• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.11
• /
• pp.88-95
• /
• 1998

This paper is the result of constructing information processing system such as living creatures' brain based on artificial life techniques. The living things are best information processing system in themselves. One individual is developed from a generative cell. And a species of this individual has adapted itself to the environment through evolution. In this paper, we propose a new method of designing neural networks using biological inspired developmental and evolutionary concept. Ontogeny of organism is embodied in cellular automata(CA) and phylogeny of species is realized by evolutionary algorithms(EAs). We call 'Evolving Cellular Automata Neural Systems' as ECANSI. The connection among cells is determined by the rule of cellular automata. In order to obtain the best neural networks in given environment, we evolve the arragemetn of initial cells. The cell, that is a neuron of neural networks, is modeled on chaotic neuron with firing or rest state like biological neuron. A final output of network is measured by frequency of firing state. The effectiveness of the proposed scheme is verified by applying it to Exclusive-OR and parity problem.

• Korean Journal of Ichthyology
• /
• v.24 no.2
• /
• pp.94-100
• /
• 2012

The spine loach, Cobitis hankugensis endemic to Korea were collected at the Nokdong River, Unbong-eup, Namwon-si, Jeollabuk-do during June 2007 for study its eggs development and early life history. The eggs were obtained by injecting gonadotropin (LHRH-1) to female and were fertilized by dry method in the laboratory condition. The matured eggs were separative, demersal and light yellowish with $1.29{\pm}0.07mm$ in diameter average. Under $23{\sim}25^{\circ}C$, the eggs were hatched in 45~52 hours after fertilization, and just hatching larvae were $4.5{\pm}0.24mm$ in total length. On 5 days after hatching, they were $6.6{\pm}0.13mm$ in total length and their yolk sacs were completely absorbed. From 25 days after hatching, they became the juvenile stage with $9.0{\pm}0.49mm$ in total length. On the 100 days after hatching, their external forms and band patterns were similar to those of adults with average $27.3{\pm}2.82mm$ in total length.

• The Korean Journal of Ecology
• /
• v.25 no.3 s.107
• /
• pp.131-137
• /
• 2002

This study was conducted to clarify the characteristics of bird community and habitat types in Mangyeong River area from Aug. 1999 to Jun. 2000. Paddy field was the most dominant land use type. Water area, mudflat, shrub field, urban area and green house were also dominant land use types in study area. Eighty-eight bird species were recorded during study period. Maximum number of species and individuals were shown as 58 species and 7,084 individuals in Oct. and Jan., respectively. There were low number of diving ducks and clumped pattern of waterfowl distribution of bird community in Mangyeong River area. Dabbling ducks distributed at upper reaches near Samrye Bridge, and plovers and sandpipers at lower reaches near estuary. Those results suggest that creation of pools over one meter water-depth and restoration of paddy field into riparian zone with diverse shrubs are required to increase the bird diversity in the Mangyeong rived.

• The Korean Journal of Ecology
• /
• v.25 no.2
• /
• pp.61-67
• /
• 2002

This study was conducted to clarify the characteristics of bird community and habita types in Mangyeong River area from Aug. 1999 to Jun. 2000. Paddy field was the most dominant land use type. Water area, mudiflat. shrub field, urban area and green house wee also dominant land use types in study area Eighty-eight bird species were recorded during study period. Maxiamum number of species and individuals were shown as 58 species and 7,084 individuals in Oct. and Jan. respecitvely. There were low number of diving ducks and clumped pattem of waterfowl distribution of bird community in Mangyeong River area. Dabbing ducks distributed at upper reaches near Samrye Bridge, and plovers and sandpipers at lower reaches near estuary. Those results suggest that creation of pools over one meter water-depth and restoration of paddy field freld into riparian zone with diverse shrubs are required to imcrease th bird diversity in the Mangyeong rived.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.5
• /
• pp.489-495
• /
• 2014

A micro-genetic algorithm (MGA) is one of the improved forms of a genetic algorithm. It is used to reduce the number of iterations and the computing resources required by using small populations. The efficiency of MGAs has been proved through many problems, especially problems with 3-5 design variables. This study proposes an optimization algorithm based on the sequential design of experiments (SDOE) and an MGA. In a previous study, the authors used the SDOE technique to reduce trial-and-error in the conventional approximate optimization method by using the statistical design of experiments (DOE) and response surface method (RSM) systematically. The proposed algorithm has been applied to various mathematical examples and a structural problem.

• Journal of Plant Biotechnology
• /
• v.32 no.2
• /
• pp.129-134
• /
• 2005

Effective micropropagation system via somatic embryognesis was established for a Phytophthora resistant Aralia elata cultivar. Different kinds of growth regulators were needed to induce embryogenic callus with different explant sources. When leaf explants were used, a combination of 2,4-D, TDZ and L-glutamine was needed, whereas when petiole and root explants needed only 1.0 mg/L 2,4-D. Embryogenic callus induction rate under the optimum culture condition was 75.0%, 67.0% and 83.0% from leaf, petiole and root segment, respectively. Somatic embryo germination and plantlet conversion rate appeared to be influenced greatly by various osmoticums. More than 90% of embryos germinated when treated with sucrose, glucose and maltose. However, the highest conversion rate (72%) was recorded on medium with 2% sucrose only. The converted plantlets grew normally on 1/2MS basal medium, were acclimatized on artificial soil mixture and survived more than 95% in the greenhouse condition. The results suggest that the species can be clonally propagated through in vitro culture system via somatic embryogenesis.

• Korean journal of applied entomology
• /
• v.37 no.2
• /
• pp.163-170
• /
• 1998

Larval morphological characters such as body color and stripe pattern were analyzed to get morphological genetic markers of beet armyworm, Spodoptera exigua (Hiibner). Body color was varied from light green to dark brown with diets. Stripe characters were classified by the presence of dorsal and lateral lines: three stripes with both lines, one stripe with dorsal line only, and zero stripe. Proportions of each stripe character increased with successive selections for its own character. Three stripe was dominant to one stripe when they were crossed. The estimated heritability in narrow sense (h2) of the stripe pattern was 0.50k0.42. About two fold more females than males were produced in zero stripe line. Stripe pattern was not significantly changed by different diets except in welsh onion which had lower proportion of three stripe individuals than that of the expected. Larval stripe pattern was also correlated with larval and pupal developmental rates and cold hardiness but not with insecticide susceptibility.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1569-1580
• /
• 2004

One commonly used approach to deal with uncertainty is Bayesian network which represents joint probability distributions of domain. There are some attempts to team the structure of Bayesian networks automatically and recently many researchers design structures of Bayesian network using evolutionary algorithm. However, most of them use the only one fittest solution in the last generation. Because it is difficult to combine all the important factors into a single evaluation function, the best solution is often biased and less adaptive. In this paper, we present a method of generating diverse Bayesian network structures through fitness sharing and combining them by Bayesian method for adaptive inference. In order to evaluate performance, we conduct experiments on learning Bayesian networks with artificially generated data from ASIA and ALARM networks. According to the experiments with diverse conditions, the proposed method provides with better robustness and adaptation for handling uncertainty.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.377-380
• /
• 2018

인간의 추론 능력이란 문제에 주어진 조건을 보고 문제 해결에 필요한 것이 무엇인지를 논리적으로 생각해 보는 것으로 문제 상황 속에서 일정한 규칙이나 성질을 발견하고 이를 수학적인 방법으로 법칙을 찾아내거나 해결하는 능력을 말한다. 이러한 인간인지 능력과 유사한 인공지능 시스템을 개발하는데 있어서 핵심적 도전은 비구조적 데이터(unstructured data)로부터 그 개체들(object)과 그들간의 관계(relation)에 대해 추론하는 능력을 부여하는 것이라고 할 수 있다. 지금까지 딥러닝(deep learning) 방법은 구조화 되지 않은 데이터로부터 문제를 해결하는 엄청난 진보를 가져왔지만, 명시적으로 개체간의 관계를 고려하지 않고 이를 수행해왔다. 최근 발표된 구조화되지 않은 데이터로부터 복잡한 관계 추론을 수행하는 심층신경망(deep neural networks)은 관계추론(relational reasoning)의 시도를 이해하는데 기대할 만한 접근법을 보여주고 있다. 그 첫 번째는 관계추론을 위한 간단한 신경망 모듈(A simple neural network module for relational reasoning) 인 RN(Relation Networks)이고, 두 번째는 시각적 관찰을 기반으로 실제대상의 미래 상태를 예측하는 범용 목적의 VIN(Visual Interaction Networks)이다. 관계 추론을 수행하는 이들 심층신경망(deep neural networks)은 세상을 객체(objects)와 그들의 관계(their relations)라는 체계로 분해하고, 신경망(neural networks)이 피상적으로는 매우 달라 보이지만 근본적으로는 공통관계를 갖는 장면들에 대하여 객체와 관계라는 새로운 결합(combinations)을 일반화할 수 있는 강력한 추론 능력(powerful ability to reason)을 보유할 수 있다는 것을 보여주고 있다. 본 논문에서는 관계 추론을 수행하는 심층신경망(deep neural networks) 중에서 Sort-of-CLEVR 데이터 셋(dataset)을 사용하여 RN(Relation Networks)의 성능을 재현 및 관찰해 보았으며, 더 나아가 파라미터(parameters) 튜닝을 통하여 RN(Relation Networks) 모델의 성능 개선방법을 제시하여 보았다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.33-40
• /
• 2021

Due to advanced complex strategies, the complexity of information that a commander must analyze is increasing. An intelligent service that can analyze battlefield is needed for the commander's timely judgment. This service consists of extracting knowledge from battlefield information, building a knowledge base, and analyzing the battlefield information from the knowledge base. This paper extract information similar to an input query by embedding the knowledge base built in the 2^nd step. The transformation model is needed to generate the embedded knowledge base and uses the random-walk algorithm. The transformed information is embedding using Word2Vec, and Similar information is extracted through cosine similarity. In this paper, 980 sentences are generated from the open knowledge base and embedded as a 100-dimensional vector and it was confirmed that similar entities were extracted through cosine similarity.