A New Abnormal Node Detection Method With Dynamic Hoeffding Test

In this letter, we propose a new method based on the dynamic Hoeffding test that can distinguish the abnormal relay nodes from those with normal packet loss in wireless communications. An asymptotic analysis of the detection performance on the Hoeffding test is conducted to determine the new dynamic detection threshold for decreasing the total probability of errors. With the theoretical guarantees, both false alarm and missed detection probabilities of the proposed scheme converge exponentially as the number of detection periods increases. Simulation results validate our analysis and demonstrate the superior detection performance of the proposed method.

Automated summary

In this letter, a new method based on the dynamic Hoeffding test is proposed to distinguish abnormal relay nodes from those with normal packet loss in wireless communications. An asymptotic analysis of the detection performance on the Hoeffding test is conducted to determine a new dynamic detection threshold for reducing the probability of errors. Theoretical guarantees are provided, showing that both false alarm and missed detection probabilities of the proposed scheme exponentially converge as the number of detection periods increases. Simulation results validate the analysis and illustrate the superior detection performance of the proposed method.