Neural networks in fisheries research

• Published in: Fisheries research Vol. 92; no. 2; pp. 115 - 139
• Main Authors: Suryanarayana, Iragavarapu, Braibanti, Antonio, Sambasiva Rao, Rupenaguntla, Ramam, Veluri Anantha, Sudarsan, Duvvuri, Nageswara Rao, Gollapalli
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.08.2008; Elsevier
• Subjects: Animal, plant and microbial ecology; Applied ecology; Artificial intelligence; Biological and medical sciences; Catch–effort; Classification; Data structures; Exploitation and management of natural biological resources (hunting, fishing and exploited populations survey, etc.); Fisheries; Forecasting; Fundamental and applied biological sciences. Psychology; Marine; Neural nets; Piscimetrics; NN; PR; Catch–effort; LDA; SVM; BP; MLP; MLR; MA; SG; PLS; Classification; FFNN; Neural nets; GP; Fisheries; Data structures; Forecasting; PCA; SOM; TF; RBFNN; PE; ARIMA; Piscimetrics; OODB; Artificial intelligence; DFA; Fishery; Catch-effort; Neural network; Catch effort
• ISSN: 0165-7836; 1872-6763
• DOI: 10.1016/j.fishres.2008.01.012

Piscimetrics deals with software implementation of experimental design, second-generation artificial intelligence tools, viz. Neural Nets (NNs), genetic algorithms, Fuzzy Logic, Expert Systems, Wavelets and Image analysis in the field of fisheries. A brief sketch of NNs is followed by a review of their applications in forecasting, classification, distribution and fisheries management since 1978. Forecasting in fisheries covers distribution of eggs, recruitment, fish growth/age, biomass and fish catch. Other major areas are identification, abundance and food products, environmental factors and collapse of fishery industry. The data structures are given in tensorial notation. The need for the paradigm shift from classical to multi-level hybrid NNs is emphasized.