Using Statistical Techniques to Improve the QC Process of Swell Noise Filtering

The current approach for the quality control (QC) process of the swell noise filtering phase carries significant drawbacks. This abstract investigates the use of statistical techniques to improve the QC process. The main approach of this analysis is to combine attributes that capture properties of the filtering process and plot them against each other in order to identify outliers. It is shown that cases which have been badly or not properly filtered will cluster away from the main group and may be detected using statistical methods such as clustering algorithms. Statistical techniques may potentially play an important role in the development of a data-driven automated QC platform.