• 한국지능시스템학회논문지
• /
• 제18권5호
• /
• pp.712-717
• /
• 2008

군집 로봇시스템에서 개개의 로봇은 스스로 주위의 환경과 자신의 상태를 스스로 판단하여 행동하고, 필요에 따라서는 다른 로봇과 협조를 통하여 어떤 주어진 일을 수행할 수 있어야 한다. 따라서 개개의 로봇은 동적으로 변화하는 환경에 잘 적응할 수 있는 학습과 진화능력을 갖는 것이 필수적이다. 본 논문에서는 구조적 위험 최소화를 기반으로 한 SVM을 이용 한 강화학습과 분산유전알고리즘을 이용한 새로운 자율이동로봇의 행동학습 및 진화방법을 제안한다. 또한 개개의 로봇이 통신을 통하여 염색체를 교환하는 분산유전알고리즘은 각기 다른 환경에서 학습한 우수한 염색체로부터 자신의 능력을 향상시킨다. 특히 본 논문에서는 진화의 성능을 향상시키기 위하여 SVM을 기반으로 한 강화학습의 특성을 이용한 선택 교배 방법을 채택하였다.

• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.279-284
• /
• 2009

군집 로봇시스템에서 개개의 로봇은 스스로 주위의 환경과 자신의 상태를 스스로 판단하여 행동하고, 필요에 따라서는 다른 로봇과 협조를 통하여 어떤 주어진 일을 수행할 수 있어야 한다. 따라서 개개의 로봇은 동적으로 변화하는 환경에 잘 적응할 수 있는 학습과 진화능력을 갖는 것이 필수적이다. 본 논문에서는 SVM을 여러 개 이용한 강화학습과 분산유전알고리즘을 이용한 새로운 자율이동로봇의 행동학습 및 진화학습을 제안한다. 또한 개개의 로봇이 통신을 통하여 염색체를 교환하는 분산유전알고리즘은 각기 다른 환경에서 학습한 우수한 염색체로부터 자신의 능력을 향상시킨다. 특히 본 논문에서는 진화의 성능을 향상시키기 위하여 Cascade SVM을 기반으로 한 강화학습의 특성을 이용한 선택 교배방법을 채택하였다.

• ETRI Journal
• /
• 제30권6호
• /
• pp.799-806
• /
• 2008

In this paper, a new design for an error correcting code (ECC) is proposed. The design is aimed to build an ECC circuitry with minimal power consumption. The genetic algorithm equipped with the symbiotic mechanism is used to design a power-efficient ECC which provides single-error correction and double-error detection (SEC-DED). We formulate the selection of the parity check matrix into a collection of individual and specialized optimization problems and propose a symbiotic evolution method to search for an ECC with minimal power consumption. Finally, we conduct simulations to demonstrate the effectiveness of the proposed method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 B
• /
• pp.577-579
• /
• 1992

A new algorithm, which combines the Evolution Strategy and the Simplex method, is proposed for the detection of magnetic body utilizing the disturbance of magnetic fields. Although the detection problem of magnetic body which belongs to the inverse problem may have many local minima, the global optimum point was found by introducing the Evolution Strategy. And the convergency rate was enhanced by introducing the Simplex method. Through the numerical examples, the applicability and usefulness of the proposed algorithm are proved.

• Structural Monitoring and Maintenance
• /
• 제1권4호
• /
• pp.427-449
• /
• 2014

A hybrid optimization method for the identification of state-space models is presented in this study. Hybridization is succeeded by combining the advantages of deterministic and stochastic algorithms in a superior scheme that promises faster convergence rate and reliability in the search for the global optimum. The proposed hybrid algorithm is developed by replacing the original stochastic mutation operator of Evolution Strategies (ES) by the Levenberg-Marquardt (LM) quasi-Newton algorithm. This substitution results in a scheme where the entire population cloud is involved in the search for the global optimum, while single individuals are involved in the local search, undertaken by the LM method. The novel hybrid identification framework is assessed through the Monte Carlo analysis of a simulated system and an experimental case study on a shear frame structure. Comparisons to subspace identification, as well as to conventional, self-adaptive ES provide significant indication of superior performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.531-533
• /
• 1997

PI(proportional-integral) controller has been extensively used in the industrial field. But in practicle case, it is difficult to tune PI gains. Evolution Strategy(ES) is used as an effective search algorithm in optimization programs. In this paper we proposed a PI controller for Spot welder system using ES with varying search space. ES with varying search space which depends on fitness values at each generation is used to tune PI control parameters. Simulation results show the proposed algorithm has accurate and robust performance with effective search ability.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 D
• /
• pp.781-783
• /
• 1997

Genetic Algorithm is a kind of an evolution programming based on natural evolution principle. It applied to probabilistic searching, machine learning and optimization, and many good results were reported. Generator maintenance scheduling is an optimization Problem with constraints. This paper applied a genetic algorithm to generator maintenance scheduling problem and tested on sample systems. The results are compared with heuristic method and branch-and-bound method.

• Nuclear Engineering and Technology
• /
• 제32권2호
• /
• pp.169-179
• /
• 2000

A detailed numerical analysis of the evolution of thermal stratification in a curved piping system in a nuclear power plant is performed. A finite volume based thermal-hydraulic computer code has been developed employing a body-fitted, non-orthogonal curvilinear coordinate for this purpose. The cell-centered, non-staggered grid arrangement is adopted and the resulting checkerboard pressure oscillation is prevented by the application of momentum interpolation method. The SIMPLE algorithm is employed for the pressure and velocity coupling, and the convection terms are approximated by a higher-order bounded scheme. The thermal-hydraulic computer code developed in the present study has been applied to the analysis of thermal stratification in a curved duct and some of the predicted results are compared with the available experimental data. It is shown that the predicted results agree fairly well with the experimental measurements and the transient formation of thermal stratification in a curved duct is also well predicted.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.16-22
• /
• 2023

Enhanced radio access technologies (RAT) are deployed in Next Generation Convergence Networks by the service providers so as to satisfy the basic requirements of end-users for e.g. QoS. Whenever the available resources are being shared simultaneously and dynamically by multiple users or distribution of allocated channels randomly, the deficiency of spectral resources and dynamic behavior of Network traffic in real time Networking, we may have problem. In order to evaluate the performance of our proposed algorithm, computer simulation has been performed on NS-2 simulator and a comparison with the existing algorithms has been made.

• ETRI Journal
• /
• 제45권6호
• /
• pp.939-951
• /
• 2023

It is critical to estimate the location using only Long-Term Evolution (LTE) and Wi-Fi information gathered by the user's smartphone and deployable for emergency rescue, regardless of whether the Global Positioning System is received. In this research, we used a vehicle to gather LTE and Wi-Fi wireless signals over a large area for an extended period of time. After that, we used the learning technique to create a positioning database that included both collection and noncollection points. We presented a two-step positioning algorithm that utilizes coarse localization to discover a rough location in a wide area rapidly and fine localization to estimate a particular location based on the coarse position. We confirmed our technology utilizing different sorts of devices in four regional types that are generally encountered: dense urban, urban, suburban, and rural. Results presented that our algorithm can satisfactorily achieve the target accuracy necessary in emergency rescue circumstances.