Towards Environment-Independent Activity Recognition Using Wi-Fi CSI with an Encoder-Decoder Network
Towards Environment-Independent Activity Recognition Using Wi-Fi CSI with an Encoder-Decoder Network
复制标题
DOI：
10.1145/3597061.3597261
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Yusuke Sugimoto;Hamada Rizk;Akira Uchiyama;Hirozumi Yamaguchi
中科院分区：
文献类型：
--
作者：
Yusuke Sugimoto;Hamada Rizk;Akira Uchiyama;Hirozumi Yamaguchi
人体活动识别（HAR）近年来因其在医疗保健，智能家居和安全方面的潜在应用而引起了人们的广泛关注。Wi-Fi信道状态信息（CSI）是用于HAR的有前途的传感器模态，提供了无设备和低成本的解决方案。然而，使用Wi-Fi CSI为HAR构建与环境无关的模型仍然是一个重大挑战。在本文中，我们提出了一种基于深度学习的活动识别系统，该系统利用从一个或多个环境中获得的CSI测量结果，即使在看不见的环境中也能提供一致和准确的性能。我们的系统采用了多任务的学习方法，是基于编码器-解码器网络架构。这使得该架构的编码器部分能够减轻环境相关因素，并提取丰富的环境不变表示。为了评估所提出的系统，我们收集了CSI样本，由三个参与者在四个不同的环境中进行的六项活动。结果表明，所提出的系统在实现环境无关的HAR的平均精度为80%的效率。此外，在数据有限的情况下，结果验证了我们的方法在环境特定模型上的优越性，最低保证金为6%。
Human Activity Recognition (HAR) has attracted considerable attention in recent years due to its potential applications in healthcare, smart homes, and security. Wi-Fi Channel State Information (CSI) is a promising sensor modality for HAR, providing a device-free and low-cost solution. However, building environment-independent models for HAR using Wi-Fi CSI remains a significant challenge. In this paper, we present a deep learning-based activity recognition system that exploits CSI measurements obtained from one or more environments to deliver consistent and accurate performance even in unseen environments. Our system employs a multi-task learning approach that is based on an encoder-decoder network architecture. This enables the encoder part of this architecture to mitigate the environment-dependent factors and extract a rich and environment-invariant representation. To evaluate the proposed system, we collected CSI samples for six activities pursued by three participants in four distinct environments. The results demonstrate the efficacy of the proposed system in achieving environment-independent HAR with an average accuracy of 80%. Additionally, the results validate the superiority of our method over environment-specific models by a minimum margin of 6% in cases of limited data.