Kobir M D Irteeja, Machado Pedro, Lotfi Ahmad, Haider Daniyal, Ihianle Isibor Kennedy
Department of Computer Science, Nottingham Trent University, 50 Shakespeare St., Nottingham NG1 4FQ, UK.
Sensors (Basel). 2025 Jun 25;25(13):3955. doi: 10.3390/s25133955.
Human Activity Recognition (HAR) is crucial for understanding human behaviour through sensor data, with applications in healthcare, smart environments, and surveillance. While traditional HAR often relies on ambient sensors, wearable devices or vision-based systems, these approaches can face limitations in dynamic settings and raise privacy concerns. Device-free HAR systems, utilising Wi-Fi Channel State Information (CSI) to human movements, have emerged as a promising privacy-preserving alternative for next-generation health activity monitoring and smart environments, particularly for multi-user scenarios. However, current research faces challenges such as the need for substantial annotated training data, class imbalance, and poor generalisability in complex, multi-user environments where labelled data is often scarce. This paper addresses these gaps by proposing a hybrid deep learning approach which integrates signal preprocessing, targeted data augmentation, and a customised integration of CNN and Transformer models, designed to address the challenges of multi-user recognition and data scarcity. A random transformation technique to augment real CSI data, followed by hybrid feature extraction involving statistical, spectral, and entropy-based measures to derive suitable representations from temporal sensory input, is employed. Experimental results show that the proposed model outperforms several baselines in single-user and multi-user contexts. Our findings demonstrate that combining real and augmented data significantly improves model generalisation in scenarios with limited labelled data.
人类活动识别（HAR）对于通过传感器数据理解人类行为至关重要，在医疗保健、智能环境和监控等领域有应用。虽然传统的HAR通常依赖于环境传感器、可穿戴设备或基于视觉的系统，但这些方法在动态环境中可能会面临局限性，并引发隐私问题。利用Wi-Fi信道状态信息（CSI）来识别人类运动的无设备HAR系统，已成为下一代健康活动监测和智能环境中一种有前景的隐私保护替代方案，特别是在多用户场景中。然而，当前的研究面临着诸多挑战，如需要大量带注释的训练数据、类别不平衡，以及在复杂的多用户环境中泛化能力差，因为在这些环境中标记数据往往很稀缺。本文通过提出一种混合深度学习方法来解决这些差距，该方法集成了信号预处理、有针对性的数据增强，以及卷积神经网络（CNN）和Transformer模型的定制集成，旨在应对多用户识别和数据稀缺的挑战。采用了一种随机变换技术来增强真实的CSI数据，随后进行混合特征提取，包括基于统计、频谱和熵的度量，以从时间感官输入中导出合适的表示。实验结果表明，所提出的模型在单用户和多用户环境中均优于多个基线。我们的研究结果表明，在标记数据有限的场景中，将真实数据和增强数据相结合可显著提高模型的泛化能力。
