2009 International Conference for Technical Postgraduates (TECHPOS) 2009
DOI: 10.1109/techpos.2009.5412048
|View full text |Cite
|
Sign up to set email alerts
|

Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
3
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 17 publications
1
3
0
Order By: Relevance
“…Section 1 presents the best results in the literature. Our experimental results prove that our chosen technique as well as the regression model are better than the other methods (Parab et al, 2010;Uwadaira et al, 2015;Mougiakakou et al, 2006;Perez-Gandia et al, 2010;Robertson et al, 2011;Pappada et al, 2011;Zecchin et al, 2012;Ming and Raveendran, 2009;Zhua et al, 2019;Wu et al, 2017).…”
Section: Discussionsupporting
confidence: 53%
See 1 more Smart Citation
“…Section 1 presents the best results in the literature. Our experimental results prove that our chosen technique as well as the regression model are better than the other methods (Parab et al, 2010;Uwadaira et al, 2015;Mougiakakou et al, 2006;Perez-Gandia et al, 2010;Robertson et al, 2011;Pappada et al, 2011;Zecchin et al, 2012;Ming and Raveendran, 2009;Zhua et al, 2019;Wu et al, 2017).…”
Section: Discussionsupporting
confidence: 53%
“…To choose the best calibration, (Ming and Raveendran, 2009) used two different techniques: PLS and feed forward backpropagation neural network. The RMSE is around 0.5282 mmol/L and 0.2952 mmol/L, respectively.…”
Section: Introductionmentioning
confidence: 99%
“…As shown in Figure 6, after predicting the blood glucose of Day 10 of all 12 volunteers with PCA and BP-ANN, we plotted the predicted and reference values in the Clarke error grid. The Clarke error grid was established by Clarke and co-workers to evaluate the clinical utility of systems for blood glucose monitoring [52,53,54]. Now it is usually used to assess the accuracy of blood glucose measurements to the standard reference value.…”
Section: Resultsmentioning
confidence: 99%
“…We expect that further absolute MARD reduction can be achieved by combining the techniques presented in this work with more sophisticated NIR hardware that has been presented in the literature [ 40 ]. As an example, NIR systems in the same wavelength range examined here, unassisted by RF sensing, reported accuracy errors on the range of ±15–50 mg/dl [ 41 , 42 , 43 , 44 ]. Adding mm-wave RF sensing to equivalent systems could be enough to bring them within a clinical accuracy range, since this is the first multi-modal system that utilizes transmission of radio waves to enhance sensing accuracy.…”
Section: Discussionmentioning
confidence: 96%