Gustavo De Assis Costa

The concrete mixture design and mix proportioning procedure, along with its influence on the compressive strength of concrete, is a well-known problem in civil engineering that requires the execution of numerous tests. With the emergence of modern machine learning techniques, the possibility of automating this process has become a reality. However, a significant volume of data is necessary to take advantage of existing models and algorithms. Recent literature presents different datasets, each with its own unique details, for training their models. In this paper, we integrated some of these existing datasets to improve training and, consequently, the models' results. Therefore, using this new dataset, we tested various models for the prediction task. The resulting dataset comprises 2358 records with seven input variables related to the mixture design, while the output represents the compressive strength of concrete. The dataset was subjected to several pre-processing techniques, and afterward, machine learning models, such as regressions, trees, and ensembles, were used to estimate the compressive strength. Some of these methods proved satisfactory for the prediction problem, with the best models achieving a coefficient of determination (R 2) above 80%. Furthermore, a website with the trained model was created, allowing professionals in the field to utilize the AI technique in their everyday problem-solving.

Expressive query capabilities can be achieved, among many other features, mainly due to the traversal of links between different data sources. In this sense, the ability of data aggregation could be a differential to some Linked Data search engines when crawling the Web of Data. However, there are many challenges specially when considering different types, structures and vocabularies used in the Web. Besides that, it is difficult to guarantee the quality of data because they are usually incomplete, inconsistent and contain outliers. Trying to overcome some of these problems, many works have applied the task of Entity Resolution using different techniques and algorithms. In this paper we present an overview of our experience obtained in the construction of an approach to integrate data sets aiming to improve search results made over the LOD. In addition to a general description of the approach and its main features, we present some preliminary results, and a brief overview of ER and ...

The integration of different datasets in the Linked Data Cloud is a key aspect to the success of the Web of Data. To tackle this problem most of existent solutions have been supported by the task of entity resolution. However, many challenges still prevail specially when considering different types, structures and vocabularies used in the Web. Another common problem is that data usually are incomplete, inconsistent and contain outliers. To overcome these limitations, some works have applied machine learning algorithms since they are typically robust to both noise and data inconsistencies and are able to efficiently utilize nondeterministic dependencies in the data. In this paper we propose an approach based in a relational learning algorithm that addresses the problem by statistical approximation method. Modeling the problem as a relational machine learning task allows exploit contextual information that might be too distant in the relational graph. The joint application of relation...

Despite all the advances, one of the main challenges for the consolidation of the Web of Data is data integration, a key aspect to semantic web data management. Most of the solutions make use of entity resolution, a task that deals with identifying and linking different manifestations of the same real world object in one or more datasets. However, data are usually incomplete, inconsistent and contain outliers and, to overcome these limitations, it is necessary to explore as much as possible the existent patterns in data. One way to extrapolate the commonly used technique of pair-wise matching is to explore the relationship structure between entities. Moreover, with the billions of RDF triples being published in the Web, scale has become a problem, posing some new challenges. Only recently some works started to consider new strategies that can deal with the problem of entity resolution in high scale datasets. In this paper we describe a Map-Reduce strategy for a relational learning a...