ORNL researchers develop ‘multitasking’ AI tool to extract cancer data in record time

To better leverage cancer data for research, scientists at ORNL are developing an artificial intelligence (AI)-based natural language processing tool to improve information extraction from textual pathology reports. In a first for cancer pathology reports, the team developed a multitask convolutional neural network (CNN)—a deep learning model that learns to perform tasks, such as identifying key words in a body of text, by processing language as a two-dimensional numerical dataset.

Read more

BP Looks to ORNL, ADIOS to Help Rein in Data

British Petroleum researchers invited ORNL data scientists to give the company’s high-performance computing team a tutorial of the laboratory’s ADIOS I/O middleware. ADIOS has helped researchers achieve scientific breakthroughs by providing a simple, flexible way to describe data in their code that may need to be written, read, or processed outside of the running simulation. ORNL researchers Scott Klasky and Norbert Podhorszki demonstrated how it could help the BP team accelerate their science by helping tackle their large, unique seismic datasets.

Read more

Tests Measure Solar Panel Performance Beyond Established Standards

In testing solar panels, the sun’s intensity, the spectral composition and the angle of light are important factors in understanding why certain panels are successful and others degrade more quickly. To address the knowledge gap in degradation mechanisms for various photovoltaic types, researchers performed tests over five years in which they collected weather data and panel performance information. The results are published in the Journal of Renewable and Sustainable Energy.

Read more

Bias-Busting Algorithms: Can AI Help VCs Diversify their Deals?

Studies show that gender bias in the venture capital (VC) industry hurts both female founders and has negative financial consequences for VC firms. Darden Professors Morela Hernandez and Roshni Raveendhran show how algorithm-aided, data-driven approaches can help investors mitigate bias and make better and more equitable funding decisions.

Read more

Rutgers study examines smoking status, health conditions in older Chinese American men

The findings of the study by the Rutgers Institute for Health, Health Care Policy and Aging Research underscore the need for culturally targeted interventions to prevent and reduce tobacco use, manage chronic disease and screen for lung cancer.

Read more

Sharing data for improved forest protection and monitoring

Although the mapping of aboveground biomass is now possible with satellite remote sensing, these maps still have to be calibrated and validated using on-site data gathered by researchers across the world. A newly established global database will support Earth Observation and encourage investment in relevant field-based measurements and research.

Read more