Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force

An intelligent sensing framework using Machine Learning (ML) and Deep Learning (DL) architectures to precisely quantify dielectrophoretic force invoked on microparticles in a textile electrode-based DEP sensing device is reported. The prediction accuracy and generalization ability of the framework was validated using experimental results. Images of pearl chain alignment at varying input voltages were used to build deep regression models using modified ML and CNN architectures that can correlate pearl chain alignment patterns of Saccharomyces cerevisiae(yeast) cells and polystyrene microbeads to DEP force. Various ML models such as K-Nearest Neighbor, Support Vector Machine, Random Forest, Neural Networks, and Linear Regression along with DL models such as Convolutional Neural Network (CNN) architectures of AlexNet, ResNet-50, MobileNetV2, and GoogLeNet have been analyzed in order to build an effective regression framework to estimate the force induced on yeast cells and microbeads. The efficiencies of the models were evaluated using Mean Absolute Error, Mean Absolute Relative, Mean Squared Error, R-squared, and Root Mean Square Error (RMSE) as evaluation metrics. ResNet-50 with RMSPROP gave the best performance, with a validation RMSE of 0.0918 on yeast cells while AlexNet with ADAM optimizer gave the best performance, with a validation RMSE of 0.1745 on microbeads. This provides a baseline for further studies in the application of deep learning in DEP aided Lab-on-Chip devices.

Dual Sacrificial Molding: Fabricating 3D Microchannels with Overhang and Helical Features

Fused deposition modeling (FDM) has become an indispensable tool for 3D printing of molds used for sacrificial molding to fabricate microfluidic devices. The freedom of design of a mold is, however, restricted to the capabilities of the 3D printer and associated materials. Although FDM has been used to create a sacrificial mold made with polyvinyl alcohol (PVA) to produce 3D microchannels, microchannels with free-hanging geometries are still difficult to achieve. Herein, dual sacrificial molding was devised to fabricate microchannels with overhang or helical features in PDMS using two complementary materials. The method uses an FDM 3D printer equipped with two extruders and filaments made of high- impact polystyrene (HIPS) and PVA. HIPS was initially removed in limonene to reveal the PVA mold harboring the design of microchannels. The PVA mold was embedded in PDMS and subsequently removed in water to create microchannels with 3D geometries such as dual helices and multilayer pyramidal networks. The complementary pairing of the HIPS and PVA filaments during printing facilitated the support of suspended features of the PVA mold. The PVA mold was robust and retained the original design after the exposure to limonene. The resilience of the technique demonstrated here allows us to create microchannels with geometries not attainable with sacrificial molding with a mold printed with a single material.

Three-Dimensional Printing of Multifunctional Nanocomposites: Manufacturing Techniques and Applications

The integration of nanotechnology into three-dimensional printing (3DP) offers huge potential and opportunities for the manufacturing of 3D engineered materials exhibiting optimized properties and multifunctionality. The literature relating to different 3DP techniques used to fabricate 3D structures at the macro- and microscale made of nanocomposite materials is reviewed here. The current state-of-the-art fabrication methods, their main characteristics (e.g., resolutions, advantages, limitations), the process parameters, and materials requirements are discussed. A comprehensive review is carried out on the use of metal- and carbon-based nanomaterials incorporated into polymers or hydrogels for the manufacturing of 3D structures, mostly at the microscale, using different 3D-printing techniques. Several methods, including but not limited to micro-stereolithography, extrusion-based direct-write technologies, inkjet-printing techniques, and popular powder-bed technology, are discussed. Various examples of 3D nanocomposite macro- and microstructures manufactured using different 3D-printing technologies for a wide range of domains such as microelectromechanical systems (MEMS), lab-on-a-chip, microfluidics, engineered materials and composites, microelectronics, tissue engineering, and biosystems are reviewed. Parallel advances on materials and techniques are still required in order to employ the full potential of 3D printing of multifunctional nanocomposites.

Three-dimensional printing of freeform helical microstructures: a review

Three-dimensional (3D) printing is a fabrication method that enables creation of structures from digital models. Among the different structures fabricated by 3D printing methods, helical microstructures attracted the attention of the researchers due to their potential in different fields such as MEMS, lab-on-a-chip systems, microelectronics and telecommunications. Here we review different types of 3D printing methods capable of fabricating 3D freeform helical microstructures. The techniques including two more common microfabrication methods (i.e., focused ion beam chemical vapour deposition and microstereolithography) and also five methods based on computer-controlled robotic direct deposition of ink filament (i.e., fused deposition modeling, meniscus-confined electrodeposition, conformal printing on a rotating mandrel, UV-assisted and solvent-cast 3D printings) and their advantages and disadvantages regarding their utilization for the fabrication of helical microstructures are discussed. Focused ion beam chemical vapour deposition and microstereolithography techniques enable the fabrication of very precise shapes with a resolution down to ∼100 nm. However, these techniques may have material constraints (e.g., low viscosity) and/or may need special process conditions (e.g., vacuum chamber) and expensive equipment. The five other techniques based on robotic extrusion of materials through a nozzle are relatively cost-effective, however show lower resolution and less precise features. The popular fused deposition modeling method offers a wide variety of printable materials but the helical microstructures manufactured featured a less precise geometry compared to the other printing methods discussed in this review. The UV-assisted and the solvent-cast 3D printing methods both demonstrated high performance for the printing of 3D freeform structures such as the helix shape. However, the compatible materials used in these methods were limited to UV-curable polymers and polylactic acid (PLA), respectively. Meniscus-confined electrodeposition is a flexible, low cost technique that is capable of fabricating 3D structures both in nano- and microscales including freeform helical microstructures (down to few microns) under room conditions using metals. However, the metals suitable for this technique are limited to those that can be electrochemically deposited with the use of an electrolyte solution. The highest precision on the helix geometry was achieved using the conformal printing on a rotating mandrel. This method offers the lowest shape deformation after printing but requires more tools (e.g., mandrel, motor) and the printed structure must be separated from the mandrel. Helical microstructures made of multifunctional materials (e.g., carbon nanotube nanocomposites, metallic coated polymer template) were used in different technological applications such as strain/load sensors, cell separators and micro-antennas. These innovative 3D microsystems exploiting the unique helix shape demonstrated their potential for better performance and more compact microsystems.