首页|Study Data from University of Amsterdam Update Knowledge of Machine Learning (Th e Road To Discovery:Machine-learningdriven Anomaly Detection In Radio Astronom y Spectrograms)
Study Data from University of Amsterdam Update Knowledge of Machine Learning (Th e Road To Discovery:Machine-learningdriven Anomaly Detection In Radio Astronom y Spectrograms)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Machine Learning have be en published.According to news reporting originating from Amsterdam,Netherland s,by NewsRx correspondents,research stated,"As radio telescopes increase in s ensitivity and flexibility,so do their complexity and data rates.For this reas on,automated system health management approaches are becoming increasingly crit ical to ensure nominal telescope operations." Financial support for this research came from Dutch Research Council (NWO) domai n Applied and Engineering Sciences (TTW).Our news editors obtained a quote from the research from the University of Amste rdam,"We propose a new machine-learning anomaly detection framework for classif ying both commonly occurring anomalies in radio telescopes as well as detecting unknown rare anomalies that the system has potentially not yet seen.To evaluate our method,we present a dataset consisting of 6708 autocorrelation-based spect rograms from the Low Frequency Array (LOFAR) telescope and assign ten different labels relating to the system-wide anomalies from the perspective of telescope o perators.This includes electronic failures,miscalibration,solar storms,netwo rk and compute hardware errors,among many more.We demonstrate how a novel self -supervised learning (SSL) paradigm,that utilises both context prediction and r econstruction losses,is effective in learning normal behaviour of the LOFAR tel escope.We present the Radio Observatory Anomaly Detector (ROAD),a framework th at combines both SSL-based anomaly detection and a supervised classification,th ereby enabling both classification of both commonly occurring anomalies and dete ction of unseen anomalies.We demonstrate that our system works in real time in the context of the LOFAR data processing pipeline,requiring <1ms to process a single spectrogram."
AmsterdamNetherlandsEuropeAstronom yCyborgsEmerging TechnologiesMachine LearningPhysicsUniversity of Amst erdam
NETL
NSTL
