TY -的A2 -周,μAU -沙阿,Hurmat阿里盟,古永锵Insoo PY - 2018 DA - 2018/09/12 TI -可靠的基于机器学习的认知无线电频谱感知网络SP - 5906097六世- 2018 AB -光谱传感至关重要在认知无线电(CR)网络。本文提出了一种可靠的频谱感知方案，该方案采用机器学习算法k -最近邻算法。在培训阶段，每个CR用户在不同的条件下生成一份感知报告，并根据全局决策，发送或保持沉默。在培训阶段，在融合中心通过多数投票对CR用户的局部决策进行组合，并将全局决策返回给每个CR用户。一个CR用户根据全局决策传输或保持沉默，在每个CR用户上全局决策与实际的主用户活动进行比较，后者通过一个确认信号确定。在培训阶段，要有足够的关于周围环境的信息。，收集PU的活动和每个CR对该活动的行为，并形成感知类。在分类阶段，每个CR用户将自己当前的感知报告与现有的感知类进行比较，计算距离向量。根据定量变量计算各感知类别的后验概率，并将感知报告分为是否存在PU两类。计算后验概率的定量变量采用k近邻算法计算。 These local decisions are then combined at the fusion center using a novel decision combination scheme, which takes into account the reliability of each CR user. The CR users then transmit or stay silent according to the global decision. Simulation results show that our proposed scheme outperforms conventional spectrum sensing schemes, both in fading and in nonfading environments, where performance is evaluated using metrics such as the probability of detection, total probability of error, and the ability to exploit data transmission opportunities. SN - 1530-8669 UR - https://doi.org/10.1155/2018/5906097 DO - 10.1155/2018/5906097 JF - Wireless Communications and Mobile Computing PB - Hindawi KW - ER -