This paper proposes a RSSI quantization and genetic algorithm based localization method. To quantize RSSI measurements from sensor nodes, we first divide sensing disks of nodes into multiple-rings and adopt genetic algorithm based on elitist preservation strategy to determine rings width. Secondly, we calculate the overlapping of rings and construct the mapping between a binary code sequence and the overlapping area. Thirdly, a density-based clustering algorithm is presented to solve the ambiguity of the target appearing area. Based on which, a two-stage centroid localization algorithm is proposed, which is especially useful for the case of irregular appearing area of the target. Finally, we construct an experimental environment to validate the performance of our algorithm.

本文提出了一种基于RSSI量化和遗传算法的定位方法。为了量化来自传感器节点的RSSI测量值，我们首先将节点的传感盘划分为多个环，然后采用基于精英保存策略的遗传算法来确定环的宽度。其次，我们计算环的重叠并构造二进制代码序列和重叠区域之间的映射。第三，提出了一种基于密度的聚类算法来解决目标出现区域的模糊性。在此基础上，提出了一种两阶段质心定位算法，该算法在目标出现区域不规则的情况下特别有用。最后，我们构建了一个实验环境来验证算法的性能。