• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.8
• /
• pp.1423-1443
• /
• 2011

Background compensation plays an important role in detecting and isolating object motion in visual tracking. Here, we propose a Genetic Hough Transform, which combines the Hough Transform and Genetic Algorithm, as a method for eliminating background motion. Our method can handle cases in which the background may contain only a few, if any, feature points. These points can be used to estimate the motion between two successive frames. In addition to dealing with featureless backgrounds, our method can successfully handle motion blur. Experimental comparisons of the results obtained using the proposed method with other methods show that the proposed approach yields a satisfactory estimate of background motion.

• Advances in Computational Design
• /
• v.1 no.3
• /
• pp.275-296
• /
• 2016

This article presents an adaptive directional differential evolution (ADDE) algorithm and its application in solving discrete sizing truss optimization problems. The algorithm is featured by a new self-adaptation approach and a simple directional strategy. In the adaptation approach, the mutation operator is adjusted in accordance with the change of population diversity, which can well balance between global exploration and local exploitation as well as locate the promising solutions. The directional strategy is based on the order relation between two difference solutions chosen for mutation and can bias the search direction for increasing the possibility of finding improved solutions. In addition, a new scaling factor is introduced as a vector of uniform random variables to maintain the diversity without crossover operation. Numerical results show that the optimal solutions of ADDE are as good as or better than those from some modern metaheuristics in the literature, while ADDE often uses fewer structural analyses.

• Asian Journal of Innovation and Policy
• /
• v.7 no.3
• /
• pp.411-437
• /
• 2018

This paper articulates the STI strategy development principles and methodologies that have been elaborated through iterative processes of STI strategy development cases for the past ten years. The consultation cases include poverty traps in Nepal and Laos, African health challenges in Nigeria and Tanzania, and ASEAN global challenges in Indonesian Water, Vietnamese Green Energy, and Filipino Food, in partnership with some multilateral agencies.The iterative elaboration process has continued with consultation activities on Thailand and on Cambodia, Laos and Myanmar in planning partnership with Thailand. The principles were originally conceptualized from the benchmarking process of the Korean STI development experience. They were further incorporated as methodologies with which relevant planning bodies are guided to address individual and regional challenges through science, technology and innovation strategies. The methodologies are strong in providing plausible holistic perspective scenarios by which various stakeholders can be engaged in the planning and implementation process. But it is heuristic in nature and can be learned only through on-the-job training process. This is the structural limitation for scaling up.

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2001.06a
• /
• pp.151-152
• /
• 2001

A common problem of the model simulations of the land surface - atmosphere interaction is to choose the appropriate spatial scale and resolution at which the simulations are to be performed. The accuracy of energy and water exchange predictions between the land surface and the atmosphere in regional and global scale atmospheric models is mainly influenced by: model simplifications applied to describe the spatial heterogeneity of land surface properties within individual grid cells; ignoring the variability of sub-grid properties (e.g. relief, vegetation, soils), and; lacks of necessary input meteorological and biophysical data.(omitted)

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.251-256
• /
• 2019

In this paper we proposed system and algorithm to recognize hand gestures based on the millimeter wave that is in 65GHz bandwidth. The proposed system is composed of millimeter wave radar board, analog to data conversion and data capture board and notebook to perform gesture recognition algorithms. As feature vectors in proposed algorithm. we used global and local zernike moment descriptor which are robust to distort by rotation of scaling of 2D data. As Experimental result, performance of the proposed algorithm is evaluated and compared with those of algorithms using single global or local zernike descriptor as feature vectors. In analysis of confusion matrix of algorithms, the proposed algorithm shows the better performance in comparison of precision, accuracy and sensitivity, subsequently total performance index of our method is 95.6% comparing with another two mehods in 88.4% and 84%.

• Journal of Korea Society of Waste Management
• /
• v.34 no.5
• /
• pp.518-527
• /
• 2017

The development of renewable energy is currently strongly required to address environmental problems such as global warming. In particular, biomass is highlighted due to its advantages. When using biomass as an energy source, the conversion process is essential. Fast pyrolysis, which is a thermochemical conversion method, is a known method of producing bio-oil. Therefore, various studies were conducted with fast pyrolysis. Most studies were conducted under a lab-scale process. Hence, scaling up is required for commercialization. However, it is difficult to find studies that address the process analysis, even though this is essential for developing a scaled-up plant. Hence, the present study carries out the process analysis of biomass pyrolysis. The fast pyrolysis system includes a biomass feeder, fast pyrolyzer, cyclone, condenser, and electrostatic precipitator (ESP). A two-stage, semi-global reaction mechanism was applied to simulate the fast pyrolysis reaction and a circulating fluidized bed reactor was selected as the fast pyrolyzer. All the equipment in the process was modeled based on heat and mass balance equations. In this study, process analysis was conducted with various reaction temperatures and residence times. The two-stage, semi-global reaction mechanism for circulating fluidized-bed reactor can be applied to simulate a scaled-up plant.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.511-516
• /
• 2002

The neural networks may have problem such that the amount of calculation for the network learning goes too big according to the dimension of the dimension. To overcome this problem, the wavelet neural networks(WNN) which use the orthogonal basis function in the hidden node are proposed. One can compose wavelet functions as activation functions in the WNN by determining the scale and center of wavelet function. In this paper, when we compose the WNN using wavelet functions, we set a single scale function as a node function together. We intend that one scale function approximates the target function roughly, the other wavelet functions approximate it finely During the determination of the parameters, the wavelet functions can be determined by the global search for solutions suitable for the suggested problem using the genetic algorithm and finally, we use the back-propagation algorithm in the learning of the weights.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.16 no.1
• /
• pp.29-36
• /
• 2008

In this paper, the orbital forming analysis of an automotive hub bearing was studied to predict forming performances using the explicit finite element method. To find an efficient solution technique for the orbital forming, axisymmetric finite element models and 3D solid element models were solved and numerically compared. The time scaling and mass scaling techniques were introduced to reduce the excessive computational time caused by small element size in case of the explicit finite element method. It was found from the numerical simulations on the orbital forming that the axisymmetric element models showed the similar results to the 3D solid element models in forming loads whereas the deformations at the inner race of bearing were quite different. Finally the strains at the inner race of bearing and the forming forces to the peen were measured for the same product of the numerical model by test, and were compared with the 3D solid element results. It was founded that the test results were in good agreements with the numerical ones.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.6
• /
• pp.47-52
• /
• 2002

The wavelet functions are originated from scaling functions and can be used as activation function in the hidden node of the network by deciding two parameters such as scale and center. In this paper, we would like to propose the mixed structure. When we compose the WNN using wavelet functions, we propose to set a single scale function as a node function together. The properties of the proposed structure is that while one scale function approximates the target function roughly, the other wavelet functions approximate it finely. During the determination of the parameters, the wavelet functions can be determined by the global search algorithm such as genetic algorithm to be suitable for the suggested problem. Finally, we use the back-propagation algorithm in the learning of the weights.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.3
• /
• pp.275-282
• /
• 2010

The effect of swirl flow on NOx in a nonpremixed turbulent hydrogen jet with coaxial air was studied. The swirl vane angle was varied from $30^{\circ}$ to $90^{\circ}$. The fuel jet air velocity and coaxial air velocity were varied in an attached flame region as $u_F=85{\sim}160m/s$ and $u_A=7{\sim}14m/s$. The objective of the current study was to analyze the characteristics of nitrous oxide emission in a swirl flow and to propose a new parameter for EINOx scaling. The experimental results show that EINOx decreases with the swirl vane angle and increased with flame length. Further, EINOx scaling factors can be determined by considering the effective diameter ($d_{F,eff}$) in a far field concept. The EINOx increased in proportion to the flame residence time (${\sim}{\tau_R}^{1/2.8}$) and the global strain rate (${\sim}{S_G}^{1/2.8}$).