Cellular Automata Machine for Pattern Recognition

Complexity, 2016

This article designs an efficient two‐class pattern classifier utilizing asynchronous cellular automata (ACAs). The two‐state three‐neighborhood one‐dimensional ACAs that converge to fixed points from arbitrary seeds are used here for pattern classification. To design the classifier, (1) we first identify a set of ACAs that always converge to fixed points from any seeds, (2) each ACA should have at least two but not huge number of fixed point attractors, and (3) the convergence time of these ACAs are not to be exponential. To address the second issue, we propose a graph, coined as fixed point graph of an ACA that facilitates in counting the fixed points. We further perform an experimental study to estimate the convergence time of ACAs, and find there are some convergent ACAs which demand exponential convergence time. Finally, we identify there are 73 (out of 256) ACAs which can be effective candidates as pattern classifier. We use each of the candidate ACAs on some standard datasets...

Lecture Notes in Computer Science, 2004

This paper presents the design and application of a treestructured pattern classifier, built around a special class of linear Cellular Automata (CA), termed as Multiple Attractor CA (MACA). Since any non-trivial classification function is non-linear in nature, the principle of realizing the non-linear function with multiple (piece-wise) linear functions is employed. Multiple (linear) MACAs are utilized to address the classification of benchmark data used to evaluate the performance of a classifier. Extensive experimental results have established the potential of MACA based tree-structured pattern classifier. Excellent classification accuracy with low memory overhead and low retrieval time prove the superiority of the proposed pattern classifier over conventional algorithms.

2001

This paper reports a Cellular Automata (CA )model for pattern recognition.The special class of CA referred to as GMACA (Generalized Multiple Attractor Cellular Automata ),is employed to design the CA based associative memory for pattern recognition.The desired GMACA are evolved through the implementation of genetic algorithm (GA).An efficient scheme to ensure fast convergence of GA is also reported.Experimental results conform the fact that the GMACA based pattern recognizer is more powerful than the Hopfield network for memorizing arbitrary patterns.

… , 2008. ICDIM 2008. …, 2008

International Journal of Pattern Recognition and Artificial Intelligence, 2002

This paper reports an efficient technique of evolving Cellular Automata (CA) as an associative memory model. The evolved CA termed as GMACA (Generalized Multiple Attractor Cellular Automata), acts as a powerful pattern recognizer. Detailed analysis of GMACA rules establishes the fact that the rule subspace of the pattern recognizing CA lies at the edge of chaos — believed to be capable of executing complex computation.

Series in Computer Vision, 2011

An overview is given on the use of cellular automata for image processing. We first consider the number of patterns that can exist in a neighbourhood, allowing for invariance to certain transformation. These patterns correspond to possible rules, and several schemes are described for automatically learning an appropriate rule set from training data. Two alternative schemes are given for coping with gray level (rather than binary) images without incurring a huge explosion in the number of possible rules. Finally, examples are provided of training various types of cellular automata with various rule identification schemes to perform several image processing tasks.

Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods, 2019

Data classification is a well studied problem where the aim is to identify the categories in the data based on a training set. Various machine learning methods have been utilized for the problem. On the other side, cellular automata have drawn the attention of researchers as the system provides a dynamic and a discrete model for computation. In this study a novel approach is proposed for the classification problem. The method is based on formation of classes in a cellular automata by the interaction of neighborhood cells. Initially, the training data instances are assigned to the cells of a cellular automaton. The state of a cell denotes the class assignment of that point in the instance space. At the beginning of the process, only the cells that have a data instance have class assignments. However, these class assignments are spread to the neighbor cells based on a rule inspired by the heat transfer process in nature. The experiments carried out denote that the model can identify the categories in the data and promising results have been obtained.

… & Mathematics with …, 1997

ln the past, Cellular Automata based models and machines [I] have been proposed for simulation of physical systems without any analytical insight into the behaviour of the underlying simulation machine. This paper makes a significant departure from this traditional approach. An elegant mathematical model using simple matrix algebra is reported in this paper for characterizing the behaviour of two-dimensional nearest neighbourhood linear cellular automata with null and periodic boundary conditions. Based on this mathematical model, a VLSI architecture of a Cellular Automata Machine (CAM) has been proposed. Interesting applications of CAM in the fields of image analysis and fractal image generation are also reported.

IEICE Transactions on Information and Systems, 2005

This paper investigates the application of the computational model of Cellular Automata (CA) for pattern classification of real valued data. A special class of CA referred to as Fuzzy CA (FCA) is employed to design the pattern classifier. It is a natural extension of conventional CA, which operates on binary string employing boolean logic as next state function of a cell. By contrast, FCA employs fuzzy logic suitable for modeling real valued functions. A matrix algebraic formulation has been proposed for analysis and synthesis of FCA. An efficient formulation of Genetic Algorithm (GA) is reported for evolution of desired FCA to be employed as a classifier of datasets having attributes expressed as real numbers. Extensive experimental results confirm the scalability of the proposed FCA based classifier to handle large volume of datasets irrespective of the number of classes, tuples, and attributes. Excellent classification accuracy has established the FCA based pattern classifier as an efficient and cost-effective solutions for the classification problem.

Lecture Notes in Computer Science, 2008

The cellular automaton (CA) with multiple attractors in its state space creates immense interest to devise solutions for pattern classification, pattern recognition, design of associative memory, query processing, etc. This work characterizes the CA state space to explore the essential properties of 1-dimensional nonlinear cellular automata with single cycle attractors. The characterization of pseudo-exhaustive bits (P E bits) is done to uniquely identify the attractor set of such a CA. Theoretical framework thus evolved provides means to synthesize a CA for a given attractor set with specified P E bits.

Cellular learning automata (CLA) is a distributed computational model which was introduced in the last decade. This model combines the computational power of the cellular automata with the learning power of the learning automata. Cellular learning automata is composed from a lattice of cells working together to accomplish their computational task; in which each cell is equipped with some learning automata. Wide range of applications utilizes CLA such as image processing, wireless networks, evolutionary computation and cellular networks. However, the only input to this model is a reinforcement signal and so it cannot receive another input such as the state of the environment. In this paper, we introduce a new model of CLA such that each cell receives extra information from the environment in addition to the reinforcement signal. The ability of getting an extra input from the environment increases the computational power and flexibility of the model. We have designed some new algorithms for solving famous problems in pattern recognition and machine learning such as classification, clustering and image segmentation. All of them are based on the proposed CLA. We investigated performance of these algorithms through several computer simulations. Results of the new clustering algorithm shows acceptable performance on various data sets. CLA-based classification algorithm gets average precision 84% on eight data sets in comparison with SVM, KNN and Naive Bayes with average precision 88%, 84% and 75%, respectively. Similar results are obtained for semi-supervised classification based on the proposed CLA.

Real-Time Imaging, 1997

his paper presents a new, fast geometrical shape recognition technique based on the properties of cellular automata (CA). The VLSI implementation of the architecture developed for this Tpur pose is also presented. The digitized binary image of the geometrical shape is loaded onto a 2D CA grid. This binary image is the initial global state of the CA. The CA evolves in time until a final stable global state is reached. The geometrical shapes are classified into four different categories, according to the symmetries of their final stable global state, and are then recognized. Eleven geometrical shapes have been recognised using the proposed technique. The die size dimensions of the chip for a 8 ϫ 8 pixel image are 2.56 mm ϫ 2.70 mm = 6.91 mm 2 , and its maximum frequency of operation is 35 MHz. Targeted applications include classification and inspection tasks in industry.

Lecture Notes in Computer Science, 2005

As the possibility of combining different classifiers into Multiple Classifier System (MCS) becomes an important direction in machine-learning, difficulties arise in choosing the appropriate classifiers to combine and choosing the way for combining their decisions. Therefore in this paper we present a novel approach -Classificational Cellular Automata (CCA). The basic idea of CCA is to combine different classifiers induced on the basis of various machine-learning methods into MCS in a non-predefined way. After several iterations of applying adequate transaction rules only a set of the most appropriate classifiers for solving a specific problem is preserved.

Intelligent Analysis of Multimedia Information, 2000

In this paper are presented solutions to develop algorithms for digital image processing focusing particularly on edge detection. Edge detection is one of the most important phases used in computer vision and image processing applications and also in human image understanding. In this chapter, implementation of classical edge detection algorithms it is presented and also implementation of algorithms based on the theory of Cellular Automata (CA). This work is totally related to the idea of understanding the impact of the inherently local information processing of CA on their ability to perform a managed computation at the global level. If a suitable encoding of a digital image is used, in some cases, it is possible to achieve better results in comparison with the solutions obtained by means of conventional approaches. The software application which is able to process images in order to detect edges using both conventional algorithms and CA based ones is written in C# programming language and experimental results are presented for images with different sizes and backgrounds.

Fundamenta Informaticae, 2008

Two new operators, namely, dependency vector (DV) and derived complement vector (DCV) are introduced in this paper to characterize the attractor basins of the additive fuzzy cellular automata (FCA) based associative memory, termed as fuzzy multiple attractor cellular automata (FMACA). The introduction of DV and DCV makes the complexity of the attractor basin identification algorithm linear in time. The characterization of the FMACA using DV and DCV establishes the fact that the FMACA provides both equal and unequal size of attractor basins. Finally, a set of algorithms is proposed to synthesize the FCA rules, attractors, and predecessors of attractors from the given DV and DCV in linear time complexity.