The problems of imbalanced datasets are generally considered asymmetric issues. In asymmetric problems, artificial intelligence models may exhibit different biases or preferences when dealing with different classes. In the process of addressing class imbalance learning problems, the classification model will pay too much attention to the majority class samples and cannot guarantee the classification performance of the minority class samples, which might be more valuable. By synthesizing the minority class samples and changing the data distribution, unbalanced datasets can be optimized. Traditional oversampling algorithms have problems of blindness and boundary ambiguity when synthesizing new samples. A modified reclassification algorithm based on Gaussian distribution is put forward. First, the minority class samples are reclassified by the KNN algorithm. Then, different synthesis strategies are selected according to the combination of the minority class samples, and the Gaussian distribution is used to replace the uniform random distribution for interpolation operation under certain classification conditions to reduce the possibility of generating noise samples. The experimental results indicate that the proposed oversampling algorithm can achieve a performance improvement of 2∼ in evaluation metrics, including G-mean, F-measure, and AUC, compared to traditional oversampling algorithms.
With the increasing prevalence of wireless communication and the use of large-scale ultra-dense networking technologies, the effect of the human body as an obstacle on electromagnetic wave propagation has gained significance in complex spaces with dense human traffic, such as indoor environments and mass transit systems. In this study, we investigate the human body shadowing properties in the sub-6GHz frequency band used in mainstream wireless communication systems. Four body shadowing models (human body double knife-edge, triple knife-edge, knife-edge diffraction model, and cylindrical diffraction models) were analyzed, and two measurement scenarios based on these theoretical models were designed to obtain actual measurements. The results show that the triple knife-edge diffraction model is optimal. In addition, the human body attenuation value was found not only to vary with frequency, but also to fluctuate as the relative position of the body and receiver were changed.
As the fleet of high-speed rail vehicles expands, ensuring train safety is of the utmost importance, emphasizing the critical need to enhance the precision of axel temperature warning systems. Yet, the limited availability of data on the unique features of high thermal axis temperature conditions in railway systems hinders the optimal performance of intelligent algorithms in alarm detection models. To address these challenges, this study introduces a novel dynamic principal component analysis preprocessing technique for tolerance temperature data to effectively manage missing data and outliers. Furthermore, a customized generative adversarial network is devised to generate distinct data related to high thermal axis temperature, focusing on optimizing the network’s objective functions and distinctions to bolster the efficiency and diversity of the generated data. Finally, an integrated model with an optimized transformer module is established to accurately classify alarm levels, provide a comprehensive solution to pressing train safety issues, and, in a timely manner, notify drivers and maintenance departments (DEPOs) of high-temperature warnings.
Foreign object intrusion severely threatens railway safety. Existing methods struggle with open-set categories, high annotation costs, and poor label-efficient generalization. To address these issues, we propose UG-Net, an unsupervised-guided label-efficient detection framework. The core idea is a two-stage strategy: first, a masked autoencoder (MAE) learns “normality” priors from unlabeled data and generates a spatial attention mask via a deep feature difference strategy; then, this mask is fused as a fourth channel into a lightweight YOLOv8n detector. This approach effectively alleviates reliance on manual annotations. On a self-constructed railway dataset, UG-Net achieved 94.56% mAP@0.5 using only 200 labeled samples, significantly outperforming the YOLOv8n baseline (86.91%). The framework provides a label-efficient solution for industrial anomaly detection.
Co-channel interference (CCI) remains a critical factor affecting link reliability in narrowband wireless systems, especially in scenarios with intensive frequency reuse, overlapping coverage, and dense terminal access. Existing interference detection methods are either computationally simple but insufficiently sensitive to short-term spectral variations, or highly accurate but dependent on labeled data and nontrivial inference resources. To address this issue, this paper proposes a lightweight CCI detection method in the FFT domain based on spectrum-jump analysis. The proposed method does not rely on absolute power growth as the primary interference indicator. Instead, it tracks the temporal inconsistency of dominant spectral-bin indices across consecutive FFT frames and converts recurrent peak-bin migration into an interference decision through a short-window counting mechanism. The method is computationally efficient, interpretable, and suitable for real-time deployment without offline model training. SDR-based measurements are combined with controlled repeated experiments to assess detector performance under varying signal-to-noise ratio (SNR), interference-to-signal ratio (ISR), carrier-frequency offset (CFO), multi-peak ambiguity, and two-path Rayleigh fading conditions. On the measured SDR record, the proposed method captures all interference-positive windows after the marked onset, while the controlled SNR/ISR experiments yield an overall detection probability of 96.0% over 250 CCI trials with no false alarms over 250 normal trials. ROC and precision–recall analyses further show that the selected threshold lies within a broad validation plateau. The results also reveal clear applicability boundaries: when the CFO approaches zero, when the interference is very weak, or when multiple stationary peaks have nearly equal power, dominant-bin migration may be weak or ambiguous. Therefore, the proposed approach is a low-complexity online detector for CCI cases that induce observable FFT-bin instability, and it can also serve as a front-end trigger for more advanced interference analysis modules.