Artificial intelligence (AI) has the ability to predict rheological properties and constituent composition of 3D-printed materials with appropriately trained models. However, these models are not currently available for use. In this work, we trained deep learning (DL) models to (1) predict the rheological properties, such as the storage (G’) and loss (G”) moduli, of 3D-printed polyacrylamide (PAA) substrates, and (2) predict the composition of materials and associated 3D printing parameters for a desired pair of G’ and G”. We employed a multilayer perceptron (MLP) and successfully predicted G’ and G” from seven gel constituent parameters in a multivariate regression process. We used a grid-search algorithm along with 10-fold cross validation to tune the hyperparameters of the MLP, and found the R² value to be 0.89. Next, we adopted two generative DL models named variational autoencoder (VAE) and conditional variational autoencoder (CVAE) to learn data patterns and generate constituent compositions. With these generative models, we produced synthetic data with the same statistical distribution as the real data of actual hydrogel fabrication, which was then validated using Student’s t-test and an autoencoder (AE) anomaly detector. We found that none of the seven generated gel constituents were significantly different from the real data. Our trained DL models were successful in mapping the input–output relationship for the 3D-printed hydrogel substrates, which can predict multiple variables from a handful of input variables and vice versa.

Pluripotent stem cells can be differentiated into all three germ-layers including ecto-, endo-, and mesoderm in vitro. However, the early identification and rapid characterization of each germ-layer in response to chemical and physical induction of differentiation is limited. This is a long-standing issue for rapid and high-throughput screening to determine lineage specification efficiency. Here, we present deep learning (DL) methodologies for predicting and classifying early mesoderm cells differentiated from embryoid bodies (EBs) based on cellular and nuclear morphologies. Using a transgenic murine embryonic stem cell (mESC) line, namely OGTR1, we validated the upregulation of mesodermal genes (Brachyury (T): DsRed) in cells derived from EBs for the deep learning model training. Cells were classified into mesodermal and non-mesodermal (representing endo- and ectoderm) classes using a convolutional neural network (CNN) model called InceptionV3 which achieved a very high classification accuracy of 97% for phase images and 90% for nuclei images. In addition, we also performed image segmentation using an Attention U-Net CNN and obtained a mean intersection over union of 61% and 69% for phase-contrast and nuclear images, respectively. This work highlights the potential of integrating cell culture, imaging technologies, and deep learning methodologies in identifying lineage specification, thus contributing to the advancements in regenerative medicine. Collectively, our trained deep learning models can predict the mesoderm cells with high accuracy based on cellular and nuclear morphologies.

Stereolithography (SLA) is a popular additive manufacturing (AM) method frequently used in research and various industrial sectors. The acrylate resin used in this research is renowned for its flexibility and durability, enabling the creation of flawless 3D-printed parts with exceptional mechanical properties. This study aims to enhance the thermomechanical properties of 3D-printed hollow glass microballoon (HGM)-filled composite materials by adding minimal HGM into the acrylate resin. We investigated the material properties through uniaxial compression tests, dynamic mechanical analysis (DMA), and scanning electron microscopy (SEM). To validate the results, a numerical investigation and a machine learning (ML) approach were carried out and compared with the experimental results. Adding a small number of microballoons increases compressive strength and stiffness. The viscoelastic behavior of the samples also provides an estimate of resilience at higher temperatures, considering the addition of filler material into the resin. Our study shows that the addition of 0.04% of HGM increased compressive strength by around 99.30% compared to the neat sample, while the stiffness increased by around 31.42% compared to the neat sample at 0.05% of HGM. It can also be estimated that the suitable range of HGM addition for the resin we used exists between 0.04% and 0.05%, where the materials achieve their maximum strength and stiffness. In addition, a predictive machine learning (ML) model, namely Random Forest Regressor (RFR), shows low mean squared error (MSE), mean absolute error (MAE), and excellent R² scores, demonstrating the goodness of the model’s performance. This modern approach can guide us to selecting a suitable filler percentage for the photopolymer resin for 3D printing and making it applicable to different engineering prospects.

The performance of Cu ₂ ZnSnS ₄ (CZTS) solar cell was investigated using a simulator called Solar Cell Capacitance Simulator(SCAPS). An n doped Zinc Oxide(n-ZnO)/Indium Sulfide(In ₂ S ₃ )/CZTS structure was used in the simulation. These materials are cheap and non-toxic which is an important factor keeping the idea of mass production in mind. The performance was recorded for different thicknesses of CZTS absorber layer, different thicknesses of the buffer layer and different values of acceptor density of CZTS. The thickness of the CZTS absorption layer was varied between 0.25-5.0μm, absorption layer carrier density was changed between 0-2*10 ¹⁴ cm ^-3 and the buffer layer was 50nm thick. CZTS layer was thicker than In ₂ S ₃ in order to increase the photon absorption which will eventually produce electricity. These parameters were optimized and the best energy conversion efficiency obtained was obtained 19.23% (with V _oc =0.835v, J _sc =27.675mA/cm ² , fill factor=83.22%). The study also includes the effect of high temperature of the proposed structure. Simulations show the favorable result which can help to prove the feasibility of highly efficient CZTS thin film solar cell.

Binary multipliers have long been a staple component in digital circuitry, serving crucial roles in microprocessor design, digital signal processing units and many more applications. This work presents a unique design for a multiplier that utilizes a reformed-array-logic approach to compute the product of two unsigned binary numbers. We employed a multiplexer and a barrel shifter to multiply partial products in a single clock cycle to speed up the traditional array logic. In addition, we have employed a combination of Carry Save Adders (CSA) and Ripple Carry Adders (RCA) to accumulate the partial products instead of using standalone RCAs to speed up the multiplication process further. Finally, we have demonstrated our design to perform multiplication of two 16-bit unsigned binary numbers on Cadence Virtuoso. Our design is modular and can be scaled up or down to accommodate the multiplication of any n-bit unsigned numbers.