Better Together: Using Multi-task Learning to Improve Feature Selection within Structural Datasets
This work addresses feature selection for structural health monitoring in engineering, but it is incremental as it applies an existing MTL method to a specific structural dataset.
The paper tackled the problem of improving feature selection for structural health monitoring by using multi-task learning (MTL) with Joint Feature Selection with LASSO on a dataset to differentiate between port and starboard sides of a tailplane in aircraft. The result showed that MTL provided interpretable results highlighting structural differences, whereas an independent learner achieved perfect F1 scores but lacked engineering insight.
There have been recent efforts to move to population-based structural health monitoring (PBSHM) systems. One area of PBSHM which has been recognised for potential development is the use of multi-task learning (MTL); algorithms which differ from traditional independent learning algorithms. Presented here is the use of the MTL, ''Joint Feature Selection with LASSO'', to provide automatic feature selection for a structural dataset. The classification task is to differentiate between the port and starboard side of a tailplane, for samples from two aircraft of the same model. The independent learner produced perfect F1 scores but had poor engineering insight; whereas the MTL results were interpretable, highlighting structural differences as opposed to differences in experimental set-up.