• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.294-299
• /
• 2012

This paper suggests a modeling technique for shape and volume prediction of fishes to cut them with identical weights for group meals. The measurement and prediction of frozen fishes for group meals are very difficult because they have a bending deformation occurring at frozen stage and a hollow by eliminating the internals. Besides there exist twinkles problem of surface caused by freeze and variable weights by moisture conditions. Therefore a complex estimation algorithm is necessary to predict the shape and volume prediction of fishes exactly. Hollow prediction, pattern classification and modeling for tails using neural network, integration based volume prediction algorithm are suggested and combined to solve those problems. In order to validate the proposed method, the experiments of 3-dimensional measurement, volume prediction and fish cutting for spanish mackerel, saury, and mackerel are executed. The cutting experiments for real fish are executed.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.7 no.2
• /
• pp.115-124
• /
• 2009

Cryogenic cutting technology is one of the most suitable technologies for dismantling nuclear facilities due to the fact that a secondary waste is not generated during the cutting process. In this paper, the feasibility of cryogenic cutting technology was investigated by using a computer simulation. In the computer simulation, a hybrid method combined with the SPH (smoothed particle hydrodynamics) method and the FE (finite element) method was used. And also, a penetration depth equation, for the design of the cryogenic cutting system, was used and the design variables and operation conditions to cut a 10 mm thickness for steel were determined. Finally, the main components of the cryogenic cutting system were manufactures on the basis of the obtained design variables and operation conditions.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.595-602
• /
• 2007

This paper proposes a method that discriminates signal peptide and predicts the cleavage site of the secretory proteins cleaved by the signal peptidase I. The preprocessing stage uses hydrophobicity scales of amino acids in order to predict the presence of signal sequence and the cleavage site. The preprocessing enhances the performance of the prediction method by eliminating the non-secretory proteins in the early stage of prediction. for the effective use of support vector machine for the signal sequence prediction, the biologically relevant distance between the amino acid sequences is defined by using the hydrophobicity and substitution matrix; the hydrophobicity can be used to Predict the location of amino acid in a cell and the substitution matrix represents the evolutionary relationships of amino acids. The proposed method showed 98.9% discrimination rates from signal sequences and 88% correct rate of the cleavage site prediction on Swiss-Prot release 50 protein database using the 5-fold-cross-validation. In the comparison tests, the proposed method has performed significantly better than other prediction methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10b
• /
• pp.1581-1584
• /
• 2001

본 논문에서는 무선 셀룰러 망에서 호 수락 제어와 대역폭 예약을 위한 효율적인 기법을 제안한다. 제안된 방식에서는 각 셀에서의 핸드오프 호 절판확률을 줄이기 위해서 무선단말 사용자의 이동패턴에 대한 통계적인 정보를 이용하여 사용자에 대한 이동성을 예측하며, 이는 데이터 압축기법을 토대로 하는 허프만 알고리즘을 통해 최적화된다[1]. 제안된 이동성 예측 기법을 통해 무선단말 사용자가 이동하게 될 셀들에 대해서 핸드오프 호를 위한 대역폭이 예약되며, 호 수락 임계치를 적절하게 조절함으로써 핸드오프 호 절단률을 최소화하고, 자원이용률을 최대화시킬 수 있다. 제안된 방식이 기존의 방식에 비해 성능이 향상될 수 있는 새로운 기법을 제시한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04a
• /
• pp.496-498
• /
• 2001

무선 ATM에서 사용하는 고주파 대역에서 채널의 효율성을 유지하기 위해서는 셀의 반경이 작아지게 되고 이는 단말의 이동시 빈번한 핸드오버를 야기시킨다. 이는 QoS 저하를 야기하거나, 핸드오버를 위한 채널이 부족하면 호가 절단되는 현상을 야기하게 된다. 이를 방지하기 위하여 사용자의 이동 패턴을 고려하여 이동 단말의 이동 경로를 예측하고, 이 패턴에 따라 핸드오버에 필요한 채널을 예약하여 효율적인 채널 할당이 가능한 기법이 제안되었다. 본 논문에서는 컴퓨터 시뮬레이션을 사용하여 이러한 이동성 예측 알고리즘의 성능을 비교 및 분석하였다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.16 no.3
• /
• pp.261-269
• /
• 2003

Steel bridges, which have been damaged by load and corrosion, need repair or strengthening. In general, before the repair welding procedure, cutting procedure carry out. Therefore, the investigating of the behavior of stress generated by cutting is so important for safety of structure. Residual stress produced by gas cutting was analyzed using 2D and 3D thermal elasto plastic FEM. According to the results, the magnitude of temperature was analyzed by 2D FEM is smaller than that was analyzed using the 3D FEM program at the start and end edge of flange. And the magnitude and distribution of residual stress of perpendicular to the cutting line was analyzed by the 2D FEM program was similar to that was analyzed by the 3D FEM program. Therefore, it is possible to predict of cutting stress by 2D and 3D FEM.

• Journal of Navigation and Port Research
• /
• v.37 no.1
• /
• pp.1-7
• /
• 2013

In this paper the developed prediction technique of wave-making resistance performance for a ship attached with a vertical blade had been verified. Numerical analysis program as a prediction technique had been developed using the Rankine source panel method and the vortex lattice method(VLM). The nonlinearity of the free surface conditions was fully taken into account using the iterative method and the trim and the sinkage of the ship were also considered in the numerical analysis program. Panel cutting method was applied to get hull surface panels. Numerical computations were carried out for a 4000TEU container carrier and the vertical blade was attached 6 different locations astern. To investigate the validity of the numerical analysis program the commercial viscous flow field analysis program FLUENT was used to obtain the viscous flow field around the ship and the model test was performed. The model test results were compared with the numerical analysis results.

• The KIPS Transactions:PartD
• /
• v.10D no.2
• /
• pp.261-266
• /
• 2003

A protein, which is a linear polymer of amino acids, is one of the most important bio-molecules composing biological structures and regulating bio-chemical reactions. Since the characteristics and functions of proteins are determined by their amino acid sequences in principle, protein sequence determination is the starting point of protein function study. This paper proposes a protein sequence prediction method based on data mining techniques, which can overcome the limitation of previous bio-chemical sequencing methods. After applying multiple proteases to acquire overlapped protein fragments, we can identify candidate fragment sequences by comparing fragment mass values with peptide databases. We propose a method to construct multi-partite graph and search maximal paths to determine the protein sequence by assembling proper candidate sequences. In addition, experimental results based on the SWISS-PROT database showing the validity of the proposed method is presented.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.100-100
• /
• 2022

일반적으로 유체와 구조물간 상호작용의 수리동역학적 모의에서는 벽경계조건을 통하여 유동에 대한 구조물의 영향이 반영된다. 하지만 도심지에서 발생한 홍수를 예측하려는 경우 이러한 방법으로는 밀집한 구조물들 사이에 형성된 좁은 길들로 인하여 세밀한 격자망을 요하여 큰 계산량을 유발하고 빠른 예측 속도를 기대할 수 없게 한다. 최근 이러한 문제를 극복하기 위해 성긴 격자망에서도 구조물의 유체에 대한 영향을 반영할 수 있도록 하는 방법들이 큰 관심을 받고 있다. 그 중에서도 다공성 천수방정식은 벽경계조건 대신 다공도(posority)의 개념을 이용한 모형으로 도시범람모의에 있어 계산량과 정확도를 가장 적절하게 타협한 모형으로 보고되고 있다. 이러한 흐름에 맞추어 본 연구는 다공도 천수방정식을 해석하는 수치 기법을 개발하였고, 여기에 최근 쌍곡선계 방정식의 수치적 연구들에서 소개된 주요 특징들이 반영되도록 설계하였다. 우선, WENO 기법과 Runge-Kutaa 기법을 통하여 공간과 시간에 대한 고차 정확도를 만족시켰다. 이 때, 재구성 변수와 알고리즘를 새롭게 제시하여 정상흐름조건에 대한 플럭스항과 생성·소멸항간 절단오차에 의한 비물리적인 흐름생성을 억제하였다. 또한, 수치모의 중 음수심의 발생으로 인하여 수치모형이 불안정해지는 현상을 막기 위해, 양-보존성 제한자를 구축하였다. 마지막으로 도심지에서 즐비한 인위적인 구조물에 의해 나타나는 지형적인 불연속의 효과를 적절하게 반영할수 있도록 정상파 재구축의 단계를 구축하여 수치 기법에 반영하였다. 이렇게 구성된 수치기법은 리만문제의 해석해에 기반하여 기존의 주요 연구들의 결과와 비교되었고, 그 결과 본 연구의 방법이 정확성, 수렴성, 안전성의 측면에서 가장 우수함을 수치적으로 증명하였다.