Discrete-time Cellular Neural Networks Research Articles

Convergence of Discrete-Time Cellular Neural Networks with Application to Image Processing

The paper considers a class of discrete-time cellular neural networks (DT-CNNs) obtained by applying Euler’s discretization scheme to standard CNNs. Let [Formula: see text] be the DT-CNN interconnection matrix which is defined by the feedback cloning template. The paper shows that a DT-CNN is convergent, i.e. each solution tends to an equilibrium point, when [Formula: see text] is symmetric and, in the case where [Formula: see text] is not positive-semidefinite, the step size of Euler’s discretization scheme does not exceed a given bound ([Formula: see text] is the [Formula: see text] unit matrix). It is shown that two relevant properties hold as a consequence of the local and space-invariant interconnecting structure of a DT-CNN, namely: (1) the bound on the step size can be easily estimated via the elements of the DT-CNN feedback cloning template only; (2) the bound is independent of the DT-CNN dimension. These two properties make DT-CNNs very effective in view of computer simulations and for the practical applications to high-dimensional processing tasks. The obtained results are proved via Lyapunov approach and LaSalle’s Invariance Principle in combination with some fundamental inequalities enjoyed by the projection operator on a convex set. The results are compared with previous ones in the literature on the convergence of DT-CNNs and also with those obtained for different neural network models as the Brain-State-in-a-Box model. Finally, the results on convergence are illustrated via the application to some relevant 2D and 1D DT-CNNs for image processing tasks.

Weak-Strong Self-Adapting Fuzzy Neural Classifier for Dynamic Object Detection in RGBD Videos

This paper presents a fuzzy neural method to model background from videos in order to detect dynamic objects. The method includes a weak fuzzy classifier that performs an initial foreground and background separation based on color and depth differences between the actual frame and background models. The outputs of this fuzzy system are weighted according to the result of the color and depth noise modeling. A degree of uncertainty and the strength of decisions, in combination with the weighting results, are used by the method to define more accurately the dynamic objects through a strong fuzzy classifier. The final stage of foreground detection is implemented with a Discrete-Time Cellular Neural Network to improve the foreground definition. Finally, the color and depth background models are updated based on a fuzzy learning rate strategy. The method was evaluated with the new SBM-RGBD database and compared against several state-of-the-art methods showing a similar or better performance considering the quantitative and qualitative evaluations.

Exponential Stability of Discrete-Time Cellular Uncertain BAM Neural Networks with Variable Delays using Halanay-Type Inequality

Exponential Stability of Discrete-Time Cellular Uncertain BAM Neural Networks with Variable Delays using Halanay-Type Inequality

Behavioral models of nonlinear filters based on discrete time cellular neural networks

The nonlinear dynamic system modeling based on the input/output relationship results from solving the approximation problem. One can distinguish two large classes: polynomials and neural networks. The different types of neural networks draw attention. The discrete time feedforward cellular neural network is suggested for filtering non-Gaussian noise, as well as the example of nonlinear filters modeling to cancel the impulse noise is represented.

Bayesian estimation of discrete-time cellular neural network coefficients

Bayesian estimation of discrete-time cellular neural network coefficients

Simulation of nuclear reactor dynamics equations using reconfigurable computing

This paper describes the application of a multilayer discrete-time cellular neural network (DT-CNN1) and its hardware implementation on a field programmable gate array (FPGA2) to model and simulate the nuclear reactor dynamics equations. A new computing architecture model based on FPGA and its detailed hardware implementation are proposed for accelerating the solution of nuclear reactor dynamics equations. The proposed FPGA-based reconfigurable computing platform is implemented on a Xilinx FPGA device and is utilized to simulate step and ramp perturbation transients in typical 2D nuclear reactor cores. Properties of the implemented specialized architecture are examined in terms of speed and accuracy against the numerical solution of the nuclear reactor dynamics equations using MATLAB and C programs. Steady state as well as transient simulations, show a very good comparison between the two methods. Also, the validity of the synthesized architecture as a hardware accelerator is demonstrated.

A 181 GOPS AKAZE Accelerator Employing Discrete-Time Cellular Neural Networks for Real-Time Feature Extraction.

This paper proposes a real-time feature extraction VLSI architecture for high-resolution images based on the accelerated KAZE algorithm. Firstly, a new system architecture is proposed. It increases the system throughput, provides flexibility in image resolution, and offers trade-offs between speed and scaling robustness. The architecture consists of a two-dimensional pipeline array that fully utilizes computational similarities in octaves. Secondly, a substructure (block-serial discrete-time cellular neural network) that can realize a nonlinear filter is proposed. This structure decreases the memory demand through the removal of data dependency. Thirdly, a hardware-friendly descriptor is introduced in order to overcome the hardware design bottleneck through the polar sample pattern; a simplified method to realize rotation invariance is also presented. Finally, the proposed architecture is designed in TSMC 65 nm CMOS technology. The experimental results show a performance of 127 fps in full HD resolution at 200 MHz frequency. The peak performance reaches 181 GOPS and the throughput is double the speed of other state-of-the-art architectures.

Cellular Neural Network-Based Methods for Distributed Network Intrusion Detection

According to the problems of current distributed architecture intrusion detection systems (DIDS), a new online distributed intrusion detection model based on cellular neural network (CNN) was proposed, in which discrete-time CNN (DTCNN) was used as weak classifier in each local node and state-controlled CNN (SCCNN) was used as global detection method, respectively. We further proposed a new method for design template parameters of SCCNN via solving Linear Matrix Inequality. Experimental results based on KDD CUP 99 dataset show its feasibility and effectiveness. Emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation which allows the distributed intrusion detection to be performed better.

Segmentation of video background regions based on a DTCNN-clustering approach

We propose a novel algorithm for segmentation of video background models in time-variant scenarios. It is robust to gradual or abrupt illumination changes, diverse kind of noises, and even scenario variation. The algorithm generates regions according to the scene composition by keeping region segmentation coherence. The proposed method based on a discrete-time cellular neural network estimates the number regions in the current background model, and then, a modified k-means algorithm is used to achieve segmentation. The findings demonstrate the robustness of the method and its superiority over two state of the art scene segmentation algorithms.

State Estimation for Discrete-Time Fuzzy Cellular Neural Networks with Mixed Time Delays

This paper is concerned with the exponential state estimation problem for a class of discrete-time fuzzy cellular neural networks with mixed time delays. The main purpose is to estimate the neuron states through available output measurements such that the dynamics of the estimation error is globally exponentially stable. By constructing a novel Lyapunov-Krasovskii functional which contains a triple summation term, some sufficient conditions are derived to guarantee the existence of the state estimator. The linear matrix inequality approach is employed for the first time to deal with the fuzzy cellular neural networks in the discrete-time case. Compared with the present conditions in the form ofM-matrix, the results obtained in this paper are less conservative and can be checked readily by the MATLAB toolbox. Finally, some numerical examples are given to demonstrate the effectiveness of the proposed results.

Stability of Impulsive Cellular Neural Networks with Time-varying Delays

The problems of exponential stability and exponential convergence rate for a class of impulsive cellular neural networks with time-varying delays are studied. By means of the Lyapunov stability theory and discrete-time Halanay-type inequality technique, stability criteria for ensuring global exponential stability of no-impulsive discrete-time cellular neural networks and impulsive discrete-time cellular neural network with time-varying delays are derived respectively, and the estimated exponential convergence rate is provided as well. Finally, the validity of the obtained results is shown by two numerical examples.

CNNEDGEPOT: CNN based edge detection of 2D near surface potential field data

All anomalies are important in the interpretation of gravity and magnetic data because they indicate some important structural features. One of the advantages of using gravity or magnetic data for searching contacts is to be detected buried structures whose signs could not be seen on the surface. In this paper, a general view of the cellular neural network (CNN) method with a large scale nonlinear circuit is presented focusing on its image processing applications. The proposed CNN model is used consecutively in order to extract body and body edges. The algorithm is a stochastic image processing method based on close neighborhood relationship of the cells and optimization of A, B and I matrices entitled as cloning template operators. Setting up a CNN (continues time cellular neural network (CTCNN) or discrete time cellular neural network (DTCNN)) for a particular task needs a proper selection of cloning templates which determine the dynamics of the method. The proposed algorithm is used for image enhancement and edge detection.The proposed method is applied on synthetic and field data generated for edge detection of near-surface geological bodies that mask each other in various depths and dimensions. The program named as CNNEDGEPOT is a set of functions written in MATLAB software. The GUI helps the user to easily change all the required CNN model parameters. A visual evaluation of the outputs due to DTCNN and CTCNN are carried out and the results are compared with each other. These examples demonstrate that in detecting the geological features the CNN model can be used for visual interpretation of near surface gravity or magnetic anomaly maps.

Existence and Global Stability of a Periodic Solution for Discrete‐Time Cellular Neural Networks

A novel sufficient condition is developed to obtain the discrete‐time analogues of cellular neural network (CNN) with periodic coefficients in the three‐dimensional space. Existence and global stability of a periodic solution for the discrete‐time cellular neural network (DT‐CNN) are analysed by utilizing continuation theorem of coincidence degree theory and Lyapunov stability theory, respectively. In addition, an illustrative numerical example is presented to verify the effectiveness of the proposed results.

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.

Existence of periodic solution for discrete-time cellular neural networks with complex deviating arguments and impulses

A class of discrete-time cellular neural networks with complex deviating arguments and impulses are considered. Sufficient conditions for the existence of periodic solution are obtained by using contraction theorem and inequality techniques. The results of this paper are new. An example is employed to illustrate our results.

MEMRISTOR CELLULAR AUTOMATA AND MEMRISTOR DISCRETE-TIME CELLULAR NEURAL NETWORKS

In this paper, we design a cellular automaton and a discrete-time cellular neural network (DTCNN) using nonlinear passive memristors. They can perform a number of applications, such as logical operations, image processing operations, complex behaviors, higher brain functions, RSA algorithm, etc. By modifying the characteristics of nonlinear memristors, the memristor DTCNN can perform almost all functions of memristor cellular automaton. Furthermore, it can perform more than one function at the same time, that is, it allows multitasking.

Existence of periodic solutions and closed invariant curves in a class of discrete-time cellular neural networks

This paper discusses the dynamical behavior of excitatory–inhibitory discrete-time cellular neural networks (DTCNNs) with piecewise linear output functions. Our analysis shows that such DTCNNs have periodic solutions and closed invariant curves, and all their solutions, except for fixed points, eventually stay on the closed invariant curves. Moreover, these results are also illustrated by examples and figures. These results demonstrate that excitatory–inhibitory DTCNNs can exhibit permanent nonlinear oscillations. Moreover, such DTCNNs with permanent nonlinear oscillations may be chosen arbitrarily to close a DTCNN satisfying the SP-Condition which ensures the complete stability of DTCNNs. Thus, this work indicates that the SP-Condition on complete stability is not robust.

Analysis of Complete Stability for Discrete-Time Cellular Neural Networks with Piecewise Linear Output Functions

This letter discusses the complete stability of discrete-time cellular neural networks with piecewise linear output functions. Under the assumption of certain symmetry on the feedback matrix, a sufficient condition of complete stability is derived by finite trajectory length. Because the symmetric conditions are not robust, the complete stability of networks may be lost under sufficiently small perturbations. The robust conditions of complete stability are also given for discrete-time cellular neural networks with multiple equilibrium points and a unique equilibrium point. These complete stability results are robust and available.

Cellular neural network

From the Publisher: The definitive reference for the world of Cellular Neural Networks (CNN). Demonstrates basic notions and possibilities using examples which include global optimization in a single transient, color halftoning and a CNN algorithm containing several cloning templates for detecting almost invisible defects in a textile pattern. The section on theory describes and analyzes discrete-time CNN. VLSI implementations detail the design of the first fully tested CNN chip and the first programmable CNN silicon chip. Features a discussion of design tools and applications. A versatile CNN software simulator accompanies the book. Designed for standard PCs under MS-DOS, this user-friendly program allows users to visualize and test their own ideas. The disk and user's manual form an essential part of this package.

Design and Analysis of High-Capacity Associative Memories Based on a Class of Discrete-Time Recurrent Neural Networks

This paper presents a design method for synthesizing associative memories based on discrete-time recurrent neural networks. The proposed procedure enables both hetero- and autoassociative memories to be synthesized with high storage capacity and assured global asymptotic stability. The stored patterns are retrieved by feeding probes via external inputs rather than initial conditions. As typical representatives, discrete-time cellular neural networks (CNNs) designed with space-invariant cloning templates are examined in detail. In particular, it is shown that procedure herein can determine the input matrix of any CNN based on a space-invariant cloning template which involves only a few design parameters. Two specific examples and many experimental results are included to demonstrate the characteristics and performance of the designed associative memories.