• Journal of information and communication convergence engineering
• /
• 제6권4호
• /
• pp.448-453
• /
• 2008

This study describes design and development techniques of estimation models for process modeling. One case study is undertaken to design a model using standard gas furnace data. Neural networks (NN) and genetic programming (GP) are each employed to model the crucial relationships between input factors and output responses. In the case study, two models were generated by using 70% training data and evaluated by using 30% testing data for genetic programming and neural network modeling. The model performance was compared by using RMSE values, which were calculated based on the model outputs. The average RMSE for training and testing were 0.8925 (training) and 0.9951 (testing) for the NN model, and 0.707227 (training) and 0.673150 (testing) for the GP model, respectively. As concern the results, the NN model has a strong advantage in model training (using the all data for training), and the GP model appears to have an advantage in model testing (using the separated data for training and testing). The performance reproducibility of the GP model is good, so this approach appears suitable for modeling physical fabrication processes.

• Advances in environmental research
• /
• 제7권2호
• /
• pp.87-107
• /
• 2018

Water quality monitoring network needs periodic evaluations based on environmental demands and financial constraints. We used a genetic algorithm to optimize the existing water quality monitoring stations on the Sefid-Rud River, which is located in the North of Iran. Our objective was to optimize the existing stations for drinking and irrigation purposes, separately. The technique includes two stages called data preparation and the optimization. On the data preparation stage, first the basin was divided into four sections and each section was consisted of some stations. Then, the score of each station was computed using the data provided by the water Research Institute of the Ministry of energy. After that, we applied a weighting method by providing questionnaires to ask the experts to define the significance of each parameter. In the next step, according to the scores, stations were prioritized cumulatively. Finally, the genetic algorithm was applied to identify the best combination. The results indicated that out of 21 existing monitoring stations, 14 stations should remain in the network for both irrigation and drinking purposes. The results also had a good compliance with the previous studies which used dynamic programming as the optimization technique.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.152-154
• /
• 2005

In this paper, we propose a new architecture of Fuzzy Polynomial Neural Networks(FPNN) by means of genetically optimized Fuzzy Polynomial Neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially Genetic Algorithms(GAs). The design of the network exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being provided by the designer and kept fixed throughout the overall development process. This restriction may hamper a possibility of producing an optimal architecture of the model. The proposed FPNN gives rise to a structurally optimized network and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. It is shown that the proposed genetic algorithms-based Fuzzy Polynomial Neural Networks is more useful and effective than the existing models for nonlinear process. We experimented with Medical Imaging System(MIS) dataset to evaluate the performance of the proposed model.

• Molecules and Cells
• /
• 제37권9호
• /
• pp.691-698
• /
• 2014

SCYL1-BP1 is thought to function in the p53 pathway through Mdm2 and hPirh2, and mutations in SCYL1-BP1 are associated with premature aging syndromes such as Geroderma Osteodysplasticum; however, these mechanisms are unclear. Here, we report significant alterations in miRNA expression levels when SCYL1-BP1 expression was inhibited by RNA interference in HEK293T cells. We functionally characterized the effects of potential kernel miRNA-target genes by miRNA-target network and protein-protein interaction network analysis. Importantly, we showed the diminished SCYL1-BP1 dramatically reduced the expression levels of EEA1, BMPR2 and BRCA2 in HEK293T cells. Thus, we infer that SCYL1-BP1 plays a critical function in HEK293T cell development and directly regulates miRNA-target genes, including, but not limited to, EEA1, BMPR2, and BRCA2, suggesting a new strategy for investigating the molecular mechanism of SCYL1-BP1.

• 한국산학기술학회논문지
• /
• 제11권5호
• /
• pp.1661-1669
• /
• 2010

본 논문에서는 센서 네트워크의 수명을 길게 하기 위해 클러스터 헤드에 집중된 에너지 과부하를 클러스터 그룹 헤드와 클러스터 헤드로 분산시켜서 에너지 소모량을 감소시키는 유전 알고리즘 기반의 에너지 효율적인 클러스터링(ECGA: Energy efficient Clustering based on Genetic Algorithm)을 제안한다. ECGA 알고리즘은 예상 에너지 비용 합계, 센서 노드 에너지 잔량의 평균 및 표준 편차를 구하여 이를 적합도 함수에 적용하였다. 이 적합도를 이용하여 최적의 클러스터 그룹 및 클러스터를 형성한다. 실험을 통하여 ECGA 알고리즘이 이전의 클러스터링 기법보다 에너지 소모를 줄이고 네트워크의 수명을 연장시켰음을 보였다.

• 인지과학
• /
• 제4권2호
• /
• pp.181-200
• /
• 1994

다층 신경망의 학습에 있어서 역전파 알고리즘은 시스템이 지역적 최소치에 빠질수 있고,탐색공간의 피라미터들에 의해 신경망 시스템의 성능이 크게 좌우된다는 단점이 있다.이러한 단점을 보완하기 의해 유전자 알고리즘이 신경망의 학습에 도입도었다.그러나 유전자 알고리즘에는 역전파 알고리즘과 같은 미세 조정되는 지역적 탐색(fine-tuned local search) 을 위한 메카니즘이 존재하지 않으므로 시스템이 전역적 최적해로 수렴하는데 많은 시간을 필요로 한다는 단점이 있다. 따라서 본 논문에서는 역전파 알고리즘의 기울기 강하 기법(gradient descent method)을 교배나 돌연변이와 같은 유전 연산자로 둠으로써 유전자 알고리즘에 지역적 미세 조정(local fine-tuning)을 위한 메카니즘을 제공해주는 새로운 형태의 GA-BP 방법을 제안한다.제안된 방법의 유용성을 보이기 위해 3-패러티 비트(3-parity bit) 문제에 실험하였다.

• 한국정보통신학회논문지
• /
• 제8권5호
• /
• pp.1089-1095
• /
• 2004

주어진 네트워크에서 최적의 스타이너 트리를 구하는 문제는 NP-hard이며, 최적에 가까운 스타이너 트리를 구하기 위하여 유전자 알고리즘을 이용한다. 본 논문에서는 이 문제를 해결하기 위하여 유전자 알고리즘에서 염색체를 기존의 이진스트링 대신 부동소수점으로 표현하였다. 먼저 주어진 네트워크에 Prim의 알고리즘을 적용하여 스패닝 트리를 구하고, 부동소수점 표현을 갖는 유전자 알고리즘을 사용하여 새로운 스타이너 점을 트리에 추가하는 과정을 반복함으로써 최적에 가까운 스타이너 트리를 구했다 이 방법을 사용하면 이진스트링을 사용하는 기존의 방법에 비해서 트리가 보다 빠르고 정확하게 최적에 가까운 스타이너 트리에 접근했다.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• 제2권1호
• /
• pp.32-41
• /
• 2021

South Korea presently harbors less than 800 long-tailed gorals (Naemorhedus caudatus), an endangered species. I report for the first time on the taxonomic status and genetic diversity of the Korean species using non-invasive fecal sampling based on mitochondrial cytochrome b gene sequence analyses. To determine the taxonomic status of this species, I reconstructed a consensus neighbor-joining tree and generated a minimum spanning network combining haplotype sequences obtained from feces with a new goral-specific primer set developed using known sequences of the Korean goral and related species (e.g., Russian goral, Chinese goral, Himalayan goral, Japanese serow, etc.). I also examined the genetic diversity of this species. The Korean goral showed only three different haplotypes. The phylogenetic tree and parsimony haplotype network revealed a single cluster of Korean and Russian gorals, separate from related species. Generally, the Korean goral has a relatively low genetic diversity compared with that of other ungulate species (e.g., moose and red deer). I preliminarily showcased the application of non-invasive fecal sampling to the study of genetic characteristics, including the taxonomic status and genetic diversity of gorals, based on mitochondrial DNA. More phylogenetic studies are necessary to ensure the conservation of goral populations throughout South Korea.

• 한국환경과학회지
• /
• 제33권4호
• /
• pp.235-247
• /
• 2024

A total of 64 individuals of Acanthogobius flavimanus, which inhabit the coast of Korea, were collected from 8 regions from July to August 2023. A haplotype network and a phylogenetic tree were created. The genomic DNA of the target fish species was compared and analyzed with the genomic DNA of four regions in Japan downloaded from the National Center for Biotechnology Information (NCBI). In the haplotype network of Acanthogoboius flavimanus, Eocheong-do (EC) and Goseong (MAJ) exhibited low genetic similarity with other regions in Korea and Japan. The Phylogenetic tree showed that the population of MAJ exhibited differences in genetic structure compared to populations in other regions of Korea and Japan, indicating a distant relationship. Most marine organisms are known to migrate and spread via ocean currents, which is the most crucial factor promoting gene flow through larvae between populations. The haplotype of Acanthogobius flavimanus in MAJ differs from the haplotypes in Korea and Japan. The population in MAJ is believed to have limited genetic exchange due to the North Korea Cold Currents. We identified haplotype patterns based on the geographical distribution of Acanthogobius flavimanus off the coast of Korea and inferred that ocean currents have some influence on genetic distances.

• 융합보안논문지
• /
• 제11권1호
• /
• pp.11-18
• /
• 2011

무선 메쉬 네트워크 기술은 유선과 유사한 전송속도를 갖는 무선망을 구축하는 기술을 의미하며, 유선 네트워크와 비교하여 보다 효율적인 망 구축의 편의성 및 유연성을 제공한다. 이러한 무선 메쉬 네트워크는 라우터 노드의 이동성이 적고 에너지 영향에도 제약이 적게 따른다는 특징을 갖고 있다. 그러나 다양한 종류의 네트워크로 구성되는 특징으로 인해서 다중 경로의 설정 및 선택 시에 발생할 수 있는 시스템 오버헤드 등 고려되어야 하는 사항들이 많다. 그러므로 이러한 네트워크 특성에 맞는 경로 설정 기술이 반영되는 네트워크의 설계 및 최적화에 주목할 필요가 있다. 본 논문에서는 다중 경로 설정 시 발생 할 수 있는 문제에 효과적으로 대응하기 위해 라우터 노드의 트래픽 상황에 따른 데이터 손실률과 대역폭 및 링크의 흡수를 평가 요소로 활용하여 유전 알고리즘을 통한 동적 경로 설정에 대한 해결방법으로 무선 메쉬 네트워크의 라우팅 메트릭 기법을 제안한다.