Enhanced Taguchi’s T-method using angle modulated Bat algorithm for prediction

Analysis of multivariate historical information in predicting future state or unknown outcomes is the core function Taguchi’s T-method. Introduced by Dr. Genichi Taguchi under Mahalanobis-Taguchi system, T-method combines regression principle and robust quality engineering element formulating a predictive model employs taguchi’s orthogonal array design optimizing through feature variable selection process. There concern regarding sub-optimality prediction accuracy, particularly when failed to offer significant number combinations search for an optimal subset features. This due fixed limited combination offered evaluation as well lack higher-order interaction combination. In response this issue, paper proposed angle modulated Bat algorithm be integrated with model. A comparison study was conducted using energy efficiency benchmark datasets mean absolute error metric used performance measure. The results show that method improved accuracy 10.74%, from 6.05 5.4, integrating only four features over original eight