EFFICIENT PRIMAL SUPPORT VECTOR MACHINE DESIGN USING PIECEWISE LINEAR APPROXIMATION BASED LINEAR PROGRAMMING OPTIMIZATION TECHNIQUES
Support Vector Machine (SVM) is one of the most popular supervised learning techniques for classification and regression tasks. This study proposes and validates a novel, fast, and efficient primal SVM design using the aid of a piecewise linear approximation approach and separable linear programming optimization techniques. The GUROBI optimizer solver is employed to address this approximation-based SVM design challenge. The proposed SVM (we term it PLASVM) designing technique guarantees a global solution through the application of mixed integer linear programming and branch and bound algorithms. The linear programming (LP) method enables SVM training with large datasets in a short amount of time. The effectiveness of the suggested PLASVM algorithms is evaluated using a laboratory gas turbine engine. Using the fault classification technique, the performance of the gas turbine engine has been guaranteed against any faulty condition. The collected findings demonstrate that the PLASVM algorithms perform better than the existing techniques regarding training speed and accuracy.
Fault Classification, Gas Turbine Engine, Global optimization, Linear Programming (LP), Piecewise Linear Approximation (PLA), Special Order Set type 2 (SOS2), Support Vector Machine (SVM), and Training algorithms