INES – National Institute of Science and Technology for Software Engineering

RSS feed


Calendar

August 2014
M T W T F S S
« Jul   Sep »
 123
45678910
11121314151617
18192021222324
25262728293031

 
  • INES at ACM Hypertext 2014

    (0)
    Publicado em August 11th, 2014Publications

    Prof. Leandro Balby will participate of the ACM Hypertext Conference to present the paper entitled “Event Recommendations in Event-Based Social Networks” in the SP 2014 Workshop. The research performs an exploratory analysis of a large dataset collected from meetup.com (a well known event-based social network) where several insights are derived for the effective development of event recommenders, which is a challenging and still a sparse area of research. After that, some of these insights are fed into state-of-the-art recommender algorithms in order to investigate the advantages and limitations of these recommenders.

    The abstract is presented as follows:
    With the large number of events published all the time in event-based social networks (EBSN), it has become increasingly diffi cult for users to nd the events that best match their preferences. Recommender systems appear as a natural solution to this problem. However, the event recommendation scenario is quite different from typical recommendation domains (e.g. movies), since there is an intrinsic new item problem involved (i.e. events can not be “consumed” before their occurrence) and scarce collaborative information. Although few works have appeared in this area, there is still lacking in the literature an extensive analysis of the different characteristics of EBSN data that can affect the design of event recommenders. In this paper we provide a contribution in this direction, where we investigate and discuss important features of EBSN such as sparsity, events life time, co-participation of users in events and geographic features. We also shed some light on the performance and limitations of several well known recommendation algorithms and combinations of them on real and large data collected from meetup.com.

  • HEALTHDRONES – Evaluating drones as a software platform for development of applications for monitoring epidemiological and crowd phenomena

    (0)
    Publicado em August 11th, 2014Projects

    The use of satellite data can be complemented by collected one by devices in flight (unmanned aerial vehicles called here “drones”). This provides a platform of data very close to reality and can be programmable by IOT (Internet Of Things) applications. These data can be used for monitoring environments at risk or under specific control (epidemiological or any crowd phenomena). This project will provide an overview of the software platforms available today for development of algorithms for unmanned aerial vehicles (UAVs) in autonomous flight to be used in IOT applications. We are primarily interested in their use for epidemiological monitoring of areas under risk, but these platforms can be used to monitor any kind of crowd event. In particular, in this project, images are captured and processed using NOAA and Meteosat 8 Satellites. They are operated by GOESERE-UFRPE (Laboratory of GIS and Remote Sensing of the Federal Rural University of Pernambuco) – http://www.dtr.ufrpe.br/geosere/ – and are used to compose the monitoring scenarios.  Images and other data are also captured and processed by the drones platforms and its sensors. This information will compound automatic surveillance scenarios of the phenomena.

    The development of a prototype for Schistosomiasis will provide an evaluation of the platforms used for this project. In this way, as the main outcome, this project will provide an overview of technologies available today, their ability to integrate with legacy systems and their programming capabilities. It is expected to evaluate at least five different air platforms and this project enables the acquisition of such platforms. The importance of this project for the industry takes on the aspect of evaluation of commercial platforms for UAVs to be a possible IDE for software applications in industry.

    This project is a coordinate action by researchers from GOESERE-UFRPE, CIN-UFPE, CESAR, LIKA, EPITRACK and ISI-TICs.

    , , , , , , ,
  • INES at ICSME 2014

    (0)
    Publicado em August 11th, 2014Uncategorized

    Juliana Araújo will attend the 30th International Conference on Software Maintenance and Evolution(ICSME) in Victoria, British Columbia, Canada- 28 September-03 October.

    Juliana will present the following paper:  How Does Exception Handling Behavior Evolve? An Exploratory Study in Java and C# Applications. This activity is part of the project “Integrando Testes com Mineração de Fluxo Excepcional para Construção de Aplicações Robustas”, in portuguese “PT”.