Lei Li

To address the problem of forest fire detection, especially in complex conditions such as low light, smoke dispersion, and changes in flame size, which are prone to be affected by the environment and may lead to the omission of flames or smoke, a method named HCANet is proposed. This method combines visible light (RGB) images and infrared (IR) images and uses hierarchical fusion to enhance the detection capability. A middle-level fusion strategy is adopted, and two dedicated components, cross-modal discrimination (CDM) and dual-Enhanced cross-modal attention (DEA), are designed. CDM is used to enhance the complementary information exchange between different types of images, and DEA is used to dynamically adjust to reduce interference. These designs can better utilize the detailed features of RGB images and the thermal sensing characteristics of IR images. Experimental results show that HCANet performs well on the data set in this paper and other public multimodal data sets, significantly outperforming single-modal methods. It can effectively identify weak fire sources and diffuse smoke, significantly improving the detection accuracy and stability, and demonstrating good generalization ability in related tasks such as vehicle detection and small target detection.

The coal mine workplace environment is a significant factor in inducing occupational health issues, such as intestinal dysfunction in coal miners. However, the mechanism by which the coal mine workplace environment induces intestinal dysfunction is still unclear. Therefore, we applied the Coal Mine Workplace Environment Biological Simulation (CEBS) model which was previously constructed to detect the intestinal pathological manifestations and changes in the gut microbiota of mice from the perspectives of intestinal function, tissue morphology, and cell molecules. CEBS mice showed increased fecal water content, shortened colon length, significant activation of MPO⁺ and CD11b⁺ numbers, and significant changes in IL-1b, IL-6, and IL-12 expression levels. In addition, we also found an imbalance in the proportions of Firmicutes, Bacteroidetes, Lactobacillus, and Parabacteroides in CEBS mice, resulting in significant changes in gut microbial diversity. After intervention with compound probiotics, the intestinal function of CEBS + Mix mice was improved and inflammation levels were reduced. Results indicated that stress in the coal mine workplace environment can lead to intestinal dysfunction and inflammatory damage of the colon and use of compound probiotics can improve intestinal dysfunction in CBES mice. In our study, we revealed that there is a correlation between coal mine workplace environment and diversity disorders of gut microbiota. This discovery has enhanced the relevant theories on the causes of intestinal dysfunction in coal miners and has suggested a new approach to intervention.

In order to identify the communication law of network public opinion in major public health emergency, a multifactor communication model based on multiagent modeling is proposed. Based on the SEIR model and NetLogo simulation analysis, the model integrates a variety of network public opinion communication characteristics and extends the existing single network public opinion communication model. Based on these studies, a network public opinion communication management system is designed and developed with Python tools. Case analysis and simulation results show that this model can better simulate the evolution trend of network public opinion communication in major public health emergency; the key communication channels of public opinion play an important role in the evolution of network public opinion, which can control and guide the network public opinion of major public health emergency from the three communication influencing factors of total number, initial number, and communication cycle. Communication cycle refers to the number of days in the process of network public opinion dissemination of major public health emergencies.

The irrational mining of coal mines can cause damage to the geological environment, resulting in the frequent occurrence of geological disasters and high risk. In order to deeply explore the influence mechanism of coal mine geological disaster vulnerability, the three characteristic indicators of exposure, sensitivity, and adaptability proposed by the VSD vulnerability framework were taken as the starting point, and the indicator weights were determined by using the order graph method. The system dynamic model of coal mine geological disaster vulnerability was established and simulated. The results show that the exposure and sensitivity decrease gradually, and adaptability shows a gradual upward trend within one simulation period. When the parameter values of each subsystem were increased by 50%, the management subsystem was the key subsystem that affected the exposure and adaptability, and the exposure and adaptability variation decreased by 11.704% and 17.900%, respectively. The key subsystem affecting sensitivity was the equipment subsystem, and the sensitivity variation decreased by 18.958%.In order to reduce the vulnerability risk of geological disaster in coal mines and improve the safety management of the project.

As one of the types of coal mine disasters and accidents, gas explosion is an important resistance affecting coal mine safety production. How to effectively identify gas explosion, find out the causes of gas explosion accidents, and make timely prediction and rectification is an urgent problem in coal mine industry. In this paper, the cause model of coal mine gas explosion is constructed based on the Bayesian network, and the cause chain of gas explosion accident is established by SPSS correlation analysis. The main factors leading to gas explosion accidents are found by parameter learning, reverse reasoning, sensitivity analysis, and key cause path. The results show that the main causes of mine gas explosion are gas accumulation and fire source explosion. The main causes of gas accumulation are no wind or breeze caused by local ventilator problems. The generation of electric spark is the main cause of fire source explosion. Cable damage, short circuit, mechanical and electrical equipment explosion, illegal operations, and lack of safety skills are also important factors leading to gas explosion.

Coal mine roof accidents are one of the main single risks faced by coal miners. According to the statistical data of coal mine accidents in China, there were 40 roof accidents and 55 deaths in 2020 alone, accounting for 32.8 and 24.4% of the total, respectively. Therefore, we can see its danger. To realize the comprehensive scientific assessment of coal mine roof accidents, first, through the collation and analysis of relevant literature reviews and accident investigation reports, combined with the expert investigation method, an assessment index system of coal mine roof accidents is constructed. Then, based on the analysis of the characteristics of the influencing factors of coal mine roof accidents, the assessment model of coal mine roof accidents is established by using the DEMATEL-ANP method. Finally, the established assessment model is applied to a coal mine to verify the rationality of the model.

The safety of foundation pit construction is gaining widespread attention. In order to reduce the risks of foundation pit construction and avoid the safety problems brought by the pits, it is necessary to study the risks of foundation pit construction. This paper takes the actual construction of a building as the background. Firstly, the possible main risks of foundation pit construction were identified and summarized, and then, the evaluation index system was formed. Secondly, the risk levels of various types of foundation pit risks were derived through analytic hierarchy process (AHP). In the expert scoring session of the Delphi method, the influences of both the degree of risk consequences and the probability of occurrence are combined. The risk value of the risk event is obtained in combination, which overcomes the bias problem of the traditional single assignment. Finally, an affiliation matrix was established to judge the affiliation of risk indicators to the risk level. The comprehensive risk evaluation level of this foundation pit project construction was assessed as level II. It is the degree of general risk.