Sea Bottom Recognition Using Multistage Fuzzy Neural Network Operating on Multi-Frequency Data
A hybrid neuro-fuzzy classifier was developed for sea-bottom identification from acoustic echoes acquired at normal incidence by a single beam echosounder. A multistage fuzzy neural network (MSFNN) structure was constructed and tested on the data collected on 38 kHz and 120 kHz echosounder's
frequencies. Two MSFNN models termed as incremental fuzzy neural network (IFNN) and aggregated fuzzy neural network (AFNN), were considered. Firstly, in IFNN, an approximate decision is undertaken based only on the one set of input variables. The decision is then fine-tuned by considering
more and more factors in following stages until the final decision, corresponding to the output class, is undertaken. In AFNN, the input variables are divided into M subsets, where each of them is fed to one sub-stage. The final output is derived by the reasoning with all intermediate variables,
which work as the outputs of sub-stages in the preceding stage. The proposed approach improves classification results twofold. Firstly, it increases generalisation ability of the system by multifrequency observations. Secondly, it reduces requirements on computation power and memory by applying
a multistage solution.
Document Type: Research Article
Publication date: 01 September 2000
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content