用混合模型提升Wi-Fi识活动的跨环境泛化能力
IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition
- 结合卷积与双向LSTM提取多尺度时序特征
- 跨场景测试准确率达95.40%，较基准提升7.58%
- 适合需要稳定部署在不同环境的智能健康应用
Wi-Fi感知是人体活动识别（HAR）的前沿技术，提供非侵入式、低成本的健康与智慧环境解决方案。尽管潜力巨大，现有方法常受领域偏移影响，在未见环境中泛化能力差，易过拟合。本文提出IBIS，一种融合Inception-BiLSTM的特征提取与SVM分类器的集成框架，旨在增强跨场景泛化能力。在多个数据集上的实验表明，IBIS在外部数据集的跨场景评估中达到95.40%的准确率，相较标准架构提升7.58%。分析证实，该方法能有效缓解基于Wi-Fi的HAR对环境的依赖性。
原文摘要 · Abstract (English)
Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and smart environments. Despite its potential, existing methods struggle with domain shift issues, often failing to generalize to unseen environments due to overfitting. This paper proposes IBIS, a robust ensemble framework combining Inception-Bidirectional Long Short-Term Memory (BiLSTM) for feature extraction and Support Vector Machine (SVM) for classification of Doppler signatures. The proposed architecture specifically targets generalization capabilities. Experimental results on multiple datasets show that IBIS achieves 95.40% accuracy, delivering a 7.58% performance gain compared to standard architectures in cross-scenario evaluations on external datasets. The analysis confirms that IBIS effectively mitigates environmental dependency in Wi-Fi-based HAR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。