To address one of the most challenging industry problems, we develop an enhanced training algorithm for anomaly detection in unlabelled sequential data such as time-series. We propose outputs a well-designed system are drawn from unknown probability distribution, U, normal conditions. introduce criterion based on classical central limit theorem that allows evaluation likelihood data-point is U....

Time-ordered data (TOD) from ground-based CMB experiments is usually filtered before map-making to reduce the contamination ground and atmospheric emissions. However, when observation region contains strong point sources, filtering process will cause a considerable leakage around which should be eliminated provide clean polarization map for scientific purposes. The method we introduce in this w...