Tarcisio H. C. Pequeno

An expert system applied to the diagnosis of psychological disorders

Psychological disorders have kept away and incapacitated professionals in different sectors of activities. The most serious problems may be associated with various types of pathologies, however, it appears, more often, as psychotic disorders, mood disorders, anxiety disorders, antisocial personality, multiple personality and addiction, causing a micro level damage to the individual and his/her family and in a macro level to the production system and the country welfare. The lack of early diagnosis has provided reactive measures, and sometimes very late, when the professional is already showing psychological signs of incapacity to work. This study aims to help the early diagnosis of psychological disorders with a hybrid proposal of an expert system that is integrated to structured methodologies in decision support (Multi-Criteria Decision Analysis - MCDA) and knowledge structured representations into production rules and probabilities (Artificial Intelligence - AI).

Human mobility in large cities as a proxy for crime

We investigate at the subscale of the neighborhoods of a highly populated city the incidence of property crimes in terms of both the resident and the floating population. Our results show that a relevant allometric relation could only be observed between property crimes and floating population. More precisely, the evidence of a superlinear behavior indicates that a disproportional number of property crimes occurs in regions where an increased flow of people takes place in the city. For comparison, we also found that the number of crimes of peace disturbance only correlates well, and in a superlinear fashion too, with the resident population. Our study raises the interesting possibility that the superlinearity observed in previous studies [Bettencourt et al., Proc. Natl. Acad. Sci. USA 104, 7301 (2007) and Melo et al., Sci. Rep. 4, 6239 (2014)] for homicides versus population at the city scale could have its origin in the fact that the floating population, and not the resident one, should be taken as the relevant variable determining the intrinsic microdynamical behavior of the system.

Collaboration networks from a large CV database: dynamics, topology and bonus impact.

Understanding the dynamics of research production and collaboration may reveal better strategies for scientific careers, academic institutions, and funding agencies. Here we propose the use of a large and multidisciplinary database of scientific curricula in Brazil, namely, the Lattes Platform, to study patterns of scientific production and collaboration. Detailed information about publications and researchers is available in this database. Individual curricula are submitted by the researchers themselves so that coauthorship is unambiguous. Researchers can be evaluated by scientific productivity, geographical location and field of expertise. Our results show that the collaboration network is growing exponentially for the last three decades, with a distribution of number of collaborators per researcher that approaches a power-law as the network gets older. Moreover, both the distributions of number of collaborators and production per researcher obey power-law behaviors, regardless of the geographical location or field, suggesting that the same universal mechanism might be responsible for network growth and productivity. We also show that the collaboration network under investigation displays a typical assortative mixing behavior, where teeming researchers (i.e., with high degree) tend to collaborate with others alike.

Natural Language Processing based on Semantic inferentialism for extracting crime information from text

This article describes an architecture for Information Extraction systems on the web, based on Natural Language Processing (NLP) and especially geared toward the exploration of information about crime. The main feature of the architecture is its NLP module, which is based on the Semantic Inferential Model. We demonstrate the feasibility of the architecture through the implementation thereof to provide input for a collaborative web-based system of registering crimes called WikiCrimes.

InferenceNet.Br: expression of inferentialist semantic content of the Portuguese language

Often, the information necessary for a complete understanding of texts is implicit, which requires drawing inferences from the use of concepts in the linguistic praxis. We consider that the usual semantic reasoners of natural language systems face difficulties in capturing this knowledge, due mainly to the lack of linguistic-semantic resources that support reasoning of this nature. This paper presents a new linguistic resource that expresses semantic-inferentialist knowledge for the Portuguese language – InferenceNet.Br – containing a base of concepts and a base of sentence patterns. These bases provide content for a top layer of semantic reasoning in natural language systems, where semantic relations are considered according to their roles in inferences, as premises or conclusions. This linguistic resource was used in a system for extracting information about crime, and the results of this proof of concept are discussed.

Support Tool in the Diagnosis of Major Depressive Disorder

Major Depressive Disorder have been responsible for millions of professionals temporary removal, and even permanent, from diverse fields of activities around the world, generating damage to social, financial, productive systems and social security, and especially damage to the image of the individual and his family that these disorders produce in individuals who are patients, characteristics that make them stigmatized and discriminated into their society, making difficult their return to the production system. The lack of early diagnosis has provided reactive and late measures, only when the professional suffering psychological disorder is already showing signs of incapacity for working and social relationships. This article aims to assist in the decision making to establish early diagnosis of these types of psychological disorders. It presents a proposal for a hybrid model composed of expert system structured methodologies for decision support (Multi-Criteria Decision Analysis - MCDA) and representations of knowledge structured in logical rules of production and probabilities (Artificial Intelligence - AI).

Multiagent Models for Police Resource Allocation and Dispatch

In this article we investigate Multi-agent simulation as a way for modeling strategies for resource allocation problems in Public Safety. The goal is to show how simulation can be used to help law enforcement authorities to evaluate, in a controlled environment, different strategies for allocating and dispatching resources, aiming at reducing both response time and the number of unattended calls. We created a Multiagent model to represent police cars that answer to emergency calls. In particular, the environment in which the agents live is a grid in which emergency occurrences appear. Random and Zipfian distributions drive the occurrence of calls. A comparison of the strategies for resource allocation in this environment shows that serving first those calls with low estimated attendance times delivers the best overall performance. However this is practically impossible since prioritization of certain crime types is necessary leading to the increase of the waiting time in the queue. Such degradation may be assimilated in real life scenarios because high priority calls are served first. Also, it is important to implement a policy of aging to avoid the cost of great degradation for low priority crimes.

SIM: um modelo semântico-inferencialista para sistemas de linguagem natural

One of the growing needs related to systems of Natural Language Processing (NLP) is that such systems must be able to perform enriched textual inferences. We argue that one reason for the current limitation of the inferences generated by these systems is that---for the most part---they are based on the characteristics of the things represented by names, and seek to draw inferences based on such characteristics. In this work, we propose the Semantic Inferentialism Model (SIM), which follows a natural path and represents a new paradigm: it seeks to express the inferential capacity of concepts and how these concepts, combined in sentence structures, contribute to the inferential power of sentences. We present a SIM-based Information Extraction System and a pre-evaluation of the results.

Information Extraction from Text Based on Semantic Inferentialism

One of the growing needs of information extraction (IE) from text is that the IE system must be able to perform enriched inferences in order to discover and extract information. We argue that one reason for the current limitation of the approaches that use semantics for that is that they are based on ontologies that express the characteristics of things represented by names, and seek to draw inferences and to extract information based on such characteristics, disregarding the linguistic praxis (i.e. the uses of the natural language). In this paper, we describe a generic architecture for IE systems based on Semantic Inferentialism. We propose a model that seeks to express the inferential power of concepts and how these concepts, combined in sentence structures, contribute to the inferential power of sentences. We demonstrate the validity of the approach and evaluate it by deploying an application for extracting information about crime reported in on line newspapers.

Multi-objective evolutionary algorithms and multiagent models for optimizing police dispatch

In this article we investigate Multi-agent simulation and Multi-objective Evolutionary Algorithms for optimizing resource allocation in Public Safety. We describe a tool that helps Law Enforcement authorities to evaluate, in a controlled environment, different strategies for allocating and dispatching resources, aiming at reducing conflicting goals such as response time, the number of unattended calls and cost of displacement of police cars. This tool is a multi-agent model to represent police cars that lives in a grid in which emergency occurrences appear. A comparison of the strategies for resource dispatch in this environment shows that serving first those calls with low estimated attendance times delivers the best overall performance in terms of waiting time. However this is practically impossible since prioritization of certain crime types is necessary leading to the increase of the waiting time in the queue. Instead of manually trying to identify the best allocation strategy to apply, we have coupled a multi-objective evolutionary algorithm to the simulation model in order to uncover automatically a function to rank the calls in the best order for attendance satisfying multiple and sometimes conflicting goals.