News by Subject Technology & Engineering

New research using machine learning on images of everyday items is improving the accuracy and speed of detecting respiratory diseases, reducing the need for specialist medical expertise. Edith Cowan University (ECU) researchers trained algorithms on a database of more than 1 million commonplace images and transferred this knowledge to identify characteristics of medical conditions which can be diagnosed with an x-ray.

Ozone levels in the earth's troposphere (the lowest level of our atmosphere) can now be forecasted with accuracy up to two weeks in advance, a remarkable improvement over current systems that can accurately predict ozone levels only three days ahead. The new artificial intelligence system developed in the University of Houston's Air Quality Forecasting and Modeling Lab could lead to improved ways to control high ozone problems and even contribute to solutions for climate change issues.

'Precision agriculture' where farmers respond in real time to changes in crop growth using nanotechnology and artificial intelligence (AI) could offer a practical solution to the challenges threatening global food security, a new study reveals.

Soil liquefaction was a major feature of the 2011 Christchurch, New Zealand earthquake that killed 185 people. Researchers developed a machine learning model to predict the amount of lateral movement that can be expected from liquefaction during a natural hazard event. Their model, trained on Christchurch data, was 70% accurate at determining the amount of displacement that occurred. The researchers used the Frontera supercomputer, one of the world's fastest, to train and test the model.

Supercomputers may no longer be needed to screen candidate materials and perform simulations for a wide variety of theoretical and commercial applications thanks to an easily accessible and computationally inexpensive new machine learning model, which has been initially trained to predict the band gap of solar energy materials as a proof of concept.

An algorithm developed at Caltech lets machines teach themselves how to recognize landscapes, even amid the changing seasons.