Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Acta Metrologica Sinica》 2018-04
Add to Favorite Get Latest Update

Water Quality Monitoring Based on Fish Movement Characteristics and XGBoost

CHENG Shu-hong;ZHANG Shi-jun;LI Lei-hua;ZHANG Dian-fan;Institute of Electrical Engineering,Yanshan University;Yanshan University Science Park;  
Realization of water quality monitoring by combining fish movement behavior with XGBoost classifier. According to the influence of water quality on the movement of fish,some characteristic parameters were introduced,such as center distance index,dispersion and distribution area,which were extracted from the movement behavior of fish. Secondly,five characteristic parameters of swimming distance,velocity,acceleration,curvature and neighborhood of fish in normal and abnormal water quality were extracted,and water quality anomaly evaluation factor database was established. Finally,different evaluation factors were input to XGBoost classifier for classification and recognition. The experimental results showed that the three characteristic parameters of the center distance index,dispersion and distribution area can reflect the water quality condition high efficiency and accurately.
【Fund】: 国家自然科学基金(61601400);; 河北省博士后基金(B2016003027);; 秦皇岛市科学技术研究与发展计划(201701B009)
【CateGory Index】: X832
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved