• Journal of the Korea Safety Management & Science
• /
• v.6 no.2
• /
• pp.187-197
• /
• 2004

The recycling cell formation problem means that disposal products are classified into recycling product families using group technology in their end-of-life phase. Disposal products have the uncertainties of product condition usage influences. Recycling cells are formed considering design, process and usage attributes. In this paper, a new approach for the design of cellular recycling system is proposed, which deals with the recycling cell formation and assignment of identical products concurrently. Fuzzy ART neural networks are applied to describe the condition of disposal product with the membership functions and to make recycling cell formation. The approach leads to cluster materials, components, and subassemblies for reuse or recycling and can evaluate the value at each cell of disposal products. Disposal refrigerators are shown as an example.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.459-465
• /
• 2000

최근 들어 인공지능과 뇌과학 분야의 연구성과를 힘입어 뇌의 기본기능을 이해하고 재구축하고자 하는 시도가 활발히 전개되고 있다. 뇌의 정보처리 기능을 실험관찰 방법으로 밝히고자 하는 신경과학, 마음의 정보 처리 기능을 역시 실험관찰 방법으로 이해하고자 하는 심리학, 그리고 정보처리모형의 구성법을 제시하는 컴퓨터과학을 통합함으로써 뇌와 마음의 작동을 정보과학의 입장에서 해명하고자 하는 접근방식이 현재 가장 가능성이 있다고 생각된다. 본 논문에서는 그와 같은 맥락에서 인공적으로 뇌를 구현하기 위하여 제안된 CAM-Brain을 소개하고, 로봇을 제어하는 문제에 적용한 예를 통하여 그 가능성을 보이고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.292-294
• /
• 2002

본 연구에서는 영상에서 효과적인 에지 연결(edge linking)을 위하여 기존의 셀룰러 신경망 구조에서 두 가지 유형의 시냅스 구조를 고려한 활성화 특성을 제안한다 제시하는 모델에서 노드들간의 측면 연결에 의한 상호 작용은 노이즈에 의한 에지 및 영상에서 추출된 비최대점(non-maximum)의 에지를 억제할 문만 아니라, 특정 노드의 원형 이웃(circular neighborhood)으로 그려되는 특징들 간의 상호 연관도를 반영하여 에지의 연결 효과를 이를 수 있게 한다. 이러한 과정은 에지를 표현하는 벡터형식의 각 성분에 대한 활성화 특성으로부터 정형화된 에너지 함수로 모델링하고 이에 대한 최적화 과정으로써 구현될 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.231-234
• /
• 2002

셀룰라 신경회로망의 연상 메모리를 이용하여 시각적인 입력 데이터의 연산을 통하여 영상 패턴의 분류와 인식을 수행한다. 셀룰라 신경회로망은 일반적인 신경회로망과 같이 비선형 데이터의 실시간 처리가 가능하고, 세 포자동자와 같이 격자구조의 셀로 이루어져 인접한 셀과 직접 정보를 주고받는다. 응용 분야로는 최적화, 선형/비선형화, 연상 메모리, 패턴인식, 컴퓨터 비젼 등에 적용할 수 있다. 영상의 이미지 픽셀을 셀룰라 신경회로망의 셀에 대응하여 전체 이미지 영상을 모든 셀룰라 신경회로망의 셀에서 동시에 병렬로 처리할 수 있어 2-D 이미지 처리에 적합하다 본 논문은 셀룰라 신경회로망에 의한 연상 메모리 구조를 설계하고, 학습된 하중값 메모리에서 가장 적당한 하중값을 선택하여 학습된 영상과 정확히 일치하는 출력을 얻는 방법을 제시한다. 학습을 통한 연상 메모리 구현에는 각각의 뉴런에서 일정하지 않은 다른 템플릿을 사용한다. 각각의 템플릿은 뉴런들 간의 연결 하중값을 나타내고 학습011 따라 갱신된다. 학습방법으로는 템플릿 하중값 학습에 뉴런들 간의 연결 하중값을 조정하는 가장 단순한 규칙인 Hebb의 학습방법이 사용되었고 분류값 학습에 LMS 알고리즘이 사용되었다

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.6
• /
• pp.10-21
• /
• 2000

The Cellular Noninear Networks structure for Distance Transform(DT) and the robust optical flow detection algorithm based on the DT are proposed. For some applications of optical flows such as target tracking and camera ego-motion computation, correct optical flows at a few feature points are more useful than unreliable one at every pixel point. The proposed algorithm is for detecting the optical flows on the trajectories only of the feature points. The translation lengths and the directions of feature movements are detected on the trajectories of feature points on which Distance Transform Field is developed. The robustness caused from the use of the Distance Transform and the easiness of hardware implementation with local analog circuits are the properties of the proposed structure. To verify the performance of the proposed structure and the algorithm, simulation has been done about various images under different noisy environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.865-870
• /
• 2006

The cellular neural networks have shown a vast computing power for the image processing in spite of the simplicity of its structure. However, it is impossible to implement the CNN hardware which would require the same enormous amount of cells as that of the pixels involved in the practical large image. In this parer, the $5\times5$ CNN hardware and the pre post processor which can be used for processing the real large image with a time-multiplexing scheme are implemented. The implemented $5\times5$ CNN hardware and pre post processor is applied to the edge detection of $256\times256$ lena image to evaluate the performance. The total number of block. By the time-multiplexing process is about 4,000 blocks and to control pulses are needed to perform the pipelined operation or the each block. By the experimental resorts, the implemented $5\times5$ CNN hardware and pre post processor can be used to the real large image processing.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3060-3062
• /
• 2000

A fast optimal path planning algorithm using the analog Cellular Nonlinear Circuits (CNC) is proposed. The proposed algorithm compute the optimal path using subgoal-based dynamic programming algorithm. In the algorithm, the optimal paths are computed regardless of the distance between the initial and the goal position. It begins to find subgoals starting from the initial position when the output of the initial cell becomes nonzero value. The suboal is set as the initial position to find the next subgoal until the final goal is reached. Simulations have been done considering the imprecise hardware fabrication and the limitation of the magnitude of input value.

• Molecules and Cells
• /
• v.45 no.2
• /
• pp.76-83
• /
• 2022

Neurons-on-a-Chip technology has been developed to provide diverse in vitro neuro-tools to study neuritogenesis, synaptogensis, axon guidance, and network dynamics. The two core enabling technologies are soft-lithography and microelectrode array technology. Soft lithography technology made it possible to fabricate microstamps and microfluidic channel devices with a simple replica molding method in a biological laboratory and innovatively reduced the turn-around time from assay design to chip fabrication, facilitating various experimental designs. To control nerve cell behaviors at the single cell level via chemical cues, surface biofunctionalization methods and micropatterning techniques were developed. Microelectrode chip technology, which provides a functional readout by measuring the electrophysiological signals from individual neurons, has become a popular platform to investigate neural information processing in networks. Due to these key advances, it is possible to study the relationship between the network structure and functions, and they have opened a new era of neurobiology and will become standard tools in the near future.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.10-19
• /
• 1999

Cellular Automata Neural Systems(CANS) are neural networks based on biological development and evolution. Each neuron of CANS has local connection and acts as a form of pulse according to the dynamics of the chaotic neuron. CANS are generated from initial cells according to the CA rule. In the previous study, to obtain the useful ability of CANS, we make the pattern of initial cells evolve. However, it is impossible to represent all solution space, so we propose an evolving method of CA rule to overcome this defect in this paper. DNA coding has the redundancy and overlapping of gene and is apt for the representation of the rule. In this paper, we show the general expression of CA rule and propose translation method from DNA code to CA rule. The effectiveness of the proposed scheme was verified by applying it to the navigation problem of autonomous mobile robot.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.1
• /
• pp.19-26
• /
• 2002

There are some difficulties to construct a sensory-motor controller for an autonomous mobile robot such as coordinating the mechanics and control system parts of the robot, and managing interaction with external environments. In previous research, we evolve the CAM-Brain, neural networks based on cellular automata, to control an autonomous mobile robot. In this paper, we propose the method of combining multi-modules evolved to do simple behavior in order to making more sophisticated behaviors because the controller composed of one neural network module is difficult to make complex behaviors. In experimental results, we can get the controller adapting to more complex environments by combining CAM-Brain modules evolved to do simple behavior by rule-based approach.