Self-Supervised WiFi-Based Activity Recognition
Self-Supervised WiFi-Based Activity Recognition
复制标题
DOI：
10.1109/gcwkshps56602.2022.10008537
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Hok-Shing Lau;Ryan McConville;M. J. Bocus;R. Piechocki;Raúl Santos-Rodríguez
中科院分区：
文献类型：
--
作者：
Hok-Shing Lau;Ryan McConville;M. J. Bocus;R. Piechocki;Raúl Santos-Rodríguez
传统的活动识别方法涉及使用可穿戴传感器或相机来识别人类活动。在这项工作中，我们从WiFi设备中提取细粒度的物理层信息，用于室内环境中的被动活动识别。虽然这些数据无处不在，但很少有方法被设计用于利用大量未标记的WiFi数据。我们建议使用自监督对比学习，以提高活动识别性能时，使用多个视图的同步接收器部署在不同的位置捕获的传输的WiFi信号。我们进行了广泛的人类活动识别（HAR）实验在两个装修的办公室，其中六个不同年龄组的参与者进行六天到一天的活动。我们将所提出的对比学习系统与传统的非对比系统进行比较，并观察到基于WiFi的活动识别任务在少数学习场景下的显着改进。也就是说，使用基于AlexNet的骨干编码器进行对比预训练，当在微调阶段仅考虑1.29%的标记训练样本时，宏F1得分增加了22%。
Traditional approaches to activity recognition involve the use of wearable sensors or cameras in order to recognise human activities. In this work, we extract fine-grained physical layer information from WiFi devices for the purpose of passive activity recognition in indoor environments. While such data is ubiquitous, few approaches are designed to utilise large amounts of unlabelled WiFi data. We propose the use of selfsupervised contrastive learning to improve activity recognition performance when using multiple views of the transmitted WiFi signal captured by synchronised receivers deployed in different positions. We conduct extensive Human Activity Recognition (HAR) experiments in two furnished office rooms, whereby six participants of different age groups performed six day-to-day activities. We compare the proposed contrastive learning system with conventional non-contrastive systems and observe significant improvement on the task of WiFi based activity recognition under few-shot learning scenarios. Namely, contrastively pretraining with an AlexNet-based backbone encoder led to a 22% increase in macro F1 score when only 1.29% of labelled training samples are considered in the fine-tuning stage.