• 통합자연과학논문집
• /
• 제3권1호
• /
• pp.49-53
• /
• 2010

Molecular docking is a critical event which mostly forms Van der waals complex in molecular recognition. Since the majority of developed drugs are small molecules, docking them into proteins has been a prime concern in drug discovery community. Since the binding pose space is too vast to cover completely, many search algorithms such as genetic algorithm, Monte Carlo, simulated annealing, distance geometry have been developed. Proper evaluation of the quality of binding is an essential problem. Scoring functions derived from force fields handle the ligand binding prediction with the use of potential energies and sometimes in combination with solvation and entropy contributions. Knowledge-based scoring functions are based on atom pair potentials derived from structural databases. Forces and potentials are collected from known protein-ligand complexes to get a score for their binding affinities (e.g. PME). Empirical scoring functions are derived from training sets of protein-ligand complexes with determined affinity data. Because non of any single scoring function performs generally better than others, some other approaches have been tried. Although numerous scoring functions have been developed to locate the correct binding poses, it still remains a major hurdle to derive an accurate scoring function for general targets. Recently, consensus scoring functions and target specific scoring functions have been studied to overcome the current limitations.

• Journal of Information Processing Systems
• /
• 제11권2호
• /
• pp.173-183
• /
• 2015

At present, it is simple to the electronic commerce credit scoring model, as a brush credit phenomenon in E-commerce has emerged. This phenomenon affects the judgment of consumers and hinders the rapid development of E-commerce. In this paper, that E-commerce credit evaluation model that uses a Gaussian density function is put forward by density test and the analysis for the anomalies of E-commerce credit rating, it can be fond out the abnormal point in credit scoring, these points were calculated by nonlinear credit scoring algorithm, thus it can effectively improve the current E-commerce credit score, and enhance the accuracy of E-commerce credit score.

• Bioinformatics and Biosystems
• /
• 제1권2호
• /
• pp.103-108
• /
• 2006

단백질-리간드 결합 예측은 새로운 신약 선도 물질을 발견하고 최적화 하는데 있어서 중요한 도구로 널리 사용되고 있다. 결합의 정확도는 일반적으로 각 결합 계산에서 사용되는 평가 함수(scoring function)에 따라 결정된다. 평가 함수는 그 함수가 가지고 있는 기력 가정에 따라 force-field based, empirical, knowledge-based의 세 가지로 분류할 수 있다. 이 중에서 force-field based 함수는 물리적인 상호작용을 가장 구체적으로 기술한다. 그러나 현재 제시된 대부분의 force-field based 함수들은 분산력과 정전기적인 힘 등의 에너지만을 고려할 뿐 엔트로피의 영향을 포함하지 않는 단점을 가지고 있다. 본 논문에서는 force-field based 평가 함수를 이용하는 경우 기존의 도킹 프로그램이 생성해 내는 구조 정보를 활용하여, 엔트로피를 고려할 수 있는 방법을 제시한다. 또한 이 방법을 DOCK 평가 함수에 적용시켰을 때 decoy discrimination에서 향상된 결과를 얻어낼 수 있음을 보였다. 이는 더 정확한 도킹 계산이 가능함을 의미한다.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권2호
• /
• pp.204-213
• /
• 2016

A differential game theory based approach is used to develop an automated maneuver generation algorithm for Within Visual Range (WVR) air-to-air combat of unmanned combat aerial vehicles (UCAVs). The algorithm follows hierarchical decisionmaking structure and performs scoring function matrix calculation based on differential game theory to find the optimal maneuvers against dynamic and challenging combat situation. The score, implying how much air superiority the UCAV has, is computed from the predicted relative geometry, relative distance and velocity of two aircrafts. Security strategy is applied at the decision-making step. Additionally, a barrier function is implemented to keep the airplanes above the altitude lower bound. To shorten the simulation time to make the algorithm more real-time, a moving horizon method is implemented. An F-16 pseudo 6-DOF model is used for realistic simulation. The combat maneuver generation algorithm is verified through three dimensional simulations.

• International Journal of Aeronautical and Space Sciences
• /
• 제13권1호
• /
• pp.99-105
• /
• 2012

Track-before-detect techniques based on dynamic programming have provided solutions for detecting targets from a sequence of images. In its application to airborne threat detection, dynamic programming solutions should take into account the distinguishable properties of objects in a collision course. This paper describes the development of a new track scoring function that accumulates scores for airborne targets in Bayesian framework. Numerical results show that the proposed scoring function has slightly better detection capabilities.

• 응용통계연구
• /
• 제13권2호
• /
• pp.489-503
• /
• 2000

다양한 형태의 데이터로부터 의사 결정에 유용한 정보 및 지식을 발견하려는 일련의 데이터분석 및 모형 선정과정을 데이터 마이닝(Data Mining)이라고 할 수 있다. 데이터 마이닝의 적용 예로는 신규고객에 대한 신용평가, 고객이탈방지 등과 같은 분야에서 발생하는 스코링 문제를 들 수 있는데 신용평가에서는 신용이 나쁠 가능성을 스코어로 나타내고 스코어가 높은 고객을 대상으로 특별관리를 할 수 있을 것이며 고객이탈방지에서는 이탈가능성을 스코어로 나타내고 스코어가 높은 고객을 대상으로 이탈 방지 캠페인을 벌일 수 있을 것이다. 본 논문에서는 스코링 문제를 사후확률에 대한 모형화 문제로 파악하였다. 폴리클라스를 스코링 문제에 적용하는 방법을 소개한 후 이를 독일 신용 데이터, 국내 모 PC통신회사 데이터 및 국내 모 이동통신 데이터에 적용하였다. 스코링의 성능은 이득률을 이용하여 평가하고자 하는데 나무 모형에 비하여 폴리클라스 방법이 우수함을 확인하였다.

• 응용통계연구
• /
• 제18권3호
• /
• pp.543-553
• /
• 2005

선형 로지스틱 모형은 신용위험 관리를 위한 신용평점 모형 구축에 있어서 널리 쓰이고 있는 방법론이다. 본 논문에서는 신용평점화를 위하여 로지스틱 회귀 방법에 기초한 스플라인 방법론을 다루고자 한다. 선형 스플라인과 자동적인 변수선택 방법을 채택하였다. 모의 실험을 통하여 스플라인 방법의 성능을 규명하였다.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.279-286
• /
• 2005

본 연구에서는 캐피탈시장에서의 고객신용예측을 위한 모형으로 여러 가지 인공신경망(Neural Network) 모형들을 유전자 알고리즘(Genetic Algorithm)을 이용하여 통합한 신용예측모형을 제안하였다. 10개의 학습된 인공신경망 모형들을 유전자알고리즘을 이용하여 종류별로 통합하여 MLP (Multi-Layered Perceptron), Linear, RBF(Radial Basis Function) 세 가지의 대표모델을 얻고 이를 다시 하나의 인공신경망 모델로 통합하였다. 이를 통합되기 이전의 각각의 인공신경망 모형들과 성능을 비교, 분석하여 본 연구에서 제안한 통합모형의 유효성과 통합방법의 타당성을 제시하였다.

• Bulletin of the Korean Chemical Society
• /
• 제29권5호
• /
• pp.921-927
• /
• 2008

Discovery of $\alpha$-glucosidase inhibitors has been actively pursued with the aim to develop therapeutics for the treatment of diabetes and the other carbohydrate mediated diseases. As a method for the discovery of new novel inhibitors of $\alpha$-glucosidase, we have addressed the performance of the computer-aided drug design protocol involving the homology modeling of $\alpha$-glucosidase and the structure-based virtual screening with the two docking tools: FlexX and the automated and improved AutoDock implementing the effects of ligand solvation in the scoring function. The homology modeling of $\alpha$-glucosidase from baker’s yeast provides a high-quality 3-D structure enabling the structure-based inhibitor design. Of the two docking programs under consideration, AutoDock is found to be more accurate than FlexX in terms of scoring putative ligands to the extent of 5-fold enhancement of hit rate in database screening when 1% of database coverage is used as a cutoff. A detailed binding mode analysis of the known inhibitors shows that they can be stabilized in the active site of $\alpha$- glucosidase through the simultaneous establishment of the multiple hydrogen bond and hydrophobic interactions. The present study demonstrates the usefulness of the automated AutoDock program with the improved scoring function as a docking tool for virtual screening of new $\alpha$-glucosidase inhibitors as well as for binding mode analysis to elucidate the activities of known inhibitors.

• Clinics in Shoulder and Elbow
• /
• 제4권2호
• /
• pp.173-180
• /
• 2001

Aim: To evaluate validity and responsiveness of four shoulder scoring systems. Material and Method: Twenty-five cases of shoulder instability(22 traumatic, 3 non-traumatic) and twenty-three cases of rotator cuff tear(12 small or medium, 10 large or massive) treated surgically were evaluated with the Shoulder Function Score of the University of Pennsylvania(Penn FS), Constant Score, UCLA Shoulder Rating Scale and Simple Shouler Test(SST), preoperatively and at final follow-up. The average follow-up was 16.0 months in instability group and 17.5 months in rotator cuff tear group. Using the SPSS program, Pearson linear correlation coefficiency(PLCC) between the scores were calculated. And to assess the construct validity, PLCC between patients' satisfaction and the scores were also calculated. Responsiveness was measured by the standardized response mean(SRM). Result: In instability group, correlation between the scoring systems was low preoperatively except between Constant and SST, but high after operation. Patients' satisfaction with the scores showed low PLCC preoperativley, but high PLCC postoperatively. SRM was high in PENN and UCLA, but when the satisfaction segment of the score was eliminated from UCLA, the SRM was the lowest. In rotator cuff tear group, there was high correlation between the scores not only preoperatively but postoperatively. And the patients' satisfaction matched well with the scores. SRM was particularly high in UCLA and SST. Even when satisfaction segment was eliminated from UCLA, the SRM was still the highest. Conclusion : Evaluation by the 4 scoring systems investigated in the study showed less consistency in instability than rotator cuff tear in terms of correlation and validity. Responsiveness was generally higher in rotator cuff tear group than in instability group except for Pennsylvania Shoulder Function Score. Therefore it is construed that use of any among the four scoring systems doesn't make difference in evaluation of rotator cuff lesions. However in instability group, care is needed because different result may be obtained according to the selection of a scoring system.