Forest fires pose severe challenges to forest management because of their unpredictability, extensive harm, broad impact, and rescue complexities. Early smoke detection is pivotal for prompt intervention and damage mitigation. Combining deep learning techniques with UAV imagery holds potential in advancing forest fire smoke recognition. However, issues arise when using UAV-derived images, especially in detecting miniature smoke patches, complicating effective feature discernment. Common deep learning approaches for forest fire detection also grapple with limitations due to sparse datasets. To counter these challenges, we introduce a refined UAV-centric forest fire smoke detection approach utilizing YOLOv5. We first enhance anchor box clustering through K-means++ to boost the classification precision and then augment the YOLOv5 architecture by integrating a novel partial convolution (PConv) to trim down model parameters and elevate processing speed. A unique detection head is also incorporated to the model to better detect diminutive smoke traces. A coordinate attention module is embedded within YOLOv5, enabling precise smoke target location and fine-grained feature extraction amidst complex settings. Given the scarcity of forest fire smoke datasets, we employ transfer learning for model training. The experimental results demonstrate that our proposed method achieves 96% AP₅₀ and 57.3% AP_50:95 on a customized dataset, outperforming other state-of-the-art one-stage object detectors while maintaining real-time performance.

Overcrowding in emergency departments (EDs) is a common problem encountered by healthcare systems worldwide. Its essence is the imbalance between the need for emergency care and available resources, such as doctors, nurses, medical supplies, and treatment facilities and spaces. Such an imbalance increases with the volume of visiting patients. To solve the problem of ED overcrowding, service providers need to ensure rational allocation of resources in the emergency process to the greatest extent. This article uses stochastic timed Petri nets (STPNs) as a modeling and simulation tool to optimize the resource allocation in the emergency care workflow. On the basis of STPN simulation architecture, we propose a novel “observation-response” block (ORB) to adaptively supplement the corresponding resources according to the local crowding situation in the emergence workflow, so as to reduce the waiting time of patients in urgent need of treatment. In this article, models of patient arrival, triage, and examination process are constructed. Then, considering the waiting time of patients as the optimization objective, the statistical simulation based on STPN models is performed to verify the effectiveness of the proposed ORB block in the emergency workflow resource optimization process. The presented work provides a feasible way for the optimal ED resource allocation.

Due to the hostile marine environment, there will inevitably be unpredictable factors during the operation of unmanned underwater vehicles, including changes in ocean currents, hull dimensions, and velocity measurement uncertainties. An improved finite-time adaptive tracking control issue is considered for autonomous underwater vehicles (AUVs) with uncertain dynamics, unknown external disturbances, and unavailable speed information. A state observer is designed to estimate the position and velocity of the vehicle via a neural network (NN) approach. The NN is used to estimate uncertainties and external disturbances. A finite-time controller is designed via backstepping and command filter techniques. A multi-input multi-output (MIMO) filter for AUVs is established, and the corresponding MIMO filter compensation signal is constructed to eliminate the effect of filtering error. All the signals of the closed-loop system are proved to be finite-time bounded. An example with comparison is given to show the effectiveness of our method.

The fast piezo-driven scanner (FPDS) compensates for vibrations in the unmanned aerial vehicle (UAV) image stabilization system. However, the hysteresis nonlinearity reduces the positioning accuracy of the FPDS. To address this challenge, this paper presents a novel weighted polynomial modified Bouc–Wen (WPMBW) model cascaded with a linear dynamic model to describe counterclockwise, asymmetric, and rate-dependent hysteresis loops of an FPDS. The proposed approach utilizes the weighted polynomial function to describe the asymmetric characteristic and the linear dynamic model to capture the rate-dependent behavior. By modifying the last two terms in the classical Bouc–Wen (CBW) model, the modified BW model directly characterizes the counterclockwise hysteresis loops with fewer parameters, circumventing the algebraic-loop problem that arises in the inverse CBW model. The pseudorandom binary sequence (PRBS) input is employed to decouple the linear dynamic model from the WPMBW model. The sinusoidal input is then applied to stimulate the hysteresis phenomenon, and the parameters of the WPMBW model are estimated by the particle swarm optimization (PSO) toolbox. Experimental results on a commercial FPDS show that the proposed model is superior to the CBW and traditional asymmetric BW models in modeling accuracy and feedforward hysteresis compensation.

In urban safety, intelligent transportation, and smart security applications, robust pedestrian detection is paramount. Methods that rely solely on visible light imaging struggle in low-light or adverse weather conditions. To address these challenges, we propose dual-modality pedestrian detection (DMPD)—a novel dual-modality pedestrian detection framework that fuses visible and infrared imaging through innovative fusion strategies. The method integrates a modal alignment module to reduce pixel-level misalignment, a differential modal fusion module to effectively combine complementary features while suppressing noise, and a mix module that enhances multiscale feature extraction via integrated convolution and self-attention mechanisms. Furthermore, the enhanced YOLOv7 is used to further boost feature representation and detection accuracy. Experimental results on the public dataset demonstrate that DMPD achieves a detection $mA{{P}_{50}}$ of 97.1% and a real-time speed of 118 FPS, outperforming state-of-the-art methods under both normal and adverse conditions, including fog, rain, and snow. These results confirm the effectiveness of the proposed fusion strategy in harnessing the complementary strengths of visible and infrared modalities, thereby offering a highly robust and scalable solution for pedestrian detection in complex urban environments.