• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.104-110
• /
• 2010

In the field of biotechnology, computer can play varied roles such as the ordinal analysis, ordianl comparison, nutation tracing, analogy comparison for drug design, estimation of protein function, cell mechanism, and verifying the role of a gene for preventing diseases. Additionally, by constructing database, it can provide an application for the cloning process in other data researches, and be used as a basis for the comparative genetics. For the most of researcher about biotechnology, they need to use the tool that can do all of job above. This study is focused on looking into problems of existing systems to analysis bio data, and designing an improved analyzing system that can propose a solution. In additional, it has been considered to improve the performance of each constituent, and all the constituents, which have been separately processed, are combind in a single system to get over old problems of the existing system.

• Journal of Intelligence and Information Systems
• /
• v.11 no.2
• /
• pp.175-195
• /
• 2005

사례기반추론(case-based reasoning)은 사례간 유사도를 평가하여 유사한 이웃사례를 찾아내고, 이웃사례의 결과를 이용하여 새로운 사례에 대한 예측결과를 생성하는 전통적인 인공지능기법 중 하나다. 이러한 사례기반추론이 최근 적용이 쉽고 간단하다는 장점과 모형의 갱신이 실시간으로 이루어진다는 점 등으로 인해, 온라인 환경에서의 고객관계관리를 위한 도구로 학계와 실무에서 주목을 받고 있다 하지만, 전통적인 사례기반추론의 경우, 타 인공지능기법에 비해 정확도가 상대적으로 크게 떨어진다는 점이 종종 문제점으로 제기되어 왔다. 이에, 본 연구에서는 사례기반추론의 성과를 획기적으로 개선하기 위한 방법으로 유전자 알고리즘을 활용한 사례기반추론의 동시 최적화 모형을 제안하고자 한다. 본 연구가 제안하는 모형에서는 기존 연구에서 사례기반추론의 성과에 중대한 영향을 미치는 요소들로 제시된 바 있는 사례 특징변수의 상대적 가중치 선정(feature weighting)과 참조사례 선정(instance selection)을 유전자 알고리즘을 이용해 최적화함으로서, 사례간 유사도를 보다 정밀하게 도출하는 동시에 추론의 결과를 왜곡할 수 있는 오류사례의 영향을 최소화하고자 하였다. 제안모형의 유용성을 검증하기 위해, 본 연구에서는 국내 한 전문 인터넷 쇼핑몰의 구매예측모형 구축사례에 제안모형을 적용하여 그 성과를 살펴보았다. 그 결과, 제안모형이 지금까지 기존 연구에서 제안된 다른 사례기반추론 개선모형들은 물론, 로지스틱 회귀분석(LOGIT), 다중판별분석(MDA), 인공신경망(ANN), SVM 등 다른 인공지능 기법들에 비해서도 상대적으로 우수한 성과를 도출할 수 있음을 확인할 수 있었다.

• Journal of Life Science
• /
• v.31 no.5
• /
• pp.453-463
• /
• 2021

Hearing loss is a group of clinically and genetically heterogeneous disorders characterized by congenital- to adult-onset deafness with frequent additional symptoms such as myopathy, nephropathy, and optic disorders. It is commonly divided into two types: syndromic, with no other symptoms, and nonsyndromic, with other symptoms. Autosomal recessive hearing loss is relatively frequent in Pakistan, which may be due in part to frequent consanguineous marriages. This study was performed by whole exome sequencing to determine the genetic causes in two Pakistani consanguineous families with autosomal recessive hearing loss. We identified a pathogenic homozygous variant (p.Leu326Gln in MYO7A) in a family with prelingual-onset hearing loss and two variants of uncertain significance (p.Val3094Ile in GPR98 and p.Asp56Gly in PLA2G6) in a family with early-onset hearing loss concurrent with muscular atrophy. The missense mutations in MYO7A and PLA2G6 were located in the highly conserved sites, and in silico analyses predicted pathogenicity, while the GPR98 mutation was located in the less conserved site, and most in silico analysis programs predicted its nonpathogenic effect. Homozygosity mapping showed that both alleles of the homozygous mutations identified in each family originated from a single founder; spread from this single source might be due to consanguineous marriages. This study will help provide exact molecular diagnosis and treatment for autosomal recessive hearing loss patients in Pakistan.

• The Korean Society of Law and Medicine
• /
• v.18 no.1
• /
• pp.237-264
• /
• 2017

With the onset of the Human Genome Project, social concerns about 'genetic information discrimination' have been raised, but the problem has not yet been highlighted in Korea. However, non-medical institutions' genetic testing which is related to disease prevention could be partially allowed under the revised "Bioethics and Safety Act" from June 30, 2016. In the case of one domestic insurance company, DTC genetic testing was provided for the new customer of cancer insurance as a complimentary service, which made the social changes related to the recognition of the genetic testing. At a time when precision medicine is becoming a new standard for medical care, discipline on genetic information discrimination has become a problem that can not be delayed anymore. Article 46 and 67 of the Bioethics Act stipulate the prohibition of discrimination on grounds of genetic information and penalties for its violation. However, these broad principles alone can not solve the problems in specific genetic information utilization areas such as insurance and employment. The United States, Canada, the United Kingdom, and Germany have different regulations that prohibit genetic information based discrimination. In the United States, Genetic Information Non-Discrimination Act takes a form that adds to the existing law about the prohibition of genetic information discrimination. In addition, the range of genetic information includes the results of genetic tests of individuals and their families, including "family history". Canada has recently enacted legislation in 2017, expanding coverage to general transactions of goods or services in addition to insurance and employment. The United Kingdom deals only with 'predictive genetic testing results of individuals'. In the case of insurance, the UK government and Association of British Insurers (ABI) agree to abide by a policy framework ('Concordat') for cooperation that provides that insurers' use of genetic information is transparent, fair and subject to regular reviews; and remain committed to the voluntary Moratorium on insurers' use of predictive genetic test results until 1 November 2019, and a review of the Concordat in 2016. In the case of employment, The ICO's 'Employment Practices Code (2011)' is used as a guideline. In Germany, Human Genetic Examination Act(Gesetz ${\ddot{u}}ber$ genetische Untersuchungen bei Menschen) stipulates a principle ban on the demand for genetic testing and the submission of results in employment and insurance. The evaluation of the effectiveness of regulatory framework, as well as the form and scope of the discipline is different from country to country. In light of this, it would be desirable for the issue of genetic information discrimination in Korea to be addressed based on the review of related regulations, the participation of experts, and the cooperation of stakeholders.

• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.11-19
• /
• 2008

In this paper, we propose a prediction method of lung cancer susceptibility using an importance evaluation of SNP data and the SVM learning, a gene data concerning getting sick with the lung cancer. Since the number of negative data is much larger that of positive data, which are to be used in the SVM learning, for each positive data, a negative data is first searched which has the same sex and the minimum age difference with the positive data. The searched negative data is then coupled with the positive data. For the importance evaluation of each SNP data, an equation which calculates the influence of each SNP data on the prediction of getting sick is adopted. The SNP data are sorted according to the evaluated importance. In experiments, we observed the prediction accuracy which varies according to the number of sorted SNP data used in the learning. LOOCV test results showed that the proposed method yields the prediction accuracy of maximum 65.0% for test data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.212-219
• /
• 2006

The important problem in designing a Fuzzy Logic Controller(FLC) is generation of fuzzy control rules and it is usually the case that they are given by human experts of the problem domain. However, it is difficult to find an well-trained expert to any given problem. In this paper, I describes an application of genetic algorithm, a well-known global search algorithm to automatic generation of fuzzy control rules for FLC design. Fuzzy rules are automatically generated by evolving initially given fuzzy rules and membership functions associated fuzzy linguistic terms. Using genetic algorithm efficient fuzzy rules can be generated without any prior knowledge about the domain problem. In addition expert knowledge can be easily incorporated into rule generation for performance enhancement. We experimented genetic algorithm with a non-trivial vehicle controling problem. Our experimental results showed that genetic algorithm is efficient for designing any complex control system and the resulting system is robust.

• Korean Journal of Microbiology
• /
• v.53 no.3
• /
• pp.216-218
• /
• 2017

We here provide the complete genome sequence of Bacillus thuringiensis C25, the strain showing antagonistic effects on fungal phytopathogens. The genome comprised of 5,308,062 bp with 35.32% G+C content of a circular chromosome and a plasmid containing 308,946 bp with 32.23% G+C content. The chromosome and plasmid genome included 5,683 protein coding DNA sequences, 107 tRNA and 42 rRNA genes.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.10
• /
• pp.677-684
• /
• 2015

It is often necessary to predict the vibration patterns of the structures from the signals of finite number of vibration sensors. This study presents the optimal placement of vibration sensors by applying the genetic algorithm and the modal expansion method. The modal expansion method is used to estimate the vibration response of the whole structure. The genetic algorithm is used to estimate the optimal placement of vibration sensors. Optimal sensor placement can be obtained so that the fitness function is minimized in the genetic algorithm. This paper discusses the comparison of the performances of two types of fitness functions, modal assurance criteria(MAC) and condition number( CN). As a result, the estimation using MAC shows better performance than using CN.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Development and Reproduction
• /
• v.7 no.1
• /
• pp.1-7
• /
• 2003

Most animals, including human beings, live in a cyclic pattern of lift that is influenced by the ambient changes of environment. The regular changes occurred by rotation of the Earth itself its revolving around the Sun, and the local environment, are reflected by the distinct behavior in the living organisms. These regular changes of environment have been imprinted into the genes within the living organisms through the evolutionary process over a long period of time. The genes are expressed by rhythms during the process of fetal development followed by growth. The environmental modifications ultimately are settled in genes, serving as a biological clock that is located putatively in the hypothalamus. Thus the biological clock governs a large number of rhythms and affects the time of birth and death lift expectancy, behavior, physiology, cell division, biochemical reaction, etc. The rhythms are readjusted to the changes of environmental cues. The biological clock has the great advantage of predicting and preparing the regular changes of environment.