A method for false alarm recognition considering threshold

A new approach to false alarm recognition is proposed. The described method divides the state of a system into three types: normal, false-alarm, and faulty, and analyzes the overlapping relations of the distribution functions of different states to determine the optimal thresholds. After a brief introduction to support vector machine (SVM), the proposed strategy based on the results using thresholds is explained. The presented evolutionary approach is illustrated by a fault injection system. The accuracy of the technique is compared with the conventional and other intelligent methods, and the obtained results are discussed.