Magali Rezende Gouvêa Meireles

A Signature Approach to Patent Classification

We propose a document signature approach to patent classification. Automatic patent classification is a challenging task because of the fast growing number of patent applications filed every year and the complexity, size and nested hierarchical structure of patent taxonomies. In our proposal, the classification of a target patent is achieved through a k-nearest neighbour search using Hamming distance on signatures generated from patents; the classification labels of the retrieved patents are weighted and combined to produce a patent classification code for the target patent. The use of this method is motivated by the fact that intuitively document signatures are more efficient than previous approaches for this task that considered the training of classifiers on the whole vocabulary feature set. Our empirical experiments also demonstrate that the combination of document signatures and k-nearest neighbours search improves classification effectiveness, provided that enough data is used to generate signatures.

Emotionally Oriented Analysis of the Experiences of Visually Impaired People on Facebook

With technological advancements, there has been a vast increase in the number of companies that fight over their market share. In search of a differentiating factor, companies are investing more and more in their products’ emotional designs. This researched work has evaluated the affects that are caused in visually impaired people when using Facebooks features and then compared them with the experiences of sighted users. To do that, these two types of Facebook users were subjected to a questionnaire that was based on the PANAS affect scale. Once the information was collected, statistics were employed so as to evaluate both users’ feelings. The results have shown that there were significant statistical differences between the sighted and the visually impaired users when the “affects” were evaluated by using the PANAS tool. The five “negative affects” that were selected (Irritability, Uselessness, Frustration, Sadness, and Confusion) were largely more relevant for the blind people in most of the evaluated features. This has indicated some serious accessibility problems. However, a high frequency of the five “positive affects” that were considered (Satisfaction, Pleasantness, Surprise, Excitement, Interest, and Determination) were additionally observed for both of these two groups. These results were interpreted as feelings of both social inclusion and social exclusion, indicating the possibility of exploring technological devices that were unavailable not long ago. After analyzing their experiences in their usage of the Facebook features, the findings have also highlighted the many differing emotions that are felt by the visually impaired and the sighted users. The resulting outcomes have indicated that there are some issues that are still open to problems and difficulties. Moreover, these issues involve human-computer interactions. Nevertheless, fortunately, there is light at the end of the tunnel, as will be revealed.

Intelligent fault management system for wireless sensor networks with reduction of power consumption

In Wireless Sensor Networks (WSN), when a hardware error is not identified and promptly corrected, all monitoring of a sensor network is compromised. This work presents a new approach to centralized fault management system for 6LoWPAN WSN. The system is based on two fault detection levels. A first level is performed locally, by all sensors within the network, using statistical methods. The second level is performed by the base station, through an ensemble of Multilayer Perceptron type Artificial Neural Networks (ANN) classifiers. One of them is continuously trained with streaming data, while the other one is used to take actual decisions about fault detection. The inputs of these ANN are outputs from a Kalman Filter and from an accelerometer. Experimental results indicate that this approach is capable of reducing message traffic and power consumption within a WSN, keeping the detection accuracy rate higher than 97%.

Comparação do processo de categorização de documentos utilizando palavras-chave e citações em um domínio de conhecimento restrito

O processo de categorizacao requer a extracao de elementos representativos de um documento de modo que sua essencia possa ser utilizada na identificacao de similaridades e na geracao de categorias. O objetivo deste trabalho e analisar as dificuldades e os resultados encontrados em dois processos diferentes de categorizacao de documentos de um dominio de conhecimento restrito, o primeiro, baseado no uso de palavras-chave e o segundo, na utilizacao de citacoes para representacao dos documentos. Para exemplificar a utilizacao de diferentes atributos na representacao dos documentos foram realizados dois experimentos. O primeiro utilizou um algoritmo de categorizacao baseado em palavras-chave. O segundo experimento gerou as categorias, utilizando Redes Neurais Artificiais, a partir das citacoes dos artigos. Em um dominio de conhecimento restrito, como o utilizado neste trabalho, foi possivel evidenciar a dificuldade na formacao de grupos que utilizam palavras-chave como atributo do processo de categorizacao devido a grande similaridade existente entre aquelas utilizadas pelos autores dos artigos. As citacoes podem ser, como mostrado no segundo experimento, um atributo alternativo e mais eficiente para esse processo. A formacao de um grupo de artigos com um expressivo acoplamento bibliografico e uma forte relacao semântica comprovou a validade do metodo proposto. A presente pesquisa detalha a metodologia utilizada nos experimentos, mostrando a importância de uma criteriosa fase de pre-processamento para a confiabilidade das bases de dados. Este estudo pode contribuir com as pesquisas relacionadas a representacao de documentos em processos de categorizacao e de recuperacao de informacao. Palavras-chave: Analise de citacao. Categorias. Inteligencia artificial. Recuperacao da informacao. Representacao da informacao.

Recuperação de informação no ambiente acadêmico: Georreferenciamento dos dados dos estudantes do Instituto de Educação Continuada da PUC Minas

Information retrieval concerns representation and efficient acess to information. The way data is presented to users is a matter of great importance to decision support routines. This article presents a case study which uses geographical information retrieval techniques and also presents the relevance of information representation through the use of thematic maps.