Real-time intelligence applications in Internet of Things (IoT) environment depend on timely data communication. However, it is challenging to transmit and analyse massive data of various modalities. Recently proposed task-oriented communication methods based on deep learning have showed its superiority in communication efficiency. In this paper, we propose a cooperative task-oriented communication method for the transmission of multi-modal data from multiple end devices to a central server. In particular, we use the transmission result of data of one modality, which is with lower rate, to control the transmission of other modalities with higher rate in order to reduce the amount of transmitted date. We take the human activity recognition (HAR) task in a smart home environment and design the semantic-oriented transceivers for the transmission of monitoring videos of different rooms and acceleration data of the monitored human. The numerical results demonstrate that by using the transmission control based on the obtained results of the received acceleration data, the transmission is reduced to 2% of that without transmission control while preserving the performance on the HAR task.

翻译：物联网（IoT）环境下的实时智能应用依赖于及时的数据通信。然而，传输并分析大量多模态数据极具挑战性。基于深度学习的任务导向通信方法近年被提出，并在通信效率上展现出优势。本文提出一种协同任务导向通信方法，用于从多个终端设备向中央服务器传输多模态数据。具体而言，我们利用低速率模态数据的传输结果来控制其他高速率模态的传输，从而减少传输数据量。以智能家居环境中的人体活动识别（HAR）任务为例，我们设计了语义导向的收发机，用于传输不同房间的监控视频以及被监测人体的加速度数据。数值结果表明，基于所接收加速度数据的分析结果进行传输控制，可在保持HAR任务性能的同时，将传输量降至未进行传输控制时的2%。