分散序列假设检验的渐进最优理论在传感器网络中的应用-应用统计专业论文.docx

II II ABSTRACT In fact, the decentralized sequential hypothesis testing problem is always studied in sensor networks, where first a set of sensors receive observations independently, then sensors send the summary messages to the fusion center, making a final decision. When we study the decentralized sequential hypothesis testing problem In the sensor networks, according to the sensors whether have full access to their own observations of information, the sensor networks can be divided into two categories: system with full local memory and system with limited local memory. When study on sensor networks, it is can establish the corresponding asymptotically Bayes sequential test respectively for these two types. From studying these two types, we can get an interesting but very useful inference, and a new minimax formulation i.e. optimal stationary sensor quantizers, which is proposed in the case of additive Gaussian sensor noise. Finally, our results that empirical model checking in the adoption of Xuefeng Mountain highway in Hunan province confirmed the possibility of new minimax formulation. The studying show that , feedback informations from the fusion center do not improve the asymptotic performance in the system with full local memory, but, even a one-bit, one-shot feedback also can obviously improve incremental performance in the case of limited local memory. Key words: Sensor networks, Decentralized sequential hypothesis testing, Tandem quantizer, Asymptotically bayes, Minimax formulation PAGE PAGE IV 目 录 摘 要 I HYPERLINK \l _bookmark0 Abstract II HYPERLINK \l _bookmark1 1 绪论 HYPERLINK \l _bookmark2 1.1 研究背景与意义 (1) HYPERLINK \l _bookmark3 1.2 国内外研究概况 (2) HYPERLINK \l _bookmark4 1.3 研究思路和主要内容 (3) HYPERLINK \l _bookmark5 2 假设检验的基本思想及问题公式化 HYPERLINK \l _bookmark6 2.1 假设检验的基本思想 (5) HYPERLINK \l _bookmark7 2.2 传感器网络问题的分类 (6) HYPERLINK \l _bookmark8 2.3 传感器网络检验问题公式化 (10) HYPERLINK \l _bookmark9 3 系统拥有完整的本地内存 HYPERLINK \l _bookmark10 3.1 构建检验??A