Can information technology (IT) effectively assist biology researchers carrying out their own activities, such as large-scale investigations on cetaceans' population distribution, habits and site-fidelity? Is it possible to define a multi-disciplinary framework in which biologists and computer scientists can work together and bring innovations? Knowledge and data management are becoming challenging problems due to the huge amount of data that it is possible to collect from multiple sensors in short periods of time, hence the need to promote positive synergies for overcoming the state of the art. As an example the photo identification of marine mammals - i.e. a non-invasive analysis protocol based on the exploitation of unique distinctive marks to discriminate an individual among a group - that has been always done manually by domain experts, can be now efficiently improved using image-processing techniques, with the aim of processing multiple images with high accuracy. In addition, three-dimensional signal processing techniques enable researchers to acquire more precise information from the data (if compared with empirical approaches), improving the accuracy, the robustness and the statistical relevance of the studies. Finally, proper strategies to collect, retrieve, exchange and exploit the information must be investigated to cope with the big data researchers are going to produce and analyse in the near future. In this paper, working examples of innovative techniques for the identification of Grampus Griseus Risso's dolphins will be presented, as well as contributions about smart database systems aimed to collect data from all over the world in a modular and scalable fashion.

Cutting-edge technologies and synergies for cetaceans' large-scale studies, knowledge upgrading and data sharing

V Reno;R Maglietta
2018

Abstract

Can information technology (IT) effectively assist biology researchers carrying out their own activities, such as large-scale investigations on cetaceans' population distribution, habits and site-fidelity? Is it possible to define a multi-disciplinary framework in which biologists and computer scientists can work together and bring innovations? Knowledge and data management are becoming challenging problems due to the huge amount of data that it is possible to collect from multiple sensors in short periods of time, hence the need to promote positive synergies for overcoming the state of the art. As an example the photo identification of marine mammals - i.e. a non-invasive analysis protocol based on the exploitation of unique distinctive marks to discriminate an individual among a group - that has been always done manually by domain experts, can be now efficiently improved using image-processing techniques, with the aim of processing multiple images with high accuracy. In addition, three-dimensional signal processing techniques enable researchers to acquire more precise information from the data (if compared with empirical approaches), improving the accuracy, the robustness and the statistical relevance of the studies. Finally, proper strategies to collect, retrieve, exchange and exploit the information must be investigated to cope with the big data researchers are going to produce and analyse in the near future. In this paper, working examples of innovative techniques for the identification of Grampus Griseus Risso's dolphins will be presented, as well as contributions about smart database systems aimed to collect data from all over the world in a modular and scalable fashion.
2018
information technology (IT)
cetaceans
proto-id
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/421244
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact