Neural network based analysis for chemical sensor arrays
Abstract
Compact, portable systems capable of quickly identifying contaminants in the field are of great importance when monitoring the environment. In this paper, we examine the effectiveness of using artificial neural networks for real-time data analysis of a sensor array. Analyzing the sensor data in parallel may allow for rapid identification of contaminants in the field without requiring highly selective individual sensors. We use a prototype sensor array which consists of nine tin-oxide Taguchi-type sensors, a temperature sensor, and a humidity sensor. We illustrate that by using neural network based analysis of the sensor data, the selectivity of the sensor array may be significantly improved, especially when some (or all) the sensors are not highly selective.
- Authors:
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Research, Washington, DC (United States); Associated Western Universities, Inc., Salt Lake City, UT (United States)
- OSTI Identifier:
- 70720
- Report Number(s):
- PNL-SA-24937; CONF-9504137-2
ON: DE95011490; TRN: 95:004761
- DOE Contract Number:
- FG06-89ER75522; AC06-76RL01830
- Resource Type:
- Conference
- Resource Relation:
- Conference: SPIE: aero sense conference, San Francisco, CA (United States), 17-21 Apr 1995; Other Information: PBD: Apr 1995
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 05 NUCLEAR FUELS; NEURAL NETWORKS; EVALUATION; HANFORD RESERVATION; RADIOACTIVE WASTE MANAGEMENT; POLLUTANTS; MONITORING; CHEMICAL ANALYSIS
Citation Formats
Hashem, S, Keller, P E, Kouzes, R T, and Kangas, L J. Neural network based analysis for chemical sensor arrays. United States: N. p., 1995.
Web.
Hashem, S, Keller, P E, Kouzes, R T, & Kangas, L J. Neural network based analysis for chemical sensor arrays. United States.
Hashem, S, Keller, P E, Kouzes, R T, and Kangas, L J. 1995.
"Neural network based analysis for chemical sensor arrays". United States. https://www.osti.gov/servlets/purl/70720.
@article{osti_70720,
title = {Neural network based analysis for chemical sensor arrays},
author = {Hashem, S and Keller, P E and Kouzes, R T and Kangas, L J},
abstractNote = {Compact, portable systems capable of quickly identifying contaminants in the field are of great importance when monitoring the environment. In this paper, we examine the effectiveness of using artificial neural networks for real-time data analysis of a sensor array. Analyzing the sensor data in parallel may allow for rapid identification of contaminants in the field without requiring highly selective individual sensors. We use a prototype sensor array which consists of nine tin-oxide Taguchi-type sensors, a temperature sensor, and a humidity sensor. We illustrate that by using neural network based analysis of the sensor data, the selectivity of the sensor array may be significantly improved, especially when some (or all) the sensors are not highly selective.},
doi = {},
url = {https://www.osti.gov/biblio/70720},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Apr 01 00:00:00 EST 1995},
month = {Sat Apr 01 00:00:00 EST 1995}
}