arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02014eess.SP
收藏

FewSense,使用Few-Shot学习的可扩展跨域Wi-Fi传感系统

FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning

Guolin Yin, Junqing Zhang, Guanxiong Shen, Yingying Chen

摘要:

Wi-Fi感测可以对人类活动进行分类,因为每个活动导致对信道状态信息(CSI)的唯一改变。现有的WiFi感测具有有限的可扩展性,因为每当添加新活动时系统需要重新训练,这导致数据收集和重新训练的开销。跨域感测可能失败,因为当涉及不同的环境或用户(域)时,活动与CSI变化之间的映射被破坏。提出了一种基于Few-Shot学习的WiFi感知系统FewSense,该系统能够在较少样本的情况下识别未知领域中的新类别。具体地,使用源域数据离线预训练特征提取器。当该系统应用于目标领域时,很少的样本被用来微调特征提取器以进行领域自适应。通过计算余弦相似度进行推理。FewSense可以通过协作融合来自多个接收器的推断来进一步提高分类准确性。我们使用三个公共数据集评估了性能,即,SignFi、Widar和Wiar。结果表明,FewSense在SignFi、Widar和Wiar数据集上识别未知领域的新类的准确率分别为90.3%、96.5%和82.7%。我们的协作传感模型将系统性能平均提高了30%。

英文摘要:

Wi-Fi sensing can classify human activities because each activity causes unique changes to the channel state information (CSI). Existing WiFi sensing suffers from limited scalability as the system needs to be retrained whenever new activities are added, which cause overheads of data collection and retraining. Cross-domain sensing may fail because the mapping between activities and CSI variations is destroyed when a different environment or user (domain) is involved. This paper proposed a few-shot learning-based WiFi sensing system, named FewSense, which can recognise novel classes in unseen domains with only few samples. Specifically, a feature extractor was pre-trained offline using the source domain data. When the system was applied in the target domain, few samples were used to fine-tune the feature extractor for domain adaptation. Inference was made by computing the cosine similarity. FewSense can further boost the classification accuracy by collaboratively fusing inference from multiple receivers. We evaluated the performance using three public datasets, i.e., SignFi, Widar, and Wiar. The results show that FewSense with five-shot learning recognised novel classes in unseen domains with an accuracy of 90.3\%, 96.5\% ,82.7\% on SignFi, Widar, and Wiar datasets, respectively. Our collaborative sensing model improved system performance by an average of 30\%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑