Hierarchical Neural Network System Research Articles

Improved fuzzy‐assisted hierarchical neural network system for design of computer‐aided English teaching system

AbstractThe world has enhanced the development of education with the rapid development of information technology in modern society to facilitate the information process. Educational technology has gained experience through the advancement of digital information network technology, from modern teaching technology to computer technology and communication technology. In this paper, an English learning system has been developed based on an improved fuzzy‐assisted hierarchical neural network system (IF‐HNNS). Improving the standard of English education is particularly important in improving intelligent education, especially the efficiency of classroom teaching. The development of an interactive educational system has changed the conventional way of teaching and facilitated individual independent learning. This English teaching system is a network updating computer‐aided learning platform. The computer‐aided system has the following advantages: (i) Easy‐to‐actualize computer‐aided learning media will provide more teaching content and teach satisfaction. (ii) The interaction of computer‐aided learning will raise interest in learning. (iii) Computer helped learners are rich in educational resources and are easy to set teaching goals. (iv) It will improve the monitoring of the education and teaching cycle using a computer‐aided learning with human‐computer interaction method.

An adaptive hierarchical fuzzy logic system for modelling of financial systems

AbstractIn this paper an intelligent hierarchical fuzzy logic system using genetic algorithms for the prediction and modelling of interest rates in Australia is developed. The proposed system uses a hierarchical fuzzy logic system in which a genetic algorithm is used as a training method for learning the fuzzy rules knowledge bases that are used for prediction of interest rates in Australia.A hierarchical fuzzy logic system is developed to model and predict three‐month (quarterly) interest rate fluctuations. The system is further trained to model and predict interest rates for six‐month and one‐year periods. The proposed system is developed with first two, three, then four and finally five hierarchical knowledge bases to model and predict interest rates.A novel architecture called a feed forward fuzzy logic system using fuzzy logic and genetic algorithms is also developed to predict interest rates. A back‐propagation hierarchical neural network system is also developed to predict interest rates for three‐month, six‐month and one‐year periods. The results obtained from these two systems are then compared with the hierarchical fuzzy logic system results and conclusions are drown on the accuracy of all systems for prediction of interest rates in Australia. Copyright © 2004 John Wiley & Sons, Ltd.

Sonar detection and classification of buried targets using broadband dolphin-like signals

Dolphins have been observed foraging for prey that bury themselves into a sandy bottom. The dolphins swim about 1 to 2 m above the bottom and scan in a circular motion or swim immediately off the bottom, scanning from side to side with their beams pointed approximately normal to the bottom. The dolphin has been emulated by using dolphinlike sonar signals (120-kHz peak frequency, 39-kHz bandwidth, 50-μs duration) in order to classify proud and buried targets in real time. The transducer was attached to a bottom-crawling remotely operated vehicle. Target echoes were received via a cable and digitized at 1 MHz. Short-time Fourier transform and the Morlet wavelet were used to obtain time-frequency representations of the echoes. Echoes were processed in a hierarchical neural network system to perform target classifications. Six targets (cast iron pot, stainless steel sphere, glass jar, concrete tile, and coral rock) were placed either on the ocean bottom or buried into the bottom. Echoes were separated into three target categories: (1) cast iron pot; (2) stainless steel sphere; and (3) remaining four objects. The neural network was able to correctly identify 74%, 97%, and 88% of the category 1, 2, and 3 test echoes.

Real-time sonar classification of proud and buried targets using dolphinlike echolocation signals

A broadband active sonar system using dolphinlike echolocation signals and biologically inspired signal processing algorithms was developed to classify proud and buried targets in real time. A dolphin simulator transducer was attached to a bottom-crawling remotely operated vehicle and used to transmit a dolphin click (120-kHz center frequency, 39-kHz bandwidth, 50-μs duration) through seawater. Reflected target echoes were received and transmitted via cable to a shore-based computer system where the echoes were digitized at 1 MHz and subsequently processed. Two time-frequency representations of the echoes, one based on the short-time Fourier transform and the other on the Morlet wavelet, were processed in a hierarchical neural network system to derive target classifications. Echolocation returns were collected from six objects (cast iron pot, stainless steel sphere, glass jar, concrete tile, and coral rock) that were placed either on the ocean bottom or buried by bottom sediment. Echoes were separated into three target categories: (1) cast iron pot; (2) stainless steel sphere; and (3) a miscellaneous category consisting of the remaining four objects. Following supervised neural network training, the system was able to correctly identify 74%, 97%, and 88% of the category 1, 2, and 3 test echoes.