Improvement of training set structure in fusion data cleaning using Time-Domain Global Similarity method
This addresses data cleaning challenges in fusion diagnostics, but appears incremental as it builds on existing similarity methods.
The paper tackled the class-imbalanced problem in data cleaning for Magnetic Confinement Fusion devices by transforming classification of original data sequences into classification based on physical similarity, resulting in improved training set structure and demonstrated performance in the EAST POINT system.
Traditional data cleaning identifies dirty data by classifying original data sequences, which is a class$-$imbalanced problem since the proportion of incorrect data is much less than the proportion of correct ones for most diagnostic systems in Magnetic Confinement Fusion (MCF) devices. When using machine learning algorithms to classify diagnostic data based on class$-$imbalanced training set, most classifiers are biased towards the major class and show very poor classification rates on the minor class. By transforming the direct classification problem about original data sequences into a classification problem about the physical similarity between data sequences, the class$-$balanced effect of Time$-$Domain Global Similarity (TDGS) method on training set structure is investigated in this paper. Meanwhile, the impact of improved training set structure on data cleaning performance of TDGS method is demonstrated with an application example in EAST POlarimetry$-$INTerferometry (POINT) system.