• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.331-342
• /
• 2005

In this paper, we propose an efficient watermarking algorithm using block indexing. The proposed algorithm is a novel blind watermarking scheme using the indexed watermark value based on the spread spectrum method. The watermark insertion is allocated into index value of each block after dividing original image into sub-blocks. The watermark embedded in mappinged with index values of blocks, And the mappinged blocks convert to DCT and then the PN sequence embedded to middle frequency band. Consequently the watermark is expressed by index value of sub-blocks. The watermark extracted from the correlation of between PN sequence and watermarked image. Experimental results demonstrate that the watermarked image has a good quality in terms of imperceptibility and is robust against various attacks.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.1-10
• /
• 2010

Impulse Radio Ultra-wideband (IR-UWB) system employing the short pulse has the tolerable characteristics for the multipath environment. The corresponding transceiver with low power consumption can be simply implemented. On the other hand, in the receiver side, the precise channel estimation is required for the knowledge of essence in channel due to the short period of pulse. The estimated gains and delays in channel are used in the rake receiver. The resulting parameters we search have a strong influence on the performance in the entire system. We introduce that the essential parameters can be obtained more precisely through the preamble in receiver side for the channel estimation and related technologies are presented.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.76-81
• /
• 2009

We propose an effective emotion recognition algorithm based on the minimum classification error (MCE) incorporating multi-modal system The emotion recognition is performed based on a Gaussian mixture model (GMM) based on MCE method employing on log-likelihood. In particular, the reposed technique is based on the fusion of feature vectors based on voice signal and galvanic skin response (GSR) from the body sensor. The experimental results indicate that performance of the proposal approach based on MCE incorporating the multi-modal system outperforms the conventional approach.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.224-230
• /
• 2013

Lane boundary detection plays a key role in the driver assistance system. This study proposes a robust method for detecting lane boundary in severe environment. First, a horizontal line detects form the original image using improved Vertical Mean Distribution Method (iVMD) and the sub-region image which is under the horizontal line, is determined. Second, we extract the lane marking from the sub-region image using Canny edge detector. Finally, K-means clustering algorithm classifi left and right lane cluster under variant illumination, cracked road, complex lane marking and passing traffic. Experimental results show that the proposed method satisfie the real-time and efficient requirement of the intelligent transportation system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.8
• /
• pp.731-735
• /
• 2001

In this paper, we propose the new audio watermarking method and can be used on line processing. Instead of the wavelet transform, we use the integer wavelet transform for the reduction of the computational load. The watermark associated with the chi-square distribution is inserted into the signal on the integer wavelet domain. When extracting the watermark, the spread spectrum methods are used with the coefficients associated with the covariance sequence. We show that the chi-square distribution is a good tool for the spread spectrum method on the wavelet domain. This watermarking technique may be sued for the control of the electrical product which can be controlled with the hidden signals and can be moved according to the audible signals simultaneously.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.576-581
• /
• 2003

Speech signal has the features of speakers. In this paper, we propose the speaker identification system which use the incremental learning based on neural network. Recorded speech signal through the Mic is passed the end detection and is divided voiced signal and unvoiced signal. The extracted 12 order cpestrum are used the input data for neural network. Incremental learning is the learning algorithm that the learned weights are remembered and only the new weights, that is created as adding new speaker, are trained. The architecture of neural network is extended with the number of speakers. So, this system can learn without the restricted number of speakers.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.12
• /
• pp.1371-1379
• /
• 2010

This paper presents an analysis of impulse dispersion for impulse radio ultra-wide band(IR-UWB) antenna. A set of antenna structure configurations are highlighted with verification based on the STFT(Short Time Fourier Transform) in 3.1~5.1 GHz: first, a taper-slotted antenna allowing the optimal impulse transmission, and second, 4 types of the omni-directional IR-UWB antenna using different feed structures(microstrip line, and CPW(Coplanar Waveguide)). The proposed STFT allows the analysis of the IR-UWB antenna's dispersion characteristic.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.515-517
• /
• 2016

In this paper, we develope a stretchable wearable device containing services for processing physiological signals to extract emotion information. The emotion extracting algorithm conducts to recognize emotion from EDR, SKT, and HRV signals measured with the fabric sensors. In addition, the suggested wearable device can also solve the problems faced with today's many other wearable devices: 1) limited battery life 2) the lack of compatibility and expandability due to run on internal components designed for smart phone 3) the design has always been a crucial factor in determining the success of main stream consumer wearable devices.

• Proceedings of the KIEE Conference
• /
• 2006.10a
• /
• pp.145-146
• /
• 2006

본 논문은 부분방전(PD: Partial Discharge)의 패턴인식 확률 극대화를 목적으로 신경망(NN: Neural Network) 파라미터 중에서 은닉층 뉴런의 수, 모멘텀(momentum)의 Step size와 Decay rate 를 최적화하기 위하여 유전 알고리즘(GA: Genetic Algonthm)을 적응하였다. 실험적 연구의 대상으로서, GIS(Gas Insulated Switchgear)사고의 주요 원인으로 보고되어있는 결함들을 인위적으로 모의한 16개 Test cell을 이용하여 부분방전을 발생시켰다. 부분방전 신호는 본 연구팀이 개발한 센서를 이용하여 검출되어 데이터베이스가 구축되어 그로부터 추출된 학습 데이터들의 학습에 다음과 같은 5가지 신경망 모델이 적응되었다: Multilayer Perception (MLP), Jordan-Elman Network (JEN), Recurrent Network (RN), Self-Organizing Feature Map (SOFM), Time-Lag Recurrent Network (TLRN). 유전 알고리즘 적용 효율성을 분석하기 위하여 동일한 데이터를 이용하여 다음과 같은 두 가지 방법을 적용한 결과를 상호 비교하였다. 우선 상기 선택된 모델만 적용하였고 다근 하나는 상기 모델과 Genetic Algorithm이 동시에 적용되었다. 모든 모델에 대하여 학습오차와 패턴 분류 확률을 비교한 결과, 유전 알고리즘 적응 시 부분방전 패턴인식 확률이 향상되었음이 확인되어 향후 신뢰성 있는 GIS 부분방전 진단기술에 활용될 수 있을 것으로 사료된다.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.05a
• /
• pp.82-87
• /
• 2001

In this paper we described the generation method of interface logic which can be replace between IP and IP handshaking signal with asynchronous logic circuit. Especially, we suggest the new \"Waveform Conversion Algorithm : Wave2VHDL\", if only mixed asynchronous timing waveform suggested which level type input and pulse type input for handshaking, we can convert waveform to flowchart and then replaced with VHDL code according to converted flowchart. Also, we assure that asynchronous electronic circuits for IP interface are generated by applying extracted VHDL source code from suggested algorithm to conventional domestic/abroad CAD Tool, and then we proved that coincidence simulation result and suggested timing diagram.g diagram.