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.

This paper contains two parts: numerical analyses and a control method. The numerical analyses of a hypersonic flying object’s aerodynamic heating environment are based on three different two-dimensional outflow fields via finite element calculations. Then, the reference temperature trajectories of a hypersonic flying object are obtained. The other one is an intelligent proportional-derivative (IPD) with a nonlinear global sliding mode control (NGSMC) based on a nonlinear extended state observer (NESO) for a real-time ground aerodynamic heating simulation of a hypersonic flying object, named a thermal-structural test with quartz lamp heaters. The composite controller is made of three sub-components: a model free frame that is independent of the system dynamic model along with an ultra-local model; a NESO for the lumped disturbances observation; and an integral sliding mode control with a nonlinear function for the observation errors compensation. The flight environment of the hypersonic flying object is from Mach number 0.6 to Mach number 5.0, with between flight altitude of 31,272 m and flight altitude of 13,577 m. The comparative results demonstrate some superiorities of the proposed composite controller in terms of tracking errors and robustness.

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.

This paper proposes a modular control framework for high-order nonlinear multi-agent systems (MASs) to achieve distributed finite-time formation tracking with a prescribed performance. The design integrates two modules to address uncertainties and safety constraints simultaneously. Module I—Prescribed Performance-Based Trajectory Generation: A virtual signal generator constructs collision/connectivity-aware reference trajectories by encoding time-varying performance bounds into formation errors. It ensures network rigidity and optimal formation convergence through dynamic error transformation. Module II—Anti-disturbance Tracking Control: A finite-time extended state observer (FTESO) estimates and compensates for uncertainties within a finite time, while a time-varying surface controller drives tracking errors into predefined performance funnels. This module guarantees rapid error convergence without violating the transient constraints from Module I. The simulations verified the accelerated formation reconfiguration under disturbances, and thus, demonstrated improved robustness and convergence over asymptotic approaches. The framework offers a systematic solution for safety-critical MAS coordination with heterogeneous high-order dynamics.

In this paper, an adaptive neural network global fractional order fast terminal sliding mode model-free intelligent PID control strategy (termed as TDE-ANNGFOFTSMC-MFIPIDC) is proposed for the hypersonic vehicle ground thermal environment simulation test device (GTESTD). Firstly, the mathematical model of the GTESTD is transformed into an ultra-local model to ensure that the control strategy design process does not rely on the potentially inaccurate dynamic GTESTD model. Meanwhile, time delay estimation (TDE) is employed to estimate the unknown terms of the ultra-local model. Next, a global fractional-order fast terminal sliding mode surface (GFOFTSMS) is introduced to effectively reduce the estimation error generated by TDE. It also eliminates arrival time, accelerates the convergence speed of the sliding phase, guarantees finite time arrival, avoids the singularity phenomenon, and bolsters robustness. Then, as the upper bound of the disturbance error is unknown, an adaptive neural network (ANN) control is designed to approximate the upper bound of the estimation error closely and mitigate the chattering phenomenon. Furthermore, the stability of the control system and the convergence time are proven by the Lyapunov stability theorem and are calculated, respectively. Finally, simulation results are conducted to validate the efficacy of the proposed control strategy.