• Nuclear Engineering and Technology
• /
• 제33권5호
• /
• pp.483-497
• /
• 2001

In this work, a neuro-fuzzy inference system combined with the wavelet denoising, PCA (principal component analysis) and SPRT (sequential probability ratio test) methods is developed to detect the relevant sensor failure using other sensor signals. The wavelet denoising technique is applied to remove noise components in input signals into the neuro-fuzzy system The PCA is used to reduce the dimension of an input space without losing a significant amount of information. The PCA makes easy the selection of the input signals into the neuro-fuzzy system. Also, a lower dimensional input space usually reduces the time necessary to train a neuro-fuzzy system. The parameters of the neuro-fuzzy inference system which estimates the relevant sensor signal are optimized by a genetic algorithm and a least-squares algorithm. The residuals between the estimated signals and the measured signals are used to detect whether the sensors are failed or not. The SPRT is used in this failure detection algorithm. The proposed sensor-monitoring algorithm was verified through applications to the pressurizer water level and the hot-leg flowrate sensors in pressurized water reactors.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2331-2334
• /
• 2003

Generally, skin color information has been widely used at the face region extraction step of the face region recognition process. But many experimental results show that they are very sensitive to the given threshold range which is used to extract the face regions at the input image. In this paper, we propose a face region extraction algorithm based on an adaptive range decision for skin color. First we extract the pixels which are regarded as the candidate skin color pixels by using the given range for skin color extraction. Then, the ratio between the total pixels and the extracted pixels is calculated. According to the ratio, we adaptively decide the range of the skin color and extract face region. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 봄 학술발표회 논문집
• /
• pp.379-386
• /
• 2001

Piled raft foundations are usually used to reduce total and differential settlements of superstructures. In the piled raft foundations, the raft is often on its own able to provide adequate bearing capacity and only few widely spaced piles are added to the foundation to keep settlements be1ow a certain limit. In this paper, experimental studies on the load sharing ratio between piles and raft are carried out. Also, for evaluating the application of optimum design technique using a genetic algorithm, optimal locations of files are compared with the results of laboratory model tests. from tile results of laboratory model tests, there are found that the load sharing ratio between files and raft is depended on the number of piles and stiffness of raft, and the optimal locations of piles became concentrated on the middle of rafts. From these results of laboratory model tests, the optimum technique using a genetic algorithm is acknowledged to the application in the piled raft.

• 전기학회논문지
• /
• 제61권6호
• /
• pp.872-878
• /
• 2012

It is quite important to improve the visual acuity of a medical image by suppressing noisy parts and simultaneously keeping the details of signal components to draw the accurate diagnostics. With this aim, we suggest a novel method to generate Rotational Kernel Transformation (RKT) filter mask with applying Bresenham's algorithm and implement an nonlinear filtering algorithm to eliminate noises. As a result, we can find the fact that RKT filter mask can be automatically created and the visual acuity of a corrupted image can be elevated in terms of the signal-to-noise ratio (SNR) with applying the RKT filter.

• 한국통신학회논문지
• /
• 제31권4C호
• /
• pp.303-309
• /
• 2006

By combining the space-time diversity technique and iterative turbo codes, space-time turbo codes(STTCS) are able to provide powerful error correction capability. However, the multi-path transmission and iterative decoding structure of STTCS make the decoder very complex. In this paper, we propose a low complexity decoder, which can be used to decode STTCS as well as general iterative codes such as turbo codes. The efficient implementation of the backward recursion and the log-likelihood ratio(LLR) update in the proposed algorithm improves the computational efficiency. In addition, if we approximate the calculation of the joint LLR by using the approximate ratio(AR) algorithm, the computational complexity can be reduced even further. A complexity analysis and computer simulations over the Rayleigh fading channel show that the proposed algorithm necessitates less than 40% of the additions required by the conventional Max-Log-MAP algorithm, while providing the same overall performance.

• 대한의용생체공학회:의공학회지
• /
• 제17권4호
• /
• pp.545-552
• /
• 1996

Researches on chromosome are very significant in cytogenetics since a gene of the chromosome controls revelation of the inheritance plasma The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an algorithm for reconstruction of the chromosDme image to improve the chromosome classification accuracy. Morphological feature parameters are extracted from the reconstructed chromosome images. The reconstruction method from chromosome image is the 32 direction line algorithm. We extract three morphological feature parameters, centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), by preprocessing ten human chromosDme images. The experimental results show that proposed algorithm is better than that of other researchers'comparing by feature parameter errors.

• 한국방사선학회논문지
• /
• 제16권2호
• /
• pp.131-139
• /
• 2022

본 연구는 척추경 나사못(Pedicle screw)을 돼지 흉추에 삽입하여 일반적인 CT검사(Non MAR)와 인공물을 줄이기 위한 금속성 인공물 감소기법(Metallic Artifact Reduction for Orthopedic Implants, O-MAR)으로 얻어진 흉추 Axial영상을 4개의 알고리즘(Standard, Soft, Bone, Detail)에 재구성하였다. 이에 얻은 영상을 image J 프로그램을 이용하여 신호대잡음비(Signal Noise Ratio, SNR)와 대조도대잡음비(Contrast to Noise Ratio, CNR)를 주어진 식에 의거하여 측정값을 구하고 흉추 척추경 나사못 삽입술 CT검사에 맞는 관전압과 알고리즘을 알아보고자 하였다. 결과적으로 Non MAR 사용한 경우에는 80, 100, 120, 140 kVp에서 soft 알고리즘이 SNR, CNR이 가장 높게 나타났다. 반면에 MAR를 사용한 경우 80 kVp에서는 Standard 알고리즘이 가장 높게 나타났고 100 kVp에서는 Standard, Soft 알고리즘이 비슷한 값으로 높게 나타났다. 120 kVp에서는 Soft, Standard 알고리즘이 비슷한 값으로 나타났고 140 kVp에서는 Soft 알고리즘에서 SNR, CNR이 가장 높게 나타났다. 따라서 Non MAR와 MAR를 비교했을 경우 MAR를 사용한다고 하더라도 관전압 변화에 따라 모든 알고리즘에서 SNR과 CNR이 증가하는 것은 아니었다. 본 연구는 이후 척추경 나사못 CT검사 영상 평가에 도움이 되는 기초자료로써 선택적인 관전압과 알고리즘 사용으로 영상의 질을 더 높일 수 있는 계기가 될 것으로 사료된다.

• 유통과학연구
• /
• 제11권6호
• /
• pp.13-19
• /
• 2013

Purpose - This study aims to predict the audit reports of listed companies on the Tehran Stock Exchange by using meta-heuristic algorithms. Research design, data, methodology - This applied research aims to predict auditors reports' using meta-heuristic methods (i.e., neural networks, the ANFIS, and a genetic algorithm). The sample includes all firms listed on the Tehran Stock Exchange. The research covers the seven years between 2005 and 2011. Results - The results show that the ANFIS model using fuzzy clustering and a least-squares back propagation algorithm has the best performance among the tested models, with an error rate of 4% for incorrect predictions and 96% for correct predictions. Conclusion - A decision tree was used with ten independent variables and one dependent variable the less important variables were removed, leaving only those variables with the greatest effect on auditor opinion (i.e., net-profit-to-sales ratio, current ratio, quick ratio, inventory turnover, collection period, and debt coverage ratio).

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.315-320
• /
• 2007

An effective reinforcement method for steel tubular joints having a large chord diameter is the use of internal ring stiffeners. This paper presents the results of a numerical study on the static strength of internally ring-stiffened tubular X- and T-joints subjected to brace axial compression loading. Nonlinear finite element analyses are used to compute the joint strength. The influence of geometrical parameters has been studied and the maximum reinforcement effect of a ring stiffener has been evaluated. A strength ratio is defined. by the ratio of ring-stiffened joint strength to unstiffened joint strength, and an equation for this strength ratio is derived by regression analysis. Design optimization for ring stiffener of tubular joints is carried out using metropolis genetic algorithm.

• 한국분무공학회지
• /
• 제5권3호
• /
• pp.9-16
• /
• 2000

In a SI engine, three-way catalyst converter has the best efficiency when A/F ratio is near the stoichiometry. The feedback control using oxygen sensors in the commercial engine has limits caused by the system delays. So it is necessary to control fuel quantity in accordance with intake air amount in order to reduce exhaust emission and improve the specific fuel consumption. Precise A/F ratio control requires measurement of air amount with respect to the cylinder and injection fuel according to the air amount In this paper, we applied nonlinear fuel injection model and developed the algorithm of A/F ratio control. This algorithm includes the methods of measurement of transient air mass flowing into each cylinder, of calculation of injection pulse width for measured air mass, and the method of feedback and engine control by using lambda sensor. Also we developed control program for IBM-PC by using C++ Builder, and tested it in the commercial engine.