Machine learning based microfluidic sensing device for viscosity measurements

Adil Mustafa; Daniyal Haider; Arnab Barua; Melikhan Tanyeri; Ahmet Erten; Ozlem Yalcin

doi:10.1039/D3SD00099K

Machine learning based microfluidic sensing device for viscosity measurements†

Adil Mustafa,

*^abh Daniyal Haider,^c Arnab Barua,^d Melikhan Tanyeri,

*^e Ahmet Erten^f and Ozlem Yalcin*^g

Author affiliations

* Corresponding authors

^a School of Life Sciences, University of Warwick, Coventry, UK
E-mail: adil.mustafa@warwick.ac.uk

^b Graduate School of Biomedical Sciences and Engineering, Koç University, Istanbul, Turkey

^c Department of Computer Technology, De Montfort University, Leicester, UK

^d Division of Computer Science and Software Engineering, Mälardalens University, Västerås, Sweden

^e Department of Engineering, Duquesne University, Pittsburgh, USA
E-mail: tanyerim@duq.edu

^f Department of Electronics and Communication Engineering, Istanbul Technical University, Istanbul, Turkey

^g School of Medicine, Koç University, Istanbul, Turkey
E-mail: ozlemyalcin@ku.edu.tr

^h Department of Biomedical Engineering, University of Bolton, Bolton, UK

Abstract

A microfluidic sensing device utilizing fluid–structure interactions and machine learning algorithms is demonstrated. The deflection of microsensors due to fluid flow within a microchannel is analysed using machine learning algorithms to calculate the viscosity of Newtonian and non-Newtonian fluids. Newtonian fluids (glycerol/water solutions) within a viscosity range of 5–100 cP were tested at flow rates of 15–105 mL h⁻¹ (γ = 60.5–398.4 s⁻¹) using a sample volume of 80–400 μL. The microsensor deflection data were used to train machine learning algorithms. Two different machine learning (ML) algorithms, support vector machine (SVM) and k-nearest neighbour (k-NN), were employed to determine the viscosity of unknown Newtonian fluids and whole blood samples. An average accuracy of 89.7% and 98.9% is achieved for viscosity measurement of unknown solutions using SVM and k-NN algorithms, respectively. The intelligent microfluidic viscometer presented here has the potential for automated, real-time viscosity measurements for rheological studies.

Sensors & Diagnostics

Machine learning based microfluidic sensing device for viscosity measurements†

Abstract

Supplementary files

Article information

Download Citation

Permissions

Machine learning based microfluidic sensing device for viscosity measurements

Social activity

Search articles by author

Spotlight

Advertisements