Using a convolution neural network, these authors show machine learning can clinically diagnose breast cancer with high accuracy.

Plant diseases can cause up to 50% crop yield loss for the popular tomato plant. A mobile device-based method to identify diseases from photos of symptomatic leaves via computer vision can be more effective due to its convenience and accessibility. To enable a practical mobile solution, a “shallow” convolutional neural networks (CNNs) with few layers, and thus low computational requirement but with high accuracy similar to the deep CNNs is needed. In this work, we explored if such a model was possible.

Current drug discovery processes can cost billions of dollars and usually take five to ten years. People have been researching and implementing various computational approaches to search for molecules and compounds from the chemical space, which can be on the order of 1060 molecules. One solution involves deep generative models, which are artificial intelligence models that learn from nonlinear data by modeling the probability distribution of chemical structures and creating similar data points from the trends it identifies. Aiming for faster runtime and greater robustness when analyzing high-dimensional data, we designed and implemented a Hybrid Quantum-Classical Generative Adversarial Network (QGAN) to synthesize molecules.

To best identify tuberculosis and pneumonia diagnoses in chest x-rays, the authors compare different deep learning convolution neural networks.

Seeking to develop a better understanding of the chemical and physical properties of amino acids that compose proteins, here the authors investigated the unusual relative insolubility of racemic mixtures of D- and L-serine compared to the solubility of pure D- or L-serine. The authors used a combination of microscopy and temperature measurements alongside previous X-ray diffraction studies to conclude that racemic DL-serine crystals consist of comparatively stronger hydrogen bond interactions compared to crystals of pure enantiomers. These stronger interactions were found to result in the unique release of heat during the crystallization of racemic mixtures.

In this study, the authors developed a model named DNA Sequence Embedding Network (DNA-SEnet) to classify DNA-asthma associations using their genomic patterns.

In many areas of the world’s oceans, diatoms such as Thalassiosira pseudonana are limited in growth by the availability of iron (Fe), which is an essential nutrient for diatoms. The authors of this study examined if Fe-limitation makes a significant difference in the proteins expressed within the chloroplast, the power source for diatoms, utilizing a new plastid isolation technique specific to diatoms and completing 14 mass spectrometry experiments.

We systematically evaluated the effects of raw material composition, heat treatment, and mechanical properties on 13-8PH stainless steel alloy. The results of the neural network models were in agreement with experimental results and aided in the evaluation of the effects of aging temperature on double shear strength. The data suggests that this model can be used to determine the appropriate 13-8PH alloy aging temperature needed to achieve the desired mechanical properties, eliminating the need for many costly trials and errors through re-heat treatments.

Here, recognizing the potential harmful effects of algal blooms, the authors used satellite images to detect algal blooms in water bodies in Wyoming based on their reflectance of near infrared light. They found that remote monitoring in this way may provide a useful tool in providing early warning and advisories to people who may live in close proximity.

In this study the authors develop an app for faster chess game entry method to help chess learners improve their game. This culminated in the Augmented Reality Chess Analyzer (ARChessAnalyzer) which uses traditional image and vision techniques for chess board recognition and Convolutional Neural Networks (CNN) for chess piece recognition.