Dana Vrajitoru

Indiana University South Bend | IUSB · Computer and Information Science

In this paper, we present an application of genetic algorithms to a problem of optimizing a car trajectory in a closed loop car race setting. The goal is to minimize the amount of turning that the car needs to do such that it can drive faster, or the total distance that it needs to travel to finish the race. We compare the results with a procedural...

In this paper, we are studying the application of a neural network to a problem related to autonomous car driving. In particular, we are interested in the correlation between noise in the data and the average error that can be achieved by the neural network, and study the issue using several data collections. We propose a measure of the noise that...

In this paper, we investigated the role of content and processes as they relate to games and programming in post-secondary computer science courses. Our examination found themes that can help computer science instructors teach both introductory and advanced programming topics. Our analysis was focused primarily on the theoretical and practical subj...

In this paper, we present a car driving system called " Gazelle " for a simulated racing competition. For this, we used both procedural methods and a neural network capable of learning. We hoped that using neural networks could lead the controller to derive more accurate equations for driving the car based on data acquired in the training process....

In this paper we present a game-playing algorithm for the game of Nine Men's Morris based on a small pattern database. The player is using a combination of game-specific heuris-tics and a pattern-based Bayesian network to make decisions about the next move. The Bayesian network is dynamically constructed and can be learned during the game play. The...

Practical Analysis of Algorithms introduces the essential concepts of algorithm analysis required by core undergraduate and graduate computer science courses, in addition to providing a review of the fundamental mathematical notions necessary to understand these concepts. Throughout the text, the explanations are aimed at the level of understanding...

In this paper we present an analysis of the complex- ity of a class of algorithms. These algorithms recursively explore a binary tree and need to make two recursive calls for one of the subtrees and only one for the other. We derive the complexity of these algorithms in the worst and in the best case and show the tree structures for which these cas...

In this paper we present a concurrent implementation of co-evolutionary genetic algorithms designed for shared memory architectures intended to take advantage of multi-core processor platforms. This algorithm divides the problems into sub-problems as opposed to the usual parallel approach dividing the population into niches. We analyze several aspe...

In this paper we present a concurrent implementation of genetic algorithms designed for shared memory architectures, intended to take advantage of multi-core processor platforms. Our algorithm divides the problems into sub-problems along the chromosome as opposed to the usual approach of dividing the population into niches. We show tests for timing...

In this paper we present a parallel implementation of genetic algorithms using a shared memory model designed to take advantage of multi-core processor platforms. Our algorithm divides the problems into sub- problems as opposed to the usual approach of dividing the population into niches. We propose an approach where the threads do not have to sync...

In this paper we present an adaptive autonomous car pilot developed for the TORCS competition environment. This software provides a multi-track competition system where the user can control a car on several different circuits and compete against other pre-defined pilots. Our pilot is composed of several control units based on the input available wi...

In this paper we present our experiments with devel- oping an intelligent agent using genetic programming, with the goal of exploring an environment with limited information in search for resources. The challenge con- sisted of evolving an agent browsing a world knowing only the altitude in a local neighborhood, looking for a balance food diet of g...

In this paper we introduce an application of multiobjec- tive optimization with genetic algorithms to the problem of graph drawing and explore the potential contribution of the genetic algorithm to solve this particular prob- lem. Given a weighted graph, we want to find a geo- metric position of every vertex (layout) consistent with the weights in...

This paper presents an effort at developing a robust, interactive framework for rendering 3D fire in real-time in a production environment. Many techniques of rendering fire in non real-time exist and are constantly employed by the movie industry and have directly influenced and inspired real-time fire rendering, including this paper. Macrolevel be...

In this paper we present an application of genetic algorithms to an autonomous pilot designed for motorized single-track vehicles (motorcycles). The pilot is implemented as a multi-agent application using a physical model of the motorcycle and is embedded in an interactive application. We compare the performance of the configuration obtained by gen...

In this paper, we are modelling a situation in an evolutionary population where a genetically inherited feature is part of a distribution of probabilities that gives it low expectations to be present in the next generation, for example, recessive features. In many such cases observed in nature, such features seem to persist longer than predicted by...

Evolution in the context of genetic algorithms is driven by the fitness function. For some applications, this factor is not easy to compute and coevolution represents an alternate solution. Thus, competition between individuals in the population can be used as a performance measure instead of an objective function, when the nature of the problem al...

In this paper we introduce an application of multiobjec- tive optimization with genetic algorithms to the problem of graph drawing and explore the potential contribution of the genetic algorithms for this particular problem.

In this paper we present an algorithm for facet detection in graphs. We dene the facets as simple cycles in the graph minimizing the length. Our algorithm detects the local structure of simple cycles intersecting in a particu- lar vertex of the graph. For this purpose, we reduce the problem to an instance of the Traveling Salesman in an in- duced c...

Chatterbots are computer programs that simulate intelligent conversation. They are situated between games and toys, as their aim is mostly to be entertaining, but the user doesn't have to follow precise rules when playing with the program. Currently business and educational applications have started to emerge as a further development of the idea of...

In this paper we introduce an application of real-coded ge- netic algorithms to the problem of consistent graph layouts and explore the potential contribution of the genetic algo- rithms for this particular problem. Given a weighted graph, we want to nd a geometric position of every vertex (lay- out) consistent with the weights in the graph. Among...

This report presents a model for simulating various reproduction modes and types restrictions from nature with the genetic algorithms. We con-sider three reproduction modes, which are self-fertilizing, hermaphrodite excluding self fertilization, and with two differentiated gender types (male and female). We start with a model in which the reproduct...

In this paper we present three algorithms that build graph layouts for undirected, weighted graphs. Our goal is to generate layouts that are consistent with the weights in the graph. All of the algorithms are force-oriented and have been successful in solving the problem up to a certain precision. They all start with a random layout and improve it...

In this paper we introduce an application of real-coded genetic algorithms to the problem of consistent graph layout and exploring the role of mutation for this particular problem. We introduce several forms of mutation, some of which being specific to this problem, and show that the choice of this operator can have a great impact on the performanc...

In this paper we're introducing a physically-based model of a motorized single-track vehicle (a motorcycle) that we have implemented in an interactive application. The vehi-cle can be driven by a multi-agent autonomous pilot using a set of perceptual information to make decisions on the control units of the vehicle.

Asphalt pavement distress, the various defects such as holes and cracks, represent a significant engineering and economic concern. It is estimated that pavement defects cause damage costing $10 billion each year in the United States alone (10). One important step in managing this problem is accurately assessing the pavement condition and its change...

In this paper we introduce a visualization application for a vehicle simulation with an automatic pilot. The application is written in OpenGL and includes a model of a vehicle (a motorcycle) based on the physical laws of motion, including kinematics, gravitation, and friction. The vehicle can be controlled by the user through keyboard and mouse com...

In this paper we present three algorithms that build graph layouts for undirected, weighted graphs. Our goal is to generate layouts that are consistent with the weights in the graph. All of the algorithms are force-oriented and have been successful in solving the problem up to a certain precision. They all start with a random layout and improve it...

Chatterbots are computer programs that simulate intelligent conversation. They make use of various techniques such as pattern matching, indexing, sentence reconstruction, and even natural language processing. In this paper we present an approach to chatterbots that mixes pattern matching with indexing and query matching methods inspired by informat...

Abstract Several studies on the variations of the crossover operator have shown that each of them presents speci?c properties that are interesting under particular circumstances The advan - tages of each operator over others are often contradictory and the best operator depends on the problem being solved This paper is based on the assumption that...

Chatterbots are computer programs that simulate intelligent conversation. They make use of various techniques such as pattern matching, indexing, sentence reconstruction, and even natural language processing. In this paper we present an approach to chatterbots that mixes pattern matching with indexing and query matching methods inspired from inform...

This article outlines the capabilities of a scientific visualization toolkit called DataViewer, and compares it to analogous software. DataViewer was originally designed for the construction of the visualization part of certain computational steering packages, and consequently it is particularly straightforward to closely couple DataViewer with num...

Gender separation is a largely encountered in the natural systems that allows the preservation of the genetic diversity in a species. In this paper, we want to analyse the mechanism by which this reproduction mode may have evolved and the way it inuences the evolution of a population toward an optimal individual.

This article outlines the capabilities of a scientific visualization toolkit called Data Viewer and compares it to analogous software. DataViewer was originally designed for the construction of the visualization part of certain computational steering packages, and consequently it is particularly straightforward to closely couple DataViewer with num...

Most of the parallel implementations of genetic algorithms divide the population into several nests or niches that evolve independently and exchange information periodically. In this paper we propose a different approach, where instead of the population, we split the problem to be solved among the processes. The new model has shown an interesting p...

This paper describes and evaluates a retrieval scheme combining the OKAPI probabilistic retrieval model with various vector-space schemes. In this study, each retrieval strategy represents both queries and documents using the same set of single terms; however they weight them differently. To combine these search schemes, we do not apply a given com...

This paper describes and evaluates a retrieval model that considers the problem of data fusion and collection fusion as two faces of the same coin. To establish a clear theoretical foundation for combining various sources of evidence provided either by different search schemes (data fusion) or by distributed information services (collection fusion)...

This paper describes and evaluates a retrieval scheme, or more precisely an additional retrieval mechanism based on interdocument relationships, that can be integrated in almost all existing retrieval schemes (e.g., Boolean, hybrid Boolean, vector-processing or probabilistic models). The intent of our approach consists of inferring knowledge about...

Searching within the context of information retrieval may be viewed as a communication process between the users and the indexers (or the authors). It is known that in expressing the same concept or idea, different people tend to use different words or phrases, and also that the meaning of words attached to document surrogates tends to change over...

. Artificial intelligence models may be used to improve performance of information retrieval (IR) systems and the genetic algorithms (GAs) are an example of such a model. This paper presents an application of GAs as a relevance feedback method aiming to improve the document representation and indexing. In this particular form of GAs, various docume...

Like other learning paradigms, the performance of the genetic algorithms (GAs) is dependent on the parameter choice, on the problem representation, and on the fitness landscape. Accordingly, a GA can show good or weak results even when applied on the same problem. Following this idea, the crossover operator plays an important role, and its study is...

Information retrieval proposes solutions for searching, in a given set of objects, for those replying to a given description. Often, these objects are documents, however other forms like image, video, sounds can be considered. Besides statistical approaches, artificial intelligence models present an attractive paradigm to improve performance in IR...

Genetic algorithms (GAs) search for good solutions to a problem by operations inspired from the natural selection of living beings. Among their many uses, we can count information retrieval (IR). In this field, the aim of the GA is to help an IR system to find, in a huge documents text collection, a good reply to a query expressed by the user. The...

Thèse sciences Neuchâtel. Bibliogr.

Summary This paper describes and evaluates a retrieval model that considers the problem of data fusion and collection fusion as two faces of the same coin. To establish a clear theoretical foundation for combining various sources of evidence provided either by different search schemes (data fusion) or by distributed information services (collection...

Summary

Summary This paper describes and evaluates a retrieval scheme, or more precisely an additional retrieval mechanism based on interdocument relationships, that can be integrated in almost all existing retrieval schemes (e.g., Boolean, hybrid Boolean, vector-processing or probabilistic models). The intent of our approach consists of inferring knowledg...

A graph layout is a geometrical representation of a graph such that the vertexes are assigned points and the edges become line segments. In this paper we present two probabilistic algorithms that build layouts for weighted graphs such that the geometrical distances between the vertexes are consistent with the weights of the edges. Both methods star...