Applications Of Cellular Neural Networks Research Articles

A Study of Cellular Neural Networks with Vertex-Edge Topological Descriptors

The Cellular Neural Network (CNN) has various parallel processing applications, image processing, non-linear processing, geometric maps, high-speed computations. It is an analog paradigm, consists of an array of cells that are interconnected locally. Cells can be arranged in different configurations. Each cell has an input, a state, and an output. The cellular neural network allows cells to communicate with the neighbor cells only. It can be represented graphically; cells will represent by vertices and their interconnections will represent by edges. In chemical graph theory, topological descriptors are used to study graph structure and their biological activities. It is a single value that characterizes the whole graph. In this article, the vertex-edge topological descriptors have been calculated for cellular neural network. Results can be used for cellular neural network of any size. This will enhance the applications of cellular neural network in image processing, solving partial differential equations, analyzing 3D surfaces, sensory-motor organs, and modeling biological vision.

A novel memristive cellular neural network with time-variant templates

Summary A cellular neural network (CNN) is a massively parallel analog array processor capable of solving various complex processing problems by using specific templates that characterize the synaptic connections. The hardware implementation and applications of CNN have attracted a great deal of attention. Recently, memristors with nanometer-scale and variable gradual conductance have been exploited to make compact and programmable electric synapses. This paper proposes and studies a novel memristive CNN (Mt-CNN) with time-variant templates realized by memristor crossbar synaptic circuits. The template parameters are estimated analytically. The Mt-CNN provides a promising solution to hardware realization of real-time template updating processes, which can be used to effectively deal with various complicated problems of cascaded processing. Its effectiveness and advantages are demonstrated by practical examples of edge detection on noisy images.

Design Automation of Neural Network Applications Using Formal Techniques—Rapid Prototyping Using the CCC Synthesizer

Cellular neural network (CNN) implementations used in real time image processing are rapidly generated by a formal High-level synthesis (HLS) toolset in this work. Industrial and academic hardware design projects can benefit from the use of the Custom Coprocessors Compilation (CCC) HLS behavioral synthesise, via the massive reduction in design and verification time. The CCC tool is built with formal compiler-compiler, Logic Programming and XML validation techniques, thus the generated RTL VHDL or Verilog models are provably-correct. In this work, we rapidly modeled CNNs in the ADA programming language, compiled and verified along with all the necessary testbenches in GNU ADA. Edge-detection, halftoning and morphological processing applications were prototyped, so as to evaluate the CCC HLS method, which was the main contribution of this work. The combination of Logic Programming and RDF validation techniques, as well as prototyping of CNN applications made this work unique.

An efficient numerical integration algorithm for single-layer Raster cellular neural networks simulator

An efficient numerical integration algorithm for single layer Raster cellular neural networks(CNN) simulator is presented in this paper. The simulator is capable of performing CNN simulations for any size of input image, thus a powerful tool for researchers investigating potential applications of CNN. This paper reports an efficient algorithm exploiting the latency properties of CNN along with numerical integration techniques; these numerical integration techniques are Euler, Runge Kutta fourth-second order 4(2), and Runge Kutta fourth-third order 4(3). Simulation results and comparisons are also presented. Comparisons include CPU time, quality measures of the pictures used in comparison, step size used, the format of input pictures. The CPU time used here is the simulation time. Key words: Single-layer cellular neural networks, numerical integration algorithms, RK 4(2), RK 4(3).

Application of cellular neural network (CNN) to the prediction of missing air pollutant data

For air-quality assessments in most major urban centers, air pollutants are monitored using continuous samplers. Sometimes data are not collected due to equipment failure or during equipment calibration. In this paper, we predict daily air pollutant concentrations (PM 10 and SO 2) from the Yenibosna and Umraniye air pollution measurement stations in Istanbul for times at which pollution data was not recorded. We predicted these pollutant concentrations using the CNN model with meteorological parameters, estimating missing daily pollutant concentrations for two data sets from 2002 to 2003. These data sets had 50 and 20% of data missing. The results of the CNN model predictions are compared with the results of a multivariate linear regression (LR). Results show that the correlation between predicted and observed data was higher for all pollutants using the CNN model (0.54–0.87). The CNN model predicted SO 2 concentrations better than PM 10 concentrations. Another interesting result is that winter concentrations of all pollutants were predicted better than summer concentrations. Experiments showed that accurate predictions of missing air pollutant concentrations are possible using the new approach contained in the CNN model. We therefore proposed a new approach to model air-pollution monitoring problem using CNN.

Applications of Cellular Neural Networks to Noise Cancelation in Gray Images Based on Adaptive Particle-swarm Optimization

This paper develops a novel method for designing templates for discrete-time cellular neural networks (DTCNN) via an adaptive particle-swarm optimization (APSO) for gray image noise cancelation. Proper selection of the inertia weight for the APSO gives a balance between global and local searching. The research results show that a larger weight helps to increase the convergence speed while a smaller one benefits the convergence accuracy. This APSO-based method can automatically update template parameters of a discrete-time cellular neural network and optimize them to remove noise interference in polluted images. Finally, examples are given to illustrate the effectiveness of the proposed APSO-CNN methodology.

Raster cellular neural network simulator for image processing applications with numerical integration algorithms

In this paper, a universal simulator for cellular neural network (CNN) is presented. This simulator is capable of performing Raster simulation for any size of input image, and thus is a powerful tool for researchers investigating potential applications of CNN. This paper reports the latency properties of CNNs along with popular numerical integration algorithms; results and comparisons are also presented.

Fast Simulation Technique of Plane Circuits via Two-Layer CNN-Based Modeling

A fast time-domain simulation technique of plane circuits via two-layer Cellular Neural Network (CNN) -based modeling, which is necessary for power/signal integrity evaluation in VLSIs, printed circuit boards, and packages, is presented. Using the new notation expressed by the two-layer CNN, 1,553 times faster simulation is achieved, compared with Berkeley SPICE (ngspice). In CNN community, CNNs are generally simulated by explicit numerical integration such as the forward Euler and Runge-Kutta methods. However, since the two-layer CNN is a stiff circuit, we cannot analyze it by using an explicit numerical integration method. Hence, to analyze the two-layer CNN and reduce the computational cost, the leapfrog method is introduced. This procedure would open an application of CNN to electronic design automation area.

Implementation and application of cellular neural networks based on single electron device

This paper realizes cellular neural networks using the characteristic of negative differential resistance of hybrid single electron transistor and complementary metallic oxide semiconductor field effect transistor structure. The main building blocks consisting of cell core circuit, A and B template circuits are designed. Then a cellular neural network (CNN) is built and its application in image processing is studied. The computer simulation shows that the designed circuits are suitable for CNN implementation owing to its simple structure, low power dissipation and fast response. It could be used to form CNN of various scales so as to further increase the density of integrated circuits.

New LMI conditions for global exponential stability of cellular neural networks with delays

In this paper, we investigate further cellular neural networks model with delays. We allow the model to have nondifferentiable and unbounded signal function, and use linear matrix inequality (LMI) framework and Homeomorphism theorem to prove the existence and uniqueness of the equilibrium, and derive some new sufficient condition ensuring global exponential stability of the networks. Two examples with their numerical simulations are provided to show the correctness of our analysis. It is believed that these results are significant and useful for the design and applications of cellular neural networks.

GENERATION OF COMPLEX STOCHASTIC TEXTURES USING CELLULAR NEURAL NETWORKS

The following paper explores possibilities of an application of Cellular Neural Networks for spontaneous generation of complex stochastic textures. The considered class of textures includes images, which are combinations of large-scale and fine-scale stochastic patterns. Accurate modeling of properties of such complex stochastic fields by means of a single 1-neighborhood CNN poses great difficulties. Therefore, we propose a method that exploits texture decomposition into two elements and involves an application of two networks, designated for performing distinct partial tasks. The first step of the proposed CNN-based texture generation procedure focuses on modeling of a coarse, large-scale textural pattern. The second step refines this pattern into a final image that is expected to closely imitate a target texture.

Application of cellular neural network (CNN) method to the nuclear reactor dynamics equations

This paper describes the application of a multilayer cellular neural network (CNN) to model and solve the nuclear reactor dynamic equations. An equivalent electrical circuit is analyzed and the governing equations of a bare, homogeneous reactor core are modeled via CNN. The validity of the CNN result is compared with numerical solution of the system of nonlinear governing partial differential equations (PDE) using MATLAB. Steady state as well as transient simulations, show very good comparison between the two methods. We used our CNN model to simulate space-time response of different reactivity excursions in a typical nuclear reactor. On line solution of reactor dynamic equations is used as an aid to reactor operation decision making. The complete algorithm could also be implemented using very large scale integrated circuit (VLSI) circuitry. The efficiency of the calculation method makes it useful for small size nuclear reactors such as the ones used in space missions.

TEXTURE GENERATION USING CELLULAR NEURAL NETWORKS

The following paper introduces an application of Cellular Neural Networks for the generation of predetermined stochastic textures. The key element for the task realization is an appropriate selection of template elements, which should provide a transformation of initial, random CNN state into a stable equilibrium, featuring desired perceptual properties. A template derivation procedure comprises two steps: linear CNN design, followed by a template-refinement procedure that involves nonlinear optimization. In addition, a procedure that extends CNN texture rendition capabilities into a realm of non-pure stochastic textures is proposed.

A new approach to the structural features of the Aegean Sea: Cellular neural network

In this study, structural features in the Aegean Sea were investigated by application of Cellular Neural Network (CNN) and Cross-Correlation methods to the gravity anomaly map. CNN is a stochastic image processing technique, which is based on template optimization using neighbourhood relationships of pixels, and probabilistic properties of two-Dimensional (2-D) input data. The performance of CNN can be evaluated by various interesting real applications in geophysics such as edge detection, data enhancement and separation of regional/residual potential anomaly maps. In this study, CNN is used in edge detection of geological bodies closer to the surface, which are masked by other structures with various depths and dimensions. CNN was first tested for (prismatic) synthetic examples and satisfactory results were obtained. Subsequently, CNN/Cross-Correlation maps and bathymetric features were evaluated together to obtain a new structural map for most of the Aegean Sea. In our structural map, the locations of the faults and basins are generally in accordance with the previous maps from restricted areas based on seismic data. In the southern and southeastern parts of the Aegean Sea, E–W trending faults cut NE–SW trending basins and faults, similar to on-shore Western Anatolia. Also, in the western, central and northern parts of the Aegean Sea, all of these structures are truncated by NE-trending faults.

A new approach for edge detection of noisy image based on CNN

AbstractA new approach for edge detection of noisy image by cellular neural network (CNN) is proposed in this paper. In order to get the reasonable template, the statistical characteristics of image are utilized, and Gibbs image model is employed to describe the stochastic dependence of an edge pixel on its neighbourhood. Based on stochastic edge image models, edge detection of noisy image is equivalent to seeking a minimum of a cost function. If the template of CNN is designed carefully, the energy function can be mapped properly to the cost function of stochastic edge image model, then CNN can be used for seeking the minimum of cost function. Genetic algorithm is efficient in the field of optimization, and we also utilized this algorithm to get the correct form of template. The results of computer simulation confirm that the new approach is very effective. Furthermore, this result also confirms that we can design template for many different questions based on statistical image model, and the area of application of CNN will be widened. Copyright © 2003 John Wiley & Sons, Ltd.

CELLULAR NEURAL NETWORKS AND VISUAL COMPUTING

Brain-like information processing has become a challenge to modern computer science and chip technology. The CNN (Cellular Neural Network) Universal Chip is the first fully programmable industrial-sized brain-like stored-program dynamic array computer which dates back to an invention of Leon O. Chua and Lin Yang in Berkeley in 1988. Since then, many papers have been written on the mathematical foundations and technical applications of CNN chips. They are already used to model artificial, physical, chemical, as well as living biological systems. CNN is now a new computing paradigm of interdisciplinary interest. In this state of development a textbook is needed in order to recruit new generations of students and researchers from different fields of research. Thus, Chua's and Roska's textbook is a timely and historic publication. On the background of their teaching experience, they have aimed at undergraduate students from engineering, physics, chemistry, as well as biology departments. But, actually, it offers more. It is a brilliant introduction to the foundations and applications of CNN which is distinguished with conceptual and mathematical precision as well as with detailed explanations of applications in visual computing.

Cellular neural networks based on resonant tunnelling diodes

AbstractResonant tunnelling diodes (RTDs) have intriguing properties which make them a primary nanoelectronic device for both analogue and digital applications. We propose two different types of RTD‐based cells for the cellular neural network (CNN) which exhibit superior performance in terms of complexity, functionality, or processing speed compared to standard cells. In the first cell model, the resistor of the standard cell is replaced by an RTD, which results in a more compact and versatile cell which requires neither self‐feedback nor a non‐linear output function, and allows three stable equilibrium points. If a resonant tunnelling transistor (RTT) is used instead of the RTD, the dynamics can be controlled through its gate voltage as an additional network parameter. In a majority of CNN applications, bistable cells are sufficient. Utilizing RTD‐based bistable logic elements to store the state of the cell, switching occurs almost instantaneously as virtually no charge transfer is necessary, and it is possible to implement non‐linear connections in a straightforward manner. Hence, it turns out that RTD‐based CNNs are tailor‐made for the implementation of extremely fast bipolar operations and non‐linear templates. The ideas presented in this paper may also be beneficially applied to other types of circuits and systems such as A/D converters or sigma‐delta modulators. Copyright © 2001 John Wiley & Sons, Ltd.

Medical image segmentation based on cellular neural network

The application of cellular neural network (CNN) has made great progress in image processing. When the selected objects extraction (SOE) CNN is applied to gray scale images, its effects depend on the choice of initial points. In this paper, we take medical images as an example to analyze this limitation. Then an improved algorithm is proposed in which we can segment any gray level objects regardless of the limitation stated above. We also use the gradient information and contour detection CNN to determine the contour and ensure the veracity of segmentation effectively. Finally, we apply the improved algorithm to tumor segmentation of the human brain MR image. The experimental results show that the algorithm is practical and effective.

Theory, design and applications of Cellular Neural Networks

Theory, design and applications of Cellular Neural Networks

Invertible operations on a Cellular Neural Network Universal Machine

This paper is concerned with the invertibility of parallel operations definable on two-dimensional binary arrays by means of a local Boolean function. In this way, it contributes to the theory of cellular automata and may open new potentialities to cellular neural network applications. We provide a theoretically new approach to the invertibility of two-dimensional additive maps which can be used to obtain detailed information on the behaviour of these operations. Other ways to make invertible operations are also investigated, including local maps which are additive in only one of the terms, and second-order cellular automata. The discussed techniques yield a rich variety of invertible operations on infinite and/or finite two-dimensional binary arrays. When implemented on CNN Universal Chips, all of these operations, performed by TeraOPS speed, become subroutines of a 2D analogic algorithm. These operations can be used in 2D cryptography. © 1998 John Wiley & Sons, Ltd.