Thomas Patrick Meyer, Fred C. Richards, Norman H. Packard · Physical Review Letters · 1989
A learning algorithm is developed to build a dynamical model from complex spatial data consisting of discrete values on a lattice evolving in time. The resulting dynamical system is a cellular automaton, and may be used for forecasting or for regenerating global spatial patterns. Part of the learning algorithm is a novel application of the genetic algorithm, originally developed in the field of machine learning. We outline extensions of this method to construct models for spatial dynamics that have continuous variables as well.
Cited by 18
Will Perkins, E. Tse, J. Medanić · 1978
Cited by 3
Karthik Sindhya, Jussi Hakanen · Computational methods in applied sciences · 2018
Cited by 1Open access
Salvatore Ingrassia, Simona C. Minotti, Giuseppe Incarbone · BOA (University of Milano-Bicocca) · 2010
Cluster-Weighted Modeling is a flexible statistical framework for modeling local relationships in heterogeneous populations on the basis on weighted combinations of local models. Besides the traditional approach based on Gaussian assumptions, here we consider Cluster Weighted Modeling based on Student-t distributions. In this paper we present an EM algorithm for parameter estimation in Cluster-Weighted models according to the maximum likelihood approach.
Cited by 0
Nickolai Alexandrov, Roland Luethy · Protein Science · 1998
A DNA/protein sequence comparison is a popular computational tool for molecular biologists. Finding a good alignment implies an evolutionary and/or functional relationship between proteins or genomic loci. Sequential similarity between two proteins indicates their structural resemblance, providing a practical approach for structural modeling, when structure of one of these proteins is known. The first step in the homology modeling is a construction of an accurate sequence alignment. The commonly used alignment algorithms do not provide an adequate treatment of the structurally mismatched residues in locally dissimilar regions. We propose a simple modification of the existing alignment algorithm which treats these regions properly and demonstrate how this modification improves sequence alignments in real proteins.
Cited by 19Open access
Compression Of Picture, A. K. Tiwari, R. V. Rajakumar · 2002
This paper concerns the intraframe coding of pictures. Conventionally the predictive coding methods use a two dimensional linear predictor which is based on the autoregressive model of the picture. This paper proposes two versions of a twodimensional lattice algorithm for linear prediction. This algorithm is arrived at by representing the forward prediction error as a function of a lower order predictor. This method is computationally efficient and possesses all the advantages of the lattice algorithm I.
Cited by 0
Munoz, Cesar, Carreno, Victor · Defense Technical Information Center (DTIC) · 2000
The Airborne Information for Lateral Spacing (AILS) program at NASA Langley Research Center aims at giving pilots the information necessary to make independent approaches to parallel runways with spacing down to 2500 feet in Instrument Meteorological Conditions. The AILS concept consists of accurate traffic information visible at the navigation display and an alerting algorithm which warns the crew when one of the aircraft involved in a parallel landing is diverting from the intended flight path. In this paper we present a model of aircraft approaches to parallel runways. Based on this model, we analyze the alerting algorithm with the objective of verifying its correctness. The formalization is conducted in the general verification system PVS.
Cited by 0
Zhang, Jincheng · Zenodo (CERN European Organization for Nuclear Research) · 2025
A sailboat is a vessel that uses wind power for navigation. Its navigation strategy is highly dependent on the changing characteristics of wind direction, sail angle, rudder direction, and the ocean environment. This paper proposes an optimization algorithm based on the sailboat navigation mechanism, called the Sailboat Navigation Optimization (SBOA-N). This algorithm simulates the sailboat's ability to sense and adjust its course in the wind field, exploit tidal perturbations, and collaborate with other sailboats to achieve a global optimization search. The algorithm incorporates sail angle adaptation, tidal perturbations, group collaboration, and a dynamic exploration weighting mechanism, and describes each calculation step with a complete mathematical formula. This algorithm not only preserves the physical characteristics of sailboat navigation but also provides an innovative search strategy, offering new solutions to complex optimization problems.
Cited by 0Open access
Pierre Moreau, David Durand, Jérôme Bosche et al. · 2020
People's movements say a lot about their activities. Whether it concerns sports, music (playing an instrument), at work, in re-education, each domain has its own specific moves. However, some of it, such as sports competition, need high-precision movements. Tools are available to measure movements in all sectors. First, sensors are placed on different strategic points on the person's body that allow us to retrieve temporal data from the body of the user. In this work, no camera is used for motion recognition in order to let the user free to go in different spaces. A considerable number of algorithms help for movement recognition such as deep learning, convolutional neural networks or dynamic modelling, but in most cases, cameras are used. So, our approach consists of two phases. First, model the users thanks to whole-body sensors and save characteristic movements. Second, we still use sensors, to model the test person to find characteristic movements depending on the activity.
Cited by 3
Paul Merrell, Dinesh Manocha · IEEE Transactions on Visualization and Computer Graphics · 2010
We present a method for procedurally modeling general complex 3D shapes. Our approach can automatically generate complex models of buildings, man-made structures, or urban data sets in a few minutes based on user-defined inputs. The algorithm attempts to generate complex 3D models that resemble a user-defined input model and satisfy various dimensional, geometric, and algebraic constraints to control the shape. These constraints are used to capture the intent of the user and generate shapes that look more natural. We also describe efficient techniques to handle complex shapes and highlight its performance on many different types of models. We compare model synthesis algorithms with other procedural modeling techniques, discuss the advantages of different approaches, and describe as close connection between model synthesis and context-sensitive grammars.
Cited by 71
Ang Li, Peter J. Stuckey, Sven Koenig et al. · Lecture notes in computer science · 2022
Cited by 8
Minghua Shi, Xiao Qing-xian, Zhou Ben-da et al. · Tehnicki vjesnik - Technical Gazette · 2017
Original scientific
Cited by 7Open access
Andrew Thompson · 2011
Abstract : The modeling of fractures typically uses the Poisson distribution to select the number of particles resulting from a fracture of a solid body. This applies to bullets when striking a plate. This report develops a method to model the number of subparticles using a mixture of Poisson distributions. The goal is to find the mixture with the smallest number of components that fits the data. Rather than attempting to find the distribution of lambda, it is assumed the values of lambda are clustered and the centroids of these clusters constitute a useful model.
Cited by 0
A. Naydysh, I. Balyuba, V Vereshchaha et al. · Modern problems of modeling · 2020
The paper considers a generalized algorithm for variable discrete geometric modeling (VDGM), as a separate direction of applied geometry with its theoretical justification and a set of practical methods and tools. Modern modeling methods are divided into discrete and continuous. Continuous (classical) methods are based on the receipt of a modeling function, which is usually analytical, which allows us to observe certain additional conditions of the problem or requirements for the result in the modeling process. At the same time, the obtained modeling function in a certain way affects the simulation result, imposing its own properties on it, which distorts the final result (sometimes even to a large extent). Therefore, modeling methods (discrete modeling) that exclude the search for a modeling function have become relevant, instead a specific algorithm for finding a solution is built. The construction of such an algorithm has certain (unique for each individual discrete modeling method) difficulties, and may require certain additional conditions and restrictions. In discrete modeling, the construction and calculation of a function is replaced by geometric constructions and transformations, which can greatly complicate the solution of the problem. Thus, the construction of the algorithm of the discrete modeling method (discrete geometric modeling) is a complex and urgent task requiring separate studies within each of the methods. This determines the relevance of considering this issue for discrete geometric modeling (DGM) and, accordingly, for the direction of variable discrete geometric modeling (VDGM). Algorithmic software is one of the important components of the complex problem of improving accuracy in the VDGM and its construction has not only scientific and technological, but also a methodological aspect. High simulation results are guaranteed by the algorithms that most fully take into account and ensure that related issues are taken into account (stability and convergence of computational schemes and algorithms, the possibility of introducing adapted coordinate systems, etc.). The basic requirements for the methods and algorithms of VDGM are determined by the results of many years of their numerous application in various problems of science and technology, as well as in various subject areas. Basically, these are: simplicity of computational algorithms; high accuracy; the ability to correct the solution to the extent that the simulation requirements are met; lack of oscillations. The paper presents a generalized VDGM algorithm, the initial data for which are experimental or statistical data on the phenomenon or process to be simulated, as well as the requirements of the modeling problem in terms of content, accuracy, criteria, etc. Its concretization to some formalized classes of problems of the VDGM are considered: – DPC thickening algorithms based on geometric relationships; – modeling based on discrete representations of polynomial functions; – algorithms for accounting a priori information; – DPC form control algorithms; – algorithms for solving systems of difference equations by methods of condensation identities; – algorithms for the transition from an uneven grid to a uniform one. Key words: variable discrete geometric modeling (VDGM), geometric image (GO), discrete geometric modeling (DGM), discretely presented curve (DPC), modeling accuracy.
Cited by 0Open access
Yonghung Tan, Chun‐Yi Su, Xuanju Dang · 2002
A gradient descent plus fuzzy control (GD+FC) learning strategy is proposed. In this method, the learning procedure is considered as a feedback control system that consists of a controlled process, a feedback mechanism, and a feedback controller. Therefore, the fuzzy control technique may be implemented in order to achieve fast and stable convergence in the learning procedure. After that the convergence feature of the proposed learning algorithm is investigated. Then, the proposed algorithm is used to train neural networks for system modeling. A comparison of the proposed algorithm with the other learning approaches, e.g. GD and PIDGD methods, is also illustrated. Finally, the article presents an example of system modeling for a temperature process with the proposed learning approach.
Cited by 0
George Karypis, Eui-Hong Han, Vipin Kumar · University of Minnesota Digital Conservancy (University of Minnesota) · 1999
Clustering in data mining is a discovery process that groups a set of data such that the intracluster similarity is maximized and the intercluster similarity is minimized. Existing clustering algorithms, such as K-means, PAM, CLARANS, DBSCAN, CURE, and ROCK are designed to find clusters that fit some static models. These algorithms can breakdown if the choice of parameters in the static model is incorrect with respect to the data set being clustered, or if the model is not adequate to capture the characteristics of clusters. Furthermore, most of these algorithms breakdown when the data consists of clusters that are of diverse shapes, densities, and sizes. In this paper, we present a novel hierarchical clustering algorithm called Chameleon that measures the similarity of two clusters based on a dynamic model. In the clustering process, two clusters are merged only if the inter-connectivity and closeness (proximity) between two clusters are high relative to the internal inter-connectivity of the clusters and closenessof items within the clusters. The merging process using the dynamic model presented in this paper facilitates discovery of natural and homogeneous clusters. The methodology of dynamic modeling of clusters used in Chameleon is applicable to all types of data as long as a similarity matrix can be constructed. We demonstrate the effectiveness of Chameleon in a number of data sets that contain points in 2D space, and contain clusters of different shapes, densities, sizes, noise, and artifacts. Experimental results on these data sets show that Chameleon can discover natural clusters that many existing state-of-the art clustering algorithms fail to find.
Cited by 33Open access
Xiaohong Li, Ran Liu, Zhiyong Feng et al. · Transactions of Tianjin University · 2009
Cited by 9
Petar Getsov · IOSR Journal of Engineering · 2014
The current article studies various predictable failure trajectories, observed during control signals loss scenarios. Using modeling techniques, certain failure mode algorithms are verified. The examined instances of failures are tested in the line-of-sight area. Certain autopilot failure regimes are studied and the resulting trajectories of airplane uncontrolled flight are scrutinized for determining failure resistant plane characteristics.
Cited by 0Open access
Yunfei Yue, T. T. Zhang, Chunyu Li et al. · 2025
An adaptive genetic algorithm for parameter extraction is proposed, which solves the problem of low efficiency of parameter extraction and improves the accuracy of parameter extraction. Firstly, adaptive parameter ranges are proposed to reduce the frequency of negative values of the intrinsic capacitive resistance, which reduces the amount of redundant calculations and makes the optimisation time much shorter. Secondly, for I-V, an adaptive weight matrix is added to the fitness function to increase the convergence and accuracy of the algorithm.
Cited by 0
Morell Higueras, Marc · RECERCAT (Consorci de Serveis Universitaris de Catalunya)
[CATALÀ] Aquest TFG tracta la implementació d'un algorisme de generació procedural que construeixi una estructura reminiscent a la d'un arbre de clima temperat, i també la implementació del pas de l'estructura a un model tridimensional, acompanyat de l'eina per a visualitzar el resultat i fer-ne l'exportació
Cited by 0Open access