Ana Cristina Bicharra Garcia

ADD+: Including rhetorical structures in active documents

A design is a plan containing guidelines to build and understand an artifact. Generally, this plan is constructed by a team of designers with different tasks, but sharing a common objective, that is, to create a high-quality, low-cost integrated artifact. Active Design Documents (ADDs) are powerful tools for cooperative design because they account for revealing the rationale among design participants while assisting each of them in their own. Design rationale capture and retrieval are critical issues on building documentation assistant tools. In this paper, we propose to achieve more efficient and effective delivery of design and designers intent by resorting to rhetorical means. The wealth of knowledge kept in ADDs knowledge bases is organized into high-level Rhetorical Structure Theory (RST) schema and mapped onto input and output screen configurations that gear the interaction between systems and users. We illustrate the effects of such an organization with evidences from an implemented version of ADD for the domain of offshore platform.

Anomaly detection based on sensor data in petroleum industry applications.

Anomaly detection is the problem of finding patterns in data that do not conform to an a priori expected behavior. This is related to the problem in which some samples are distant, in terms of a given metric, from the rest of the dataset, where these anomalous samples are indicated as outliers. Anomaly detection has recently attracted the attention of the research community, because of its relevance in real-world applications, like intrusion detection, fraud detection, fault detection and system health monitoring, among many others. Anomalies themselves can have a positive or negative nature, depending on their context and interpretation. However, in either case, it is important for decision makers to be able to detect them in order to take appropriate actions. The petroleum industry is one of the application contexts where these problems are present. The correct detection of such types of unusual information empowers the decision maker with the capacity to act on the system in order to correctly avoid, correct or react to the situations associated with them. In that application context, heavy extraction machines for pumping and generation operations, like turbomachines, are intensively monitored by hundreds of sensors each that send measurements with a high frequency for damage prevention. In this paper, we propose a combination of yet another segmentation algorithm (YASA), a novel fast and high quality segmentation algorithm, with a one-class support vector machine approach for efficient anomaly detection in turbomachines. The proposal is meant for dealing with the aforementioned task and to cope with the lack of labeled training data. As a result, we perform a series of empirical studies comparing our approach to other methods applied to benchmark problems and a real-life application related to oil platform turbomachinery anomaly detection.

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.

Sensor data analysis for equipment monitoring

Sensors play a key role in modern industrial plant operations. Nevertheless, the information they provide is still underused. Extracting information from the raw data generated by the sensors is a complicated task, and it is usually used to help the operator react to undesired events, other than preventing them. This paper presents SDAEM (Sensor Data Analysis for Equipment Monitoring), an oil process plant monitoring model that covers three main goals: mining the sensor time series data to understand plant operation status and predict failures, interpreting correlated data from different sensors to verify sensors interdependence, and adjusting equipments working set points that leads to a more stable plant operation and avoids an excessive number of alarms. In addition, as time series data generated by sensors grow at an extremely fast rate, SDAEM uses parallel processing to provide real-time feedback. We have applied our model to monitor a process plant of a Brazilian offshore platform. Initial results were promising since some undesired events were recognized and operators adopted the tool to assist them finding good set points for the oil processing equipments.

A semiotic framework for multi-user interfaces

Semiotic approaches to user interface designs have shown that system interfaces are messages sent from the designers to the users. It is through the systems interface that the designers tell the users the problems the system is able to solve and how the users should interact with it to solve these problems. In a multi-users environment this message is more complex, since the designers must also tell the users how to interact in the group. To create such message is not an easy task and designers should be provided with a good designing tool. In this article we present a semiotic framework that is the first step in the direction of the construction of a multi-users interface design environment. The framework has three dimensions: action, communication and observation and provides support for the analysis of multi-users systems interface and understanding of interactions in the group. It can also be a helpful guide to designers of multi-users interfaces.

Semiotic traces of computational thinking acquisition

Computational thinking involves many different abilities, including being able to represent real and imaginary worlds in highly constrained computer languages. These typically support very selective kinds of perspectives, abstractions and articulation compared to the unlimited possibilities provided by natural languages. This paper reports findings from a qualitative empirical study with novice programmers, carried out with AgentSheets in a Brazilian public school. The driving research question was: How do meanings expressed in natural language narratives relate to computational constructs expressed in programs produced by novices? We used semiotic and linguistic analysis to compare meaning representations in natural and artificial texts (game descriptions in Brazilian Portuguese and Visual AgenTalk code). We looked for recurring relations and what they might mean in the context of computational thinking education. Our findings suggest that the semiotic richness of AgentSheets can be explored to introduce different aspects of computational thinking in principled and theoretically-informed ways.

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.

HYRIWYG: leveraging personalization to elicit honest recommendations

This paper presents HYRIWYG (How You Rate Influences What You Get), a reputation system applicable to Internet Recommendation Systems (RS). The novelty lies in the incentive mechanism that encourages evaluators to volunteer their true opinion. Honesty is encouraged because rewards are indexed by the quality of the RSs suggestions.

An Analysis of Constructed Categories for Textual Classification Using Fuzzy Similarity and Agglomerative Hierarchical Methods

Ambiguity is a challenge faced by systems that handle natural language. To assuage the issue of linguistic ambiguities found in text classification, this work proposes a text categorizer using the methodology of Fuzzy Similarity. The grouping algorithms Stars and Cliques are adopted in the Agglomerative Hierarchical method and they identify the groups of texts by specifying some time of relationship rule to create categories based on the similarity analysis of the textual terms. The proposal is that based on the methodology suggested, categories can be created from the analysis of the degree of similarity of the texts to be classified, without needing to determine the number of initial categories. The combination of techniques proposed in the categorizerpsilas phases brought satisfactory results, proving to be efficient in textual classification.

Text Classification Techniques in Oil Industry Applications

The development of automatic methods to produce usable structured information from unstructured text sources is extremely valuable to the oil and gas industry. A structured resource would allow researches and industry professionals to write relatively simple queries to retrieve all the information regards transcriptions of any accident. Instead of the thousands of abstracts provided by querying the unstructured corpus, the queries on structured corpus would result in a few hundred well-formed results.