This paper introduces an analytic method to determine the sensitivity to random parameter variations of analog VLSI neural network architectures for linear image filtering. The authors compare the robustness of severa...
详细信息
This paper introduces an analytic method to determine the sensitivity to random parameter variations of analog VLSI neural network architectures for linear image filtering. The authors compare the robustness of several different circuit architectures for low pass filtering. This method can also determine which components within a particular architecture should specified the most precisely.< >
In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphases on applications to microscopy. We discuss the basic linear theory of the CNN...
详细信息
In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphases on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.< >
In this paper we report on a fast, complex and efficient implementation of the Cellular Neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 50...
详细信息
In this paper we report on a fast, complex and efficient implementation of the Cellular Neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 500,000 image frames per second.< >
The theory of fuzzy sets and the development of qualitative reasoning have had similar motivations: coping with complexity in reasoning about the properties of physical systems. An approach is described that utilizes ...
详细信息
The theory of fuzzy sets and the development of qualitative reasoning have had similar motivations: coping with complexity in reasoning about the properties of physical systems. An approach is described that utilizes fuzzy sets to develop a fuzzy qualitative simulation algorithm that allows a semiquantitative extension to qualitative simulation, providing three significant advantages over existing techniques. Firstly, it allows a more detailed description of physical variables, through an arbitrary, but finite, discretisation of the quantity space. The adoption of fuzzy sets also allows common-sense knowledge to be represented in defining values through the use of graded membership, enabling the subjective element in system modelling to be incorporated and reasoned with in a formal way. Secondly, the fuzzy quantity space allows more detailed description of functional relationships in that both strength and sign information can be represented by fuzzy relations holding against two or multivariables. Thirdly, the quantity space allows ordering information on rates of change to be used to compute temporal durations of the state and the possible transitions. Thus, an ordering of the evolution of the states and the associated temporal durations are obtained. This knowledge is used to develop an effective temporal filter that significantly reduces the number of spurious behaviors. Experimental results with the algorithm are presented and comparison with other recently proposed methods is made.
The theory of fuzzy sets and the development of qualitative modelling have had similar motivations: coping with complexity in reasoning about the behaviour of physical systems. The paper presents a synthesis of these ...
详细信息
The theory of fuzzy sets and the development of qualitative modelling have had similar motivations: coping with complexity in reasoning about the behaviour of physical systems. The paper presents a synthesis of these techniques, providing a fuzzy qualitative modelling method for performing qualitative simulation that offers significant advantages over existing qualitative simulation methods. The resulting simulation algorithm is termed FuSim hereafter. This development makes a significant contribution towards the full-scale industrial applications of qualitative modelling. The paper shows a typical example of utilising fuzzy qualitative models in fault diagnosis of continuous dynamic systems, based on an iterative search technique.< >
This paper considers decentralized control of linear multivariable systems in a discrete convolution framework. Definitions and theorems are presented that indicate whether a decentralized system is stable, minimal ph...
详细信息
This paper considers decentralized control of linear multivariable systems in a discrete convolution framework. Definitions and theorems are presented that indicate whether a decentralized system is stable, minimal phase and robust, and guide-lines are presented for choosing the loop interconnections. Existing steady-state results are extended to the dynamic case in terms of characteristic patterns and examples are given that implement the methodology using the simulation package CBSL.
Recent results are given on a computer-aided analytic/simulation methodology for designing a class of realizable FMS scheduling controls. It is implemented by means of a PC-oriented program package, PETSIM, written in...
详细信息
Recent results are given on a computer-aided analytic/simulation methodology for designing a class of realizable FMS scheduling controls. It is implemented by means of a PC-oriented program package, PETSIM, written in C+. It encompasses a bounded iterative sequence of dual-model building, simulation and performance evaluation based on Stochastic Petri Nets and Queueing Networks so that a sub-optimal plant activity sequence is obtained, and a Petri-net controller model derived. Analytic formulae are derived indicating lower and upper bounds on the desired solutions, together with simulation results.
A two-layer continuous-time cellular neural network for finding the Radon transform of a binary image is presented. The functionality of this cellular neural network follows from the functionality of the connected com...
详细信息
A two-layer continuous-time cellular neural network for finding the Radon transform of a binary image is presented. The functionality of this cellular neural network follows from the functionality of the connected component detector cellular neural network.
The programmability (as a stored program) of the CNN Universal Machine is discussed first. It is shown why and in which sense this machine is universal. A new type of algorithm, the analogic one, is introduced. The ap...
Various types of CNNs are summarized and the taxonomy of CNN is given according to the different types of grids, processors, interactions, and modes of operation. Next, the CNN Universal Machine is introduced. The arc...
暂无评论