Recent Submissions

  • O método de Levenberg-Marquadt estocástico aplicado ao treinamento de redes neurais artificiais 

    Benatti, Kléber; Bueno, Luis Felipe Cesar da Rocha [UNIFESP]; Nazaré, Tiago (2020-07-30)
    Este trabalho apresenta resultados referentes ao TCC do primeiro autor no curso de especialização em Data Science financiado pelo Itaú-Unibanco. O método de Levenberg-Marquadt tem mostrado bons resultados na resolução de ...

  • Effect of chronic stress and aerobic exercise on glycemic control in rats 

    Marcondes, Fernanda Klein; Sanches, Andrea; Costa, Rafaela; Casarini, Dulce Elena [UNIFESP]; Cunha, Tatiana Sousa [UNIFESP] (Federation Amer Soc Exp Biol, 2016)
  • Production of rotary jet spun ultrathin fibers of poly-butylene adipate-co- terephthalate (PBAT) filled with nanocomposites 

    Andrade, P. O. [UNIFESP]; Santo, A. M. E. [UNIFESP]; Costa, M. M.; Lobo, A. O. (Spie-Int Soc Optical Engineering, 2017)
    Composite fibers of bioabsorbable poly-butylene adipate-co-terephthalate (PBAT) reinforced with superhydrophilic carbon nanotubes and hydroxyapatite nanocrystals were obtained by rotary jet spinning technique (RJS). The ...

  • Structural behavior of coal obtained from Kraft lignin at different carbonizing rates 

    Brazil, Tayra R. [UNIFESP]; Baldan, Mauricio R.; Massi, Marcos [UNIFESP]; Rezende, Mirabel C. [UNIFESP] (Elsevier Science Bv, 2017)
    Biomass is a renewable resource which importance has attracted much attention face to the concerns involving the environmental and the oil crisis. The aim of this work is to convert lignin into coal by carbonization heat ...

  • Edge Detection Robust to Intensity Inhomogeneity: A 7T MRI Case Study 

    Cappabianco, Fabio A. M. [UNIFESP]; Lellis, Lucas Santana [UNIFESP]; Miranda, Paulo; Ide, Jaime S.; Mujica-Parodi, Lilianne R. (Springer International Publishing Ag, 2017)
    Edge detection is a fundamental operation for computer vision and image processing applications. As of 1986, John Canny proposed a methodology that became known due to its simplicity, small number of parameters, and high ...

  • The Radar Cross Section of a Military Transport Helicopter in the X-Band 

    Alves, Mauro A.; Folgueras, Luiza C. [UNIFESP]; Martin, Inacio M.; da Silva, Ricardo E. G.; de Abreu, Alessandro J. (IEEE, 2017)
    As a consequence of their large size and surface geometry, military transport helicopters have usually large radar cross sections (RCS). Depending on the type of the mission these helicopters are carrying, it would be ...

  • Measurements of Extremely Low Frequency Waves (1-12 Hz) Produced by Ionospheric High-Frequency Waves 

    Martin, Inacio M.; Alves, Mauro A.; de Abreu, Alessandro J.; Gomes, Marcelo P.; Folgueras, Luiza C. [UNIFESP] (IEEE, 2017)
    In a recent study, a process for the generation of Extremely Low Frequency (ELF) waves in the range of 1-12 Hz produced by diamagnetic currents generated by heat in ionosphere by high frequency (HF) waves has been proposed. ...

  • Extending the Differential Image Foresting Transform to Root-based Path-cost Functions with Application to Superpixel Segmentation 

    Condori, Marcos A. T.; Cappabianco, Fabio A. M. [UNIFESP]; Falcao, Alexandre X.; Miranda, Paulo A. V. (Ieee, 2017)
    The Image Foresting Transform (IFT) is a general framework to develop image processing tools for a variety of tasks such as image segmentation, boundary tracking, morphological filtering, pixel clustering, among others. ...

  • Optimization of Wavelet Filters for Parity Relation-Based Fault Detection 

    Paiva, Henrique Mohallem [UNIFESP]; Harrop Galvao, Roberto Kawakami; Queiroz Duarte, Marco Aparecido (IEEE, 2017)
    This paper revisits a wavelet approach for parity relation-based fault detection and proposes an improvement through the adaptation of the wavelet filters employed in the decomposition of the residue signal. In the parity ...

  • The influence of aluminum incorporation on the Structural and Electrical Properties of ZnO Thin Films For Applications in Piezoresistive Sensors 

    Cardoso, G. W. A. [UNIFESP]; Leal, G. [UNIFESP]; Massi, M. [UNIFESP]; da Silva Sobrinho, A. S.; Libardi, J. (IEEE, 2017)
    Zinc oxide thin films have high resistivity, plus thermal and chemical stability. Such properties make this material suitable for fabrication of piezo-electric sensors and surface acoustic wave devices that are used in ...

  • Mid-level Image Representation for Fruit Fly Identification (Diptera: Tephritidae) 

    Leonardo, Matheus Macedo; Avila, Sandra; Zucchi, Roberto A.; Faria, Fabio A. [UNIFESP] (Ieee, 2017)
    Fruit flies are of huge biological and economic importance for the farming of different countries in the World, especially for Brazil. Brazil is the third largest fruit producer in the world with 44 million tons in 2016. ...

  • Characterization of Nanocomposites for Hydrogen Storage 

    Oliveira, Amanda D.; Beatrice, Cesar A. G.; Passador, Fabio R. [UNIFESP]; Pessan, Luiz A. (Amer Inst Physics, 2017)
    The use of hydrogen as an energy carrier suitable to replace gasoline and other fossil fuels has been widely discussed as a way to sustainably fuel our civilization. However, hydrogen storage is a major harrier in the ...

  • Polymer Nanocomposites for Hydrogen Storage 

    Beatrice, Cesar A. G.; Oliveira, Amanda D.; Passador, Fabio R. [UNIFESP]; Pessan, Luiz A. (Amer Inst Physics, 2017)
    Hydrogen is considered to be a clean, economical and safe renewable energy source that would be ideal to replace fossil fuels, because it is light, highly abundant and its oxidation product (water) is environmentally benign. ...

  • Unauthorized Access based on HTTP Redirection and MitM - UARiM 

    Ortiz, Tiago Viger [UNIFESP]; Lino Kimura, Bruno Yuji [UNIFESP]; Rosset, Valerio [UNIFESP] (IEEE, 2017)
    HTTP Digest Access Authentication (DAA) is a security protocol widely used in embedded systems. Historically, the DAA has presented vulnerabilities that motivated the revising of its specification, including the use of ...

  • Improving Actuator-Sensor-Actuator Communication Performance in WSANs using a Multicast Approach based on Bloom Filters 

    de Oliveira Guimaraes, Marcelo Guido [UNIFESP]; Rosset, Valerio [UNIFESP] (IEEE, 2017)
    In Wireless Sensor and Actuator Networks (WSANs), to ensure the communication between multiple actuators is an essential issue. In line with this, we propose a multicast routing protocol, named Multicast Border Oriented ...

  • BMINSAR: A NOVEL APPROACH FOR INSAR PHASE DENOISING BY CLUSTERING AND BLOCK MATCHING 

    Barreto, Thiago L. M.; Rosa, Rafael A. S.; Wimmer, Christian; Moreira, Joao R.; Bins, Leonardo S.; Almeida, Jurandy [UNIFESP]; Cappabianco, Fabio A. M. [UNIFESP] (IEEE, 2017)
    We present a novel approach for phase denoising in Interferometric Synthetic Aperture Radar (InSAR) images, named as Block-Matching InSAR (BMInSAR). It uses k-means clustering to solve the block matching similarity search ...

  • Comparing Keyframe Summaries of Egocentric Videos: Closest-to-Centroid Baseline 

    Kuncheva, Ludmila I.; Yousefi, Paria; Almeida, Jurandy [UNIFESP] (IEEE, 2017)
    Evaluation of keyframe video summaries is a notoriously difficult problem. So far, there is no consensus on guidelines, protocols, benchmarks and baseline models. This study contributes in three ways: (1) We propose a new ...

  • An Alternative Approach for Binary and Categorical Self-Organizing Maps 

    Santana, Alessandra [UNIFESP]; Morais, Alessandra [UNIFESP]; Quiles, Marcos G. [UNIFESP] (IEEE, 2017)
    One of the most used neural network model for clustering data is the Self-Organizing Map (SOM). Over the years, it has been applied in many areas, from computing to biology, and therefore a wide range of data types have ...

  • Automatically Design Distance Functions for Graph-based Semi-Supervised Learning 

    Miquilini, Patricia [UNIFESP]; Rossi, Rafael G.; Quiles, Marcos G. [UNIFESP]; de Melo, Vinicius V. [UNIFESP]; Basgalupp, Marcio P. [UNIFESP] (Ieee, 2017)
    Automatic data classification is often performed by supervised learning algorithms, producing a model to classify new instances. Reflecting that labeled instances are expensive, semi supervised learning (SSL) methods prove ...

  • GEEK: Grammatical Evolution for automatically Evolving Kernel functions 

    Sousa, Arua de M.; Lorena, Ana C. [UNIFESP]; Basgalupp, Marcio P. [UNIFESP] (Ieee, 2017)
    One of the key aspects in the successful use of kernel methods such as Support Vector Machines is the proper choice of the kernel function. While there are several well known kernel functions which can produce satisfactory ...

View more