Dragonfly algorithm–support vector machine approach for prediction the optical properties of blood

Подход на основе алгоритма стрекозы и метода опорных векторов для прогнозирования оптических свойств крови
Faiza Omari, Latifa Khaouane, Maamar Laidi, Abdellah Ibrir, Mohamed Roubehie Fissa, Mohamed Hentabli, Salah Hanini
2023-06-28

Dragonfly Algorithmabsorption coefficientblood optical propertiesscattering coefficientsupport vector regression
Knowledge of the optical properties of blood plays important role in medical diagnostics and therapeutic applications in laser medicine. In this paper, we present a very rapid and accurate artificial intelligent approach using Dragonfly Algorithm/Support Vector Machine models to estimate the optical properties of blood, specifically the absorption coefficient, and the scattering coefficient using key parameters such as wavelength (nm), hematocrit percentage (%), and saturation of oxygen (%), in building very highly accurate Dragonfly Algorithm-Support Vector Regression models (DA-SVR). 1000 training and testing sets were selected in the wavelength range of 250-1200 nm and the hematocrit of 0-100%. The performance of the proposed method is characterized by high accuracy indicated in the correlation coefficients (R) of 0.9994 and 0.9957 for absorption and scattering coefficients, respectively. In addition, the root mean squared error values (RMSE) of 0.972 and 2.9193, as well as low mean absolute error values (MAE) of 0.2173 and 0.2423, this result showed a strong match with the experimental data. The models can be used to accurately predict the absorption and scattering coefficients of blood, and provide a reliable reference for future studies on the optical properties of human blood.
1
A Dragonfly Algorithm–Support Vector Regression approach predicts blood absorption and scattering coefficients from wavelength, hematocrit, and oxygen saturation.
2
Prediction accuracy was high, with correlation coefficients of 0.9994 for absorption and 0.9957 for scattering coefficients.
3
Reported errors were RMSE 0.972 and 2.9193, and MAE 0.2173 and 0.2423 for the two predicted optical properties, respectively.
4
The DA-SVR models closely matched experimental data and may provide a rapid reference for studies of human blood optical properties.
5
The models were developed using 1,000 training and testing sets covering wavelengths of 250–1200 nm and hematocrit values from 0–100%.

human blood

the prediction of blood optical properties—absorption and scattering coefficients—as functions of wavelength, hematocrit, and oxygen saturation

Publication Details
Publication Date
2023-06-28
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Faiza Omari
Latifa Khaouane
Maamar Laidi
Abdellah Ibrir
Mohamed Roubehie Fissa
Mohamed Hentabli
Salah Hanini
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%