Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

The digital ‘connected’ earth: open technology for providing location-based services on degraded communication environments

  • Piedrafita Moreno, Ramón
  • Bejar Hernández, Rubén
  • Blasco Marín, Rubén Cristóbal
  • Marco Marco, Álvaro
  • Zarazaga Soria, Francisco Javier
In the current world, it is easy to listen that everybody and everything is connected. Over this connected world, the concept of location-based services has grown in order to provide digital services in everyplace and at every time. Nevertheless, this is not 100% true because the connection is not guaranteed for many people and in many places. These are the Degraded Communications Environments (DCE), environments where the availability of high-speed communications is not guaranteed in at least the 75% of the time. This paper works over the experience of a previous work in developing light protocols that do not need broadband for communication. This work provides an extension of these protocols for the inclusion of mobile devices as elements of the communication process and a set of libraries to allow the development of applications in DCE. The work done has involved the development of two frameworks: an Android framework that makes the incorporation of Android devices easier and a server-based framework that provides the server side for the development of the referred applications. A use case that uses these two frameworks has been developed. Finally, all technology developed is available throw a public Git repository.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Machine learning for automatic rule classification of agricultural regulations: A case study in Spain

  • Espejo-Garcia, Borja
  • Martinez-Guanter, Jorge
  • Pérez-Ruiz, Manuel
  • Lopez-Pellicer, Francisco J.
  • Zarazaga-Soria, F. Javier
Currently, pest management practices require modern equipment and the use of complex information, such as regulations and guidelines. The complexity of regulations is the root cause of the emergence of automated solutions for compliance assessment by translating regulations into sets of machine-processable rules that can be run by specialized modules of farm management information systems (FMIS). However, the manual translation of rules is prohibitively costly, and therefore, this translation should be carried out with the support of artificial intelligence techniques. In this paper, we use the official Spanish phytosanitary products registry to empirically evaluate the performance of four popular machine learning algorithms in the task of correctly classifying pesticide regulations as prohibitions or obligations. Moreover, we also evaluate how to improve the performance of the algorithms in the preprocessing of the texts with natural language processing techniques. Finally, due to the specific characteristics of the texts found in pesticide regulations, resampling techniques are also evaluated. Experiments show that the combination of the machine learning algorithm Logic regression, the natural language technique part-of-speech tagging and the resampling technique Tomek links is the best performing approach, with an F1 score of 68.8%, a precision of 84.46% and a recall of 60%. The experimental results are promising, and they show that this approach can be applied to develop a computer-aided tool for transforming textual pesticide regulations into machine-processable rules. To the best of our knowledge, this is the first study that evaluates the use of artificial intelligence methods for the automatic translation of agricultural regulations into machine-processable representations.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

End-to-end sequence labeling via deep learning for automatic extraction of agricultural regulations

  • Espejo-Garcia, Borja
  • Lopez-Pellicer, Francisco J.
  • Lacasta, Javier
  • Piedrafita Moreno, Ramón
  • Zarazaga-Soria, F. Javier
In the European Union, production standards in the form of legal regulations play an important role in farming. Because of the increasing amount of regulations, it is desirable to transform human-oriented regulations into a set of computer-oriented rules to provide decision support through the Farm Management Information System. To obtain the logical structure of rules, automatically labeling their meaningful information is necessary. In this work, we evaluate the performance of 8 different state-of-the-art deep learning architectures to develop an end-to-end sequence labeler for phytosanitary regulations. This sequence labeler extracts different meaningful information items to determine which pesticides can be applied to a crop, the place of the treatment, when it can be applied, and the maximum number of applications. The architectures evaluated do not require feature engineering and, hence, they are applicable to the agricultural regulations of different countries. The best system is a neural network that uses character embeddings, Bidirectional Long short-term memory and Softmax. It achieves a performance of 88.3% F 1 score.