The Internet of Things (IoT) networks have become the infrastructure to enable the detection and reaction of anomalies in various domains, where an efficient sensory data gathering mechanism is fundamental since IoT nodes are typically constrained in their energy and computational capacities. Besides, anomalies may occur occasionally in most applications, while the majority of time durations may reflect a healthy situation. In this setting, the range, rather than an accurate value of sensory data, should be more interesting to domain applications, and the range is represented in terms of the category of sensory data. To decrease the energy consumption of IoT networks, this paper proposes an energy-efficient sensory data gathering mechanism, where the category of sensory data is processed by adopting the compressed sensing algorithm. The sensory data are forecasted through a data prediction model in the cloud, and sensory data of an IoT node is necessary to be routed to the cloud for the synchronization purpose, only when the category provided by this IoT node is different from the category of the forecasted one in the cloud. Experiments are conducted and evaluation results demonstrate that our approach performs better than state-of-the-art techniques, in terms of the network traffic and energy consumption.

中文翻译：

---

物联网网络中基于压缩传感的节能传感数据收集

物联网（IoT）网络已成为可在各个域中检测和反应异常的基础结构，在该域中，有效的感官数据收集机制至关重要，因为IoT节点通常受其能量和计算能力的限制。此外，在大多数应用程序中偶尔可能会出现异常，而大多数持续时间可能反映出健康状况。在此设置中，范围而不是感官数据的准确值对于领域应用而言应该更为有趣，并且范围以感官数据的类别表示。为了降低物联网网络的能耗，本文提出了一种节能的传感数据收集机制，该机制通过采用压缩传感算法处理传感数据的类别。感官数据是通过云中的数据预测模型进行预测的，并且仅当此IoT节点提供的类别不同于该IoT节点的类别时，才需要将IoT节点的感官数据路由到云以进行同步。在云端预测一个。进行了实验，评估结果表明，在网络流量和能耗方面，我们的方法比最先进的技术性能更好。