• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.447-450
• /
• 2004

This paper proposes remotely sensed image classification method by fuzzy c-means clustering algorithm using average intra-cluster distance. The average intra-cluster distance acquires an average of the vector set belong to each cluster and proportionates to its size and density. We perform classification according to pixel's membership grade by cluster center of fuzzy c-means clustering using the mean-values of training data about each class. Fuzzy c-means algorithm considered membership degree for inter-cluster of each class. And then, we validate degree of overlap between clusters. A pixel which has a high degree of overlap applies to the maximum likelihood classification method. Finally, we decide category by comparing with fuzzy membership degree and likelihood rate. The proposed method is applied to IKONOS remote sensing satellite image for the verifying test.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.68-80
• /
• 1996

In this paper, we propose a novel color image segmentation algorithm based on clustering in 3-dimensional color space employing the mathematical morphology. More specifically, since we take into account the topological properties such as the shape, connectivity and distribution of clusters in the clustering process, the number of clusters in the color cube, as well as their centers, can be easily obtained, without a priori knowledge on the input images. Intensive computer simulation has been performed and the results are discussed in this paper. The resutls of the simulation on the images in various color coordinates show that the segmentation is independent of the choice of color coordinates and the shape of clustes. Segmentation results of the vector quantizer are also presented for the comparison purpose.

• Journal of electromagnetic engineering and science
• /
• v.17 no.1
• /
• pp.39-43
• /
• 2017

In this paper, a systematic and statistical calibration technique was implemented to calibrate a high-speed signal converting system containing multiple digital-to-analog converters (DACs). The systematic error (especially the imbalance between DACs) in the current combining network of the multi-DAC system was modeled and corrected by calculating the path coefficients for individual DACs with wideband reference signals. Furthermore, by applying a Kalman filter to suppress noise from quantization and clock jitter, accurate coefficients with minimum noise were identified. For correcting an arbitrary waveform generator with two DACs, a co-simulation platform was implemented to estimate the system degradation and its corrected performance. Simulation results showed that after correction with 4.8 Gbps QAM signal, the signal-to-noise-ratio improved by approximately 4.5 dB and the error-vector-magnitude improved from 4.1% to 1.12% over 0.96 GHz bandwidth.

• Proceedings of the Korea Database Society Conference
• /
• 1995.12a
• /
• pp.173-176
• /
• 1995

본 논문에서 다루는 내용은 멀티미디어 정보처리시 이용되는 여러 신호 처리용 하드웨어에서 필요로 하는 벡터 트랜스퍼메이션(Vector Transformation)및 오소그날 트랜스퍼메이션(Orthogonal Transformation)에 유용할 뿐만 아니라 여러 형태의 다양한 연산(elementary function including trigonometric functions)을 하나의 단일화된 알고리즘으로 구현할 수 있게 한 CORDIC(Coordinate Rotation Digit Computer)연산［1］［2］에 관한 연구이다. CORDIC 연산기를 실현함에 있어서 고속 연산을 위해 고속 가산기(fast adder)로서 CSA(Carry Save Adder)를 선택하는데, 본 논문의 연구 초점은 CORDIC연산기를 하드웨어로 실현하기 전에 Bit-Level의 시뮬레이터를 통하여, CSA의 특징상 발생할 수 있는 문제점어 대해 설명하고, 해결 방법［3］을 이용하여 원하는 값에 접근하는가를 확인하여 다양한 Bit의 조작으로 오차의 정도에 따라 유효한 CORDIC연산기를 실현하는데 도움이 되고자 한다.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.9-20
• /
• 2014

In this paper, we propose an automatic fluency evaluation algorithm for English speaking tests. In the proposed algorithm, acoustic features are extracted from an input spoken utterance and then fluency score is computed by using support vector regression (SVR). We estimate the parameters of feature modeling and SVR using the speech signals and the corresponding scores by human raters. From the correlation analysis results, it is shown that speech rate, articulation rate, and mean length of runs are best for fluency evaluation. Experimental results show that the correlation between the human score and the SVR score is 0.87 for 3 speaking tests, which suggests the possibility of the proposed algorithm as a secondary fluency evaluation tool.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.2
• /
• pp.171-171
• /
• 1999

In case of field weakening region torque is directly affected by flux. In this region the flux reference is decreased inversely proportional to the rotor speed. As the flux is decreased the magnetizing inductance is normally increased. The increased magnetizing inductance limited voltage for controlling current. In this paper, measuring q axis voltage in field weakening region magnetizing inductance in flux calculating can be readjusted. Computer simulation and experiment results demonstrate the efficacy of the proposed method. Proposed algorithm is expected to the application of the adjustable drive system in the spinning and weaving field.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.249-254
• /
• 2002

In this paper, we propose an adaptive Beamforming Algorithm, called MC-LMS, for adaptive antenna applied to an MC-CDMA system. New method for updating the weight vector based on the MSE criterion is derived. Computer simulations show that MC-LMS algorithm is capable of rejecting co-channel interference that affects the MC-CDMA system. Thus, the BER performance of the MC-CDMA system is much higher than that of the MC-CDMA system without using adaptive antenna and that of the DS-CDMA system with adaptive antenna in multi-path Rayleigh fading channel.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.134-138
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.311-316
• /
• 2002

In this paper, an adaptive beamforming algorithm, based on the Minimum Mean Squared Error (MMSE) criterion, is devised fer adaptive antenna applied to an MC-CDMA system. A new method for updating the weight vector is derived. Computer simulations show that proposed algorithm is capable of rejecting co-channel interference that affects the MC-CDMA system. Thus, the BER performance of the MC-CDMA system is improved compared with that of the MC-CDMA system without using adaptive antenna and that of the DS-CDMA system with adaptive antenna in multi-path Ricean fading channel.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.3
• /
• pp.627-638
• /
• 1999

In this paper, the system with an artificial intelligent that is able itself to adjust the perimeter condition of the plant is presented. The proposed intelligent system is composed of two learning vector quantization(LVQ) networks, which are used mostly in the field of the pattern recognition and signal processing. From the external condition of the plant, the first LVQ network recognizes the pattern of the sensed signal and the second LVQ network judges synthetically user's characteristics and performs learning. The controller controls the plant using the reference value, which is the output value of the synthetic judgement part. In order to verify the usefulness of the proposed method, we simulated the two LVQs are implemented for the artificial intelligent illuminator as well as being carried out computer simulations. We implemented the proposed artificial intelligent illuminator and perform the experiment.