• 제목/요약/키워드: Self-organized

검색결과 476건 처리시간 0.245초

Trajectory Estimation of a Moving Object using Kohonen Networks

  • Ju, Jin-Hwa;Lee, Dong-Hui;Lee, Jae-Ho;Lee, Jang-Myung
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2004년도 ICCAS
    • /
    • pp.2033-2036
    • /
    • 2004
  • A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.

  • PDF

비선형 시스템 식별기로서의 자율분산 신경망 (Self-Organized Ditributed Networks as Identifier of Nonlinear Systems)

  • 최종수;김형석;김성중;최창호
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1995년도 하계학술대회 논문집 B
    • /
    • pp.804-806
    • /
    • 1995
  • This paper discusses Self-organized Distributed Networks(SODN) as identifier of nonlinear dynamical systems. The structure of system identification employs series-parallel model. The identification procedure is based on a discrete-time formulation. The learning with the proposed SODN is fast and precise. Such properties arc caused from the local learning mechanism. Each local networks learns only data in a subregion. Large number of memory requirements and low generalization capability for the untrained region, which are drawbacks of conventional local network learning, are overcomed in the SODN. Through extensive simulation, SODN is shown to be effective for identification of nonlinear dynamical systems.

  • PDF

Dependence of Retardation Dispersion on the Ultraviolet Polarization Direction During Photopolymerization of Self-organized Smectic Reactive Mesogen Molecules

  • Jeong, Jinyoung;Choi, Yu-Jin;Jeong, Kwang-Un;Lee, Ji-Hoon
    • Current Optics and Photonics
    • /
    • 제2권3호
    • /
    • pp.286-290
    • /
    • 2018
  • We investigated the dependence of the retardation dispersion on the polarization direction of ultraviolet (UV) light during the photopolymerization of self-organized smectic reactive mesogen (RM) molecules. RM retarder film that was photopolymerized with UV light linearly polarized parallel to the layer plane showed negative dispersion (ND) of retardation for a wide range of UV polymerization temperatures. On the other hand, film that was photopolymerized with unpolarized UV light showed negative dispersion in a narrow range of UV polymerization temperatures. With a certain UV polymerization temperature, the dispersion of retardation was converted from positive to negative, depending on the UV polarization.

Effects of the Superlattices on STM Imaging of Self-organized Substituted Alkyl Chain Monolayers on a Graphite Surface

  • Son, Seung Bae;Hahn, Jae Ryang
    • Bulletin of the Korean Chemical Society
    • /
    • 제33권12호
    • /
    • pp.4155-4160
    • /
    • 2012
  • We characterized the physisorption of p-iodo-phenyl octadecyl ether molecules (I-POE) onto superlattice regions of graphite surfaces using scanning tunneling microscopy (STM). The formation of self-organized I-POE monolayers does not affect the overall structures of moir$\acute{e}$ patterns and their modulation periods. However, the packing density of the I-POE monolayer and the orientations of lamella structures were sensitive to the underlying superlattice structure. Depending on the bias voltage, the STM images selectively showed moir$\acute{e}$ pattern, I-POE layer, or both. Reflecting the local density of states at a certain energy level, the STM images thereby revealed the relative energy level scale of the superlattice with respect to the molecular orbitals of I-POE.

자율분산 신경회로망을 이용한 간접 적응제어 (Indirect Adaptive Control Based on Self-Organized Distributed Network(SODN))

  • 최종수;김형석;김성중;권오신
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1996년도 하계학술대회 논문집 B
    • /
    • pp.1182-1185
    • /
    • 1996
  • The objective of this paper is to control a nonlinear dynamical systems based on Self-Organized Distributed Networks (SODN). The learning with the SODN is fast and precise. Such properties are caused from the local learning mechanism Each local network learns only data in a subregion. Methods for indirect adaptive control of nonlinear systems using the SODN is presented. Through extensive simulation, the SODN is shown to be effective for adaptive control of nonlinear dynamic systems.

  • PDF

아파트 단지 내 사이버 공동체 활성화 방안 연구 I - 사이버 공동체 실태와 콘텐츠의 유형화 - (The Revitalization Schemes for Virtual Communities in Apartment Complexes - The Status and Classification of the Virtual Communities -)

  • 강순주;이영애
    • 한국주거학회논문집
    • /
    • 제19권1호
    • /
    • pp.57-66
    • /
    • 2008
  • In the past, strong social bands, which had spontaneous communities, existed in Korean traditional society. However, while it's developing through industrialization; monolithic apartment houses were introduced which causes less interaction between neighbors. With the growing attention to the higher living quality, various schemes to revitalize the community spirits have been groped, including to improve in hardhearted neighborhood relationships and to cope with the dreariness in the city. With the development of the internet and the spread of 'digital home', the communities in cyber space have been especially revitalized since the information-oriented society. In a move to strengthen the communities in apartment complexes, this study tries to find the revitalization scheme for virtual communities in apartment complexes by analyzing the contents of its web sites and understanding the world of virtual community. These are compared and analyzed. The related virtual communities ("cafe" or "blogs") are also analyzed. The results are as follows. 1) There are some differences among the contents provided by apartment virtual community developing companies, still, it could be categorized into four types; "apartment complex introduction and management information" "community revitalization" "living guide" "individual services" 2) The contents provided by self-organized communities of residents neither require additional charge nor special membership for information while the formation is not systematized. 3) In the comparison of apartment virtual community developing companies with residents self-organized communities, "apartment complex introduction and management information" on freeboard, notice, request and Q&A, and "community revitalization" on communication board are both provided throughout the web sites. 4) The contents provided by apartment virtual community developing companies makes the information available in a wide range with managers, on the other hand, self-organized communities emphasize on showing attachment and concern of residents and requiring communications between neighborhoods.

Dense RGB-D Map-Based Human Tracking and Activity Recognition using Skin Joints Features and Self-Organizing Map

  • Farooq, Adnan;Jalal, Ahmad;Kamal, Shaharyar
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제9권5호
    • /
    • pp.1856-1869
    • /
    • 2015
  • This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.

Patterned Surfaces in Self-Organized Block Copolymer Films with Hexagonally Ordered Microporous Structures

  • Hayakawa Teruaki;Kouketsu Takayuki;Kakimoto Masa-alki;Yokoyama Hideaki;Horiuchi Shin
    • Macromolecular Research
    • /
    • 제14권1호
    • /
    • pp.52-58
    • /
    • 2006
  • A novel fabrication of the patterned surfaces in the polymer films was demonstrated by using the self-organizing character of the block copolymers of polystyrene-b-oligothiophenes and polystyrene-b-aromatic amide dendron. Hexagonally arranged open pores with a micrometer-size were spontaneously formed by casting the polymer solutions under a moist air flow. The amphiphilic character of the block copolymers played the crucial role as a surfactant to stabilize the inverse emulsion of water in the organic solvent, and subsequently the aggregated structure of the hydrophilic oligothiophene or aromatic amide dendron segments remained on the interiors of the micropores. The chemical composition on the top of the surface of the microporous films was characterized by energy-filtering transmission electron microscopy (EFTEM) or a time-of-flight secondary ion mass spectrometer (ToF-SIMS). The characterizations clearly indicated that the patterned surfaces in the self-organized block copolymer films with the hexagonally ordered microporous structures were fabricated in a single step.

광 섬유내의 광유도 위상격자가 형성되는 자기조직 역학에 관한 연구 (Self-Organized Dynamics of Photoinduced Phase Grating formation in Optical Fibers)

  • 안성혁
    • 한국광학회지
    • /
    • 제4권4호
    • /
    • pp.464-473
    • /
    • 1993
  • 본 논문에서는 광섬유에 아르곤 레이저 빔이 입사될 때 생기는 위상격자 형성에 관한 역학을 다룬다. 간단한 쌍광자 표백모델(two-photon bleaching model)을 이용하여 위상격자가 시간이 지남에 따라 이상적인(ideal) 격자로 자기조직됨(self-organized)을 보인다. 광섬유의 각점에서의 시간에 따른 상태전개는 하나의 보편 매개변수(universial parameter)에 의해 나타내어지고 또한 이 광섬유계를 기술하는 연립편미분 방정식이 이 매개변수에 의해 연립 상 미분 방정식으로 간소화 된다. 이 연립 상 미분 방정식을 이용하여 위상격자가 자라나는 상태는 한 고정점(a fixed point)를 향해 가는 과정이고 이 고정점은 완벽히 위상맞춤(phase-matched)된 격자에 해당된다는 것을 보인다.

  • PDF