• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.1972-1986
• /
• 2017

With the advent of the knowledge economy, science and technology resources have played an important role in economic competition, and their optimal allocation has been regarded as very important across the world. Thus, allocation optimization research for regional science and technology resources is significant for accelerating the reform of regional science and technology systems. Regional science and technology resource allocation optimization is modeled as a double-layer optimization model: the entire system is characterized by top-layer optimization, whereas the subsystems are characterized by bottom-layer optimization. To efficaciously solve this optimization problem, we propose a mixed search method based on the orthogonal genetic algorithm and sensitivity analysis. This novel method adopts the integrated modeling concept with a combination of the knowledge model and heuristic search model, on the basis of the heuristic search model, and simultaneously highlights the effect of the knowledge model. To compare the performance of different methods, five methods and two channels were used to address an application example. Both the optimized results and simulation time of the proposed method outperformed those of the other methods. The application of the proposed method to solve the problem of entire system optimization is feasible, correct, and effective.

• Korean Management Science Review
• /
• v.18 no.1
• /
• pp.135-145
• /
• 2001

In recent environment of dynamic management, there is growing recognition that information and knowledge management systems are essential for efficient/effective decision making by CEO. To cope with this situation, we suggest the Data-Miming scheme as a key component of integrated information and knowledge management system. The proposed system measures business performance by considering both VA(Value-Added), which represents stakeholder’s point of view and EVA (Economic Value-Added), which represents shareholder’s point of view. To mine the new information & Knowledge discovery, we applied the improved genetic algorithms that consider predictability, understandability (lucidity) and reasonability factors simultaneously, we use a linear combination model for GAs learning structure. Although this model’s predictability will be more decreased than non-linear model, this model can increase the knowledge’s understandability that is meaning of induced values. Moreover, we introduce a random variable scheme based on normal distribution for initial chromosomes in GAs, so we can expect to increase the knowledge’s reasonability that is degree of expert’s acceptability. the random variable scheme based on normal distribution uses statistical correlation/determination coefficient that is calculated with training data. To demonstrate the performance of the system, we conducted a case study using financial data of Korean automobile industry over 16 years from 1981 to 1996, which is taken from database of KISFAS (Korea Investors Services Financial Analysis System).

• 한국디지털정책학회:학술대회논문집
• /
• 2003.12a
• /
• pp.191-210
• /
• 2003

In modern dynamic management environment, there is growing recognition that information & knowledge management systems are essential for CEO's Efficient/effective decision making, As a key component to cope with this current, we suggest the management performance analysis system based on Knowledge Discovery in Database (KDD). The system measures management performance that is considered with both VA(Value-Added), which represents stakeholder's point of view and EVA(Economic Value-Added), which represents shareholder's point of view, The relationship between management performance and some 80 financial ratios is analyzed, and then important financial ratios are drawn out. In analyzing the relationship, we applied KDD process which includes such as multidimensional cube, OLAP(On -Line Analytic Process), data mining and AHP(Analytic Hierarchy Process). To demonstrate the performance of the system, we conducted a case study using financial data over the 16-years from 1981 to 1996 of Korean automobile industry which is taken from database of KISFAS(Korea Investors Services Financial Analysis System).

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.247-249
• /
• 2005

Cleavage Site 분석 및 예측은 바이러스 증식에 필요한 핵심 단백질인 Protease$(3CL^{pro})$를 예측하게 하고, 예측한 Protease의 활성을 억제함으로써 바이러스 중식을 저지하게 된다. 본 연구에서는 신경망과 결정트리, 유전자 알고리즘을 이용하여 SARS-CoV의 cleavage site를 분석하고, 학습 결과에서 추출된 규칙(Rule)에 의해 cleavage site를 예측한다. 또한 신경망에서 학습된 지식(Knowledge)을 이용하여 유전자 알고리즘의 성능을 향상시키는 지식기반 유전자 알고리즘 (KBGA: Knowledge-Based Genetic Algorithm)을 제안한다.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.164-169
• /
• 2003

In this paper, we propose the integrated Bayesian network framework to reconstruct genetic regulatory networks from genome expression data. The proposed model overcomes the dimensionality problem of multivariate analysis by building coherent sub-networks from confined gene clusters and combining these networks via intermediary points. Gene Shaving algorithm is used to cluster genes that share a common function or co-regulation. Retrieved clusters incorporate prior biological knowledge such as Gene Ontology, pathway, and protein protein interaction information for extracting other related genes. With these extended gene list, system builds genetic sub-networks using Bayesian network with MDL score and Sparse Candidate algorithm. Identifying functional modules of genes is done by not only microarray data itself but also well-proved biological knowledge. This integrated approach can improve there liability of a network in that false relations due to the lack of data can be reduced. Another advantage is the decreased computational complexity by constrained gene sets. To evaluate the proposed system, S. Cerevisiae cell cycle data [1] is applied. The result analysis presents new hypotheses about novel genetic interactions as well as typical relationships known by previous researches [2].

• Journal of muscle and joint health
• /
• v.26 no.3
• /
• pp.184-194
• /
• 2019

Purpose: There has been a considerable increase in the number of women giving birth at advanced age. The genetic screening of such women is highly desirable. Clinical nurses, however, are not adequately trained to assist such clients. This study aims at identifying the educational needs of nurses in order for them to provide better care and treatment for such women. Methods: 206 South Korean clinical nurses participated in this study. Study variables were measured by nurses' attitudes toward terminating pregnancy (ATP), knowledge of prenatal genetic screening and diagnosis (K-PGSD), and information needs for prenatal genetic screening and diagnosis (I-PGSD). The statistical analysis included T-test, analysis of variance and Pearson's Correlation Coefficient. Results: Mean scores were 34.57±5.73 for ATP, 16.44±3.04 for K-PGSD, and 78.81±10.95 for I-PGSD. The findings demonstrate that nurses have high information needs (I-PGSD) to take better care of women who have positive results from their amniocentesis tests. Conclusion: Information needs among clinical nurses are not currently being met. Education for nurses must include training in counseling to encourage patients' autonomous decision-making regarding their pregnancies.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.3
• /
• pp.319-326
• /
• 1994

Automatic control has been for the most part applied to linear systems where ti can be approximately formalized. In case that it is not definitely established the mathematical modelling to control objects, it requires manual control strategies which put under the human rule. In this paper, it constructs an FLC (Fuzzy Logic Controller) in order to turn a hand control into an automatic control in the domain of swimming pool that has been almost absolutely dependant on a skilled worker's experience. Genetic algorithms upgrade the knowledge which is acquired from human expert, using by FLC, so as to maintain knowledge in the very optimal way. It also designs an algorithm that modifies the rule base and the membership function at the same time, and ultimately will show that it can get better result than human controllers.

• Journal of Genetic Medicine
• /
• v.13 no.2
• /
• pp.65-71
• /
• 2016

Cell-free nucleic acids (cf-NAs) originate in trophoblasts and are detected in the maternal plasma. Using innovative bioinformatic technologies such as next-generation sequencing, cf-NAs in the maternal plasma have been rapidly applied in prenatal genetic screening for fetal aneuploidy. Amniotic fluid is a complex and dynamic fluid that provides growth factors and protection to the fetus. In 2001, the presence of cf-NA in amniotic fluid was reported. Amniotic fluid is in direct contact with the fetus and is derived from fetal urine and maternal and fetal plasma. Therefore, these genetic materials have been suggested to reflect fetal health and provide real-time genetic information regarding fetal development. Recently, several studies evaluated the global gene expression changes of amniotic fluid cell-free RNA according to gestational age. In addition, by analyzing the transcriptome in the amniotic fluid of fetal aneuploidy, potential key pathways and novel biomarkers for fetal chromosomal aneuploidy were identified. Here, we review the current knowledge of cell-free RNA in amniotic fluid and suggest future research directions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.707-712
• /
• 1998

This paper presents several softcomputing techniques such as neural networks, fuzzy logic and genetic algorithms : Neural networks as brain metaphor provide fundamental structure, fuzzy logic gives a possibility to utilize top-down knowledge from designer, and genetic algorithms as evolution metaphor determine several system parameters with the process of bottom up development. With these techniques, we develop a pattern recognizer which consists of multiple neural networks aggregated by fuzzy integral in which genetic algorithms determine the fuzzy density values. The experimental results with the problem of recognizing totally unconstrained handwritten numeral show that the performance of the proposed method is superior to that of conventional methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.162-165
• /
• 1996

In this paper, we proposed an optimization method of the membership function and the numbers of fuzzy rule base for the stabilization controller of the inverted pendulum system by genetic algorithm(GAs). Conventional methods to these problems need to an expert knowledge or human experience. The proposed genetic algorithm method will tune automatically the input-output membership parameters and will optimize their rule-base.