碩士 / 中華大學 / 科技管理研究所 / 94 / This thesis proposes a method for real-time monitoring of water quality, based on temporal trajectory of live fish. This method includes a floating grid representation for describing the temporal trajectories, and a neural network mechanism for efficiently discriminating significant changes of the trajectories. The proposed method could be implemented as a warning system fish farms and drinking water processing facilities. To assess the performance of the proposed method, several experiments were conducted using waters with different pH parameters, where the temporal trajectories of the live fish were collected. The results were favorable in both effectiveness and efficiency. The major advantage of the proposed method is that some unknown substances affecting the water quality can be detected in real time according the fish swimming patterns.
Identifer | oai:union.ndltd.org:TW/094CHPI0230099 |
Date | January 2006 |
Creators | TSUENG-FANG TSAI, 蔡翠芳 |
Contributors | HENG MA, 馬恆 |
Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
Language | zh-TW |
Detected Language | English |
Type | 學位論文 ; thesis |
Format | 43 |
Page generated in 0.0081 seconds