Florianópolis, Santa Catarina, Brasil
1 mil seguidores Más de 500 os

Unirse para ver el perfil

Acerca de

Experienced Machine Learning Engineer with over 6 years of experience in machine learning…

Actividad

Unirse para ver toda la actividad

Experiencia y educación

  • 3778

Mira la experiencia completa de Renato

Mira su cargo, antigüedad y más

o

Al hacer clic en «Continuar» para unirte o iniciar sesión, aceptas las Condiciones de uso, la Política de privacidad y la Política de cookies de LinkedIn.

Licencias y certificaciones

Únete para ver todas las certificaciones

Publicaciones

  • Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism

    IEEE Access

    Hyperspectral images contain tens to hundreds of bands, implying a high spectral resolution. This high spectral resolution allows for obtaining a precise signature of structures and compounds that make up the captured scene. Among the types of processing that may be applied to Hyperspectral Images, classification using machine learning models stands out. The classification process is one of the most relevant steps for this type of image. It can extract information using spatial and spectral…

    Hyperspectral images contain tens to hundreds of bands, implying a high spectral resolution. This high spectral resolution allows for obtaining a precise signature of structures and compounds that make up the captured scene. Among the types of processing that may be applied to Hyperspectral Images, classification using machine learning models stands out. The classification process is one of the most relevant steps for this type of image. It can extract information using spatial and spectral information and spatial-spectral fusion. Artificial Neural Network models have been gaining prominence among existing classification techniques. They can be applied to data with one, two, or three dimensions. Given the above, this work evaluates Convolutional Neural Network models with one, two, and three dimensions to identify the impact of classifying Hyperspectral Images with different types of convolution. We also expand the comparison to Recurrent Neural Network models, Attention Mechanism, and the Transformer architecture.. Furthermore, a novelty pre-processing method is proposed for the classification process to avoid generating data leaks between training, validation, and testing data. The results demonstrated that using 1 Dimension Convolutional Neural Network (1D-CNN), Long Short-Term Memory (LSTM), and Transformer architectures reduces memory consumption and sample processing time and maintain a satisfactory classification performance up to 99% accuracy on larger datasets. In addition, the Transfomer architecture can approach the 2D-CNN and 3D-CNN architectures in accuracy using only spectral information. The results also show that using two or three dimensions convolution layers improves accuracy at the cost of greater memory consumption and processing time per sample. Furthermore, the pre-processing methodology guarantees the disassociation of training and testing data.

    Otros autores
    Ver publicación

Reconocimientos y premios

  • Second Place at Inova Agora Hackathon

    Softplan

    Developed a medicine supply chain security platform using blockchain – Brazil;

  • Dean`s List of North Dakota State University

    North Dakota State University

    Undergraduates with a semester average of 3.50 or above and complete at least 12 credits with honor points.

    https://www.ndsu.edu/registrar/academics/deanslist/spring/

  • Renato Maciel named High Scholar

    University of Nebraska - Lincoln

    High Scholars: students other than Chancellor's Scholars and Superior Scholars who are in the top 10 percent of their class.

    http://unl.meritpages.com/Renato-Cotrim-Maciel/2775174?expand=5364197

  • Dean's List Renato Maciel of Santa Catarina named to Dean's List at UNL

    University of Nebraska - Lincoln

    Renato Maciel of Santa Catarina was named to the fall semester Dean's List by the University of Nebraska-Lincoln College of Business istration.

    http://unl.meritpages.com/Renato-Cotrim-Maciel/2775174?expand=5032136

Idiomas

  • Inglês

    Competencia bilingüe o nativa

  • Espanhol

    Competencia básica limitada

  • Português

    Competencia bilingüe o nativa

Recomendaciones recibidas

4 personas han recomendado a Renato

Unirse para verlo

Más actividad de Renato

Ver el perfil completo de Renato

  • Descubrir a quién conocéis en común
  • Conseguir una presentación
  • ar con Renato directamente
Unirse para ver el perfil completo

Perfiles similares

Otras personas con el nombre de Renato Maciel en Brasil

Hay 305 personas más con el nombre de Renato Maciel en Brasil en LinkedIn

Ver a otras personas con el nombre de Renato Maciel

Añade nuevas aptitudes con estos cursos

Ver todos los cursos