You need JavaScript to view this

Determining the confidence levels of sensor outputs using neural networks

Abstract

This paper describes an approach for determining the confidence level of a sensor output using multi-sensor arrays, sensor fusion and artificial neural networks. The authors have shown in previous work that sensor fusion and artificial neural networks can be used to learn the relationships between the outputs of an array of simulated partially selective sensors and the individual analyte concentrations in a mixture of analyses. Other researchers have shown that an array of partially selective sensors can be used to determine the individual gas concentrations in a gaseous mixture. The research reported in this paper shows that it is possible to extract confidence level information from an array of partially selective sensors using artificial neural networks. The confidence level of a sensor output is defined as a numeric value, ranging from 0% to 100%, that indicates the confidence associated with a output of a given sensor. A three layer back-propagation neural network was trained on a subset of the sensor confidence level space, and was tested for its ability to generalize, where the confidence level space is defined as all possible deviations from the correct sensor output. A learning rate of 0.1 was used and no momentum terms were used  More>>
Authors:
Broten, G S; Wood, H C [1] 
  1. Saskatchewan Univ., Saskatoon, SK (Canada). Dept. of Electrical Engineering
Publication Date:
Dec 31, 1995
Product Type:
Conference
Report Number:
INIS-CA-0053; CONF-950623-
Reference Number:
SCA: 220400; PA: AIX-28:075825; EDB-98:020651; SN: 97001880377
Resource Relation:
Conference: 35. annual conference of the Canadian Nuclear Association and 16th annual conference of the Canadian Nuclear Society, Saskatoon (Canada), 4-7 Jun 1995; Other Information: PBD: 1995; Related Information: Is Part Of CNS proceedings of the 16. annual conference, volume I and II; Wight, A.L.; Loewer, R. [eds.]; PB: [2 v. ] p.
Subject:
22 NUCLEAR REACTOR TECHNOLOGY; NEURAL NETWORKS; ON-LINE MEASUREMENT SYSTEMS; COMPUTER NETWORKS; FEASIBILITY STUDIES; MEASURING INSTRUMENTS; MONITORING; REACTOR INSTRUMENTATION; RELIABILITY; SIGNAL CONDITIONING
OSTI ID:
568554
Research Organizations:
Canadian Nuclear Society, Toronto, ON (Canada)
Country of Origin:
Canada
Language:
English
Other Identifying Numbers:
Other: ON: DE98603788; TRN: CA9700824075825
Availability:
INIS; OSTI as DE98603788
Submitting Site:
INIS
Size:
pp. [14]
Announcement Date:

Citation Formats

Broten, G S, and Wood, H C. Determining the confidence levels of sensor outputs using neural networks. Canada: N. p., 1995. Web.
Broten, G S, & Wood, H C. Determining the confidence levels of sensor outputs using neural networks. Canada.
Broten, G S, and Wood, H C. 1995. "Determining the confidence levels of sensor outputs using neural networks." Canada.
@misc{etde_568554,
title = {Determining the confidence levels of sensor outputs using neural networks}
author = {Broten, G S, and Wood, H C}
abstractNote = {This paper describes an approach for determining the confidence level of a sensor output using multi-sensor arrays, sensor fusion and artificial neural networks. The authors have shown in previous work that sensor fusion and artificial neural networks can be used to learn the relationships between the outputs of an array of simulated partially selective sensors and the individual analyte concentrations in a mixture of analyses. Other researchers have shown that an array of partially selective sensors can be used to determine the individual gas concentrations in a gaseous mixture. The research reported in this paper shows that it is possible to extract confidence level information from an array of partially selective sensors using artificial neural networks. The confidence level of a sensor output is defined as a numeric value, ranging from 0% to 100%, that indicates the confidence associated with a output of a given sensor. A three layer back-propagation neural network was trained on a subset of the sensor confidence level space, and was tested for its ability to generalize, where the confidence level space is defined as all possible deviations from the correct sensor output. A learning rate of 0.1 was used and no momentum terms were used in the neural network. This research has shown that an artificial neural network can accurately estimate the confidence level of individual sensors in an array of partially selective sensors. This research has also shown that the neural network`s ability to determine the confidence level is influenced by the complexity of the sensor`s response and that the neural network is able to estimate the confidence levels even if more than one sensor is in error. The fundamentals behind this research could be applied to other configurations besides arrays of partially selective sensors, such as an array of sensors separated spatially. An example of such a configuration could be an array of temperature sensors in a tank that is not in equilibrium. (Abstract Truncated)}
place = {Canada}
year = {1995}
month = {Dec}
}