TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Mäkiö, Juho
A1  - Glukhov, D.
A1  - Bohush, R.
A1  - Hlukhava, T.
T1  - Fuzzy Logic Approximation and Deep Learning Neural Network for Fish Concentration Maps
T2  - Atlantis Highlights in Computer Sciences;
International Conference on Digital Technologies in Logistics and Infrastructure (ICDTLI), 04.04.-05.04.2019, St. Petersburg (Russia)
N2  - This paper proposes an algorithm to obtain topographic maps of lakes, maps of fish concentration and a map of predator location based on the results of an intelligent sonar data processing. The algorithm is based on the following steps: input frame separation into overlapping blocks, blocks-processing using convolutional neural networks (CNN) YOLO v2, and merging extracted bounding boxes around one object. To construct maps of the distribution of features along the lake, we propose a novel method for constructing the approximation of GPS- referenced CNN results based on the original implementation of fuzzy logic.
KW  - Sonar data
KW  - Fish concentration
KW  - Maps of lakes
KW  - Fuzzy logic
KW  - Convolutional neural networks
Y1  - 2019
SN  - 2589-4900
SS  - 2589-4900
SN  - 978-94-6252-799-7
SB  - 978-94-6252-799-7
U6  - https://doi.org/10.2991/icdtli-19.2019.84
DO  - https://doi.org/10.2991/icdtli-19.2019.84
VL  - 1
SP  - 484
EP  - 488
ER  -