Cellular neural network with trapezoidal activation function

This paper presents a cellular neural network (CNN) scheme employing a new non‐linear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly non‐separable data points and realize Boolean operations (including eXclusive OR) by using only a single‐layer CNN. In order to simplify the stability analysis, a feedback matrix W is defined as a function of the feedback template A and 2D equations are converted to 1D equations. The stability conditions of CNN with TAF are investigated and a sufficient condition for the existence of a unique equilibrium and global asymptotic stability is derived. By processing several examples of synthetic images, the analytically derived stability condition is also confirmed. Copyright © 2005 John Wiley & Sons, Ltd.     

Guiding a mobile robot with cellular neural networks

We show how cellular neural networks (CNNs) are capable of providing the necessary signal processing needed for visual navigation of an autonomous mobile robot. In this way, even complex feature detection and object recognition can be obtained in real time by analogue hardware, making fully autonomous real‐time operation feasible. An autonomous robot was first simulated and then implemented by simulating the CNN with a DSP. The robot is capable of navigating in a maze following lines painted on the floor. Images are processed entirely by a CNN‐based algorithm, and navigation is controlled by a fuzzy‐rule‐based algorithm. Copyright © 2002 John Wiley & Sons, Ltd.     

Complete stability of feedback CNNs with dynamic memristors and second‐order cells

The paper considers a feedback cellular neural network (CNN) obtained by interconnecting elementary cells with an ideal capacitor and an ideal flux‐controlled memristor. It is supposed that during the analogue computation of the CNN the memristors behave as dynamic elements, so that each dynamic memristor (DM)‐CNN cell is described by a second‐order differential system in the state variables given by the capacitor voltage and the memristor flux. The proposed networks are called DM‐CNNs, that is CNNs using a dynamic (D) memristor (M). After giving a foundation to the DM‐CNN model, the paper establishes a fundamental result on complete stability, that is convergence of solutions toward equilibrium points, when the DM‐CNN has symmetric interconnections. Because of the presence of dynamic memristors, a DM‐CNN displays peculiar and basically different dynamic properties with respect to standard CNNs. First of all a DM‐CNN computes during the time evolution of the memristor fluxes, instead of the capacitor voltages as for a standard CNN. Furthermore, when a steady state is reached, the memristors keep in memory the result of the computation, that is the limiting values of the fluxes, while all memristor currents and voltages, as well as all currents, voltages, and power in the DM‐CNN vanish. Instead, for standard CNNs, currents, voltages, and power do not drop off when a steady state is reached. Copyright © 2016 John Wiley & Sons, Ltd.     

Multi‐template approach to realize central pattern generators for artificial locomotion control

Biologically inspired control of artificial locomotion often makes use of the concept of central pattern generator (CPG), a network of neurons establishing the locomotion pattern within a lattice of neural activity. In this paper a new approach, based on cellular neural networks (CNNs), for the design of CPGs is presented. From a biological point of view this new approach includes an approximated chemical synapse realized and implemented in a CNN structure. This allows to extend the results, previously obtained with a reaction‐diffusion‐CNN (RD‐CNN) for the locomotion control of a hexapod robot, to a more general class of artificial CPGs in which the desired locomotion pattern and the switching among patterns are realized by means of a spatio‐temporal algorithm implemented in the same CNN structure. Copyright © 2002 John Wiley & Sons, Ltd.     

基于BERT-DSA-CNN和知识库的电网调控在线告警识别

电网调控告警识别是实现智能电网调度的重要环节。为提高电网调控告警识别的准确率,针对电网数据量庞大、有效信息提取困难、传统知识库知识迁移能力较差等问题,提出一种基于BERT-DSA-CNN和知识库的电网调控在线告警识别方法。首先在自然语言处理-深度学习的文本数据挖掘架构基础上,经过分词、去停用词等步骤,利用BERT模型获取电网调控告警信息词向量。然后将词向量输入CNN深度学习模型进行训练,并根据电网告警信息的特点引入DSA机制对CNN模型进行改进。最后提出了融合深度学习模型和传统知识库的电网调控在线告警识别方案。通过大量的算例结果分析得出,该方法相比Word2vec、传统CNN、传统知识库、离线学习等方法,具有更高的准确性和有效性,对不同的故障类型均具有较好的识别能力,为工程应用提供了一种思路。     

Implementing extra element theorem using nullor approach

This letter presents a method of implementing the extra element theorem (EET) on the computer by using the nullor method. The EET involves the calculation of two driving‐point impedances (dpi's), namely the conventional dpi, Z_d, and the null dpi, Z_n. The proposed method is used mainly for calculating Z_n. The method is simplified by representing any given circuit using exclusively RC‐nullor and R‐nullor equivalent circuits, thereby permitting the use of a single (parallel) version of the EET. The proposed method is applied to the linearized boost converter model to derive the fragmented version of the duty‐ratio‐to‐output transfer function. Copyright © 1999 John Wiley & Sons, Ltd.     

An efficient paradigm for wavelet‐based image processing using cellular neural networks

We propose a novel paradigm for cellular neural networks (CNNs), which enables the user to simultaneously calculate up to four subband images and to implement the integrated wavelet decomposition and a subsequent function into a single CNN. Two sets of experiments were designated to test the performance of the paradigm. In the first set of experiments, the effects of seven different wavelet filters and five feature extractors were studied in the extraction of critical features from the down‐sampled low‐low subband image using the paradigm. Among them, the combination of DB53 wavelet filter and the r=2 halftoning processor was determined to be most appropriate for low‐resolution applications. The second set of experiments demonstrated the capacity of the paradigm in the extraction of features from multi‐subband images. CNN edge detectors were embedded in a two‐subband digital wavelet transformation processor to extract the horizontal and vertical line features from the LH and HL subband images, respectively. A CNN logic OR operator proceeds to combine the results from the two subband line‐edge detectors. The proposed edge detector is capable of delineating more subtle details than using typical CNN edge detector alone, and is more robust in dealing with low‐contrast images than traditional edge detectors. The results demonstrate the proposed paradigm as a powerful and efficient scheme for image processing using CNN. Copyright © 2008 John Wiley & Sons, Ltd.     

The analogic cellular neural network as a bionic eye

The conception of the CNN universal machine has led quite naturally to the invention of the analogic CNN bionic eye (henceforth referred to simply as the bionic eye). the basic idea is to combine the elementary functions, the building blocks, of the retina and other 2 1/2 D sensory organs, algorithmically, in a stored programme of a CNN universal machine, through the use of artificial analogic programmes. the term bionic is defined in a rigorous way: it is a nonlinear, dynamic, spatiotemporal biological model implemented in a stored programme electronic (optoelectronic) device; this device is in our case the analogic CNN universal machine (or chip). The aim of this paper is to report on this new invention, particularly to electronic and computer engineers, in a tutorial way. We begin by summarizing (1) the biological aspects of the range of retinal function (the retinal universe), (2) the CNN paradigm and the CNN universal machine architecture and (3) the general principles of retinal modelling in CNN. Next we describe new CNN circuit and template design innovations that can be used to implement physiological functions in the retina and other sensory organs using the CNN universal machine. Finally we show how to combine given retinal functional elements implemented in the CNN universal machine with analogic algorithms to form the bionic retina. the resulting system can be used not only for simulating biological retinal function but also for generating functions that go far beyond biological capabilities. Several bionic retina functions, different topographic modalities and analogic CNN algorithms can then be combined to form the analogic CNN bionic eye. the qualitative aspects of the models, especially the range of dynamics and accuracy considerations in VLSI optoelectronic implementations, are outlined. Finally, application areas of the bionic eye and possibilities of constructing innovative devices based on this invention (such as the bionic eyeglass or the visual mouse) are described.     

Analysis of time-varying cellular neural networks for quadratic global optimization

The algorithm for quadratic global optimization performed by a cellular neural network (CNN) with a slowly varying slope of the output characteristic (see References 1 and 2) is analysed. It is shown that the only CNN which finds the global minimum of a quadratic function for any values of the input parameters is the network composed by only two cells. If the dimension is higher than two, even the CNN described by the simplest one-dimensional space-invariant template Â=[A₁, A₀, A₁], fails to find the global minimum in a subset of the parameter space. Extensive simulations show that the CNN described by the above three-element template works correctly within several parameter ranges; however, if the parameters are chosen according to a random algorithm, the error rate increases with the number of cells. © 1998 John Wiley & Sons, Ltd.     

Ring oscillator structures with explicitly separated nonlinearity

In this letter, we propose RC and LC nonlinear sinusoidal ring oscillator structures which can also generate subsidiary quadrature outputs. A tanh(x) nonlinearity is employed and is explicitly separated from the oscillators' linear building block (a first‐order all‐pass filter). Numerical and spice simulation results are given. Copyright © 2010 John Wiley & Sons, Ltd.     

Generation of n-double scrolls via cellular neural networks

N-double scrolls are chaotic attractors generated by Chua's circuit when its non-linear resistor characteristic is appropriately modified. They have recently been introduced, simulated and studied analytically by Suykens and Vandewalle. In this paper a new approach to generate n-double scroll attractors is introduced. They have been derived from a connection of three simple generalized cellular neural network cells called a state controlled CNN (SC-CNN). In this way it is established that n-double scroll attractors can be generated using an SC-CNN. The circuit implementation of the introduced system and some experimental results referring to the 2-double scroll attractor are reported.     

Use of lossless transmission‐line segments and shunt resistors for TLM diffusion modelling

In diffusion modelling by means of the transmission‐line matrix (TLM) method, a nodal arrangement of using lossless transmission‐line segments and series resistors is almost exclusively adopted and is currently considered as a standard approach. In this paper, the use of shunt resistors instead of series resistors is shown to represent an equally valid configuration. As a starting point, we have derived the telegrapher's equation in its most general form for TLM modelling of diffusion processes. A general algorithm based on the shunt‐resistor TLM model for implementing a numerical solution of the diffusion equation in multiple dimensions is given. Fundamental analysis and calculated examples confirm that the alternative shunt‐resistor configuration does not exhibit the unwanted absorption effects suggested by a recent paper (Internat. J. Numerical Model.: Electronic Networks, Devices and Fields 2002; 15 :261). Copyright © 2003 John Wiley & Sons, Ltd.     

Adaptive state feedback control by orthogonal approximation functions

For a class of feedback linearizable systems a state feedback adaptive control based on orthogonal approximation functions is designed, under the assumption of matching conditions for the uncertainties and of known bounds on a given compact set for the unknown non‐linear function. By virtue of Bessel inequality, the bound on the unknown non‐linear function gives a bound on the norm of the optimal weight vector for any choice of the number of approximating functions, which allows us to design a robust state feedback adaptive scheme with parameter projections. The resulting control algorithm has several advantages over available schemes: it does not require a priori bounds on the approximation error and on the optimal weight vector; it is repeatable, since the set of initial conditions for the state and the parameter estimates from which a class of reference signals is tracked is explicitly given; it characterizes the L_∞ and L₂ performance of the tracking error in terms of both the approximation and the parameter estimation error; it gives full flexibility in the choice of the number of approximating orthogonal functions. Copyright © 2002 John Wiley & Sons, Ltd.     

Compact CMOS implementation of a low‐power,current‐mode programmable cellular neural network

We report on the design and characterization of a full‐analog programmable current‐mode cellular neural network (CNN) in CMOS technology. In the proposed CNN, a novel cell‐core topology, which allows for an easy programming of both feedback and control templates over a wide range of values, including all those required for many signal processing tasks, is employed. The CMOS implementation of this network features both low‐power consumption and small‐area occupation, making it suitable for the realization of large cell‐grid sizes. Device level and Monte Carlo simulations of the network proved that the proposed CNN can be successfully adopted for several applications in both grey‐scale and binary image processing tasks. Results from the characterization of a preliminary CNN test‐chip (8×1 array), intended as a simple demonstrator of the proposed circuit technique, are also reported and discussed. Copyright © 2001 John Wiley & Sons, Ltd.     

Intercept measure of non‐linear stages

Intercept points are often used to describe the non‐linear performance of transceiver stages. This letter introduces an intercept measure. The intercept measure is a performance parameter including both intercept point and gain parameters. Particularly for low gain stages the intercept measure is useful and is better to use than the traditional output intercept point. The intercept measure is very useful as a single non‐linear performance parameter. Copyright © 2003 John Wiley & Sons, Ltd.     

The research and realization about automatic abstracting based on text clustering and natural language understanding

A method of realization of automatic abstracting based on text clustering and natural language understanding is explored, aimed at overcoming shortages of some current methods. The method makes use of text clustering and can realize automatic abstracting of multi-documents. The algorithm of twice word segmentation based on the title and first sentences in paragraphs is investigated. Its precision and recall is above 95 %. For a specific domain on plastics, an automatic abstracting system named TCAAS is implemented. The precision and recall of multi-document’s automatic abstracting is above 75%. Also, the experiments prove that it is feasible to use the method to develop a domain automatic abstracting system, which is valuable for further in-depth study. __________ Translated from Transactions of Beijing Institute of Technology (Natural Science Edition), 2005, 25(8): 705–709 (in Chinese)     

Fast recognition of bird sounds using extreme learning machines

Recognition of bird species by their sounds can bring considerable significance to both ecologists and ornithologists for measuring the biodiversity in the reserves, and studying climate changes. In this letter, we propose an efficient method based on an extreme learning machine (ELM) to classify bird sounds of 86 species of birds in very limited training and testing time. Experimental results prove that, the proposed ELM method can achieve the best recognition performance (81.1 %, unweighted average recall) compared with K‐nearest neighbours (K‐NN), support vector machines (SVM), neural networks (NN), and deep neural networks (DNN) pre‐trained by an autoencoder. In addition, ELM requires the least total time for training and testing (2.047 ± 0.034 s). © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Cellular neural networks for real-time DNA microarray analysis

A new methodology for real-time processing of DNA chip images is proposed. The idea developed here is to use the cellular neural network (CNN) array to analyze the DNA microarray. A CNN is an analog dynamic processor array that reflects this property: the processing elements interact directly within a finite local neighborhood. Due to its architecture, a two-dimensional CNN array is widely used to solve image processing and pattern recognition problems; moreover, the parallelism characteristic of this structure allows one to perform the most computationally expensive image analysis tasks three orders of magnitude faster than a classical CPU-based computer. This approach, thanks to the supercomputing capabilities of the CNN architecture, makes the whole DNA chip methodology fully parallel and also makes the processing phase, until now very time consuming, a real-time step. We discuss the results of testing an algorithm based on the CNN universal machine (CNN-UM) that has been designed to classify the image data. The algorithm is implemented in an analogic (analog and logic) microprocessor.     

Watermarking on CNN‐UM for image and video authentication

In this paper a new approach to fragile watermarking technique is introduced. This problem is particularly interesting in the field of modern multimedia applications, when image and video authentication are required. The approach exploits the cellular automata suitability to work as pseudorandom pattern generators and extends the related algorithms under the framework of the cellular non‐linear networks (CNNs). The result is a novel way to perform watermarking generation in real time, using the presently available CNN‐universal chip prototypes. In this paper, both the CNN algorithms for fragile watermarking as well as on‐chip experimental results are reported, confirming the suitability of CNNs to successfully act as real‐time watermarking generators. The availability of CNN‐based visual microprocessors allows to have powerful algorithms to watermark in real time images or videos for efficient smart camera applications. Copyright © 2004 John Wiley & Sons, Ltd.     

TLM for diffusion: consistent first time step. Two‐dimensional case

In initializing a transmission line matrix (TLM) diffusion model it is necessary to consider both initial concentration (temperature) and initial flow. As usual, only one of them is given; an auxiliary formula is necessary to calculate the distribution for the first time step. It has been shown that the standard formula may introduce additional numerical errors (International Journal of Numerical Modelling: Electronic Networks, Devices and Fields 1993; 6 :135; International Journal of Numerical Modelling: Electronic Networks, Devices and Fields 1993; 6 :161) and that these errors can persist over many time steps. In this paper, we show how an initial modification to the normal TLM algorithm can remove such errors, and we demonstrate the method by applying it to a two‐dimensional TLM heat diffusion model for a copper plate. Copyright © 2002 John Wiley & Sons, Ltd.