Radio Frequency Fingerprint Identification (RFFI) is a promising device authentication technique that utilizes inherent hardware flaws in transmitters to achieve device identification, thus effectively maintaining the security of the Internet of Things (IoT). However, time-varying channels degrade accuracy due to factors like device aging and environmental changes. To address this, we propose an RFFI method integrating Zero-Forcing (ZF) equalization and KAN-ResNet. Firstly, the Wi-Fi preamble signals under the IEEE 802.11 standard are Zero-Forcing equalized, so as to effectively reduce the interference of time-varying channels on RFFI. We then design a novel residual network, KAN-ResNet, which adds a KAN module on top of the traditional fully connected layer. The module combines the B-spline basis function and the traditional activation function Sigmoid Linear Unit (SiLU) to realize the nonlinear mapping of the complex function, which enhance the classification ability of the network for RFF features. In addition, to improve the generalization of the model, the grid of B-splines is dynamically updated and L1 regularization is introduced. Experiments show that on datasets collected 20 days apart, our method achieves 99.4% accuracy, reducing the error rate from 6.3% to 0.6%, outperforming existing models.

Deep neural networks have been widely applied to fiber optic sensor systems, where the detection of external intrusion in metro tunnels is a major challenge; thus, how to achieve the optimal balance between resource consumption and accuracy is a critical issue. To address this issue, we propose a lightweight deep learning model, the Temporal Efficient Residual Network (TEResNet), for the detection of anomalous intrusion. In contrast to the majority of two-dimensional convolutional approaches, which require a deep architecture to encompass both low- and high-frequency domains, our methodology employs temporal convolutions and a compact residual network architecture. This allows the model to incorporate lower-level features into the higher-level feature formation in subsequent layers, leveraging informative features from the lower layers, and thus reducing the number of stacked layers for generating high-level features. As a result, the model achieves a superior performance with a relatively small number of layers. Moreover, the two-dimensional feature map is reduced in size to reduce the computational burden without adding parameters. This is crucial for enabling rapid intrusion detection. Experiments were conducted in the construction environment of the Guangzhou Metro, resulting in the creation of a dataset containing 6948 signal segments, which is publicly accessible. The results demonstrate that TEResNet outperforms the existing intrusion detection methods and advanced deep learning networks, achieving an accuracy of 97.12% and an F1 score of 96.15%. With only 48,009 learnable parameters, it provides an efficient and reliable solution for intrusion detection in metro tunnels, aligning with the growing demand for lightweight and robust information processing systems.