Inhaúma Neves Ferraz

STEMBR: a stemming algorithm for the Brazilian Portuguese language

Stemming algorithms have traditionally been utilized in information retrieval systems as they generate a more concise word representation. However, the efficiency of these algorithms varies according to the language they are used with. This paper presents STEMBR, a stemmer for Brazilian Portuguese whereby the suffix treatment is based on a statistical study of the frequency of the last letter for words found in Brazilian web pages. The proposed stemmer is compared with another algorithm specifically developed for Portuguese. The results show the efficiency of our stemmer.

From data to knowledge mining

Abstract Most past approaches to data mining have been based on association rules. However, the simple application of association rules usually only changes the users problem from dealing with millions of data points to dealing with thousands of rules. Although this may somewhat reduce the scale of the problem, it is not a completely satisfactory solution. This paper presents a new data mining technique, called knowledge cohesion (KC), which takes into account a domain ontology and the users interest in exploring certain data sets to extract knowledge, in the form of semantic nets, from large data sets. The KC method has been successfully applied to mine causal relations from oil platform accident reports. In a comparison with association rule techniques for the same domain, KC has shown a significant improvement in the extraction of relevant knowledge, using processing complexity and knowledge manageability as the evaluation criteria.

Artificial Neural Networks Ensemble Used for Pipeline Leak Detection Systems

The physical and operational properties of pipelines vary greatly. There is thus no universally applicable method, external or internal, which possesses all the features and the functionality required for a perfect leak detection performance. The authors of this paper know quite well that traditional methods, in a low uncertainty environment, overcome artificial intelligence methods of leak detection systems. If one considers the real world as a creator of uncertainties, neural networks and fuzzy systems emerge as important promising technologies for the development of leak detection systems. In this work, we propose a method for constructing ensembles of ANNs for pipeline leak detection. The results obtained in our experiments were satisfactory.Copyright

Electronic participatory budgeting (e-PPB): increasing people participation in the decision-making process

The advances in information and communication technology (ICT) have raised new expectations to bring democracy to its full potential. This paper discusses three unsuccessful attempts to revive Athenian democracy using ICT to deal with participation scalability. We argue that the lack of the appropriate technological layers caused disappointments and distrust in the population.

Sharing design perspectives through storytelling

Design consists of analyzing scenarios and proposing artifacts, obeying the initial set of requirements that lead from initial to goal state. Finding or creating alternative solutions, analyzing them, and selecting the best one are expected steps in the designer’s decision making process. Very often, not a sole designer, but a team of them is engaged in the design process, sharing their expertise and responsibility to achieve optimum projects. In a design team, most conflicts occur due to misunderstanding of one’s assessment of specifications and contexts. Decision explanations play a key role in teamwork success. Designers are rational agents trained to follow rational methods. Acceptable justifications include value function, requirements, constraints, and criteria. Generally, explanations are delivered in a multimedia fashion, composed of text, graphics and gestures, to provide the audience the ability to perceive what was contextually imagined. The more spatial the reasoning is, the richer the explanation channel should be. This paper presents CineADD, a design explanation generation model based on cinema techniques such as animation, scripting, editing, and camera movements. The idea is to provide designers with a tool for describing the way their projects should be visually explained, as in a movie. Designers develop their projects in an active design document environment. Rationale is captured as a design model, so explanations can be generated instead of retrieved. The captured design model serves as a base to visually reconstruct design, giving emphasis and guidance by using movie storytelling techniques. CineADD was implemented for the domain of oil pipeline layout showing the feasibility of this approach. We expect CineADD to become a commodity attachable to any intelligent CAD system.

Ontology in association rules.

Data mining has emerged to address the problem of transforming data into useful knowledge. Although most data mining techniques, such as the use of association rules, may substantially reduce the search effort over large data sets, often, the consequential outcomes surpass the amount of information humanly manageable. On the other hand, important association rules may be overlooked owing to the setting of the support threshold, which is a very subjective metric, but rooted in most data mining techniques. This paper presents a study on the effects, in terms of precision and recall, of using a data preparation technique, called SemPrune, which is built on domain ontology. SemPrune is intended for pre- and post-processing phases of data mining. Identifying generalization/specialization relations, as well as composition/decomposition relations, is the key to successfully applying SemPrune.

ADDGEO: an intelligent agent to assist geologist finding petroleum in offshore lands

In this paper, we present an intelligent agent (ADDGEO) that assists geologists identifying rocks constituents during thin section analysis. ADDGEO is a hybrid tool using both a knowledge base and a neural net to recognize existent visual patterns in thin sections alone or with the user participation. ADDGEO was recently deployed in a Brazilian oil company presenting benefits to improve the geologists task completion. In addition, it has shown a potential use as a training tool.

An Expert System Based on Parametric Net to Support Motor Pump Multi-Failure Diagnostic

Early failure detection in motor pumps is an important issue in prediction maintenance. An efficient condition-monitoring scheme is capable of providing warning and predicting the faults at early stages. Usually, this task is executed by humans. The logical progression of the condition-monitoring technologies is the automation of the diagnostic process. To automate the diagnostic process, intelligent diagnostic systems are used. Many researchers have explored artificial intelligence techniques to diagnose failures in general. However, all papers found in literature are related to a specific problem that can appear in many different machines. In real applications, when the expert analyzes a machine, not only one problem appears, but more than one problem may appear together. So, it is necessary to propose new methods to assist diagnosis looking for a set of occurring fails. For some failures, there are not sufficient instances that can ensure good classifiers induced by available machine learning algorithms. In this work, we propose a method to assist fault diagnoses in motor pumps, based on vibration signal analysis, using expert systems. To attend the problems related to motor pump analyses, we propose a parametric net model for multi-label problems. We also show a case study in this work, showing the applicability of our proposed method.

Lithofacies recognition hybrid bench

Well offshore petroleum exploration is a risky, but very profitable task. Determining the rock formation of each layer of a given reservoir diminishes the risks of expending a great deal of money drilling dry wells. Since collecting offshore rock samples is difficult and expensive, geologists must decide upon drilling based on indirect measures called well log. Traditional statistical methods have been used to assist this task. Neural networks have also been successfully used. As an alternative fuzzy logic based systems have an extra appeal of intuitive comprehension of some uncertainties. This paper presents a hybrid tool that combines neural networks, fuzzy logic and neuro-fuzzy logic to improve human intuition when analyzing the potential of oil fields.

Applying Multiple Regression Analysis to Adjust Operational Limits in Condition-Based Maintenance

Condition-based maintenance (CBM) seeks to implement a policy wherein maintenance management decisions are based on the identification of the current condition of monitored machinery. It involves not only collecting data but also comparing them with reference values and, if necessary generating alerts based on preset operational limits. This approach is adopted by a system responsible for monitoring turbomachinery plants in oil platforms, to identify when a machine deserves special attention. With the purpose of extending the functionalities of such system for dynamically adjusting the detection limits and thus improving the precision in setting the appropriate time for maintenance, we proposed an approach based on the identification of clusters of correlated variables and multiple regression analysis. In this paper, we describe our approach and discuss our experience in implementing such functionalities.