. In the operation of the receiver system to remove radio interference, the signal vector distortion received in the channel where fading was present achieved good results by compensating for signal errors. When there was distortion, the response characteristics of the received signals were superior to the common matching filter according to the computer simulation. The long-code MMSE receiver proposed in the study was able to prolong the cycle by $16{\times}T_b$ in the fading environment to fulfill the satisfaction.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2595-2597
• /
• 2002

오늘날 많은 디지털 저장 매체의 발달로 방대한 양의 영상 데이터가 데이터베이스화 되고 있으며 이러한 데이터베이스에서 필요한 영상 데이터론 효율적으로 검색하는 방범이 중요한 문제로 대두되고 있다. 현재 영상의 색상, 형태 및 질감 특성을 사용하여 다양한 영상 검색 방법이 제안되고 있으며 본 연구에선 이중 질감을 특징으로 하는 Gator 특징 벡터를 사용하고자 한다. 즉, 영상의 인터레스트 포인트를 찾아내어 그 점에서 Gabor 웨이블릿을 이용하여 특징 벡터를 추출하고 VQ를 기반으로 한 히스토그램 인터섹션 방법을 이용하여 영상 검색을 한다. 기존의 Gator 웨이블릿 방법은 영상의 회전에 대해 잘 동작하지 못하는 단점을 가지고 있으며 이는 회전 영상에 대한 검색율 저하에 크게 작용한다. 이 문제를 해결하고자 본 논문에선 회전 불변 Gabor 필터를 이용한 영상 검색 방법을 제안하고자 한다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.6
• /
• pp.59-70
• /
• 2002

This paper proposes a position and speed sensorless vector control for Synchronous Reluctance Motor(SynRM) operating at optimum efficiency and high response, in which core loss is taken into account, and discusses the performance of system. The proposed control scheme is based on the flux estimation combined stator voltage and current. In this paper, current angle condition of efficiency optimization which minimizes the copper and iron losses is derived based on the equivalent circuit model of the SynRM. The research result of closed loop position and speed control with efficiency optimization control is given to verify the proposed scheme.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.8
• /
• pp.1376-1385
• /
• 2000

The phase characteristic of delay line in feedfarward linearizer has been changed due to variation of operating temperature. In this paper, design method of fixed phase control circuit of group delay line using adaptive vector control is derived. To maintain transfer characteristics of nominal operating temperature, the error correlated signals, which are changed adaptively due to changing of temperature, are added to main signals. The proposed method maintains transfer characteristics under 0.06dB of insertion loss and 0.36$^{\circ}$ of phase variation in case of 1-tone(880 MHz) and under 0.07 dB of insertion loss and 0.35$^{\circ}$ of phase variation in case of 2-tones(877 MHz, 882 MHz) for 10dB input power dynamic range and +/-10$^{\circ}$ phase variation respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1207-1212
• /
• 2011

This paper presents a study on the DSP(Digital Signal Processor) controller for the PBW(power-by-wire) system using BLDC(Brushless Direct Current) servo motor pump. The PBW hydraulic actuator was realized with hydraulic pump driven by BLDC servo motor, hydraulic cylinder and controller. This PBW system needs speed control of servo motor for linear thrust action of hydraulic cylinder. This paper implements a servo controller with vector control algorithm and MIN-MAX PWM technique. As CPU of a controller, TMS320F2812 DSP was adopted because it has PWM waveform generator, A/D converter, SPI(Serial Peripheral Interface) port and many input/output port etc.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1092-1099
• /
• 2006

Displayed system equationally using accurate dynamic modeling of whole system including induction motor and load to analyze induction motor to normal condiction's action characteristic as well as transient characteristic using power converter device such as inverter in this paper. Also, presume adhesive power calculation through speed sensorless vector control and load torque disturbance observer for maximum tractive force control. Confirmed proposed algorithm through simulation and an experiment using railroad experiment equipment to embody control algorithm of such system. With relation of adhesive power about the wage speed by speed addition and subtraction of railway vehicle, embodied all sorts item by experiment equipment.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.7
• /
• pp.17-24
• /
• 2009

Increasing use of information system has led to larger amount of developing expenses and demands on software. Until recent days, the model using regression analysis based on statistical algorithm has been used. However, Machine learning is more investigated now. This paper estimates the software cost using SVR(Support Vector Regression). a sort of machine learning technique. Also, it finds the best set of parameters applying immune algorithm. In this paper, software cost estimation is performed by SVR based on immune algorithm while changing populations, memory cells, and number of allele. Finally, this paper analyzes and compares the result with existing other machine learning methods.

• The Korean Journal of Applied Statistics
• /
• v.37 no.5
• /
• pp.643-661
• /
• 2024

This study investigates the effectiveness of 3D skeleton data for human action recognition by comparing the classification performance of machine learning and deep learning models. We use the subset of the NTU RGB+D dataset, containing only frontal-view recordings of 40 individuals performing 60 different actions. Our study uses linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) as machine learning models, while the deep learning models are hierarchical bidirectional RNN (HBRNN) and semantics-guided neural network (SGN). To evaluate model performance, cross-subject cross-validation is conducted. Our analysis demonstrates that action type significantly impacts model performance. Cluster analysis by action category shows no significant difference in classification performance between machine learning and deep learning models for easily recognizable actions. However, for actions requiring precise differentiation based on frontal-view joint coordinates such as 'clapping' or 'rubbing hands', deep learning models show a higher performance in capturing subtle joint movements compared to machine learning models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2252-2258
• /
• 2013

In this paper, parallel orthogonal matching pursuit (POMP) is proposed to supplement the simultaneous orthogonal matching pursuit (S-OMP) which has been widely used as a greedy algorithm for sparse signal recovery for multiple measurement vector (MMV) problem. The process of POMP is simple but effective: (1) multiple indexes maximally correlated with the observation vector are chosen at the first iteration, (2) the conventional S-OMP process is carried out in parallel for each selected index, (3) the index set which yields the minimum residual is selected for reconstructing the original sparse signal. Empirical simulations show that POMP for MMV outperforms than the conventional S-OMP both in terms of exact recovery ratio (ERR) and mean-squared error (MSE).