West Virginia University
An artificial associative neural net for underground mine landmark recognition.
Abstract
dc:description.abstractA new bi-directional associative memory (BAM), a type of artificial neural net, is proposed, defined, demonstrated and tested as the core classifier in a landmark recognition system for underground mine navigation. The simulation of this new BAM shows improved ability in recognizing images of objects as compared with the BAM proposed by Kosko. This dissertation documents: (1) A new bi-directional associative memory model which shows an obvious improvement over the Kosko BAM in applications of pattern recognition; (2) A new distinctive system structure using the proposed BAMs for multiple feature space pattern recognition applications; (3) The analysis of simulation results for underground mine landmark recognition. (4) Image sets of underground mine objects for system testing in future applications.
Degree
thesis:*- Name thesis:degree_name
- PhD
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Lane Department of Computer Science and Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Li, Peijian
- Contributors dc:contributor
-
- R.S. Nutter
- C.S. Sims
- A. Noore
- W.L. Cooley
Identifiers
dc:identifier.*- Identifier
- https://researchrepository.wvu.edu/etd/9292