Image classification and control of microfluidic systems

Current microfluidic-based microencapsulation systems rely on human experts to monitor and oversee the entire process spanning hours in order to detect and rectify when defects are found. This results in high labor costs, degradation and loss of quality in the desired collected material, and damage to the physical device. We propose an automated monitoring and classification system based on deep learning techniques to train a model for image classification into four discrete states. Then we develop an actuation control system to regulate the flow of material based on the predicted states. Experimental results of the image classification model show class average recognition rate of 95.5%. In addition, simulated test runs of our valve control system verify its robustness and accuracy.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  D. Weitz,et al.  Monodisperse Double Emulsions Generated from a Microcapillary Device , 2005, Science.

[3]  Hak-Hee Kang,et al.  Effective Formation of Silicone-in-Fluorocarbon-in-Water Double Emulsions: Studies on Droplet Morphology and Stability , 2002 .

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Jose Alvarez-Ramirez,et al.  Stabilization of oil-in-water-in-oil (O1/W/O2) Pickering double emulsions by soluble and insoluble whey protein concentrate-gum Arabic complexes used as inner and outer interfaces , 2018 .

[6]  Zhiqiang Shen,et al.  DSOD: Learning Deeply Supervised Object Detectors from Scratch , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Du T. Nguyen,et al.  Automated detection and sorting of microencapsulation via machine learning. , 2019, Lab on a chip.

[9]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[10]  Sai Gu,et al.  Double emulsion production in glass capillary microfluidic device: Parametric investigation of droplet generation behaviour , 2015 .

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Say Chye Joachim Loo,et al.  Microencapsulation of Dye‐ and Drug‐Loaded Particles for Imaging and Controlled Release of Multiple Drugs , 2012, Advanced healthcare materials.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[17]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..