Earticle

Vehicle License Plate Images Segmentation is a substantial stage for developing an Automatic License Plate Recognition (ALPR) system. In this paper, it is considered an efficient segmentation algorithm for extracting vehicle license plate images using Cellular Neural Networks (CNN). The learning CNN templates values are formulated as an optimization problem to achieve the desired performances which can be found by means of Adaptive Fuzzy (AF) algorithm and Neuro-Fuzzy (NF) algorithm techniques. The main objective of the paper is to compare the performances of standard CNN, Adaptive Fuzzy (AF), and Neuro-Fuzzy (NF) on real data of several vehicle license plate images of standard Indonesia License Plates. The results are then compared with ideal vehicle license plate images. Quantitative analysis between ideal vehicle license plate images and segmented vehicle license plate images is presented in terms of Peak signal-to-noise ratio (PSNR), Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). From the performance analysis, the CNN template optimized by ANFIS algorithm is more recommended than the standard CNN edge detector or the CNN template optimized by Adaptive Fuzzy algorithm in vehicle license plate image segmentation. It is shown from the calculation that PSNR is 80% better than the standard CNN, and the resulted MSE and RMSE are 70% better than the standard CNN. Whereas the CNN template optimized by Adaptive Fuzzy algorithm achieves the PSNR 90% better than the standard CNN, but it yields the MSE and RMSE 40% worse than the standard CNN.

The machine-part cell formation problem explains the topics surrounding the creation of part families based on the processing needs of the components, and the classification of machine groups based on their capacity to process exact part families in manufacturing. Allocate the specified machines and parts into cells so that the grouping efficiency is maximized. The objective of the paper is to cluster the parts based upon self-organizing map (SOM). After clustering, Minkowski distance is used to sort the machines and some bottlenecks are introduced during the clustering process which can be removed manually by rearranging. We are going to implement self-organizing map (SOM) which is a type of artificial neural network technique to solve this problem. The proposed Minkowski distance approach produced solution with a good group efficiency.

This paper demonstrates that there is a unique exponentially stable equilibrium state of a class of impulsive cellular neural network with delays. The analysis exploits M-matrix theory and generalized comparison principle to derive some easily verifiable sufficient conditions for the global exponential stability of the equilibrium state. The results extend and improve earlier publications. An example with its simulation is given for illustration of theoretical results.

In this paper, we consider the global exponential stability of cellular neural networks with time-varying delays. Based on the Lyapunov function method and convex optimization approach, a novel delay-dependent criterion of the system is derived in terms of LMI (linear matrix inequality). In order to solve effectively the LMI convex optimization problem, the interior point algorithm is utilized in this work. Two numerical examples are given to show the effectiveness of our results.

In this paper, a class of bi-directional associative memory (BAM) fuzzy cellular neural networks with distributed delays and impulses is formulated and investigated. By employing an integro-differential inequality with impulsive initial conditions and the topological degree theory, some sufficient conditions ensuring the existence and global exponential stability of equilibrium point for impulsive BAM fuzzy cellular neural networks with distributed delays are obtained. In particular, the estimate of the exponential convergence rate is also provided, which depends on the delay kernel functions and system parameters. It is believed that these results are significant and useful for the design and applications of BAM fuzzy cellular neural networks. An example is given to show the effectiveness of the results obtained here.

In this paper, the problem of delay-dependent stability analysis for cellular neural networks systems with time-varying delays was considered. By using a new Lyapunov-Krasovskii function, delay-dependant stability conditions of the delayed cellular neural networks systems are proposed in terms of linear matrix inequalities (LMIs). Examples are provided to demonstrate the reduced conservatism of the proposed stability results.

In this paper cellular neutral networks with time-varying delays and continuously distributed delays are considered. Without assuming the global Lipschitz conditions of activation functions, some sufficient conditions for the existence and exponential stability of the almost periodic solutions are established by using the fixed point theorem and differential inequality techniques. The results of this paper are new and complement previously known results.

In this paper cellular neural networks with continuously distributed delays are considered. Sufficient conditions for the existence and exponential stability of the almost periodic solutions are established by using fixed point theorem, Lyapunov functional method and differential inequality technique. The results of this paper are new and they complement previously known results.

This paper considers the problem of existence and exponential stability of almost periodic solution for shunting inhibitory cellular neural networks with distributed delays and large impulses. Based on the contraction principle and Gronwall-Bellman's inequality, some sufficient conditions are obtained. The results of this paper are new and they complement previously known results.

In this paper, a supervised algorithm for the evaluation of geophysical sites using a multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. ML-CNN is a stochastic image processing technique based on template optimization using neighborhood relationships of the pixels. The separation/enhancement and border detection performance of the proposed method is evaluated by various interesting real applications. A genetic algorithm is used in the optimization of CNN templates. The first application is concerned with the separation of potential field data of the Dumluca chromite region, which is one of the rich reserves of Turkey; in this context, the classical approach to the gravity anomaly separation method is one of the main problems in geophysics. The other application is the border detection of archeological ruins of the Hittite Empire in Turkey. The Hittite civilization sites located at the Sivas-Altinyayla region of Turkey are among the most important archeological sites in history, one reason among others being that written documentation was first produced by this civilization.

This paper is the result of constructing information processing system such as living creatures´ brain based on artificial life techniques. The living things are best information processing system in themselves. One individual is developed from a generative cell. And a species of this individual has adapted itself to the environment through evolution. We present a new type of neural architecture consistiong of chaotic neurons and implementation. To evolve chaotic neural systems, we use cellular automata. In order to obtain the best neural networks in the environment, we evolve the arrangement of initial cells. The cell, that is neuron of neural networks, is modeled on chaotic ...

In this paper, we propose a new approach of solving the stereopsis problem with a discrete-time cellular neural network(DTCNN) where each node has connections only with its local neithbors. Because the matching process of stereo correspondence depends on its geometrically local characteristics, the DTCNN is suitable for the stereo correspondence. Moreover, it can be easily implemented in VLSI. Therefore, we employed a two-layer DTCNN with dual templates, which are determined with the back propagation learning rule. Based on evaluation of the proposed approach for several random-dot stereograms, its performance is better than that of the Marr-Poggio algorithm.

본 논문에서는 이산시간 cellular 신경회로망(DTCNN)의 효율적인 디지털 하드웨어 구조를 제안한다. DTCNN은 셀간의 연결 형태를 결정하는 템플릿(template)내에서 국소적이며 공간 불변적인 특징을 가진다. 이와 같은 DTCNN의 특징과 분산연산 방식을 결합하여 간단한 하드웨어와 적은 연결선으로 DTCNN 하드웨어를 구현하였다. 또한 분산연산의 특징인 비트별 연산 방식을 사용하여 셀 간의 연결을 위한 넓은 버스 폭을 단일 비트로 줄였다. 본 논문에서는 제안한 구조를 프로그래밍이 가능한 FPGA를 사용하여 가변적인 구조를 갖는 DTCNN 보드로 구현하였다.

In this paper, we propose an efficient digital architecture for the discrete-time cellular neural networks (DTCNN's). DTCNN's have the locality and the translation invariance in the templates which determine the patterns of the connection between the cells. Using distributed arithmetic (DA) and the characteristics of DTCNN, we propose a simple implementation of DTCNN. The bus width in the cell-to-cell interconnection is reduced to one bit because of DA's bitwise operation. We implemented the reconfigurable architecture of DTCNN using programmable FPGA.

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.

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

본 논문에서는 연상 메모리 기능을 수행하는 공간-변형 셀룰라 신경망의 설계 방법론을 제안한다. 셀룰라 신경망에 관한 알려진 결과들과 새로 도출된 이론을 기반으로, 주어진 양극 벡터들을 기대할만한 성능으로 기억할 수 있는 공간-변형 셀룰라 신경망을 얻는 설계 방법론을 제안한다. 본 논문에서 제안된 설계 방법론의 주요 부분은 일반화된 고유값 문제(GEVP)와 선형행렬 부등식 문제(LMIP)를 푸는 것으로 이루어지며, 이 문제들은 현재 내부점 방법에 의해 효과적으로 풀릴 수 있다. 제안된 방법의 정당성은 설계 예제를 통해서 증명한다.

The Cellular Nonlinear Networks structure for Distance Transform (DT) and the robust optical flow detection algorithm based on the DT are proposed. 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 zooming image.

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.

인간 두뇌의 연상과 기억 작용의 모델링을 통한 구현의 일부분으로, 본 논문에서는 Hebb 의 학습방법과 non-cloning template를 사용하여 discrete-time cellular neural networks의 연상메모리 기능을 구현한다. 본 논문에서 사용된 학습방법은 각 셀의 인접한 셀과의 연결상태에 따라 하중값 메트릭스를 구현한다. 이러한 방법은 새로운 패턴의 추가 학습과 삭제가 쉽고, 또한 쉽게 구현 할 수 있는 장점이 있다. 이 방법으로 모의 실험에서는 교통표지판의 분류에 사용한다.

Darwin Machine은 자기 자신의 구조를 전자적인 속도로 진화해 나가는 하드웨어로서 복잡한 구조와 성질으 진화 기법을 사용하여 만들어 나가는 진화공학(Evolutionary Engineering)의 한 예이다. 하드웨어가 전자적인 속도로 진화하기 위해서는 각각으리 하드웨어 구성요소들이 병렬적으로 작동해햐 하는데 셀룰라 오토마타는 이러한 문제를 해결하는 적합한 구조이며, 하드췌어에 쉽게 이식할 수 있는 장점이 있다. 신경망의 학습 능력과 진한 연산을 이용하면 효율적인 진화를 유도할 수 있다. 본 논문에서는 이러한 하드웨어 구현을 위한 셀룰라 오토마타에 기반한 신경망을 보이고자 한다.