Guangdong Ocean University

Yunrong Yan

Zhao Li

Shoujun Zhang

Xurui Liao

Qi Lin

Feng Wang

Aimin Lu

Qing Feng

Kun Zhang

Zhenyu Jiang

Banglin Deng

Wei Wang

Xiaojun Tan

Chengqi Sun

Yin Sun

Jianan Zheng

Qijun Zhou

An ontologically driven method and a system for constructing a fish knowledge graph in a target region, including: combing a fish data source in the target region, constructing a fish knowledge ontology in the target region, and collecting text data and image data; according to the fish knowledge ontology of the target region, performing knowledge extraction on the text data, and measuring information content of knowledge extraction results to obtain text information weights; according to the fish knowledge ontology in the target region, performing the knowledge extraction on the image data, and measuring information content of the knowledge extraction results to obtain image information weights; according to the text information weights and the image information weights, matching the first knowledge extraction results with the fish knowledge ontology in the target region, and constructing a multi-modal knowledge graph. The processing accuracy and efficiency of the unstructured fish information can be improved.

Ontology-driven method and system for constructing fish knowledge graph in target region

A passive integrated transponder (PIT)-based fish school trajectory monitoring method and system for a marine ranch are provided. The method includes: using a PIT reader to obtain PIT tag information of each fish of a target fish school during a monitoring period; generating a three-dimensional (3D) fish school trajectory map of the target fish school; generating a motion sequence of each fish, inputting the motion sequence of each fish into a motion trajectory correction model, and outputting a corrected motion sequence of each fish; generating a first corrected 3D fish school trajectory map of the target fish school during the monitoring period, and generating a second corrected 3D fish school trajectory map; and generating motion information of the target fish school, and feeding back the second corrected 3D fish school trajectory map and the motion information of the target fish school to monitoring personnel.

PIT-based fish school trajectory monitoring method and system for marine ranch

A neural network-based water quality monitoring device for a marine ranch includes a floating board and a host computer monitor. The host computer monitor is disposed on a top of the floating board, and the host computer monitor is provided with a water quality monitoring system, and the water quality monitoring system is configured to collect water quality parameters of the marine ranch and analyze collected water quality parameters. The environmental monitoring unit is configured to use a hyperspectral water quality multiparameter monitor to monitor continuous spectral segments within a target wavelength range in water body in the marine ranch to monitor in real time data including a concentration of dissolved substances in the water, growth of algae, water pollution, water color, and presence of solid floating objects on water surface. The device can apply multiple water quality tests to improve the effectiveness and accuracy of water quality monitoring.

Neural network-based water quality monitoring device for marine ranch and deployment method thereof

Growing community of inventors

Zhanjiang, China

Yunrong Yan