博士 / 國立中興大學 / 生物產業機電工程學系所 / 103 / Abstract
The primary objective of this study was to develop an adaptive neural-based fuzzy inference system (ANFIS) for feeding decision-making in aquaculture. Silver perch (Bidyanus bidyanus) were raised under semi-intensive conditions in Taiwan. Because dissolved oxygen (DO) is a key factor that is helpful in detecting the appetite of fish at the initial period of the feeding activity and because the flocking and struggle behaviors of food-searching fish have a transient effect on the measurement of the DO, a simple water-reused rearing tank was prepared to measure the DO to develop an intelligent feeding decision control system. The experimental results demonstrated that the value of the dissolved oxygen increased continuously and rapidly during the feeding process, so that the change rate of dissolved oxygen in 80 seconds and the maximum change of dissolved oxygen in 4 minutes were first applied to find the characteristic parameters that have relation with the bass`s searching behaviors.
A three-layer back-propagation artificial neural network was utilized to establish a feeding recognition system for aquaculture. The two characteristic factors were used as the input parameters of this neural network. In order to find the best model for recognition, the type and number of the training sample, the nodes of the hidden layer were changed during the training process. The tests show the feeding decision made by the neural network approach, with an accuracy of 96.1%, is close to actual searching behaviors. In the equivalent ANFIS of the fuzzy logic controller (FLC), two linguistic variables were used to describe the food-searching state of the fish population and establish a rule base composed of 15 rules. Furthermore, an alternate hybrid learning approach, which is a fuzzy logic technique based on artificial neural networks, was suggested to quickly model the linguistic variables and evaluate their relative contributions. The results indicated that a decision threshold of 0.17, which was inferred using the fuzzy logic approach, considerably benefits the feeding decision; the high rate of accurate judgments (with an accuracy of 97.89% for training data and 100% for predicting data), which was obtained by the ANFIS model, was close to the actual food searching behaviors of fish. Therefore, the application of the ANFIS model to the feeding decision system in an aquaculture rearing tank has considerable potential for success.
| Identifer | oai:union.ndltd.org:TW/103NCHU5415002 |
| Date | January 2015 |
| Creators | Te-Hui Wu, 吳德輝 |
| Contributors | 黃 裕 益 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 91 |
Page generated in 0.0081 seconds