首页|Research from Pennsylvania State University (Penn State) Provides New Data on Ma chine Learning (The Evaluation of Machine Learning Techniques for Isotope Identi fication Contextualized by Training and Testing Spectral Similarity)

Research from Pennsylvania State University (Penn State) Provides New Data on Ma chine Learning (The Evaluation of Machine Learning Techniques for Isotope Identi fication Contextualized by Training and Testing Spectral Similarity)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news reporting from University Pa rk, Pennsylvania, by NewsRx journalists, research stated, "Precise gamma-ray spe ctral analysis is crucial in high-stakes applications, such as nuclear security. " Financial supporters for this research include Defense Threat Reduction Agency; Sandia National Laboratories. Our news correspondents obtained a quote from the research from Pennsylvania Sta te University (Penn State): "Research efforts toward implementing machine learni ng (ML) approaches for accurate analysis are limited by the resemblance of the t raining data to the testing scenarios. The underlying spectral shape of syntheti c data may not perfectly reflect measured configurations, and measurement campai gns may be limited by resource constraints. Consequently, ML algorithms for isot ope identification must maintain accurate classification performance under domai n shifts between the training and testing data. To this end, four different clas sifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Percept ron) were trained on the same dataset and evaluated on twelve other datasets wit h varying standoff distances, shielding, and background configurations. A tailor ed statistical approach was introduced to quantify the similarity between the tr aining and testing configurations, which was then related to the predictive perf ormance."

Pennsylvania State University (Penn Stat e)University ParkPennsylvaniaUnited StatesNorth and Central AmericaCyb orgsEmerging TechnologiesMachine Learning

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Oct.4)