MR-Radix: a multi-relational data mining algorithm

Background: Once multi-relational approach has emerged as an alternative for analyzing structured data such as relational databases, since they allow applying data mining in multiple tables directly, thus avoiding expensive joining operations and semantic losses, this work proposes an algorithm with multi-relational approach. Methods: Aiming to compare traditional approach performance and multi-relational for mining association rules, this paper discusses an empirical study between PatriciaMine - an traditional algorithm - and its corresponding multi-relational proposed, MR-Radix. Results: This work showed advantages of the multi-relational approach in performance over several tables, which avoids the high cost for joining operations from multiple tables and semantic losses. The performance provided by the algorithm MR-Radix shows faster than PatriciaMine, despite handling complex multi-relational patterns. The utilized memory indicates a more conservative growth curve for MR-Radix than PatriciaMine, which shows the increase in demand of frequent items in MR-Radix does not result in a significant growth of utilized memory like in PatriciaMine. Conclusion: The comparative study between PatriciaMine and MR-Radix confirmed efficacy of the multi-relational approach in data mining process both in terms of execution time and in relation to memory usage. Besides that, the multi-relational proposed algorithm, unlike other algorithms of this approach, is efficient for use in large relational databases.

Brazilian portuguese wordNet: a computational linguistic exercise of encoding bilingual relational lexicons

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

A influência de Georg Simmel no pensamento social de Ulrich Beck: pela compreensão do conflito no individualismo e nos processos de individualização

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Book Review of Laud Humphreys: Prophet of Homosexuality and Sociology by John F. Galliher, Wayne H. Brekhus, and David P. Keys

As an undergraduate sociology major, the only thing I learned about Oklahoman Laud Humphreys's classic, Tearoom Trade (1970) was how it violated standards of informed consent in social science research. As Galliher, Brekhus, and Keys recount in their biography, Laud Humphreys: Prophet of Homosexuality and Sociology, sociology graduate student Laud Humphreys needed to supplement his (quite likely, participant) observational research of men who had sex in public bathrooms (i.e., tearooms) in St. Louis in the mid-1960s with a formal questionnaire. Knowing that these men would never agree if they knew they were selected because of their participation in highly stigmatized and criminal behavior, Humphreys recorded their license plates, got their home addresses, and interviewed them as part of a "community health survey." Herein lies the deception and the major source of the controversy. What I didn't fully appreciate when I was a student, however, and what the authors so deftly illuminate is the importance of this work not only for debates around ethical issues of social science research, but more importantly, perhaps, for the study of sexuality, deviance, and urban life.

Modelling shared attention through relational reinforcement learning

Shared attention is a type of communication very important among human beings. It is sometimes reserved for the more complex form of communication being constituted by a sequence of four steps: mutual gaze, gaze following, imperative pointing and declarative pointing. Some approaches have been proposed in Human-Robot Interaction area to solve part of shared attention process, that is, the most of works proposed try to solve the first two steps. Models based on temporal difference, neural networks, probabilistic and reinforcement learning are methods used in several works. In this article, we are presenting a robotic architecture that provides a robot or agent, the capacity of learning mutual gaze, gaze following and declarative pointing using a robotic head interacting with a caregiver. Three learning methods have been incorporated to this architecture and a comparison of their performance has been done to find the most adequate to be used in real experiment. The learning capabilities of this architecture have been analyzed by observing the robot interacting with the human in a controlled environment. The experimental results show that the robotic head is able to produce appropriate behavior and to learn from sociable interaction.

Social Networks, Segregation and Poverty in Sao Paulo

The associations between segregation and urban poverty have been intensely scrutinized by the sociology and urban studies literatures. More recently, several studies have emphasized the importance of social networks for living conditions. Yet relatively few studies have tested the precise effects of social networks, and fewer still have focused on the joint effects of residential segregation and social networks on living conditions. This article explores the associations between networks, segregation and some of the most important dimensions of access to goods and services obtained in markets: escaping from social precariousness and obtaining monetary income. It is based on a study of the personal networks of 209 individuals living in situations of poverty in seven locales in the metropolitan area of Sao Paulo. Using network analysis and multivariate techniques, I show that relational settings strongly influence the access individuals have to markets, leading some individuals into worse living conditions and poverty. At the same time, although segregation plays an important role in poverty, its effects tend to be mediated by the networks in which individuals are embedded. Networks in this sense may enhance or mitigate the effects of isolation produced by space.

MR-Radix: a multi-relational data mining algorithm

Abstract Background Once multi-relational approach has emerged as an alternative for analyzing structured data such as relational databases, since they allow applying data mining in multiple tables directly, thus avoiding expensive joining operations and semantic losses, this work proposes an algorithm with multi-relational approach. Methods Aiming to compare traditional approach performance and multi-relational for mining association rules, this paper discusses an empirical study between PatriciaMine - an traditional algorithm - and its corresponding multi-relational proposed, MR-Radix. Results This work showed advantages of the multi-relational approach in performance over several tables, which avoids the high cost for joining operations from multiple tables and semantic losses. The performance provided by the algorithm MR-Radix shows faster than PatriciaMine, despite handling complex multi-relational patterns. The utilized memory indicates a more conservative growth curve for MR-Radix than PatriciaMine, which shows the increase in demand of frequent items in MR-Radix does not result in a significant growth of utilized memory like in PatriciaMine. Conclusion The comparative study between PatriciaMine and MR-Radix confirmed efficacy of the multi-relational approach in data mining process both in terms of execution time and in relation to memory usage. Besides that, the multi-relational proposed algorithm, unlike other algorithms of this approach, is efficient for use in large relational databases.

Fattori relazionali e di coordinamento nella filiera agro-alimentare: una valutazione della governance relazionale nel settore lattiero caseario sardo

Characteristics of modern food demand force retailers to acquire more information about product process along the food supply chain to ensure that product are in accordance with consumer preference. Therefore, the product process involves more information flows between buyer and supplier which requires collaborative efforts. These changes translate into several studies on the inter-organizational relationship in agri-food systems. Studies on inter-organizational relationships have been conducted in various academic disciplines, including sociology, psychology, law, economics, marketing, management, and combination of these. Inter-organizational relationships is an interaction between organizations which involved firms horizontally, as well as, vertically. In this study we deal with vertical, buyer-seller relationship which are sometimes referred to chain relationships. We define vertical business relationship in the agriculture-food based sector as “agri-food chain relationships”. The focus is on sustainable inter-organizational relationships in a way that they can be scientifically investigated. We study characteristics which ensure that a relationship is long-lasting and rewarding for all involved parties in the sardinian dairy. We test the theoretical model using structural equation modeling. The results suggest that the most important determinant for the relationships is technology and the price isn’t significant for the relationship governance.

Non-normal modal logics, quantification, and deontic dilemmas. A study in multi-relational semantics

This dissertation is devoted to the study of non-normal (modal) systems for deontic logics, both on the propositional level, and on the first order one. In particular we developed our study the Multi-relational setting that generalises standard Kripke Semantics. We present new completeness results concerning the semantic setting of several systems which are able to handle normative dilemmas and conflicts. Although primarily driven by issues related to the legal and moral field, these results are also relevant for the more theoretical field of Modal Logic itself, as we propose a syntactical, and semantic study of intermediate systems between the classical propositional calculus CPC and the minimal normal modal logic K.

Machine Learning applicato al Web Semantico: Statistical Relational Learning vs Tensor Factorization

Obiettivo della tesi è analizzare e testare i principali approcci di Machine Learning applicabili in contesti semantici, partendo da algoritmi di Statistical Relational Learning, quali Relational Probability Trees, Relational Bayesian Classifiers e Relational Dependency Networks, per poi passare ad approcci basati su fattorizzazione tensori, in particolare CANDECOMP/PARAFAC, Tucker e RESCAL.