Alejandro Padilla

Data Mining in Web Applications

The World Wide Web is rapidly emerging as an important medium for commerce as well as for the dissemination of information related to a wide range of topics (e.g., business and government). According to most predictions, the majority of human information will be available on the Web. These huge amounts of data raise a grand challenge, namely, how to turn the Web into a more useful information utility (Garofalakis et al., 1999) . At the moment with the popularity of Internet, people are exhibited to a lot of information that is available for study. Nowadays there is also a great amount of applications and services that are available through Internet as they are seeking, chats, sales, etc., nevertheless much of that information is not useful for many people, but in the area of Data Mining, all the information available in the Internet represents a work opportunity and it is possible to do a lot of analysis on the basis of these with specific purposes. Knowledge Discovery and Data Mining are powerful data analysis tools. The rapid dissemination of these technologies calls for an urgent examination of their social impact. We show an overview of these technologies. The terms “Knowledge Discovery” and “Data Mining” are used to describe the ‘non-trivial extraction of implicit, previously unknown and potentially useful information from data (Wahlstrom & Roddick, 2000). Knowledge discovery is a concept that describes the process of searching on large volumes of data for patterns that can be considered knowledge about the data. The most well-known branch of knowledge discovery is data mining.

Planning and Allocation Tasks in a Multicomputer System as a Multi-objective Problem

In this article we address the task planning and assignment problem in a multicomputer system using architectural 2D mesh. The problem of planning and allocation of tasks to a group of computers consists of several sub-problems that can be made to correspond to functions to optimize.The proposed solution to this problem is; first: establish the identification of distinct parts that are involved, such as; maximizing processor usage, minimize task wait time in the queue and avoid indefinite task delay (starvation). Second: a planning algorithm and an allocation algorithm are implemented through the search engine within the queue, the first algorithm makes a previous planning to the allocation to identify the task lists that fit in the mesh, and the second is a sole variant distribution algorithm to identify the best allocations in the processor mesh through a dynamic quadratic allocation. Finally, our final results are presented; they allow us to see that a previous allocation in the queue and a search engine allocation of the tasks best positions in the available (free) sub meshes, are determining factors for bettering the longevity of the processors and optimize answer time in a multicomputer system.

Genetic Algorithm with Immigration Like Strategies of Diversification

This paper presents an improvement in the process of diversification of populations in the genetic algorithms using immigration and an appropriate selection of operators. The proposal significantly enhance the quality of solutions obtained, because it prevents premature convergence like result from the loss of diversity in the genetic material of individuals by inbreeding between them, the inbreeding can be avoided with the migration operator. The developed algorithm was run with the instances kroA100, and gil269 of the benchmarks available in the TSPLIB and some results are shows in this work.

SERS and ANFIS: Fast Identification of the Presence of Retrovirus in CD4 Cells, Cause of AIDS

The harmful presence of retrovirus in CD4cells of the human immune system can result in the syndrome of human immunodeficiency known as AIDS, a disease that has extended widely across the entire planet.This paper proposes to obtain characteristic RAMAN spectra with specific peaks detected, eliminating the noise of high frequency (HF) and fluorescence of the signal obtained with SERS and improved with ANFIS. With the spectra cleaned of this noise (HF and fluorescence) the characteristic RAMAN spectra of each microorganism or retrovirus (HIV) in this case is defined. This method provides the specialists with important clinical tools to express an efficient diagnosis of AIDS.

A Sentiment Analysis Model: To Process Subjective Social Corpus through the Adaptation of an Affective Semantic Lexicon

The social networks proliferation over the Internet has generated an interest from the users to express communicate and make opinions about different topics, services or people. This has led the creation of tools, methods, techniques and models that are enable to obtain information from the web in order to analyze and identify the emotion that is shown by the users in their opinions, this has given the key to the development and improvement of sentimental semantic lexicons to the emotional analysis in opinions. This paper shows the proposal of the Model to Analyze Emotions in subjective social corpus through the adaptation of an affective semantic lexicon, focused on the extension of an affective lexicon in order to adequate to the Spanish spoken in Mexico considering the linguistic variations.

Use of chatterbot for accessing learning objects on mobile devices with a data mining search engine

The use of learning objects across multiple platforms and the creation of learning repositories that are used to direct access into the learning objects and the deployment has been generated a new need in applying information, they are considered as educational resources that can be employed in technology-support learning, just like the use of a chatterbot, with his own search engine to locate learning objects using data mining.

Hybrid System to Determine the Ranking of a Returning Participant in Eurovision

Many problems involve not structured environments which can be solved from the perspective of particle swarm optimization (PSO). In this research analyze the voting behavior in a popular song contest held every year in Europe. The dataset makes it possible to analyze the determinants of success, and gives a rare opportunity to run a direct test of vote trading from logrolling. We show that they are rather driven by linguistic and cultural proximities between singers and voting countries. With this information it is possible to predict the score of a new country, redistributed the assigned votes for a lot of the participants, this paper tries to explain this social behavior.

Comparative of Effectiveness When Classifying Colors Using RGB Image Representation with PSO with Time Decreasing Inertial Coefficient and GA Algorithms as Classifiers

Several transformations from basic RGB representation in digital color images have been developed, CIELab and HSV are commonly applied for color classification, because in this colors spaces there is only a single value adjusted for a specific color detection, nevertheless this transformation require high computational power for transforming every single pixel in a picture. Artificial intelligence (AI) algorithms have been applied before for color classification, but using indistinctly RGB, CIELab and HSV representations among other color transformations even when this transformation can be omitted since they were developed for color classification without AI algorithms. In this paper, is proposed an algorithm for optimizing line equations obtained from three spaces directly generated as a dimensional reduction of the RGB space and we show the comparison of the achieved results optimizing these equations with a GA and PSO algorithms.

A 'non-model building' approach to solving hierarchical functions

The hierarchical Bayesian optimization algorithm (hBOA) by M. Pelikan and D.E. Goldberg (2001), used diversity preservation along with the original Bayesian optimization algorithm BOA by M. Pelikan et al. (1999) to tackle boundedly difficult hierarchical functions. However, model building can be an expensive process, and a pertinent question is the possibility of developing operators that can solve certain classes of hierarchical functions in the traditional GA domain. This study shows, that by following a three-step approach to hierarchical problem solving - effective linkage learning, merging of low-order BBs, and diversity preservation - it is possible to use competent (non-model building) selec-to-recombinative GAs to solve certain classes of hierarchical functions. Experimental bounds were found on the type of hierarchical problems that could be solved, and perturbation based linkage detection was found to be the limiting factor.