Field Programmable Gate Array Implementation of a Neural Network-based Intelligent Sensor System

A multi-layer perceptron neural network with floatingpoint number system is implemented on a field programmable gate array (FPGA). IEEE-754 32-bit single precision floatingpoint number is used to represent values in the neural network accurately. The neural network forms the core of an intelligent s...

Full description

Saved in:
Bibliographic Details
Main Authors: Patra, J.C., Han Yang Lee, Meher, P.K., Ee Luang Ang
Format: Conference Proceeding
Language:English
Subjects:
Field programmable gate arrays
FPGA
Intelligent networks
intelligent sensor
Intelligent sensors
Light sources
Multi-layer neural network
Multilayer perceptrons
Neural networks
Sensor arrays
Sensor phenomena and characterization
Sensor systems
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A multi-layer perceptron neural network with floatingpoint number system is implemented on a field programmable gate array (FPGA). IEEE-754 32-bit single precision floatingpoint number is used to represent values in the neural network accurately. The neural network forms the core of an intelligent sensor system which has the ability to mitigate the nonlinear influence on the sensor output by external disturbances. Training is performed on the neural network to approximate the response characteristics of a sensor for different level of disturbances so as to compensate for the nonlinearity. The intelligent sensor system is implemented on Celoxica RC203E development board which contains a Xilinx Virtex-II FPGA chip. A custom-built intelligent light intensity sensor is used for experimentation and the neural network is able to achieve a maximum full-scale (FS) error of plusmn1.5% under the nonlinear influence caused by the varying distance between the sensor and the light source. In terms of root mean squared error (RMSE), it is able to achieve a RMSE of 0.0052
DOI:10.1109/ICARCV.2006.345341