Energy Efficiency of a wireless sensor network (WSN) relies on its main characteristics, including hop-number, user's location, allocated power, and relay. Identifying nodes, which have more impact on these characteristics, is, however, subject to a substantial computational overhead and energy consumption. In this paper, we proposed an active learning approach to address the computational overhead of identifying critical nodes in a WSN. The proposed approach can overcome biasing in identifying non-critical nodes and needs much less effort in fine-tuning to adapt to the dynamic nature of WSN. This method benefits from the cooperation of clustering and classification modules to iteratively decrease the required number of data in a typical supervised learning scenario and to increase the accuracy in the presence of uninformative examples, i.e., non-critical nodes. Experiments show that the proposed method has more flexibility, compared to the state-of-the-art, to be employed in large scale WSN environments, the fifth-generation mobile networks (5G), and massively distributed IoT (i.e., sensor networks), where it can prolong the network lifetime.

翻译：无线传感器网络的能量效率依赖于其主要特性，包括跳数、用户位置、分配功率和转发节点。然而，识别对这些特性影响更大的节点会带来巨大的计算开销和能耗。本文提出了一种主动学习方法，以解决识别无线传感器网络中关键节点时的计算开销问题。所提方法能够克服在识别非关键节点时可能出现的偏差，并且几乎无需精细调整即可适应无线传感器网络的动态特性。该方法利用聚类模块与分类模块的协同作用，在典型监督学习场景中迭代减少所需数据量，并在存在非信息性样本（即非关键节点）时提高准确性。实验表明，与现有先进方法相比，所提方法在大型无线传感器网络环境、第五代移动网络以及大规模分布式物联网（即传感器网络）中具有更高的灵活性，能够延长网络寿命。