publications

2015

1. Classification of low-level atmospheric structures based on a pyramid representation and a machine learning method

   Sierra, S., Molina, J.F., Cruz-Roa, A., Pabón, J.D., Ramos-Pollán, R., González, F.A., and Franco, H.

   2015

   Abs

   The atmosphere is a highly complex fluid system where multiple intrinsic and extrinsic phenomena superpose at same spatial and temporal dominions and different scales, making its characterization a challenging task. Despite the novel methods for pattern recognition and detection available in the literature, most of climate data analysis and weather forecast rely on the ability of specialized personnel to visually detect atmospheric patterns present in climate data plots. This paper presents a method for classifying low-level wind flow configurations, namely: confluences, difluences, vortices and saddle points. The method combines specialized image features to capture the particular structure of low-level wind flow configurations through a pyramid layout representation and a state-of-the-art machine learning classification method. The method was validated on a set of volumes extracted from climate simulations and manually annotated by experts. The best results into the independent test dataset was 0.81 of average accuracy among the four atmospheric structures.

2017

1. Convolutional neural networks for author profiling: Notebook for PAN at CLEF 2017

   Sierra, S., Montes-Y-gómez, M., Solorio, T., and González, F.A.

   In 2017

   Abs

   Social media data allows researchers to establish relationships between everyday language and people’s sociodemographic variables, such as gender, age, language variety or personality. These variables configure social groups, where author profiling attempts to exploit the idea that they share a common language. This work describes our proposed method for the PAN 2017 Author Profiling shared task. We trained separate models for gender and language variety using a Convolutional Neural Network (CNN). We explored parameters such as the size of the input of the network, the size of the convolutional kernels, the number of kernels and the type of input. We found experimentally that sequences of words performed better than sequences of characters as input for the CNN. We obtained 0.66, 0.73, 0.81 and 0.57 of accuracy in the test partition for English, Spanish, Portuguese and Arabic respectively.

2. Convolutional neural networks for authorship attribution of short texts

   Shrestha, P., Sierra, S., González, F.A., Rosso, P., Montes-Y-Gómez, M., and Solorio, T.

   In 2017

   Abs

   We present a model to perform authorship attribution of tweets using Convolutional Neural Networks (CNNs) over character n-grams. We also present a strategy that improves model interpretability by estimating the importance of input text fragments in the predicted classification. The experimental evaluation shows that text CNNs perform competitively and are able to outperform previous methods.

2018

1. Automatic authorship analysis using deep neural networks

   Sierra, Sebastian

   2018
2. Combining textual and visual representations for multimodal author profiling: Notebook for PAN at CLEF 2018

   Sierra, Sebastian, and González, Fabio A

   In 2018
3. Load curve characterization based on real time measurements: Case of study in Colombia

   Restrepo, Jorge A., Sierra, Sebastian, and Rosero, Javier A.

   In 2018