摘要
Data selection-based summation fusion （DSSF） was developed to overcome the shortcomings ot previously developed likelihood ratio tests based on channel statistics （LRT-CS） for the problem of fusing censored binary decisions transmitted over Nakagami fading channels in a wireless sensor network （WSN）. The LRT-CS relies on detection probabilities of the local sensors, while the detection probabilities are a priori unknown for uncooperative targets. Also, for Nakagami fading channels, the LRT-CS involves an infinite series, which is cumbersome for real-time application. In contrast, the DSSF only involves data comparisons and additions and does not require the detection probabilities of local sensors. Furthermore, the performance of DSSF is only slightly degraded in comparison with the LRT-CS when the detection probabilities of local sensors are a priori unknown. Therefore, the DSSF should be used in a WSN with limited resources.
Data selection-based summation fusion （DSSF） was developed to overcome the shortcomings ot previously developed likelihood ratio tests based on channel statistics （LRT-CS） for the problem of fusing censored binary decisions transmitted over Nakagami fading channels in a wireless sensor network （WSN）. The LRT-CS relies on detection probabilities of the local sensors, while the detection probabilities are a priori unknown for uncooperative targets. Also, for Nakagami fading channels, the LRT-CS involves an infinite series, which is cumbersome for real-time application. In contrast, the DSSF only involves data comparisons and additions and does not require the detection probabilities of local sensors. Furthermore, the performance of DSSF is only slightly degraded in comparison with the LRT-CS when the detection probabilities of local sensors are a priori unknown. Therefore, the DSSF should be used in a WSN with limited resources.
