Ricardo Contreras

Using Genetic Algorithms to Model Road Networks

A model based on genetic algorithms views the allocation of people and private vehicles as an optimization problem, anticipating traffic congestion effects and adjusting the infrastructure accordingly.

Computerized adaptive tests and item response theory on a distance education platform

This article presents how Computerized Adaptive Tests and Item Response Theory are modified for using in a Distance Education Platform, MISTRAL, showing the advantages of using this technique, the way in which the knowledge acquisition is accomplished, how it links to student profile and how the students and materials are evaluated.

Using Ant Colony Optimization for Edge Detection in Gray Scale Images

Digital image processing is a research topic that has been studied from different perspectives. In this paper we propose an approach based on a paradigm that arises from artificial life; more specifically ant colonies foraging behavior. Ant based algorithms have shown interesting results in a wide variety of situations, including optimization and clustering. In this work we compare different ant colony algorithms on a set of images, for the detection of edges. Results are presented as images, in which ants have built specific solutions, and discussed within an image-processing framework.

Chilean virtual observatory

This paper presents the challenges, architecture and current status of the Chilean Virtual Observatory (ChiVO), which is a software infrastructure for accessing and processing astronomical data generated in Chile. As ChiVO is part of the International Virtual Observatory Alliance (IVOA), we strictly follow the protocols and standards that this organization produce. However, there are always open challenges due to the new observational technologies and local requirements that motivates research on every new virtual observatory, such as the complex data models and Big Data problems that the ALMA Observatory is confronting. The current ChiVO prototype includes IVOA compliant services as well as new solutions designed for ALMA data, all of them using modern software technologies.

Automatic Lane Correction in DGGE Images by Using Hybrid Genetic Algorithms

DGGE (denaturing gradient gel electrophoresis) images are a particular type of images obtained by electrophoresis, that are used with different purposes. One of them is to study microbial biodiversity. Processing of this kind of images is a quite difficult problem, affected by various factors. Among these factors, the noise and distortion affect the quality of images, and subsequently, accuracy in interpreting the data. One of the problems this process presents is that lanes on the image are not perfectly aligned, and so the automatic processing of these images, e.g., for detection and quantification of bands, is not reliable. We present some methods for processing DGGE images that allow to improve their quality and thereof, improving biological conclusions. Results obtained with pure genetic algorithms, genetic algorithms hybridized with Tabu Search and genetic algorithms combined with Simulated Annealing are presented.

Automatic detection and automatic classification of structures in astronomical images

The study of the astronomical structures is important to the astronomical community because it can help to identify objects, which can be classified based on their internal structure or their relation to other objects. For this reason, it is developed an automated tool to analyze astronomical images into its components. Firstly, a 2D images is decomposed into different spatial scales based on wavelet transform. Then, it is implemented a detection algorithms to each spatial scale, such as Clumpfind, Gaussclump, or Dendrogram techniques. The goal is to build a new algorithm and tool that is available to the community and satisfies the requirements of the next Chilean Virtual Observatory (ChiVO).

A comparison of methods for the vehicle routing problem

This work introduces an implementation of an evolving technique, more precisely genetic algorithms, to deal with a known problem: the Capacitated Vehicle Routing Problem (CVRP), in which vehicles have limited carrying capacity of the goods that must be delivered. It is presented a comparison with a known heuristic: Greedy Randomized Adaptive Search Procedure (GRASP), obtaining results that improve previous results for similar instances.

Dealing with Bullying through Genetic Algorithms

Aggression in schools is a problem for which there is no a simple solution. On the other side, it is known that a specific configuration in the distribution of students can affect the behavior among them. Based on a previous experience, we propose to apply genetic algorithms in order to deal with the large number of configurations that can arise on these types of problems. Introducing the concept of penalization has shown to be an interesting concept that allows to reach feasible solutions in reduced computing times. Real environments were considered to conduct the experiments. The set of solutions has been analyzed an accepted as a helpful tool to minimize negative interactions in a classroom.

DESIGNING ROAD NETWORKS FOR TRANSPORT PLANNING USING EVOLUTIONARY COMPUTATION

In this article, a new approach to designing optimum urban road networks using evolutionary methods is described. The model is capable of finding a road network that addresses the private transport assignment in a certain city area. Experiments using our model in real transport assignment tasks show the promise of the approach to improve existing roads and create new roads as projected in a near future.

A New Approach for an Artificial Evolving System

We have built an adaptive system (AS) that is able to evolve and improve its answering ability to all reiterative questions from an artificial environment. Indeed, we have created a basic artificial system that is able to do what is usually understood as a natural systems behavior. In this work, rather than using logic, we encourage coherence, because it is not logic correctness but harmony between the system and its environment the primary goal of our work. As a central part of the system, we have designed and implemented an Existential Machine and experimental results show that evolution is feasible for restricted environments. In this article, the core idea supporting the system is shown, a rapid view over the existential machine is presented, and a set of results pointing to future applications is discussed.