Renato de Freitas Bulcão-Neto

An automatic linking service of document images reducing the effects of OCR errors with latent semantics

Robust Information Retrieval (IR) systems have been demanded due to the widespread and multipurpose use of document images, and the high number of document images repositories available nowadays. This paper presents a novel approach to support the automatic generation of relationships among document images by exploiting Latent Semantic Indexing (LSI) and Optical Character Recognition (OCR). The LinkDI service extracts and indexes document images content, obtains its latent semantics, and defines relationships among images as hyperlinks. LinkDI was experimented with document images repositories, and its performance was evaluated by comparing the quality of the relationships created among textual documents and among their respective document images. Results show the feasibility of LinkDI relating OCR output with high degradation.

An Ontology-based Representation Service of Context Information for the Internet of Things

In the Internet of Things (IoT) paradigm, a context management system (CMS) should support the context life cycle including acquisition, modeling, reasoning and distribution of context information. The context modeling phase is responsible for the representation of context information in a format which should meet IoT requirements such as expressiveness, reuse, extension and interoperability. In this paper, we present the Hermes Widget IoT service, which represents context information using the semantics of IoT-oriented ontologies such as IoT-Lite and Semantic Sensor Network (SSN). As contribution, Hermes Widget IoT allows any context provider object (e.g. a sensor) to be located, used, and have its corresponding context information represented and made available for querying through the Internet.

Modeling and Inference Based on the Semantics of Monitoring of Human Vital Signs

This paper contributes with a knowledge representation model of the human vital sign monitoring activity based on Semantic Web specifications for ontologies and Horn-like rules. The proposed model is founded in interviews with intensive care units professionals, medical and nursing literature, and the reuse of existing ontologies. As a result, this work contributes with an ontology describing vital signs, actors and temporal information involved in monitoring, a set of requirements underlying to that model, and dozens of Horn-like rules describing alarms and the respective abnormal values for each vital sign.

An Answer Ranking Method in Medical Social Networks

Patient-oriented medical social networks aim to help their users, with different levels of knowledge, by providing information and support on specific medical and health issues. As one of such pioneering networks, the MedHelp includes forums which allow interaction between users seeking health and medical information with other users who know or live in the context of the information, so they can share their experiences. However, there is no explicit control over what is being answered by users. Therefore, filtering and sorting the answers are fundamental tasks. This work presents PERank as a method and a tool which aim to order answers to questions on forums of medical social networks. By manipulating documents about Type 1 Diabetes disease, experimentation results demonstrate the feasibility of PERank for a low number of best-ranked answers being analyzed.

A Lightweight Mobile Service for Context Representation through an IoT-oriented Ontology

Internet of Things is a paradigm in which sensors, actuators, devices or things seamlessly interact with each other to achieve common goals. Such interaction is reachable if an expressive, interoperable and lightweight representation of context information exists. The literature has recommended ontologies as the main formalism for context information representation, but depending on the ontology being used it can be complex and heavy to run on resource-constrained devices. This paper presents a mobile service which represents context information using the emergent IoT-Lite ontology. An experiment with such service is performed in terms of time behavior and memory utilization when representing an increasing amount of data. Results demonstrate our service is lightweight if considered the amounts of time and memory spent for representing ontology-based data even in a resource-constrained device.