This work considers a scenario in which an edge server collects data from Internet of Things (IoT) devices equipped with wake-up receivers. Although this procedure enables on-demand data collection, there is still energy waste if the content of the transmitted data following the wake-up is irrelevant. To mitigate this, we advocate the use of Tiny Machine Learning (ML) to enable a semantic response from the IoT devices, so they can send only semantically relevant data. Nevertheless, receiving the ML model and the ML processing at the IoT devices consumes additional energy. We consider the specific instance of image retrieval and investigate the gain brought by the proposed scheme in terms of energy efficiency, considering both the energy cost of introducing the ML model as well as that of wireless communication. The numerical evaluation shows that, compared to a baseline scheme, the proposed scheme can realize both high retrieval accuracy and high energy efficiency, which reaches up to 70% energy reduction when the number of stored images is equal to or larger than 8.

翻译：本文考虑了一种场景，其中边缘服务器从配备唤醒接收器的物联网设备收集数据。尽管此过程能够实现按需数据收集，但如果唤醒后传输的数据内容无关，仍会浪费能量。为缓解这一问题，我们倡导使用微型机器学习来实现物联网设备的语义响应，使其仅发送语义相关的数据。然而，在物联网设备上接收机器学习模型并执行处理会消耗额外能量。我们针对图像检索这一具体实例，评估了所提方案在能效方面的增益，同时考虑了引入机器学习模型的能量成本以及无线通信的能量成本。数值评估表明，与基准方案相比，所提方案既能实现高检索精度，又能达到高能效，当存储图像数量大于等于8张时，能量消耗可降低高达70%。