GNN-based Concentration Prediction for Random Microfluidic Mixers
TimeWednesday, July 13th5:06pm - 5:30pm PDT
Location3002, Level 3
Emerging Device Technologies
DescriptionAccurate preparation of fluid samples with microfluidic mixers is a fundamental step in various biomedical applications, where concentration prediction and generation are critical. Finite element analysis (FEA) is the most commonly used simulation method for concentration prediction, such as COMSOL. However, the FEA simulation process is time-consuming with poor scability for large biochip sizes. This paper proposes a concentration prediction method based on the graph neural networks (GNN), which efficiently and accurately predicts the generated concentration by random microfluidic mixers of different sizes. Experimental results verify the effectiveness of the proposed method.