SiMWiSense: Simultaneous Multi-Subject Activity Classification Through Wi-Fi Signals
SiMWiSense: Simultaneous Multi-Subject Activity Classification Through Wi-Fi Signals
复制标题
DOI：
10.1109/wowmom57956.2023.00019
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Khandaker Foysal Haque;Milin Zhang;Francesco Restuccia
中科院分区：
文献类型：
--
作者：
Khandaker Foysal Haque;Milin Zhang;Francesco Restuccia
Wi-Fi 传感领域的最新进展在家庭监控、远程医疗、道路安全和家庭娱乐等领域带来了大量普遍应用。大多数现有作品仅限于对单个人类受试者在给定时间的活动分类。相反，更现实的场景是实现同时的、多主体的活动分类。在这种情况下，第一个关键挑战是班级数量随着科目和活动的数量呈指数增长。此外，众所周知，Wi-Fi 传感系统很难适应新的环境和主题。为了解决这两个问题，我们提出了 SiMWiSense，这是第一个基于 Wi-Fi 的同步多主题活动分类框架，可推广到多个环境和主题。我们通过使用从最靠近主题的设备计算出的通道状态信息（CSI）来解决可扩展性问题。我们通过实验证明了这种直觉，确认当使用最接近主体的收发器计算的 CSI 进行分类时，可以获得最佳的准确度。为了解决泛化问题，我们开发了一种全新的小样本学习算法，称为特征可重用嵌入学习（FREL）。通过在 3 个不同环境和 3 个受试者同时执行 20 种不同活动的广泛数据收集活动，我们证明 SiMWiSense 的分类准确率高达 97%，而 FREL 与传统的卷积神经网络 (CNN) 相比，准确率提高了 85%，与最先进的少样本嵌入学习 (FSEL) 相比，准确率提高了 20%，每个类别仅使用 15 秒的额外数据。出于可重复性的目的，我们共享 1 TB 数据集和代码存储库1 [1].1https://github.com/kfoysalhaque/SiMWiSense
Recent advances in Wi-Fi sensing have ushered in a plethora of pervasive applications in home surveillance, remote healthcare, road safety, and home entertainment, among others. Most of the existing works are limited to the activity classification of a single human subject at a given time. Conversely, a more realistic scenario is to achieve simultaneous, multi-subject activity classification. The first key challenge in that context is that the number of classes grows exponentially with the number of subjects and activities. Moreover, it is known that Wi-Fi sensing systems struggle to adapt to new environments and subjects. To address both issues, we propose SiMWiSense, the first framework for simultaneous multi-subject activity classification based on Wi-Fi that generalizes to multiple environments and subjects. We address the scalability issue by using the Channel State Information (CSI) computed from the device positioned closest to the subject. We experimentally prove this intuition by confirming that the best accuracy is experienced when the CSI computed by the transceiver positioned closest to the subject is used for classification. To address the generalization issue, we develop a brand-new few-shot learning algorithm named Feature Reusable Embedding Learning (FREL). Through an extensive data collection campaign in 3 different environments and 3 subjects performing 20 different activities simultaneously, we demonstrate that SiMWiSense achieves classification accuracy of up to 97%, while FREL improves the accuracy by 85% in comparison to a traditional Convolutional Neural Network (CNN) and up to 20% when compared to the state-of-the-art few-shot embedding learning (FSEL), by using only 15 seconds of additional data for each class. For reproducibility purposes, we share our 1 TB dataset and code repository1 [1].1https://github.com/kfoysalhaque/SiMWiSense