In UWB-based indoor positioning research, NLOS signals severely degrade localization accuracy. To address the NLOS/LOS disRIMination challenge, this paper proposes the RIM-Net model, which enhances CIR signal feature learning by integrating residual blocks and LSTM architectures. Unlike conventional methods that process only the magnitude of CIR signals, RIM-Net explicitly models both real and imaginary components of CIR signals to improve classification accuracy. Experimental results demonstrate that RIM-Net achieves an average accuracy of 92.36% on benchmark datasets while maintaining generalization capabilities above 85% in unseen environments. Furthermore, the optimization of the TOA algorithm validated the effectiveness of RIM-Net in localization, achieving an average performance improvement of 9.66%. This approach provides an effective solution for NLOS/LOS identification in complex channel conditions within UWB positioning systems.
Heat stress severely impacts pig welfare and farm productivity. However, existing methods lack the capability to detect subtle physiological cues (e.g., skin erythema) in complex farm environments while maintaining real-time efficiency. This paper proposes PigStressNet, a novel lightweight detector designed for accurate and efficient heat stress recognition. Our approach integrates four key innovations: (1) a Normalization-based Attention Module (NAM) integrated into the backbone network enhances sensitivity to localized features critical for heat stress, such as posture and skin erythema; (2) a Rectangular Self-Calibration Module (RCM) in the neck network improves spatial feature reconstruction, particularly for occluded pigs; (3) an MBConv-optimized detection head (MBHead) reduces computational cost in the head by 72.3%; (4) the MPDIoU loss function enhances bounding box regression accuracy in scenarios with overlapping pigs. We constructed the first fine-grained dataset specifically annotated for pig heat stress (comprising 710 images across 5 classes: standing, eating, sitting, lying, and stress), uniquely fusing posture (lying) and physiological traits (skin erythema). Experiments demonstrate state-of-the-art performance: PigStressNet achieves 0.979 mAP for heat stress detection while requiring 15.9% lower computation (5.3 GFLOPs) and 11.7% fewer parameters compared to the baseline YOLOv12-n model. The system achieves real-time inference on embedded devices, offering a viable solution for intelligent livestock management.