This paper extends results from the traditional D-optimality machinery to derive an efficient technique for simultaneous variable selection and sensor selection. An important advantage of the proposed technique is the convexity of the formulated optimization task along with a byproduct of straightforward sparsity. The theoretical foundation of the proposed method is explored at great length, and a variety of examples are provided to demonstrated the effectiveness of our technique. Comparisons with existing techniques are offered that provide evidence as the superiority of our technique on a variety of indicators.
Department, Program, or Center
The John D. Hromi Center for Quality and Applied Statistics (KGCOE)
Fokoue, Ernest, "Efficient techniques for simultaneous variable selection and sensor selection via convex selection inducing penalties" (2011). Accessed from
RIT – Main Campus