Osteosarcoma is a type of bone cancer that affects young adults and children. Early diagnosis of osteosarcoma is crucial to successful treatment. The current methods of diagnosis, which include imaging tests and biopsy, are time consuming and prone to human error. Hence, we used deep learning to extract patterns and detect osteosarcoma from histological images. We hypothesized that the combination of two different technologies (transfer learning and data augmentation) would improve the efficacy of osteosarcoma detection in histological images. The dataset used for the study consisted of histological images for osteosarcoma and was quite imbalanced as it contained very few images with tumors. Since transfer learning uses existing knowledge for the purpose of classification and detection, we hypothesized it would be proficient on such an imbalanced dataset. To further improve our learning, we used data augmentation to include variations in the dataset. We further evaluated the efficacy of different convolutional neural network models on this task. We obtained an accuracy of 91.18% using the transfer learning model MobileNetV2 as the base model with various geometric transformations, outperforming the state-of-the-art convolutional neural network based approach.

Recent research suggests that the "American Dream" of income mobility may be becoming increasingly hard to obtain. Datta and Schmitz explore the role of government spending in socioeconomic opportunity by determining which state government spending components are associated with increased income mobility.

There are believed to be ~20,000 nebulae in the Milky Way Galaxy. However, humans have only cataloged ~1,800 of them even though we have gathered 1.3 million nebula images. Classification of nebulae is important as it helps scientists understand the chemical composition of a nebula which in turn helps them understand the material of the original star. Our research on nebulae classification aims to make the process of classifying new nebulae faster and more accurate using a hybrid of deep learning and machine learning techniques.

Solar and radio frequency harvesters serve as a viable alternative energy source to batteries in many cases where the battery cannot be easily replaced. Using specifically designed circuit models, the authors quantify the reliability of different harvested energy sources to identify the most practical and efficient forms of renewable energy.

The purpose of this study was to investigate the relationship between colorism and police killings of unarmed African American suspects. The authors collected data from the Washington Post database, which reports unarmed African American victims from 2015–2021, and found that the victims who were killed by police were darker on average than a control population of African Americans that had not encountered the police.

Cancer is often caused by improper function of a few proteins, and sometimes it takes only a few proteins to malfunction to cause drastic changes in cells. Here the authors look at the genes that were mutated in patients with a type of pancreatic cancer to identify proteins that are important in causing cancer. They also determined which proteins currently lack effective treatment, and suggest that certain proteins (named KRAS, CDKN2A, and RBBP8) are the most important candidates for developing drugs to treat pancreatic cancer.

Seeking to investigate the effects of ambient pollutants on human respiratory health, here the authors used machine learning to examine asthma in Lost Angeles County, an area with substantial pollution. By using machine learning models and classification techniques, the authors identified that nitrogen dioxide and ozone levels were significantly correlated with asthma hospitalizations. Based on an identified seasonal surge in asthma hospitalizations, the authors suggest future directions to improve machine learning modeling to investigate these relationships.

In our work we followed the formation of gas bubbles on the surface of the vessel walls in different carbonated liquids, over different time intervals, at different temperatures and in vessels made of different materials. Our results made it possible to identify patterns affecting the process of formation and disappearance of carbon dioxide bubbles.

In this study, the authors investigate the demographic indicators for voter shift between the 2016 and 2020 presidential elections based on demographic data put through a K-nearest neighbors classification algorithm and Principal Component Analysis.

This study compares different methods for cooking vegetables to determine which retain iron and ascorbic acid, or vitamin C, levels the most.