• The Journal of Korean Medical History
• /
• v.20 no.2
• /
• pp.65-69
• /
• 2007

Although a table of descent is a mandatory primary source for studying medical persons, but most of those who practiced medicine were not but of step families. Because members of step families are not usually recorded accurately, preceeding studies did not put much emphasis on them. But as more researchers study biography and the number of studies done on historical figures are increasing tremendously, its value as a source has increased as well. In order to research a person, obtaining background information is a priority, which includes to what family they belong to, to what specific branch of the family they belong to, etc. Whether or not the person has ever worked with a public institution is important as well.

• Journal of Biomedical Engineering Research
• /
• v.28 no.6
• /
• pp.817-824
• /
• 2007

Tractography using Diffusion Tensor Magnetic Resonance Imaging (DT-MRI) is a method to determine the architecture of axonal fibers in the central nervous system by computing the direction of the principal eigenvector in the white matter of the brain. However, the fiber tracking methods suffer from the noise included in the diffusion tensor images that affects the determination of the principal eigenvector. As the fiber tracking progresses, the accumulated error creates a large deviation between the calculated fiber and the real fiber. This problem of the DT-MRI tractography is known mathematically as the ill-posed problem which means that tractography is very sensitive to perturbations by noise. To reduce the noise in DT-MRI measurements, a tensor-valued median filter which is reported to be denoising and structure-preserving in fiber tracking, is applied in the tractography. In this paper, we proposed the modified gradient descent method which converges fast and accurately to the optimal tensor-valued median filter by changing the step size. In addition, the performance of the modified gradient descent method is compared with others. We used the synthetic image which consists of 45 degree principal eigenvectors and the corticospinal tract. For the synthetic image, the proposed method achieved 4.66%, 16.66% and 15.08% less error than the conventional gradient descent method for error measures AE, AAE, AFA respectively. For the corticospinal tract, at iteration number ten the proposed method achieved 3.78%, 25.71 % and 11.54% less error than the conventional gradient descent method for error measures AE, AAE, AFA respectively.

• Journal of the korean Society of Automotive Engineers
• /
• v.11 no.2
• /
• pp.24-33
• /
• 1989

본 고에서는 이러한 추세에 따라서, 보다 효율적인 optimization program에 대해서 소개하고자 한다. 사용한 최적화 알고리즘은 ALM(augmented lagrange multiplier) 방법을 적용해서 구속조건이 있는 문제를 구속조건이 없는 문제로 변환한 후, self-scaling BFGS(broydon-flecher-goldfarb-schanno)를 적용한다. BFGS의 각 descent 방향에서의 step 길이는, sequential search로 unimodal point를 구해서, golden section 방법으로 refine을 한후, cubic approximation을 적용해서 구한다.

• Structural Engineering and Mechanics
• /
• v.45 no.1
• /
• pp.53-67
• /
• 2013

This study aimed to develop a model to accurately predict the acceleration of structural systems during an earthquake. The acceleration and applied force of a structure were measured at current time step and the velocity and displacement were estimated through linear integration. These data were used as input to predict the structural acceleration at next time step. The computation tool used was the Volterra/Wiener neural network (VWNN) which contained the mathematical model to predict the acceleration. For alleviating problems of relatively large-dimensional and nonlinear systems, the VWNN model was utilized as the signal processing tool, including the Taylor series components in the input nodes of the neural network. The number of the intermediate layer nodes in the neural network model, containing the training and simulation stage, was evaluated and optimized. Discussions on the influences of the gradient descent with adaptive learning rate algorithm and the Levenberg-Marquardt algorithm, both for determining the network weights, on prediction errors were provided. During the simulation stage, different earthquake excitations were tested with the optimized settings acquired from the training stage to find out which of the algorithms would result in the smallest error, to determine a proper simulation model.

• Proceedings of the KIEE Conference
• /
• 2009.04b
• /
• pp.46-49
• /
• 2009

An optimal design procedure is proposed to effectively reduce the torque ripple by optimizing the rotor pole shape of the spoke type IPMSM with concentrated winding. The procedure is composed of two steps. In step I, the steepest descent method (SDM) is used with only two design variables to rapidly approach the optimal shape. From the near optimal rotor shape as a result of the step I, the design variables are reselected and the drawing spline curves are utilized to explain more complex shape with the Kriging model in step II. By using an optimal design procedure, we show that the optimized rotor pole shape of the spoke type IPMSM effectively reduces the torque ripple while still maintaining the average torque.

• Journal of applied mathematics & informatics
• /
• v.6 no.3
• /
• pp.735-746
• /
• 1999

Based on an active set strategy a method for solving lin-early constrained indefinite quadratic programs to solve the correspond-ing system of equations at each iteration is presented. The algorithm takes two descent directions to strictly decrease the value of objective function and obtains a suitable step to maintain feasibility. Computa-tional results on a range of quadratic test problems are given.

• Journal of Advanced Marine Engineering and Technology
• /
• v.23 no.4
• /
• pp.574-582
• /
• 1999

This paper discusses the multi-level optimization method in dynamic optimization problems through stiffened plate of ship structures. In structural optimization the computational cost increases rapidly as the number of design variables increases. And we need a great amount of cal-culation and time on problems of modified dynamic characteristics of large and complicated struc-tures. In this paper the multi-level optimization is proposed which decreases computational time and cost. the dynamic optimum designs of stiffened plate that control the natural frequency and minimize weight subjected to constraints condition are derived. The way to apply the multi-level optimization methods in this study follow: In the first step the dynamic characteristics is controlled for the two-dimensional model of stiffened plate by sensitivity analysis and quasi-least squares methods. In the second step the cross-section of the stiffener is decided so that the weight is minimized under needed constraints by the steepest descent or ascent method. In the third the three-dimensional model is made based on the results of the first step and the second step confirmation and finer tuning of the objective function are carried out. It is shown that the results are effective in the optimum modification for dynamic characteristics of the stiffened plate.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.803-805
• /
• 2000

In this paper, we propose fuzzy-neural Networks(FNN) which is useful for identification algorithms. The proposed FNN model consists of two steps: the first step, which determines premise and consequent parameters approximately using FCM_RI method, the second step, which adjusts the premise and consequent parameters more precisely by gradient descent algorithm. The FCM_RI algorithm consists FCM clustering algorithm and Recursive least squared(RLS) method, this divides the input space more efficiently than convention methods by taking into consideration correlations between components of sample data. To evaluate the performance of the proposed FNN model, we use the time series data for gas furnace.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.152-159
• /
• 2005

For high-speed data communication in band-limited channels, main of the bit error are fading and ISI(Inter-Symbol Interference). The common way of dealing with ISI is using equalization in the receiver. In this thesis, channel adaptive equalizer which uses Fuzzy Stochastic Gradient(FSG) and Constant Modulus Algorithm(CMA) is nonlinear equalizer, or Blind equalizer, that works directly on the signals with no training sequences required. This equalizer employs Takagi-Sugeno's fuzzy model that uses the FSG algorithm, to automatically regulate the step size of the descent gradient vector, combining fast convergence rate and low mean square error(MSE), and the CMA which is a special case of Godard's algorithm, to having multiple dispersion constants($R_p$).