• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.9 no.6
• /
• pp.735-745
• /
• 1998

The method of moments has been widely used in the analysis of TM scattering problems. Recently, significant advances in the development of fast and efficient techniques for solving large problems have been reported. In such methods, iterative matrix solvers are preferred by virtue of their speed and low memory requirements. But for near resonant and strong multiple scattering problems, e.g., involving an aircraft engine inlet, a large number of iterations is required for convergence. In this paper, an efficient approximate inverse based preconditioner is used to reduce this number of iterations. By using the matrix partitioning method, the computational is used to reduce this number of iterations. By using the matrix partitioning method, the computational cost for obtaining the approximate inverse is reduced to O(N). We apply this preconditioner to an O(NlogN) algorithm, the multilevel fast multipole algorithm, for the aircraft engine inlet problem. The numerical results show the efficiency of this preconditioner.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1798_1799
• /
• 2009

본 논문에서는 강인한 손 영역 특징 점 추출 방법을 제안한다. 제안하는 방법은 HCbCr 칼라 모델을 생성한 후 퍼지 색상 필터에 적용하여 손 후보 영역을 추출한다. 최종적으로 손 영역을 추출하기 위해서 레이블링 기법을 사용한다. 그 후, 추출된 손 영역의 실루엣을 추출하고 히스토그램 기법을 적용하여 손 영역 내의 COG를 추출 한다. 손 영역 특징 점 추출을 위해 Canny edge 기법과 Chain Code기법, DP(Douglas-Peucker)기법들을 이용하여 전처리 과정을 거쳐 1차 특징점을 추출한다. 추출된 1차 특징 점을 Convex Hull기법에 적용하여 최종적인 손 영역 특징 점을 추출한다. 마지막으로, 복잡하고 다양한 실내 환경에서의 실험을 통해 그 응용 가능성을 증명한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.108-111
• /
• 2010

본 논문에서는 기존의 2차원 영상/비디오 압축 기술을 홀로그램의 특성에 적합하게 변형시켜서 홀로그램 데이터를 압축하는 압축 기법을 제안하였다. 컴퓨터 생성 홀로그램(computer generated holograms, CGH) 기법을 이용해 생성한 디지털 홀로그램을 사용하였다. 본 논문에서는 전처리된 디지털 홀로그램에 대해 분할, 주파수 변환, 움직임 예측과 주파수 영역에서의 잔여영상 생성 기법을 적용하여 데이터 압축을 수행한다. 압축은 H.264/AVC, 무손실 압축기법인 BinHex와, 선형 양자화를 이용하였고, 실험 결과를 보면 제안한 데이터 압축 기법은 전체 압축률이 10:1~90:1까지 변화함에따라 25.4dB~16.5dB로 감소함을 확인할 수 있다. 그러나 시각적인 영상의 품질은 앞서 제시한 PSNR값 보다 훨씬 우수함을 확인 할 수 있다.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.45-51
• /
• 2020

Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.476-485
• /
• 2003

This paper proposers a preprocessing approach to improving the quality of the music produced by the EVRC(enhanced variable rate codec) which is one of the CDMA(Code Division Multiple Access) voice codecs. Since the EVRC is optimized only for speech signals, it can deteriorate the quality of the music passed through it. One of the problems with the EVRC-coded music is time-clipping, which usually occurs when subsequent frames are encoded at Rate l/8. Since the EVRC determines the bit rate for an input frame based on the long-term prediction gain, we increase the long-term prediction gain in order for the most of the frames to be encoded at Rate 1 or Rate 1/2. Experimental results show that the approach works well on music signals and the number of time-clipped frames is considerably reduced.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.128-138
• /
• 2019

In this paper, we present fusion methods for two different lofargrams. Since the conventional method synthesizes the lofargrams using frequency spectrum, it has limited performance in fusion of tonal signals which have two-dimensional information of the time-frequency domain. Proposed algorithm uses a two-dimensional directional bilateral filter for preprocessing and fuses two lofargrams based on comparison of local anisotropy of the lofargrams. After noise is suppressed and tonals are sharpened, the local anisotropy can be used as a criterion to divide tonals and noise. The experiment results using simulated data and real data showed that the proposed algorithms result in similar or lower noise level of the fused lofargram than conventional algorithms and decrease tonal omission in fusion process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.600-608
• /
• 2020

Machine learning constructs an objective function from learning data, and predicts the result of the data generated by checking the objective function through test data. In machine learning, input data is subjected to a normalisation process through a preprocessing. In the case of numerical data, normalization is standardized by using the average and standard deviation of the input data. In the case of nominal data, which is non-numerical data, it is converted into a one-hot code form. However, this preprocessing alone cannot solve the problem. For this reason, we propose a method that uses ontology to normalize input data in this paper. The test data for this uses the received signal strength indicator (RSSI) value of the Wi-Fi device collected from the mobile device. These data are solved through ontology because they includes noise and heterogeneous problems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.380-386
• /
• 2022

This paper proposes a method for structuring the preprocessing process of a training image when color is applied using Pix2Pix, one of the adversarial generative neural network techniques. This paper concentrate on the prediction result can be damaged according to the degree of light reflection of the training image. Therefore, image preprocesisng and parameters for model optimization were configured before model application. In order to increase the image resolution of training and prediction results, it is necessary to modify the of the model so this part is designed to be tuned with parameters. In addition, in this paper, the logic that processes only the part where the prediction result is damaged by light reflection is configured together, and the pre-processing logic that does not distort the prediction result is also configured.Therefore, in order to improve the usability, the accuracy was improved through experiments on the part that applies the light reflection tuning filter to the training image of the Pix2Pix model and the parameter configuration.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2024

The introduction of Smart Factories has transformed manufacturing towards more objective and efficient line management. However, most companies are not effectively utilizing the vast amount of sensor data collected every second. This study aims to use this data to predict product quality and manage production processes efficiently. Due to security issues, specific sensor data could not be verified, so semiconductor process-related training data from the "SAMSUNG SDS Brightics AI" site was used. Data preprocessing, including removing missing values, outliers, scaling, and feature elimination, was crucial for optimal sensor data. Oversampling was used to balance the imbalanced training dataset. The SVM (rbf) model achieved high performance (Accuracy: 97.07%, GM: 96.61%), surpassing the MLP model implemented by "SAMSUNG SDS Brightics AI". This research can be applied to various topics, such as predicting component lifecycles and process conditions.

• Clean Technology
• /
• v.7 no.3
• /
• pp.169-178
• /
• 2001

Textile printing prints around twenty bilion linear meters of textile each year. Rotary and flat bed screen printing requires pre and post treatments, leading to the loss of dyes and the environmental problems due to effluents. Digital ink jet printing can offer a solution to the existing problems, especially the environmental problems, in addition to its flexibility. Pigments are used as a dispersion inks in the digital inkjet textile printing. Molecular dynamic simulation like Stokesian dynamic simulation was employed to simulate the behavior of pigments and velocity distribution under the pressure driven flow in the printer nozzle. The simulation shows that the particle distribution in the flow are uniform if particle volume fraction is low, the ratio of nozzle and particle diameter is large, and the dimensionless average suspension velocity is low.