Recently, the forest observation using the spaceborne sensor becomes a top issue in the carbon monitoring. Covering more than 20% of the global terrestrial areas, forests are rapidly decreasing, corresponding to 20% carbon dioxide release from the land. Deforestation and forest degradation mainly occurred in the developing country. L-band SAR is sensitive for monitoring the forest biomass, fore...

Protein dimer interfaces (homodimer - same polypeptide and heterodimer - different polypeptide) display geometric and chemical properties that give the non-covalent assembly its stability and specificity. Therefore, it is important to understand the molecular principles of dimer interaction. Several studies on homodimer interaction are available. However, a study on the effect of ligands (i.e. ...

Machine Learning and Data Mining research strongly depend on the quality and quantity of the real world datasets for the evaluation stages of the developing methods. In the context of the emerging Online Multi-Target Regression and Multi-Label Classification methodologies, datasets present new characteristics that require specific testing and represent new challenges. The first difficulty found...

A wide variety of systems from many different fields use geospatial data to represent physical environments. These systems, and the data on which they operate, are not only becoming more complex, but they are increasingly being connected together. Although each system may be interested in very different aspects of the environment, the geospatial data they use must be consistent and correlated w...

Musical pieces can be modeled as complex networks. This fosters innovative ways to categorize music, paving the way towards novel applications in multimedia domains, such as music didactics, multimedia entertainment and digital music generation. Clustering these networks through their main metrics allows grouping similar musical tracks. To show the viability of the approach, we provide results ...

This paper introduces the problem of generating descriptions of n-dimensional spatial data by decomposing it via modelbased clustering. I apply the approach to the error function of supervised classification algorithms, a practical problem that uses Natural Language Generation for understanding the behaviour of a trained classifier. I demonstrate my system on a dataset taken from CoNLL shared t...

an important step in considering of gene expression data is obtained groups of genes that have similarity patterns. biclustering methods was recently introduced for discovering subsets of genes that have coherent values across a subset of conditions. the las algorithm relies on a heuristic randomized search to find biclusters. in this paper, we introduce biclustering las algorithm and then appl...

Generative models reduce the need of acquiring laborious labeling for the dataset. Text generation techniques can be applied for improving language models, machine translation, summarization, and captioning. This project experiments on different recurrent neural network models to build generative adversarial networks for generating texts from noise. The trained generator is capable of producing...

A new (to our knowledge) method for generating the modified spectrum autointerferometric correlation (MOSAIC) trace from the second-harmonic generation frequency-resolved optical gating (SHG FROG) dataset is shown. Examples are presented illustrating enhanced visual sensitivity, applicability, and complementary qualitative pulse characterization using SHG FROG.

In this paper, we present the D-TUNA corpus, which is the first semantically annotated corpus of referring expressions in Dutch. Its primary function is to evaluate and improve the performance of REG algorithms. Such algorithms are computational models that automatically generate referring expressions by computing how a specific target can be identified to an addressee by distinguishing it from...