Efficient Feature Selection of Power Quality Events using Two Dimensional (2D) Particle Swarms
This work addresses feature selection for Power Quality event analysis, which is incremental as it builds on existing methods by adding a new dimension to guide the search process.
The paper tackled feature selection for Power Quality events by proposing a two-dimensional learning framework that incorporates subset cardinality, achieving significantly better and more robust feature subsets compared to six existing methods across fourteen event classes and various noise levels.
A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the information about the subset cardinality (i.e., the number of features) as an additional learning dimension to effectively guide the search process. The efficacy of this approach has been demonstrated considering fourteen distinct classes of PQ events which conform to the IEEE Standard 1159. The search performance of the 2D learning approach has been compared to the other six well-known feature selection wrappers by considering two induction algorithms: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). Further, the robustness of the selected/reduced feature subsets has been investigated considering seven different levels of noise. The results of this investigation convincingly demonstrate that the proposed 2D learning can identify significantly better and robust feature subsets for PQ events.