• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.580-585
• /
• 2009

This paper introduces GP(Genetic Programming) based corner detectors for an image processing. Various empirical algorithms have been studied to improve computational speed and accuracy including typical approaches, such as Harris and SUSAN. The these techniques are highly efficient, because properties of corner points are inspected and reflected into the algorithms. However these approaches are limited in discovering an innovative algorithm. In this study, we try to discover a more efficient technique by creating corner detector automatically using evolution of GP. The proposed method is compared to the existing corner detectors for test images.

• Journal of the Society of Naval Architects of Korea
• /
• v.43 no.6 s.150
• /
• pp.700-706
• /
• 2006

As development of information technology, companies stress the need of knowledge management. Companies construct ERP system including knowledge management. But, it is not easy to formalize knowledge in organization. They experience that constructing information system help knowledge management. Now, we focus on engineering knowledge. Because engineering data contains experts' experience and know-how in its own, engineering knowledge is a treasure house of knowledge. Korean shipyards are leader of world shipbuilding industry. They have accumulated a store of knowledge and data. But, they don't have data mining tool to utilize accumulated data. This paper treats development of data mining tools for the utilization of shipbuilding knowledge based on genetic programming(GP).

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.1
• /
• pp.1-11
• /
• 2014

In the initial design stage, the technology for estimating and managing the weight of a floating offshore structure, such as a FPSO (Floating, Production, Storage, and Off-loading unit) and an offshore wind turbine, has a close relationship with the basic performance and the price of the structure. In this study, using the genetic programming (GP), being used a lot in the approximate estimating model and etc., the weight estimation model of the floating offshore structure was studied. For this purpose, various data for estimating the weight of the floating offshore structure were collected through the literature survey, and then the genetic programming method for developing the weight estimation model was studied and implemented. Finally, to examine the applicability of the developed model, it was applied to examples of the weight estimation of a FPSO topsides and an offshore wind turbine. As a result, it was shown that the developed model can be applied the weight estimation process of the floating offshore structure at the early design stage.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.603-609
• /
• 2010

This paper introduces an objects recognition algorithm based on SURF(Speeded Up Robust Features) and GP(Genetic Programming) based gaits generation. Combining both methods, a recognition based intelligent walking for quadruped robots is proposed. The gait of quadruped robots is generated by means of symbolic regression for each joint trajectories using GP. A position and size of target object are recognized by SURF which enables high speed feature extraction, and then the distance to the object is calculated. Experiments for objects recognition and autonomous walking for quadruped robots are executed for ODE based Webots simulation and real robot.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1218-1227
• /
• 2004

Multi-domain engineering systems include electrical, mechanical, hydraulic, pneumatic, and thermal components, making it difficult to design a system because of their complexity and inter domain nature. In order to obtain an optimal design, a unified design approach for each domain and an automated search method are required. This paper suggests a method for automatically synthesizing designs for multi-domain systems using the combination of bond graph that is domain independent and genetic programming that is well recognized as a powerful tool for open-ended search. To investigate the effect of proposed approach, an eigenvalue design problem is tested for some sample target sets of eigenvalues with different embryos.

• Journal of Navigation and Port Research
• /
• v.26 no.2
• /
• pp.189-192
• /
• 2002

In Korea, most of small fishing vessels whose lengths are under 24m frequently cause maritime accidents due to flood and capsize. In this situation, however, there are no stability criteria and data for small fishing vessels. In this paper, the authors investigated data of 10 real ships which were built since 1990, and derived equations for evaluating ship's stability using Genetic Programming. Also, the validity of GM estimation using Genetic Programming was shown with comparison of GM value by GM value by foreign standards. More data of real ships are needed for the application of these theory to ship design process.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.12 no.6
• /
• pp.304-310
• /
• 2002

Novel charge trap type memory devices with reoxidized oxynitride gate dielectrics made by NO annealing and reoxidation process of initial oxide on substrate have been fabricated using 0.35 $\mu \textrm{m}$ retrograde twin well CMOS process. The feasibility for application as NVSM memory device and characteristics of traps have been investigated. For the fabrication of gate dielectric, initial oxide layer was grown by wet oxidation at $800^{\circ}C$ and it was reoxidized by wet oxidation at $800^{\circ}C$ after NO annealing to form the nitride layer for charge trap region for 30 minutes at $850^{\circ}C$. The programming conditions are possible in 11 V, 500 $\mu \textrm{s}$ for program and -13 V, 1ms for erase operation. The maximum memory window is 2.28 V. The retention is over 20 years in program state and about 28 hours in erase state, and the endurance is over $3 \times 10^3$P/E cycles. The lateral distributions of interface trap density and memory trap density have been determined by the single junction charge pumping technique. The maximum interface trap density and memory trap density are $4.5 \times 10^{10} \textrm{cm}^2$ and $3.7\times 10^{18}/\textrm{cm}^3$ respectively. After $10^3$ P/E cycles, interlace trap density increases to $2.3\times 10^{12} \textrm{cm}^2$ but memory charges decreases.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.117-127
• /
• 2001

The Main object of this research is directed to LG Oil company harbor in kwangyang-hang, where various ships ranging from 300 ton to 48000ton DWT use seven berths in the harbor. This harbor suffered from inefficient and unsafe management procedures since it is difficult to set guidelines for arrival and departure of ships according to the weather conditions and the current guidelines dose not offer clear basis of its implications. Therefore, it has long been suggested that these guidelines should be improved. This paper proposes a decision-support system, which can quantitatively decide the possibility of entry or departure on a harbor by analyzing the weather conditions (wind, current, and wave) and taking account of factors such as harbor characteristics, ship characteristics, weight condition, and operator characteristics. This system has been verified using 5$_{th}$ and 7$_{th}$ berth in Kwangyang-hang harbor. Machine learning technique using genetic programming(GP) is introduced to the system to quantitatively decide and produce results about the possibility of entry or arrival, and weighted linear associative memory (WLAM) method is also used to reduce the amount of calculation the GP has to perform. Group of additive genetic programming trees (GAGPT) is also used to improve learning performance by making it easy to find global optimum.mum.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2000.02a
• /
• pp.78-78
• /
• 2000

다결정 실리콘-게르마늄 (poly-SiGe)은 태양전지 개발에 있어서 중요한 물질이다. 우리는 소량의 Ge(x=0.05)으로부터 다량의 Ge(x=0.67)을 함유한 수소화된 비정질 실리콘-게르마늄 (a-SiGe:H) 박막의 고상결정화 과정을 ESR (electron spin resonance)방법으로 조사해보았다. 먼저 PECVD 방법으로 Corning 1737 glass 위에 a-Si1-xGex:H 박막을 증착시켰다. 증착가스는 SiH4, GeH4 가스를 썼으며, 기판온도는 20$0^{\circ}C$, r.f. 전력은 3W, 증착시 가스압력은 0.6 Torr 정도이었다. 증착된 a-SiGe:H 박막은 $600^{\circ}C$ N2 분위기에서 다시 가열되어 고상결정화 되었고, 결정화 정도는 XRD (111) peak의 세기로부터 구해졌다. ESR 측정은 상온 x-band 영역에서 수행되었다. 측정된 ESR스팩트럼은 두 개의 Gaussian 함수로써 Si dangling-bond와 Ge dangling-bond 신호로 분리되었다. 가열 초기의 a-SiGe:H 박막 결함들의 스핀밀도의 증가는 수소 이탈에 기인하고, 또 고상결정화 과정에서 결정화된 정도와 Ge-db 스핀밀도의 변화는 서로 깊은 상관관계가 있음을 알 수 있었다. 특히 Ge 함유량이 큰 박막 (x=0.21, 0.67)에서 뿐만 아니라 소량의 Ge이 함유된 박막(x=0.05)에서도 Ge dangling-bond가 Si dangliong-bond 보다 고상결정화 과정에서 더 중요한 역할을 한다는 것을 알수 있었다. 또한 초기 열처리시 Si-H, Ge-H 결합에서 H의 이탈로 인하여 나타나는 Si-dangling bond, Ge-dangling bond 스핀밀도의 최대 증가 시간은 x 값에 의존하였는데 이러한 결과는 x값에 의존하는 Si-H, Ge-H 해리에너리지로 설명되어 질 수 있다. 층의 두께가 500 미만인 커패시터의 경우에 TiN과 Si3N4 의 계면에서 형성되는 슬릿형 공동(slit-like void)에 의해 커패시터의 유전특성이 파괴된다는 사실을 알게 되었으며, 이러한 슬릿형 공동은 제조 공정 중 재료에 따른 열팽창 계수와 탄성 계수 등의 차이에 의해 형성된 잔류응력 상태가 유전막을 기준으로 압축응력에서 인장 응력으로 바뀌는 분포에 기인하였다는 사실을 확인하였다.SiO2 막을 약화시켜 절연막의 두께가 두꺼워졌음에도 기존의 SiO2 절연막의 절연 파괴 전압 및 누설 전류오 비교되는 특성을 가졌다. 이중막을 구성하고 있는 안티퓨즈의 ON-저항이 단일막과 비교해 비슷한 것을 볼 수 잇는데, 그 이유는 TiO2에 포함된 Ti가 필라멘트에 포함되어 있어 필라멘트의 저항을 감소시켰기 때문으로 사료된다. 결국 이중막을 구성시 ON-저항 증가에 의한 속도 저하 요인은 없다고 할 수 있다. 5V의 절연파괴 시간을 측정한느 TDDB 테스트 결과 1.1$\times$103 year로 기대수치인 수십 년보다 높아 제안된 안티퓨즈의 신뢰성을 확보 할 수 있었다. 제안된 안티퓨즈의 이중 절연막의 두께는 250 이고 프로그래밍 전압은 9.0V이고, 약 65$\Omega$의 on 저항을 얻을수 있었다.보았다.다.다양한 기능을 가진 신소재 제조에 있다. 또한 경제적인 측면에서도 고부가 가치의 제품 개발에 따른 새로운 수요 창출과 수익률 향상, 기존의 기능성 안료를 나노(nano)화하여 나노 입자를 제조, 기존의 기능성 안료에 대한 비용 절감 효과등을 유도 할 수 있다. 역시 기술적인 측면에서도 특수소재 개발에 있어 최적의 나노 입자 제어기술 개발 및 나노입자를 기능성 소재로 사용하여 새로운 제품의 제조와 고압 기상 분사기술의 최적화에 의한 기능성 나노 입자 제조 기술을 확립하고 2차 오염 발생원인 유기계 항균제를 무기계 항균제로 대체할 수 있다. 이와 더불

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.477-482
• /
• 2015

Linear regressions and evolutionary nonlinear regression based compensation techniques for the short-range prediction of wind speed are investigated. Development of an efficient MOS(Model Output Statistics) is necessary to correct systematic errors of the model, but a linear regression based MOS is hard to manage an irregular nature of weather prediction. In order to solve the problem, a nonlinear and symbolic regression method using GP(Genetic Programming) is suggested for a development of MOS for wind speed prediction. The proposed method is compared to various linear regression methods for prediction of wind speed. Also, statistical analysis of distribution for UM elements for each method is executed. experiments are performed for KLAPS(Korea Local Analysis and Prediction System) re-analysis data from 2007 to 2013 year for Jeju Island and Busan area in South Korea.