• 한국정보통신학회논문지
• /
• 제10권2호
• /
• pp.406-412
• /
• 2006

본 논문에서는 차선 추출을 위해서 OHT(Optimized Hough Transform) 알고리듬을 제안한다. 입력 영상을 그레이 영상으로 변환하고 변환된 그레이 영상은 수평 투영을 통해 주변 배경 영역과 도로 영역으로 분리된다. 분리된 도로 영역에서 OHT(Optimized Hough Transform) 알고리듬을 적용한다. OHT(Optimized Hough Transform) 알고리듬은 다음과 같이 특징지어진다. 첫째, 윤곽선 방향각을 이용해서 차선후보 픽셀을 최소화하였으며, 둘째, 좌우 차선의 범위는 제한된 ${\theta}$값으로서 정의하였다. 실험 결과, 제안한 알고리듬이 기존의 Hough Transform보다 훨씬 효율적임을 알 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제5권2호
• /
• pp.189-199
• /
• 1999

This paper presents an optimization algorithm for a stable Self Dynamic Neural Network(SDNN) using genetic algorithm. Optimized SDNN is applied to a problem of controlling nonlinear dynamical systems. SDNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. The real-time implementation is very important, and thus the neuro controller also needs to be designed such that it converges with a relatively small number of training cycles. SDW has considerably fewer weights than DNN. Since there is no interlink among the hidden layer. The object of proposed algorithm is that the number of self dynamic neuron node and the gradient of activation functions are simultaneously optimized by genetic algorithms. To guarantee convergence, an analytic method based on the Lyapunov function is used to find a stable learning for the SDNN. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed optimized SDNN considering stability is demonstrated by case studies.

• International Journal of Aeronautical and Space Sciences
• /
• 제15권1호
• /
• pp.20-31
• /
• 2014

This paper deals with the development of a realistic shape optimization of damaged columns that are subjected to conservative and non-conservative forces, using the Genetic Algorithm (GA). The analysis is based on the design of the most optimized shape of the column under the constraint of constant weight, considering the Static, Vibrational, and Flutter characteristics. Under the action of conservative and non-conservative longitudinal forces, an elastic column loses its stability. A numerical analysis based on FEM has been performed on a uniform damaged column, to compute the fundamental buckling load, vibration frequency, and flutter load, under various end restraints. An optimization search based on the Genetic Algorithm is then executed, to find the optimal shape design of the column. The optimized column references the one having the highest buckling load, highest vibration frequency, and highest flutter load, among all the possible shapes of the column, for a given volume. A comparison is then made between the values obtained for the optimized damaged column, and those obtained for the optimized undamaged column. The comparison reveals that the incorporation of damage in the column alters its optimal shape to only a certain extent. Also, the critical load and frequency values for the optimized damaged column are comparatively low, compared with those obtained for the optimized undamaged column. However, these results hold true only for moderate-intensity damage cases. For high intensity damage, the optimal shape may not remain the same, and may vary, according to the severity of damage.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제1권1호
• /
• pp.87-94
• /
• 2001

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

• 전기학회논문지
• /
• 제57권1호
• /
• pp.40-45
• /
• 2008

This paper presents an optimal design of a permanent magnet actuator(PMA) using a parallel genetic algorithm. Dynamic characteristics of permanent magnet actuator model are analyzed by coupled electromagnetic-mechanical finite element method. Dynamic characteristics of PMA such as holding force, operating time, and peak current are obtained by no load test and compared with the analyzed results by coupled finite element method. The permanent magnet actuator model is optimized using a parallel genetic algorithm. Some design parameters of vertical length of permanent magnet, horizontal length of plunger, and depth of permanent magnet actuator are predefined for an optimal design of permanent magnet actuator model. Furthermore dynamic characteristics of the optimized permanent magnet actuator model are analyzed by coupled finite element method. A displacement of plunger, flowing current of the coil, force of plunger, and velocity of plunger of the optimized permanent magnet actuator model are compared with the results of a primary permanent magnet actuator model.

• The Journal of the Acoustical Society of Korea
• /
• 제25권1E호
• /
• pp.8-13
• /
• 2006

In this paper, an Optimized Ambisonic Panning Algorithm (OAPA) which reduces sound localization error, is proposed. In the conventional Ambisonic Panning Algorithm (APA), sound localization is usually different from the panning angle, especially when listeners are not in an ideal listening position, because of low signal separation among other channels. To overcome this problem, an OAPA using window functions is proposed. A proper window function can be verified, comprising of higher harmonic components than 2M+1 and improved DPC and channel separation. Analysis results demonstrate that the proposed method results in higher signal separation among other channels and lower sound localization errors than the conventional APA.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2004년도 학술대회지
• /
• pp.67-72
• /
• 2004

Many port states such as New Zealand, the USA, Australia and Canada have strict regulations to prevent ships which arrive in their port from discharging polluted ballast water which contain harmful aquatic organism and pathogens. They are notified that transfer of polluted ballast water can cause serious injury to public health and damage to property and environment. For this reason, they perceived that the ballast exchange in deep sea is the most effective method, together with submitting the ballast management plan which contains the effective exchange method, ballast system and safety consideration. In this study, we pursued both nautical engineering analysis and optimization of algorithm in order to generate the sequence of stability and rapidity. Heuristic Algorithm was chosen on the basis of optimality and applicability to a sequential exchange problem. We have built an optimized algorithm, for automatic exchange of ballast water, by redefining core elements of the $A^\ast$ algorithm, such as node, operator and evaluation function. Final version of the optimized algorithm has been applied to existing bulk carrier and the performance of the algorithm has been verified successfully.

• 한국해양공학회지
• /
• 제18권4호
• /
• pp.65-70
• /
• 2004

Many port states, such as New Zealand, U.S.A., Australia, and Canada, have strict regulations to prevent arriving ships from discharging polluted ballast water that contains harmful aquatic organisms and pathogens. They are notified that transfer of polluted ballast water can cause serious injury to public health and damage to property and environment. For this reason, ballast exchange in deep sea is perceived as the most effective method of emptying ballast water. The ballast management plan contains the effective exchange method, ballast system, and safety considerations. In this study, we pursued both nautical engineering analysis and optimization of the algorithm, in order to generate the sequence of stability and rapidity. A heuristic algorithm was chosen on the basis of optimality and applicability to a sequential exchange problem. We have built an optimized algorithm for the automatic exchange of ballast water, by redefining core elements of the A$\ast$ algorithm, such as node, operator, and evaluation function. The final version of the optimized algorithm has been applied to existing bulk carrier, and the performance of the algorithm has been successfully verified.

• International Journal of Internet, Broadcasting and Communication
• /
• 제8권1호
• /
• pp.42-52
• /
• 2016

In this paper, we propose the 16-bits optimization design of the ARIA block-cipher algorithm for embedded systems with 16-bits processors. The proposed design adopts 16-bits XOR operations and rotated shift operations as many as possible. Also, the proposed design extends 8-bits array variables into 16-bits array variables for faster chained matrix multiplication. In evaluation experiments, our design is compared to the previous 32-bits optimized design and 8-bits optimized design. Our 16-bits optimized design yields about 20% faster execution speed and about 28% smaller footprint than 32-bits optimized code. Also, our design yields about 91% faster execution speed with larger footprint than 8-bits optimized code.

• 대기
• /
• 제30권4호
• /
• pp.335-346
• /
• 2020

Three free parameters included in a cumulus parameterization are optimized by using micro-genetic algorithm for three precipitation cases occurred in the Korea Peninsula during the summer season in order to reduce biases in a regional model associated with the uncertainties of the parameters and thus to improve the predictability of precipitation. The first parameter is the one that determines the threshold in convective trigger condition. The second parameter is the one that determines boundary layer forcing in convective closure. Finally, the third parameter is the one used in calculating conversion parameter determining the fraction of condensate converted to convective precipitation. Optimized parameters reduce the occurrence of convections by suppressing the trigger of convection. The reduced convection occurrence decreases light precipitation but increases heavy precipitation. The sensitivity experiments are conducted to examine the effects of the optimized parameters on the predictability of precipitation. The predictability of precipitation is the best when the three optimized parameters are applied to the parameterization at the same time. The first parameter most dominantly affects the predictability of precipitation. Short-range forecasts for July 2018 are also conducted to statistically assess the precipitation predictability. It is found that the predictability of precipitation is consistently improved with the optimized parameters.