The investigation in this paper targets the design and the evaluation of jamming intrusion detection based on Fuzzy Logic in wireless mesh IoT Networks in a distributed manner. Our approach uses information collected at local nodes and from the sink as input to the fuzzy logic controller. In order to find the best set of inputs, distributed or centralized, we made a comparison between five different combinations of parameters. The investigation uses the values of the ETX, Retransmissions, Packets Drop per terminal (PDPT) and Packet Delivery Ratio (PDR) as inputs to a fuzzy inference system to get Jamming Index (JI) as the system's output. The proposed method was evaluated based on the following metrics: Accuracy, Precision, Specificity, False positive rate (FPR), Recall, False negative rate (FNR) and ROC curve. In order to evaluate this approach, we implement experiments in various scenarios using the Contiki OS and the Cooja simulator tool.

翻译：本文的调查目标是以分布式的方式设计和评价无线网网中基于Fuzzy逻辑的干扰探测。我们的方法将在当地节点和水槽收集的信息用作对模糊逻辑控制器的投入。为了找到最佳的投入,我们对五种不同的参数组合进行了分布式或集中式的比较。调查将ETX、再传输、每终点站的垃圾桶和包装传送率(PDDR)的值用作对一个模糊的推断系统的投入,以便把干扰指数(JI)作为系统的产出。拟议的方法是根据以下指标进行评估的:精确度、精度、特性、假正率(FPR)、回调、假负率(FNR)和ROC曲线。为了评估这一方法,我们利用Contiki OS和Cooja 模拟工具在各种情景中进行实验。