• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.809-817
• /
• 2020

In the design and development process of Small-Sat power distribution and transmission module, the stability of dynamic resources was evaluated by a deep learning algorithm. The requirements for the stability evaluation consisted of the power distribution function of the power distribution module and demand module to the SAR radar in Small-Sat. To verify the performance of the switching power components constituting the power module PDM, the reliability was verified using a dynamic neural network. The adoption material of deep learning for reliability verification is the power distribution function of the payload to the power supplied from the small satellite main body. Modeling targets for verifying the performance of this function are output voltage (slew rate control), voltage error, and load power characteristics. First, to this end, the Coefficient Structure area was defined by modeling, and PCB modules were fabricated to compare stability and reliability. Second, Levenberg-Marquare based Two-Way NARX neural network Sigmoid Transfer was used as a deep learning algorithm.

• Journal of Animal Science and Technology
• /
• v.65 no.2
• /
• pp.365-376
• /
• 2023

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

• Journal of the Society of Naval Architects of Korea
• /
• v.54 no.3
• /
• pp.187-195
• /
• 2017

The operation planning of transports used to move blocks is the one of key factors. Furthermore, reducing the running time through the effective plan contributes to pulling forward the whole logistic process of the shipyard and substantially saving the fuel consumption of itself as well. The past researches of the transporter focused on finding only the shortest distances, so called, Manhattan distance. However, these searching approaches cannot help having the significant difference in the real operational time and distance with the minimum cost approach which considers the speed retardation for turns or safety at the intersection. This study suggests the noble transporter's operational model which could take account of the consuming operational time around the crossroads on the shipyard. Concretely, the proposed method guarantees the minimization of transporters' turns and passage number which are huge burdensome to the operation time and the whole planning of transports with the given period. Resultantly, this paper is willing to explain the appropriateness of our approach, compared with the previous ones.

• Korean Journal of Optics and Photonics
• /
• v.14 no.4
• /
• pp.377-382
• /
• 2003

We propose a new optical watermarking method, which can protect the copyright of digital data, using a binary phase hologram and a Mach-Zehnder interferometer. Using a simulated annealing algorithm, the binary phase hologram of the mark image to be hidden is designed. We obtained a watermarked image by linearly superposing the hologram, which is the watermark, in the original image. The extraction processing of the mark image from the watermarked image is achieved by placing the phase-modulated watermarked image on a LCD in one path and the phase-modulated original image on another LCD in the other path in the Mach-Zehnder interferometer. The mark image was obtained by inverse Fourier transforming the phase modulated interference intensity. We confirmed that the proposed method is robust for the cropped images through computer simulation, and we implemented it optically using LCDs which are phase modulation devices.

• Industrial Engineering and Management Systems
• /
• v.10 no.2
• /
• pp.134-139
• /
• 2011

The problem of scheduling in permutation flowshops has been extensively investigated by many researchers. Recently, attempts are being made to consider more than one objective simultaneously and develop algorithms to obtain a set of Pareto-optimal solutions. Varadharajan et al. (2005) presented a multi-objective simulated-annealing algorithm (MOSA) for the problem of permutation-flowshop scheduling with the objectives of minimizing the makespan and the total flowtime of jobs. The MOSA uses two initial sequences obtained using heuristics, and seeks to obtain non-dominated solutions through the implementation of a probability function, which probabilistically selects the objective of minimizing either the makespan or the total flowtime of jobs. In this paper, the same problem of heuristically developing non-dominated sequences is considered. We propose an effective heuristics based on simulated annealing (SA), in which the weighted sum of the makespan and the total flowtime is used. The essences of the heuristics are in selecting the initial sequence, setting the weight and generating a solution in the search process. Using a benchmark problem provided by Taillard (1993), which was used in the MOSA, these conditions are extracted in a large-scale experiment. The non-dominated sets obtained from the existing algorithms and the proposed heuristics are compared. It was found that the proposed heuristics drastically improved the performance of finding the non-dominated frontier.

• Journal of Ocean Engineering and Technology
• /
• v.17 no.6
• /
• pp.38-46
• /
• 2003

Aim of this article is to propose Micro-Genetic Simulated Annealing (${\mu}GSA$) as a hybrid metaheuristics approach to find the global optimum of nonlinear optimisation problems. This approach combines the features of modern metaheuristics such as micro-genetic algorithm (${\mu}GAs$) and simulated annealing (SA) with the general robustness of parallel exploration and asymptotic convergence, respectively. Therefore, ${\mu}GSA$ approach can help in avoiding the premature convergence and can search for better global solution, because of its wide spread applicability, global perspective and inherent parallelism. For the superior performance of the ${\mu}GSA$, the five well-know benchmark test functions that were tested and compared with the two global optimisation approaches: scatter search (SS) and hybrid scatter genetic tabu (HSGT) approach. A practical application to structural sandwich panel is also examined by optimism the weight function. From the simulation results, it has been concluded that the proposed ${\mu}GSA$ approach is an effective optimisation tool for soloing continuous nonlinear global optimisation problems in suitable computational time frame.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1137-1142
• /
• 2013

FBG sensors are mainly used to measure strain and temperature of structures. In this paper, an interrogator of FBG sensors is developed and implemented to measure the crack of structures using FPGA and DSP. Developed interrogator consists of an optical source, an optical circulator, an optical grating and a CCD sensor and controller. The spectrum of the reflected light from the FBG sensor is analyzed and peak wavelength is detected. Next, strain of structure can be measured using shift of peak wavelength. Centroid algorithm and Gaussian fitting which are mainly applied to detect peak wavelength of the interrogator are compared in this paper. As a result of experiment, Gaussian fitting is suitable for a developed interrogator.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2166-2176
• /
• 2017

Electricity price prediction plays a crucial part in making the schedule and managing the risk to the competitive electricity market participants. However, it is a difficult and challenging task owing to the characteristics of the nonlinearity, non-stationarity and uncertainty of the price series. This study proposes a hybrid improved strategy which incorporates data preprocessor components and a forecasting engine component to enhance the forecasting accuracy of the electricity price. In the developed forecasting procedure, the Seasonal Adjustment (SA) method and the Ensemble Empirical Mode Decomposition (EEMD) technique are synthesized as the data preprocessing component; the Coupled Simulated Annealing (CSA) optimization method and the Least Square Support Vector Regression (LSSVR) algorithm construct the prediction engine. The proposed hybrid approach is verified with electricity price data sampled from the power market of New South Wales in Australia. The simulation outcome manifests that the proposed hybrid approach obtains the observable improvement in the forecasting accuracy compared with other approaches, which suggests that the proposed combinational approach occupies preferable predication ability and enough precision.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.6
• /
• pp.133-149
• /
• 2017

As cities face increasing problems such as aging, environmental pollution and growth limits, we have been trying to incorporate sustainability into urban planning and related policies. However, it is very difficult to generate a 'sustainable spatial plans' because there are trade-offs among environmental, society, and economic values. This is a kind of non-linear problem, and has limitations to be solved by existing qualitative expert knowledge. Many researches from abroad have used the meta heuristic optimization algorithms such as Genetic Algorithms(GAs), Simulated Annealing(SA), Ant Colony Optimization(ACO) and so on to synthesize competing values in spaces. GAs is the most frequently applied theory and have been known to produce 'good-enough plans' in a reasonable time. Therefore we collected the research on 'spatial optimization model based GAs' and analyzed in terms of 'study area', 'optimization objective', 'fitness function', and 'effectiveness/efficiency'. We expect the results of this study can suggest that 'what problems the spatial optimization model can be applied to' and 'linkage possibility with existing planning methodology'.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.423-426
• /
• 2013

본 연구에서는 임분 단위에서 산림의 이산화탄소 흡수 및 저장 기능을 최적화 할 수 있는 최적의 산림시업체계를 도출하고자하였고, 이를 위해 임분 생장모델과 Simulated Annealing 휴리스틱 기법을 적용하여 임분탄소 최적화 프로그램을 개발하였다. 휴리스틱 알고리즘에서 최적해를 찾기 위해 반복 실행 되는 과정에서 더 이상 최적해을 찾지 못하고 목표 값이 어떤 일정한 값(Local Optimum)에 계속 머무는 현상을 해결하기 위해 임계치를 적용하며, SA 휴리스틱 기법에서는 열균형테스트를 이용하고 있다. 개발된 프로그램을 이용하여 3가지 산림 시업 시나리오에 대한 비교 분석을 실시하기 위해 프로그램을 실행한 결과, 목재수확량의 경우 목재수확량을 최대를 목표로 한 대안이 3개 시나리오 가운데 목재수확량이 가장 높은 것으로 나타났으며, 또한 탄소저장량에서도 탄소저장량을 최적화한 대안이가 탄소저장량이 가장 높은 것으로 나타나 프로그램이 목적에 맞게 개발된 것으로 판단됐다. 또한 열균형 테스트의 온도저감율을 조정하여 프로그램을 반복실행하여 온도저감율이 프로그램 실행 시에 미치는 영향을 분석한 결과 온도저감율에 따라 출력되는 목적함수의 최적값과 프로그램 반복횟수가 영향을 받는 것으로 나타나 프로그램 실행을 최적으로 하기위해 온도 저감율의 파라미터 값을 0.1로 설정하였다.