• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.15-15
• /
• 2000

In the past couple of years, there has been increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fused models have been proposed to implement different types of fuzzy reasoning mechanisms and inevitably they suffer from the dimensionality problem when dealing with complex real-world problem. To overcome the problem, we propose the self-organizing networks with activation nodes based on fuzzy inference and polynomial function. The proposed model consists of two parts, one is fuzzy nodes which each node is operated as a small fuzzy system with fuzzy implication rules, and its fuzzy system operates with Gaussian or triangular MF in Premise part and constant or regression polynomials in consequence part. the other is polynomial nodes which several types of high-order polynomials such as linear, quadratic, and cubic form are used and are connected as various kinds of multi-variable inputs. To demonstrate the effectiveness of the proposed method, time series data for gas furnace process has been applied.

• 한국컴퓨터정보학회지
• /
• 제1권2호
• /
• pp.73-94
• /
• 1995

본 논문은 유통정보 네트워크 활성화 방안에 대하여 효율적인 NDB(Network Data Base)을 설계하였다. NDB(Network Data Base)의 구조는 논리 구조, 격납 구조, 물리 구조로 형성되어 데이터는 하나의 레코드로서 표현되고 데이터들 간의 관계는 링크로서 표현되었다. 또한 데이터베이스의 논리적 구조를 표현한 자료 구조도(Data Structure Diagram:DSD)가 계층 모델로 나타내었다. 각 노드는 레코드 타입을 나타내었고, 타입들을 연결하는 방향을 지닌 링크, 논리적인 격납 형태로 구성되어 데이터베이스를 설계하는데 물리 매체상 서로 연관성 있게 설계되어 자료의 검색과 억세스 효율에 큰 영향을 미쳤다. 또한 설계된 시스템에 네트워크를 형성하고, 네트워크 표준화를 위해 OSI 환경하에서 POS(Point Of Sale)시스템을 이용하여 효율적인 유통 정보 네트워크를 활성화시켰다.

• BMB Reports
• /
• 제35권4호
• /
• pp.371-376
• /
• 2002

The receptor activator of nuclear factor kappa B (RANK) is a member of the tumor necrosis factor (TNF) receptor superfamily. It plays a critical role in osteoclast differentiaion, lymph node organogenesis, and mammary gland development. The stimulation of RANK causes the activation of transcription factors NF-${\kappa}B$ and activator protein 1 (AP1), and the mitogen activated protein kinase (MAPK) c-Jun N-terminal kinase (JNK). In the signal transduction of RANK, the recruitment of the adaptor molecules, TNF receptor-associated factors (TRAFs), is and initial cytoplasmic event. Recently, the association of the MAPK kinase kinase, transforming growth factor-$\beta$-activated kinase 1 (TAK1), with TRAF6 was shown to mediate the IL-1 signaling to NF-${\kappa}B$ and JNK. We investigated whether or not TAK1 plays a role in RANK signaling. A dominant-negative form of TAK1 was discovered to abolish the RANK-induced activation of AP1 and JNK. The AP1 activation by TRAF2, TRAF5, and TRAF6 was also greatly suppressed by the dominant-negative TAK1. the inhibitory effect of the TAK1 mutant on RANK-and TRAF-induced NF-${\kappa}B$ activation was also observed, but less efficiently. Our findings indicate that TAK1 is involved in the MAPK cascade and NF-${\kappa}B$ pathway that is activated by RANK.

• International Journal of Control, Automation, and Systems
• /
• 제6권3호
• /
• pp.453-459
• /
• 2008

The neural network is currently being used throughout numerous control system fields. However, it is not easy to obtain an input-output pattern when the neural network is used for the system of a single feedback controller and it is difficult to obtain satisfactory performance with when the load changes rapidly or disturbance is applied. To resolve these problems, this paper proposes a new mode to implement a neural network controller by installing a real object for control and an algorithm for this, which can replace the existing method of implementing a neural network controller by utilizing activation function at the output node. The real plant object for controlling of this mode implements a simple neural network controller replacing the activation function and provides the error back propagation path to calculate the error at the output node. As the controller is designed using a simple structure neural network, the input-output pattern problem is solved naturally and real-time learning becomes possible through the general error back propagation algorithm. The new algorithm applied neural network controller gives excellent performance for initial and tracking response and shows a robust performance for rapid load change and disturbance, in which the permissible error surpasses the range border. The effect of the proposed control algorithm was verified in a test that controlled the speed of a motor equipped with a high speed computing capable DSP on which the proposed algorithm was loaded.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.129-132
• /
• 2022

초해상화란 저화질의 이미지를 고화질의 이미지로 변환하는 과정이다. 본 연구에서는 ESPCN 을 이용하여 연구를 진행하였다. 초해상화 심층 신경망에서 각 노드를 거칠 때 가중치를 결정하는 활성화 함수에 따라 같은 입력 데이터를 받더라도 다른 품질의 이미지가 출력될 수 있다. 따라서 활성화 함수 ReLU, ELU, Swish를 적용시켜 같은 입력 이미지에 대한 출력 이미지의 품질을 비교하여 초해상화에 가장 적합한 활성화 함수를 찾는 것이 이 연구의 목적이다. 초해상화를 위한 Dataset은 BSDS500 Dataset을 사용하였으며, 전처리 과정에서 이미지를 정사각형으로 자른 뒤 저화질화 하였다. 저화질화된 이미지는 모델의 입력 이미지에 사용되었고, 원본 이미지는 이후 출력 이미지와 비교하여 평가하는데 사용되었다. 학습 결과 머신 러닝에 주로 쓰이는 ReLU보다는 그 단점이 개선된 ELU, swish가 훈련 시간은 오래 걸렸지만 좋은 성능을 보였다.

• 융합신호처리학회논문지
• /
• 제2권3호
• /
• pp.79-85
• /
• 2001

본 논문에서는 퍼지 보상기와 자기구성 신경회로망을 이용하여 3축 매니퓰레이터의 역 기구학 해를 구하는 방법을 제안한다. 가우시안 위치 함수를 활성화 함수로 사용하는 자기구성 신경회로망은 학습 시작시 1개의 은닉층 노드를 가지고 학습을 하면서 점차적으로 은닉층의 노드수를 증가시킴으로서 최적의 노드수를 얻을 수 있으며, 퍼지 보상기는 신경회로망의 양호한 학습비를 얻는다. 이와 같이 시스템을 구성하여 빠른 학습속도와 학습비의 개선 그리고 빠른 정상상태로의 수렴을 확인하였다.

• Nutrition Research and Practice
• /
• 제1권2호
• /
• pp.94-99
• /
• 2007

The immunostimulating activities of mucilage fraction from yam were investigated. The proliferation of BSA-primed lymph node cells was enhanced between 4.1- to 10.9-fold compare to control, when cultured with 1 to $25{\mu}g/mL$ of yam-mucilage fraction. It showed strong immunostimulating activity than ginseng extract and as remarkable as Bifidobacterium adolescentis M101-4 known as a positive immunostimulator. Mitogenicity to lymph node cells was fully induced by concanavalin A and lipopolysaccharide. The proliferation of splenocytes and Peyer's patch cells was enhanced between 5.0- to 14.1-fold and 2.4- to 6.4-fold, respectively, when cultured with 1 to $25{\mu}g/mL$ of yam-mucilage fraction. It enhanced the production of cytokines such as tumor necrosis $factor-{\alpha}$ and IL-6 in the culture of RAW 264.7 macrophage cells. In the culture of lipopolysaccharide-stimulated RAW 264.7 cells, production of cytokines was as similar as compared to controls. In unstimulated RAW 264.7 cells, both tumor necrosis $factor-{\alpha}$ and IL-6 production were enhanced between 15.6- to 60.1-fold and 2.3- to 9.1-fold, respectively. Mucilage fraction from yam is expected to be a safe immunopotentiator to maintain the host immunity and develop a physiologically functional food.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.123-145
• /
• 2017

Due to the increasing demand for spectrum resources, cognitive radio networks and dynamic spectrum access draw a lot of research into efficiently utilizing limited spectrum resources. To set up cluster-based CR ad-hoc common channels, conventional methods require a relatively long time to successfully exchange the initialization messages. In this paper, we propose a fast and reliable common channel initialization protocol for CR ad-hoc networks. In the proposed method, the cluster head sequentially broadcasts a system activation signal through its available channels with a predetermined correlation pattern. To detect the cluster head's broadcasting channels and to join the cluster, each member node implements fast Fourier transform (FFT) and computes autocorrelation of an FFT bin sequence for each available channel of the member node. This is compared to the predetermined reference pattern. The join request and channel decision procedures are also presented in this paper. In a simulation study, the performance of the proposed method is evaluated.

• 한국전자통신학회논문지
• /
• 제17권5호
• /
• pp.783-790
• /
• 2022

SNS와 동영상 플랫폼의 발전은 콘텐츠의 생산과 소비의 활성화를 폭발시키는 계기를 마련하였다. 하지만 Legacy system에서는 Host 기반의 위치 중심의 데이터 전송으로 인해 효율적 운용과 관리에 있어서 태생적 한계가 발생하게 되었다. 이에 대한 대안으로써 콘텐츠 중심 네트워크(CCN, Contents Centric Network)가 연구되었다. 본 논문에서는 CCN 환경에서 실시간 스트리밍 서비스 간 정보제공자와 정보요청자 사이 위치한 중간노드들이 이동 또는 사용 제한 시 정보요청자 측에서 단절 또는 전송 품질의 저하 등의 문제를 해결하고자 무선 수신 세기에 대한 모니터링을 통해 장애 발생 이전 적극적 대응을 통해 안정적 중간노드 관리 메커니즘을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2513-2533
• /
• 2018

In cognitive radio technology, the overall efficiency of communications systems can be improved without allocating additional bands by allowing a secondary system to utilize the licensed band when the primary system, which has the right to use the band, does not use it. In this paper, we propose a fast and reliable common channel initialization protocol without any exchange of initialization messages between the cluster head and the member nodes in cognitive ad-hoc networks. In the proposed method, the cluster and member nodes perform channel-based spectrum sensing. After sensing, the cluster head transmits a system activation signal through its available channels with a predetermined angle difference pattern. To detect the cluster head's transmission channels and to join the cluster, each member node implements fast Fourier transform (FFT) and computes autocorrelation for the angle difference sequence of the received signal patterns. This is compared to the predetermined reference angle difference pattern. The join-request and channel-decision procedures are presented in this paper. Performance evaluation of the proposed method is presented in the simulation results.