Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data

Manne Hannula; Erkki Alarousu; Tuukka Prykäri; Risto Myllylä

doi:10.1117/12.729497

Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data

Manne Hannula^*, Erkki Alarousu, Tuukka Prykäri, Risto Myllylä

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Low Coherence Doppler Flowmetry (LCDF) measurement produces a signal, which frequency domain characteristics are in connection to the speed of the flow. In this study performances of Artificial Neural Network (ANN) and Multilinear Regression (MLR) methods in prediction of pulp flow speed from the LCDF measurement data were compared. In the study the pulp flow speed was estimated distinctly from consecutive frequency bands of the LCDF data with both methods. The smallest estimation error in flow speed with the ANN method was 20% and with the MLR method 30%, depending on the selected frequency band. The results indicate the relationship between characteristics of the LCDF measurement and pulp flow speed includes remarkable number of nonlinear components. The result is in line with theoretical calculations about the Doppler shifts occurrence in the LCDF data.

Original language	English (US)
Title of host publication	Advanced Laser Technologies 2006
DOIs	https://doi.org/10.1117/12.729497
State	Published - 2007
Externally published	Yes
Event	Advanced Laser Technologies 2006 - Brasov, Romania Duration: Sep 8 2006 → Sep 12 2006

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	6606
ISSN (Print)	0277-786X

Other

Other	Advanced Laser Technologies 2006
Country/Territory	Romania
City	Brasov
Period	09/8/06 → 09/12/06

Keywords

LDF
Nonlinear model
Pulp and paper

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Applied Mathematics
Electrical and Electronic Engineering
Computer Science Applications

Access to Document

10.1117/12.729497

Cite this

Hannula, M., Alarousu, E., Prykäri, T., & Myllylä, R. (2007). Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data. In Advanced Laser Technologies 2006 Article 660616 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6606). https://doi.org/10.1117/12.729497

@inproceedings{a1dd1263b014496ba3585f42affc4aa6,

title = "Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data",

abstract = "Low Coherence Doppler Flowmetry (LCDF) measurement produces a signal, which frequency domain characteristics are in connection to the speed of the flow. In this study performances of Artificial Neural Network (ANN) and Multilinear Regression (MLR) methods in prediction of pulp flow speed from the LCDF measurement data were compared. In the study the pulp flow speed was estimated distinctly from consecutive frequency bands of the LCDF data with both methods. The smallest estimation error in flow speed with the ANN method was 20% and with the MLR method 30%, depending on the selected frequency band. The results indicate the relationship between characteristics of the LCDF measurement and pulp flow speed includes remarkable number of nonlinear components. The result is in line with theoretical calculations about the Doppler shifts occurrence in the LCDF data.",

keywords = "LDF, Nonlinear model, Pulp and paper",

author = "Manne Hannula and Erkki Alarousu and Tuukka Pryk{\"a}ri and Risto Myllyl{\"a}",

year = "2007",

doi = "10.1117/12.729497",

language = "English (US)",

isbn = "0819467448",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Advanced Laser Technologies 2006",

note = "Advanced Laser Technologies 2006 ; Conference date: 08-09-2006 Through 12-09-2006",

}

Hannula, M, Alarousu, E, Prykäri, T & Myllylä, R 2007, Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data. in Advanced Laser Technologies 2006., 660616, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6606, Advanced Laser Technologies 2006, Brasov, Romania, 09/8/06. https://doi.org/10.1117/12.729497

Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data. / Hannula, Manne; Alarousu, Erkki; Prykäri, Tuukka et al.
Advanced Laser Technologies 2006. 2007. 660616 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6606).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data

AU - Hannula, Manne

AU - Alarousu, Erkki

AU - Prykäri, Tuukka

AU - Myllylä, Risto

PY - 2007

Y1 - 2007

N2 - Low Coherence Doppler Flowmetry (LCDF) measurement produces a signal, which frequency domain characteristics are in connection to the speed of the flow. In this study performances of Artificial Neural Network (ANN) and Multilinear Regression (MLR) methods in prediction of pulp flow speed from the LCDF measurement data were compared. In the study the pulp flow speed was estimated distinctly from consecutive frequency bands of the LCDF data with both methods. The smallest estimation error in flow speed with the ANN method was 20% and with the MLR method 30%, depending on the selected frequency band. The results indicate the relationship between characteristics of the LCDF measurement and pulp flow speed includes remarkable number of nonlinear components. The result is in line with theoretical calculations about the Doppler shifts occurrence in the LCDF data.

AB - Low Coherence Doppler Flowmetry (LCDF) measurement produces a signal, which frequency domain characteristics are in connection to the speed of the flow. In this study performances of Artificial Neural Network (ANN) and Multilinear Regression (MLR) methods in prediction of pulp flow speed from the LCDF measurement data were compared. In the study the pulp flow speed was estimated distinctly from consecutive frequency bands of the LCDF data with both methods. The smallest estimation error in flow speed with the ANN method was 20% and with the MLR method 30%, depending on the selected frequency band. The results indicate the relationship between characteristics of the LCDF measurement and pulp flow speed includes remarkable number of nonlinear components. The result is in line with theoretical calculations about the Doppler shifts occurrence in the LCDF data.

KW - LDF

KW - Nonlinear model

KW - Pulp and paper

UR - http://www.scopus.com/inward/record.url?scp=35148884767&partnerID=8YFLogxK

U2 - 10.1117/12.729497

DO - 10.1117/12.729497

M3 - Conference contribution

AN - SCOPUS:35148884767

SN - 0819467448

SN - 9780819467447

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Advanced Laser Technologies 2006

T2 - Advanced Laser Technologies 2006

Y2 - 8 September 2006 through 12 September 2006

ER -

Comparison of artificial neural network and multilinear regression analysis models in estimation of pulp flow speed from low coherence Doppler flowmetry measurement data

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this