• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.174-177
• /
• 2016

네트워크-온-칩 (Network-on-Chip, NoC)에서 임계경로 문제를 개선하기 위해 라우터에 라디오 주파수 (RF) 모듈을 집적하는 무선 네트워크-온-칩(Wireless Network-on-Chip, WNoC)은 코어와 무선 인터페이스 라우터 (Wireless Interface Router, WIR)의 매핑 정보에 따라 통신량이 많은 코어간의 임계경로가 변화하여 지연시간에 악영향을 줄 수 있다. 본 논문에서는 코어들이 서브넷을 구성하는 small world 구조 WNoC에서 지연시간을 최적화하기 위해 코어 간의 통신량을 고려한 유전알고리즘(Genetic Algorithm, GA) 기반 코어 및 WIR의 매핑 기법을 제안하였다. 제안한 기법이 통신량이 많은 코어간의 임계경로를 최적화할 수 있도록 하였다. 모의실험 결과를 통해 무작위 매핑과 비교하여 제안하는 기법이 $4{\times}4$ 메시 기반 small world 구조에서 지연시간을 평균 33% 감소시키는 것을 확인하였다.

• 전자공학회논문지CI
• /
• 제44권2호
• /
• pp.11-18
• /
• 2007

신경회로망의 학습에 널리 사용되고 있는 오차역전파 알고리즘은 최급하강법을 기초로 하고 있기 때문에 초기값에 따라서는 극소값에 떨어지거나, 신경회로망을 학습시킬 때 중간층 유닛수를 얼마로 설정하는 등의 문제점이 있다. 따라서 이러한 문제점을 해결하기 위하여, 본 논문에서는 3비트 패리티 판별을 위하여 신경회로망의 학습에 교차법, 돌연변이법에 새로운 기법을 도입한 개량형 유전적 알고리즘을 제안한다. 본 논문에서는 세대차이, 중간층 유닛수의 차이, 집단의 개체수의 차이에 대하여 실험을 실시하여, 본 방식이 학습 속도의 면에서 유효하다는 것을 나타낸다.

• 한국정보통신학회논문지
• /
• 제19권9호
• /
• pp.2037-2043
• /
• 2015

본 논문에서는 제안한 알고리즘은 이전 유전 알고리즘의 분산처리를 위해 라우터 그룹 단위인 셀을 도입하였다. 셀 단위로 유전 알고리즘을 시행하여 전체 네트워크의 탐색 지연시간을 줄이는 방법을 제시하였다. 또한, 실험을 통하여 기존 최적경로 알고리즘인 Dijkstra 알고리즘에서 네트워크가 손상되었을 경우 제안한 알고리즘에는 대체 경로 설정의 연산시간이 단축되었으며 손상된 네트워크의 셀 안에서 2순위의 경로를 가지고 있으므로 Dijkstra 알고리즘보다 신속하게 대체경로를 설정하도록 설계되었다. 이는 제안한 알고리즘이 네트워크상에서 Dijkstra 알고리즘이 손상되었을 경우 대체 경로설정을 보완할 수 있음을 확인하였다.

• 한국통신학회논문지
• /
• 제40권9호
• /
• pp.1686-1692
• /
• 2015

본 논문에서는 메쉬 네트워크의 이동노드에 대해 기존의 유전알고리즘을 이용한 빔형성과 같은 성능을 가지면서 빠른 수렴속도를 가지고 지역해에 빠지지 않는 개선된 유전알고리즘을 제안한다. 제안한 빔형성 유전알고리즘은 빠른 수렴속도를 얻기 위해서 교배과정에서 적합도가 높은 염색체의 일정비율을 추출하고 지역해에 빠지는 것을 방지하기 위해 하위 염색체로 교배에 사용하였다. 그리고 적합도 측정용 빔형성의 기준 빔패턴을 가우시안 함수를 이용하여 수렴속도를 더욱 빠르게 하였다. 전산모의 실험을 통하여 제안한 빔형성 유전알고리즘이 기존의 빔형성 유전알고리즘 방식과 비교하여 약 20%의 빠른 수렴속도가 향상되었음을 보였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제1권1호
• /
• pp.87-94
• /
• 2001

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.175-178
• /
• 2003

In recent years, several researchers have presented the extensive research reports on network optimization problems. In our real life applications, many important network problems are typically formulated as a Maximum flow model (MXF) or a Minimum Cost flow model (MCF). In this paper, we propose a Genetic Algorithm (GA) approach used a priority-based chromosome for solving the bicriteria network optimization problem including MXF and MCF models(MXF/MCF).

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.115-118
• /
• 2000

In order to approximate a nonlinear function, modular wavelet networks combining wavelet theory and modular concept based on single layer neural network have been proposed as an alternative to conventional wavelet neural networks and kind of modular network. Modular wavelet networks provide better approximating performance than conventional one. In this paper, we propose an effective method to construct an optimal modualr wavelet network using genetic algorithm. This is verified through experimental results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.223-226
• /
• 1997

Usually, the Evolutionary Algorithms(EAs) are considered more efficient for optimal, system design because EAs can provide higher opportunity for obtaining the global optimal solution. This paper presents a mechanism of co-evolution consists of the two genetic algorithms(GAs). This mechanism includes host populations and parasite populations. These two populations are closely related to each other, and the parasite populations plays an important role of searching for useful schema in host populations. Host population represented by feedforward neural network and the result of co-evolution we will find the optimal structure of the neural network. We used the genetic algorithm that search the structure of the feedforward neural network, and evolution strategies which train the weight of neuron, and optimize the net structure. The validity and effectiveness of the proposed method is exemplified on the stabilization and position control of the inverted-pendulum system.

• BMB Reports
• /
• 제50권11호
• /
• pp.535-536
• /
• 2017

A novel approach has been used to identify functional interactions relevant to human disease. Using high-throughput human-yeast genetic interaction screens, a first draft of disease interactome was obtained. This was achieved by first searching for candidate human disease genes that confer toxicity in yeast, and second, identifying modulators of toxicity. This study found potentially disease-relevant interactions by analyzing the network of functional interactions and focusing on genes implicated in amyotrophic lateral sclerosis (ALS), for example. In the subsequent proof-of-concept study focused on ALS, similar functional relationships between a specific kinase and ALS-associated genes were observed in mammalian cells and zebrafish, supporting findings in human-yeast genetic interaction screens. Results of combined analyses highlighted MAP2K5 kinase as a potential therapeutic target in ALS.