Unsafe behaviors on construction sites are a major cause of accidents, highlighting the need for effective detection and prevention. Traditional methods like manual inspections and video surveillance often lack real-time performance and comprehensive coverage, making them insufficient for diverse and complex site environments. This paper introduces GeoIoU-SEA-YOLO, an enhanced object detection model integrating the Geometric Intersection over Union (GeoIoU) loss function and Structural-Enhanced Attention (SEA) mechanism to improve accuracy and real-time detection. GeoIoU enhances bounding box regression by considering geometric characteristics, excelling in the detection of small objects, occlusions, and multi-object interactions. SEA combines channel and multi-scale spatial attention, dynamically refining feature map weights to focus on critical features. Experiments show that GeoIoU-SEA-YOLO outperforms YOLOv3, YOLOv5s, YOLOv8s, and SSD, achieving high precision (mAP@0.5 = 0.930), recall, and small object detection in complex scenes, particularly for unsafe behaviors like missing safety helmets, vests, or smoking. Ablation studies confirm the independent and combined contributions of GeoIoU and SEA to performance gains, providing a reliable solution for intelligent safety management on construction sites.

This paper presents significant improvements in the accuracy and computational efficiency of safety helmet detection within industrial environments through the optimization of the you only look once version 5 small (YOLOv5s) model structure and the enhancement of its loss function. We introduce the convolutional block attention module (CBAM) to bolster the model’s sensitivity to key features, thereby enhancing detection accuracy. To address potential performance degradation issues associated with the complete intersection over union (CIoU) loss function in the original model, we implement the modified penalty-decay intersection over union (MPDIoU) loss function to achieve more stable and precise bounding box regression. Furthermore, considering the original YOLOv5s model’s large parameter count, we adopt a lightweight design using the MobileNetV3 architecture and replace the original squeeze-and-excitation (SE) attention mechanism with CBAM, significantly reducing computational complexity. These improvements reduce the model’s parameters from 15.7 GFLOPs to 5.7 GFLOPs while increasing the mean average precision (mAP) from 82.34% to 91.56%, demonstrating its superior performance and potential value in practical industrial applications.

In the era of digital music proliferation, music genre classification has become a crucial task in music information retrieval. This paper proposes a novel channel-aware convolutional neural network (ECAS-CNN) designed to enhance the efficiency and accuracy of music genre recognition. By integrating an adaptive channel attention mechanism (ECA module) within the convolutional layers, the network significantly improves the extraction of key musical features. Extensive experiments were conducted on the GTZAN dataset, comparing the proposed ECAS-CNN with traditional convolutional neural networks. The results demonstrate that ECAS-CNN outperforms conventional methods across various performance metrics, including accuracy, precision, recall, and F1-score, particularly in handling complex musical features. This study validates the potential of ECAS-CNN in the domain of music genre classification and offers new insights for future research and applications.

Automated safety monitoring on construction sites requires precise helmet-status detection and robust multi-object tracking in long, occlusion-rich video sequences. This study proposes a two-stage framework: (i) a YOLOv5 model enhanced with self-adaptive coordinate attention (SACA), which incorporates coordinate-aware contextual information and reweights spatial–channel responses to emphasize head-region cues—SACA modules are integrated into the backbone to improve small-object discrimination while maintaining computational efficiency; and (ii) a DeepSORT tracker equipped with fuzzy-logic gating and temporally consistent update rules that fuse short-term historical information to stabilize trajectories and suppress identity fragmentation. On challenging real-world video footage, the proposed detector achieved a mAP@0.5 of 0.940, surpassing YOLOv8 (0.919) and YOLOv9 (0.924). The tracker attained a MOTA of 90.5% and an IDF1 of 84.2%, with only five identity switches, outperforming YOLOv8 + StrongSORT (85.2%, 80.3%, 12) and YOLOv9 + BoT-SORT (88.1%, 83.0%, 10). Ablation experiments attribute the detection gains primarily to SACA and demonstrate that the temporal consistency rules effectively bridge short-term dropouts, reducing missed detections and identity fragmentation under severe occlusion, varied illumination, and camera motion. The proposed system thus provides accurate, low-switch helmet monitoring suitable for real-time deployment in complex construction environments.

Construction sites are complex environments, and unsafe behaviors by workers, such as not wearing safety helmets or reflective vests, can easily lead to accidents. When using target detection technology to detect unsafe behaviors, the results are often unsatisfactory due to the complexity of the background and the small size of the targets. This paper proposes an unsafe behavior detection algorithm based on dual adaptive feature fusion. The algorithm is based on YOLOv5, introducing a front-end adaptive feature fusion module (FE-AFFM) at the head of the backbone network for deep data processing, improving the model’s feature extraction capability in complex backgrounds. Simultaneously, a back-end adaptive feature fusion module (BE-AFFM) is introduced at the tail of the network to strengthen feature fusion. In the experimental verification phase, this paper selects a self-made laboratory dataset and verifies the effectiveness of the improved algorithm through ablation experiments, algorithm comparisons, and heatmap analysis. The average accuracy of the improved algorithm is 3.6% higher than the baseline model, and the detection effect on small targets is significantly improved, meeting the actual needs of construction sites. This paper also selects the publicly available dataset SHWD for algorithm comparison experiments. The results show that the improved algorithm still has a significant advantage over mainstream algorithms, verifying the generalization ability of the improved model.

Monitoring the early-age evolution of cementitious materials is essential for ensuring the quality and reliability of concrete structures. However, most ultrasonic approaches rely on empirical correlations and lack a physics-based mechanism to describe the continuous viscoelastic transition during hydration. This study proposes a fractional-order ultrasonic sensing framework that couples a fractional Zener viscoelastic model with ultrasonic attenuation theory to quantitatively link microstructural evolution and measured acoustic responses. A custom ultrasonic measurement system was developed to capture real-time attenuation during hydration under different water-cement ratios. Results show that the fractional-order model achieves higher accuracy and robustness than classical integer-order and empirical models. The fractional parameter $\beta$ serves as a physically interpretable indicator that reflects the transition from viscous-dominated to elastic-dominated behavior and aligns with known hydration development. The proposed framework provides a compact, physics-informed sensing strategy for early-age characterization of cementitious materials and offers potential for intelligent construction and high-end structural monitoring.