Percorrer por autor "Pinto, Filipe"
A mostrar 1 - 5 de 5
Resultados por página
Opções de ordenação
- Database marketing intelligence supported by ontologiesPublication . Pinto, Filipe; Santos, Manuel Filipe; Marques, Alzira; Mota Pinto, Filipe; Marques, AlziraMarketing departments handles with a great volume of data which are normally task or marketing activity dependent. This requires the use of certain, and perhaps unique, specific knowledge background and framework. This article aims to introduce an almost unexplored research at marketing field: the ontological approach to the Database Marketing process. We propose a framework supported by ontologies and knowledge extraction from databases techniques. Therefore this paper has two purposes: to integrate the ontological approach into Database Marketing and to create a domain ontology, a knowledge base that will enhance the entire process at both levels, marketing and knowledge extraction techniques. In order to structure and systematize the marketing concepts, Action Research methodology has been applied. At the end of this research the ontologies will be used to pre-generalize the Database Marketing knowledge through a knowledge base.
- INTCare: On-line knowledge discovery in the intensive care unitPublication . Gago, Pedro; Fernandes, C.; Pinto, Filipe; Santos, M.F.In our work aim to automate the knowledge discovery process. In this paper we present the INTCare system, an intelligent decision support system for intensive care medicine. INTCare is an agent based system that has (autonomous) agents responsible both for data acquisition and model updating thus reducing the need for human intervention. In the present, INTCare is predicting organ failure and probability of in-hospital death. Reliable prediction results facilitate a change from the current reactive behavior to a pro-active one thus enhancing the quality of service. The functional and structural aspects are presented as are some results obtained using data collected from the bedside monitors.
- Pervasive Information Systems to Intensive Care Medicine. Technology Acceptance ModelPublication . Aguiar, Jorge; Portela, Filipe; Santos, Manuel Filipe; Machado, José; Abelha, António; Silva, Álvaro; Rua, Fernando; Pinto, FilipeThe usability of information systems in critical environments like Intensive Care Units (ICU) is far than the expected and desirable. Typically, ICUs have a set of not integrated information silos and a high number of data recorded in paper. Whenever ICU professionals need to make a decision they have to deal with a high number of data sources containing useful information. Unfortunately, they can't use those sources due to the difficulty of evaluating them in a correct time. Pervasive Intelligent Decision Support Systems (PIDSS), operating automatically and in real-time, can be used to improve the decision making if they are suited to the requirements of the ICU. In this work a PIDSS have been assessed in terms of quality and user acceptance making use of Technology Acceptance Model (TAM). TAM proved to be very useful when combined with Delphi method features to involve the professionals and to make the system usable.
- Process Mining: a framework proposal for Pervasive Business IntelligencePublication . Guarda, Teresa; Santos, Manuel Filipe; Augusto, Maria Fernanda; Silva, Carlos; Pinto, FilipeIn recent years, global growth slowed, the markets have matured and become more competitive. The impact of computing in organizations made information technology a strategic element to the acquisition and maintenance of competitive advantage. Based on the literature review in the related areas of Business Intelligence (BI) and Process Mining (PM), is presented a framework for improving the decisionmaking processes in organizations.
- Resurgery Clusters in Intensive MedicinePublication . Peixoto, Ricardo; Portela, Filipe; Pinto, Filipe; Santos, Manuel Filipe; Machado, José; Abelha, António; Rua, FernandoThe field of critical care medicine is confronted every day with cases of surgical interventions. When Data Mining is properly applied in this field, it is possible through predictive models to identify if a patient, should or should not have surgery again upon the same problem. The goal of this work is to apply clustering techniques in collected data in order to categorize re-interventions in intensive care. By knowing the common characteristics of the re-intervention patients it will be possible to help the physician to predict a future resurgery. For this study various attributes were used related to the patient’s health problems like heart problems or organ failure. For this study it was also considered important aspects such as age and what type of surgery the patient was submitted. Classes were created with the patients’ age and the number of days after the first surgery. Another class was created where the type of surgery that the patient was operated upon was identified. This study comprised Davies Bouldin values between -0.977 and -0.416. The used variables, in addition to being provided by Hospital de Santo António in Porto, they are provided from the electronic medical record.