An Energy Efficient Scheme Using Heuristic Algorithms for 5G H-CRAN

Fourati, Lamia Chaari; Mâaloul, Rihab; Jmaïel, Mohamed

doi:10.1007/978-3-030-99584-3_44

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the high-level fusion approach (Figure c), individual classification and regression model outputs from each single data matrix and the outcomes from the individual models are combined using a weighting to obtain the final decision. In this study, we utilized the central limit theorem (CLT) to calculate the fused prediction ( X IR , R ) taking the standard deviation of the prediction from individual data sets weighted according to eqs and where σ IR , R is the variance of the combined estimates from both Raman and IR instruments, σ R is the standard deviation of the estimated (i.e., astaxanthin) values for sample m using Raman data, X R is the average estimated (i.e., astaxanthin) value of sample m using Raman data, σ IR is the standard deviation of the estimated (i.e., astaxanthin) values for sample m using IR data, and X IR the average estimated (i.e., astaxanthin) value of sample m using IR data.…”

Section: Methodsmentioning

confidence: 99%

Raman and Infrared Spectroscopic Data Fusion Strategies for Rapid, Multicomponent Quantitation of Krill Oil Compositions

Ahmmed

Fuller

Killeen

et al. 2021

ACS Food Sci. Technol.

View full text Add to dashboard Cite

Krill oil contains eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA), long chain omega-3 polyunsaturated fatty acids with essential roles in human health, and astaxanthin, a naturally occurring keto-carotenoid that protects EPA+DHA against oxidation. Here, we assess Raman and IR spectroscopy (as stand-alone techniques and paired using three different data-fusion approaches) as methods for simultaneous quantitation of EPA+DHA and astaxanthin in krill oil. Raman spectroscopy could accurately (RMSEP = 40 μg g–1, r 2 p = 0.98) quantitate astaxanthin in krill oil despite its low concentrations (212–693 μg g–1). This analysis could be performed directly through gelatin capsules with no loss of prediction accuracy (RMSEP = 27 μg g–1, r2 p = 0.99). Fusing IR and Raman data did not improve the astaxanthin quantitation models. EPA+DHA quantitation was more accurate using “mid-level” fusion (RMSEP = 1.2%, r 2 p = 0.99) than models from either Raman (RMSEP = 4.5%, r 2 p = 0.90) or IR (RMSEP = 7.3%, r 2 p = 0.73). Data fusion also significantly improved quantitation accuracy for quantification of other fatty acid classes.

show abstract

Section: Methodsmentioning

confidence: 99%