• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권10호
• /
• pp.591-597
• /
• 2003

In this paper, a best-basis selection algorithm that improves the performance of the coding gains and the computational complexity is proposed. The proposed algorithm limits the computational complexity according to the resolved threshold value and decomposes the parent subbands by using the top-down tree search and the relative energy between the parent subbands and the child subbands. For the experiments of the proposed algorithm, the bit-rates, the peak signal-to-noise ratio (PSNR), and the reconstructed images are presented by using the Quad-tree coder. The result of the proposed algorithm is compared to that of DWT algorithm using the Quad-tree coder for a set of standard test images. In addition, the result of the proposed algorithm is compared to that of JPEG-2000 algorithm and that of S+P algorithm.

• ETRI Journal
• /
• 제22권2호
• /
• pp.1-10
• /
• 2000

Pattern recognition is one of the most common problems encountered in engineering and scientific disciplines, which involves developing prediction or classification models from historic data or training samples. This paper introduces a new approach, called the Representational Capability (RC) algorithm, to handle pattern recognition problems using radial basis function (RBF) models. The RC algorithm has been developed based on the mathematical properties of the interpolation and design matrices of RBF models. The model development process based on this algorithm not only yields the best model in the sense of balancing its parsimony and generalization ability, but also provides insights into the design process by employing a design parameter (${\delta}$). We discuss the RC algorithm and its use at length via an illustrative example. In addition, RBF classification models are developed for heart disease diagnosis.

• Structural Engineering and Mechanics
• /
• 제37권6호
• /
• pp.575-592
• /
• 2011

For seismic resistant design of critical structures, a dynamic analysis, either response spectrum or time history is frequently required. Owing to the lack of recorded data and the randomness of earthquake ground motion that may be experienced by structure in the future, usually it is difficult to obtain recorded data which fit the requirements (site type, epicenteral distance, etc.) well. Therefore, the artificial seismic records are widely used in seismic designs, verification of seismic capacity and seismic assessment of structures. The purpose of this paper is to develop a numerical method using Artificial Neural Network (ANN) and wavelet packet transform in best basis method which is presented for the decomposition of artificial earthquake records consistent with any arbitrarily specified target response spectra requirements. The ground motion has been modeled as a non-stationary process using wavelet packet. This study shows that the procedure using ANN-based models and wavelet packets in best-basis method are applicable to generate artificial earthquakes compatible with any response spectra. Several numerical examples are given to verify the developed model.

• 제어로봇시스템학회논문지
• /
• 제13권6호
• /
• pp.560-567
• /
• 2007

The objective of this research is to optimize the designing parameters of the parallel manipulator with large orientation workspace at the boundary position of the constant orientation workspace (COW). The method uses a simple genetic algorithm(SGA) while considering three different kinematic performance indices: COW and the global conditioning index(GCI) to evaluate the mechanism's dexterity for translational motion of an end-effector, and orientation workspace of two angle of Euler angles to obtain the large rotation angle of an end-effector at the boundary position of COW. Total fifteen cases divided according to the combination of the sphere radius of COW and rotation angle of orientation workspace are studied, and to decide the best model in the total optimized cases, the fuzzy inference system is used for each case's results. An optimized model is selected as a best model, which shows better kinematic performances compared to the basis of the pre-existing model.

• 한국음향학회지
• /
• 제21권4호
• /
• pp.178-178
• /
• 2002

In this paper, we propose an adaptive wavelet method for car interior noise cancellation. For this purpose, we use a node dependent threshold which minimizes the Bayesian risk. We propose a noise estimation method based on spectral entropy using histogram of intensity and a candidate best basis instead of Donoho's best bases. And we modify the hard threshold function. Experimental results show that the proposed algorithm is more efficient, especially to heavy noisy signal than conventional one.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2004년도 춘계 학술발표회 제16권1호
• /
• pp.432-437
• /
• 2004

In this study, Pavement Management System(PMS) was developed to overcome the unscientific pavement management limitations of the past. PMS program is economic, efficient and scientific. Also, it produces the best maintenance method through exact judgement and logical analysis of pavement condition. First of all, the logical algorithm, that is such as investigation and analysis of pavement, detailed naked eye investigation and the estimation for whole system etc., was composed on the basis of the domestic and the outside data on PMS and pavement condition data of Seoul metropolitan. And then it was verified that this algorithm is suitable through the research examples of PMS data and the results of detailed naked eye investigation. Also, Geographic Information System(GIS) was integrated on PMS program. Therefore, PMS program was developed so as to use easily on the basis of the logical algorithm.

• Geomechanics and Engineering
• /
• 재33권6호
• /
• pp.567-581
• /
• 2023

The prediction and achievement of a proper rock fragmentation size is the main challenge of blasting operations in surface mines. This is because an optimum size distribution can optimize the overall mine/plant economics. To this end, this study attempts to develop four improved artificial intelligence models to predict rock fragmentation through cascaded forward neural network (CFNN) and radial basis function neural network (RBFNN) models. In this regards, the CFNN was trained by the Levenberg-Marquardt algorithm (LMA) and Conjugate gradient backpropagation (CGP). Further, the RBFNN was optimized by the Dragonfly Algorithm (DA) and teaching-learning-based optimization (TLBO). For developing the models, the database required was collected from the Midouk copper mine, Iran. After modeling, the statistical functions were computed to check the accuracy of the models, and the root mean square errors (RMSEs) of CFNN-LMA, CFNN-CGP, RBFNN-DA, and RBFNN-TLBO were obtained as 1.0656, 1.9698, 2.2235, and 1.6216, respectively. Accordingly, CFNN-LMA, with the lowest RMSE, was determined as the model with the best prediction results among the four examined in this study.

• 한국통신학회논문지
• /
• 제34권7C호
• /
• pp.681-686
• /
• 2009

H.264/Ave에서 p-프레임 부호화에 추가된 인트라 예측은 화질과 비트율 모두를 다소 개선시키고 있으나, 계산량을 크게 증가시키고 있다. 계산량의 증가를 줄이기 위해 본 논문은 최적 인트라 블록 모드가 매크로 블록의 영상 내용에 의존하는 특성을 이용한 영상 내용 기반 인트라 예측 부호화를 제안한다. 제안된 알고리즘은 영상 복잡도와 최적 인터 블록 모투로 매크로블록외 영상 내용을 평가하고, 영상 내용을 근거로 인트라 블록 모드를 선택하거나 배제한다. 모의실험 결과는 기존 알고리즘과 비교하여 제안된 알고리즘이 화질에서 평균 0.01 dB가 감소하교 비트휩l서 평균 0.38%가 증가하나, 부호화 계산 시간에서 평균 37.02% 의 큰 감소를 보여주고 있다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권6호
• /
• pp.455-463
• /
• 2010

본 논문은 다양한 형태의 웹 문서에 적용하기 위해서, 언어의 통계정보 및 후처리 규칙에 기반하여 개선한 문장경계 인식 기술을 제안한다. 제안한 방법은 구두점 생략 및 띄어쓰기 오류가 빈번한 웹문서에 적용하기 위해서 문장경계로 사용될 수 있는 모든 종결어미를 대상으로 학습하여 문장경계 인식을 수행하였다. 또한 문장경계인식 성능을 최대화하기 위해서 다양한 실험을 통해 최적의 자질 및 학습데이터를 선정하였고, 학습데이터에 의존적인 통계모델의 오류를 규칙에 기반 해서 보정하였다. 성능 실험은 다양한 문서별 성능 측정을 위해서 구두점이 주로 문장경계로 사용된 문어체 위주의 평가셋1(신문기사와 블로그 문서)과 구두점 생략 및 띄어쓰기 오류가 빈번한 웹 문서 위주의 평가셋2(웹 사이트의 게시판 글)를 대상으로 성능을 측정하였다. 평가 척도로는 F-measure를 사용하였으며, 기존 연구와 동일하게 구두점만을 문장경계 대상으로 학습한 기본 모델을 만들어서 실험한 결과, 평가셋1에 대해서 96.5%의 성능을 보였지만, 평가셋2에 대해서는 56.7%로 매우 저조한 성능을 보였다. 제안하는 개선 방법은 기본 모델을 웹 문서의 특징을 반영시키도록 자질 및 엔진을 개선시켰고, 최종 모델을 평가셋2로 평가한 결과, 96.3%의 성능을 보여서 39.6%의 성능 향상이 있음을 확인하였다.

• Smart Structures and Systems
• /
• 제25권6호
• /
• pp.765-778
• /
• 2020

The present study intends to find a proper solution for the estimation of the physical behaviors of enlarged piles through a combination of small-scale laboratory tests and a hybrid computational predictive intelligence process. In the first step, experimental program is completed considering various critical influential factors. The results of the best multilayer perceptron (MLP)-based predictive network was implemented through three mathematical-based solutions of dragonfly algorithm (DA), whale optimization algorithm (WOA), and ant lion optimization (ALO). Three proposed models, after convergence analysis, suggested excellent performance. These analyses varied based on neurons number (e.g., in the basis MLP hidden layer) and of course, the level of its complexity. The training R² results of the best hybrid structure of DA-MLP, WOA-MLP, and ALO-MLP were 0.996, 0.996, and 0.998 where the testing R² was 0.995, 0.985, and 0.998, respectively. Similarly, the training RMSE of 0.046, 0.051, and 0.034 were obtained for the training and testing datasets of DA-MLP, WOA-MLP, and ALO-MLP techniques, while the testing RMSE of 0.088, 0.053, and 0.053, respectively. This obtained result demonstrates the excellent prediction from the optimized structure of the proposed models if only population sensitivity analysis performs. Indeed, the ALO-MLP was slightly better than WOA-MLP and DA-MLP methods.