home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!spool.mu.edu!caen!destroyer!ubc-cs!alberta!ian
- From: ian@cs.UAlberta.CA (Ian Parsons)
- Subject: Report available: ALNs quantifying Tar sands feedstock.
- Message-ID: <ian.716145138@square-crk>
- Summary: Report available anonymous ftp: Adaptive Logic Neworks application.
- Keywords: applications, adaptive logic networks
- Sender: news@cs.UAlberta.CA (News Administrator)
- Nntp-Posting-Host: square-crk.cs.ualberta.ca
- Organization: University of Alberta, Edmonton, Canada
- Date: Thu, 10 Sep 1992 17:12:18 GMT
- Lines: 40
-
-
- Hello,
-
- A report on an application to quantify tar sands feed using near-infrared
- spectroscopy and adaptive logic networks is now available using
- anonymous ftp at menaik@cs.ualberta.ca. Comments and input are welcome.
- The file is located in the directory pub and is called alntarsands.ps.Z.
-
- The abstract:
-
- The usefulness of Adaptive Logic Networks (ALNs) to analyse Near-Infrared
- (NIR) spectra of tar sands feedstock in a plant situation is examined.
- Laboratory experiments with tar sands do show good correlation between NIR
- and physical analysis using traditional mathematical and back propagation
- neural network techniques. The plant results are inconclusive due to poor
- correlation between the spectra and the physical grab samples. Regardless
- which of the three correlation techniques used the error of prediction is
- similar. A priori knowledge reduced the data set needed for input from
- 585 variables to 25. The reduction did not compromise the resolution of the
- spectra and is based on the shape of peaks. Training and testing of ALN trees
- are fast despite the large number of nodes. ALN trees can be easily converted
- to hardware which is needed in a harsh plant environment. More work is
- currently being done to reduce the error between the observed spectral results
- and the physical analysis.
-
- All comments and input should be emailed to me as I don't have time to
- read this group as regularly as I should. I worked for Western Research
- Centre (WRC) for 12 years so finding this project was easy. Finding quick
- and reliable methods to quantify tarsands feedstock is an ongoing research
- area at WRC. I developed the code using Atree Release 2.0 on a Unix platform
- (Sparc).
-
- email: ian@cs.ualberta.ca
-
- Ian Parsons
- Univerity of Alberta
-
- ps. The file should be labeled aln.tar.ps.Z but too many people will get
- confused :)
-
-