Cerrar

No. de sistema: 000040143

LDR _ _ 00000nab^^22^^^^^za^4500
008 _ _ 180529m20189999cau^r^p^^^^^^z0^^^a0eng^d
040 _ _ a| ECO
c| ECO
043 _ _ a| n-mx-tb
044 _ _ a| cau
100 1 _ a| Mendoza Carranza, Manuel
c| Dr.
245 1 0 a| Disentangling the complexity of tropical small-scale fisheries dynamics using supervised Self-Organizing Maps
520 1 _ a| Tropical small-scale fisheries are typical for providing complex multivariate data, due to their diversity in fishing techniques and highly diverse species composition. In this paper we used for the first time a supervised Self-Organizing Map (xyf-SOM), to recognize and understand the internal heterogeneity of a tropical marine small-scale fishery, using as model the fishery fleet of San Pedro port, Tabasco, Mexico. We used multivariate data from commercial logbooks, including the following four factors: fish species (47), gear types (bottom longline, vertical line+shark longline and vertical line), season (cold, warm), and inter-annual variation (2007±2012). The size of the xyf-SOM, a fundamental characteristic to improve its predictive quality, was optimized for the minimum distance between objects and the maximum prediction rate. The xyf-SOM successfully classified individual fishing trips in relation to the four factors included in the model. Prediction percentages were high (80±100%) for bottom longline and vertical line + shark longline, but lower prediction values were obtained for vertical line (51±74%) fishery. A confusion matrix indicated that classification errors occurred within the same fishing gear. Prediction rates were validated by generating confidence interval using bootstrap. The xyf-SOM showed that not all the fishing trips were targeting the most abundant species and the catch rates were not symmetrically distributed around the mean. Also, the species composition is not homogeneous among fishing trips. Despite the complexity of the data, the xyf-SOM proved to be an excellent tool to identify trends in complex scenarios, emphasizing the diverse and complex patterns that characterize tropical small scale-fishery fleets.
533 _ _ a| Reproducción electrónica en formato PDF
538 _ _ a| Adobe Acrobat profesional 6.0 o superior
650 _ 4 a| Pesquerías de pequeña escala
650 _ 4 a| Métodos de pesca
651 _ 4 a| Barra de San Pedro, Centla (Tabasco, México)
700 1 _ a| Ejarque, Elisabet
e| coaut.
700 1 _ a| Nagelkerke, Leopold A. J.
e| coaut.
773 0 _
t| PLoS One
g| Vol. 13, no. 5, art. no. e0196991 (May 2018), p. 1-28
x| 1932-6203
856 4 1 u| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0196991
z| Artículo electrónico
856 _ _ u| http://aleph.ecosur.mx:8991/F?func=service&doc_library=CFS01&local_base=CFS01&doc_number=000040143&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA
y| Artículo electrónico
901 _ _ a| Artículo con arbitraje
902 _ _ a| GOG / MM
904 _ _ a| Mayo 2018
905 _ _ a| Artecosur
905 _ _ a| Artfrosur
905 _ _ a| Biblioelectrónica
906 _ _ a| Producción Académica ECOSUR
LNG eng
Cerrar
Disentangling the complexity of tropical small-scale fisheries dynamics using supervised Self-Organizing Maps
Mendoza Carranza, Manuel (autor)
Ejarque, Elisabet (autor)
Nagelkerke, Leopold A. J. (autor)
Contenido en: PLoS One. Vol. 13, no. 5, art. no. e0196991 (May 2018), p. 1-28. ISSN: 1932-6203
No. de sistema: 40143
Tipo: - Artículo con arbitraje
PDF PDF
  • Consulta (1)




Inglés

"Tropical small-scale fisheries are typical for providing complex multivariate data, due to their diversity in fishing techniques and highly diverse species composition. In this paper we used for the first time a supervised Self-Organizing Map (xyf-SOM), to recognize and understand the internal heterogeneity of a tropical marine small-scale fishery, using as model the fishery fleet of San Pedro port, Tabasco, Mexico. We used multivariate data from commercial logbooks, including the following four factors: fish species (47), gear types (bottom longline, vertical line+shark longline and vertical line), season (cold, warm), and inter-annual variation (2007±2012). The size of the xyf-SOM, a fundamental characteristic to improve its predictive quality, was optimized for the minimum distance between objects and the maximum prediction rate. The xyf-SOM successfully classified individual fishing trips in relation to the four factors included in the model. Prediction percentages were high (80±100%) for bottom longline and vertical line + shark longline, but lower prediction values were obtained for vertical line (51±74%) fishery. A confusion matrix indicated that classification errors occurred within the same fishing gear. Prediction rates were validated by generating confidence interval using bootstrap. The xyf-SOM showed that not all the fishing trips were targeting the most abundant species and the catch rates were not symmetrically distributed around the mean. Also, the species composition is not homogeneous among fishing trips. Despite the complexity of the data, the xyf-SOM proved to be an excellent tool to identify trends in complex scenarios, emphasizing the diverse and complex patterns that characterize tropical small scale-fishery fleets."


  • Adobe Acrobat profesional 6.0 o superior