To accurately and efficiently detect fires in complex tunnel environments，an enhanced YOLOv8s-based tunnel fire detection algorithm was proposed. Firstly，the Cross-Stage Partial Transformer Block (CSP-PTB) module was introduced to reconstruct the backbone network structure，thereby reducing computational complexity while preserving feature extraction capabilities. Secondly，CBAM was integrated to enhance the perception of the model of key areas and improve the discriminative power of feature representation. Finally，the Normalized Wasserstein Distance (NWD) loss function was employed to optimize the training process，effectively addressing the issue of insufficient detection accuracy for small targets. Experimental results demonstrate that the improved YOLOv8s model achieves a mean average precision (mAP) of 0.848，representing a 2% improvement over the original YOLOv8s model. The recall rate reachs 0.812，marking a significant increase of 9.3% compared to the original model. Additionally，the computational cost (GFLOPS) of the improved model is reduced by 6.7%，achieving dual objectives of performance enhancement and efficiency optimization. Compared with mainstream object detection models such as Faster R-CNN(Faster Region-based Convolutional Neural Network)，SSD(Single Shot MultiBox Detector)，and YOLOv5s，the improved model exhibits superior performance，with mAP improvements of 7.3%，10.1%，and 4.2%，respectively，thus meeting the stringent requirements for tunnel fire detection.

In order to predict the slope state more accurately and effectively prevent the slope instability accident，an improved ISSA-KELM slope stability prediction model was proposed. Firstly，six main factors such as bulk density and cohesion in slope instability characteristics were used as prediction indexes to establish a data set for slope stability evaluation. Secondly，SSA was enhanced by incorporating Sine chaotic mapping，Levy flight strategy，dynamic adaptive weights，and fusion of optimal explosion strategy and reverse learning. These improvements aimed at enhancing the global search capability and stability of SSA. Subsequently，ISSA was employed to optimize the kernel parameter ψ and regularization coefficient C in KELM for improved prediction accuracy while avoiding overfitting issues associated with KELM. The results show that the accuracy rate，precision，recall rate and F₁ score of ISSA-KELM model reached 0.945 9，1，0.866 7 and 0.929，respectively，which are superior to SSA-KELM，PSO-KELM and PSO-SVM models，and the predicted results of the model are the closest to the actual values. It shows that the established ISSA-KELM model has strong generalization ability.

Taking improving the safety and efficiency of tower crane operation as an example，a method of integrated identification of fatigue state and unsafe behavior was proposed in order to detect the potential safety hazards of drivers in real time. A live video stream was captured via a camera，and the video was analyzed and pre-processed to extract critical information for identifying subsequent fatigue and unsafe behavior. In terms of fatigue state recognition，the analysis method based on the state of eyes and mouth was used to monitor the physiological indicators such as the state of eyes opening and closing，the blink frequency and yawn frequency. In terms of unsafe behavior identification，computer vision and deep learning technology were combined to detect the potential dangerous operations of drivers in real time，thus ensuring timely detection of safety risks. The results show that the performance of the optimized YOLOv5-ECA(Efficient Channel Attention) model is significantly improved in fatigue state and unsafe behavior recognition. The accuracy rate and recall rate of the model on the test set are more than 90%，showing good recognition ability.

In order to enrich the safety & security management theories and innovate the safety & security management paradigm，the research work of parallel safety & security management was carried out based on the parallel system theory and safety & security management theory. Firstly，starting from the parallel system theory and combining with the knowledge of modern safety & security management，the concept of parallel safety & security management was explored and the parallel safety & security management conceptual model was proposed. On this basis，the parallel safety & security management model was constructed and explained. Finally，taking urban safety & security as an example，this paper analyzed the application of the parallel safety & security management model. The research shows that parallel safety & security management is a new paradigm for safety & security management through realizing the virtual-real interaction between artificial safety & security systems and real safety & security systems to achieve multiple objectives such as solving complex safety & security problems，effective implementation of safety & security solutions and efficient training of personnel. Its model has the characteristics of breaking the constraints of real-world conditions，flexibility and scalability，high performance distributed computing，redundancy and fault tolerance，simulation prediction and continuous improvement，task scheduling and load balancing，which can provide a model reference for safety & security management of complex systems，such as urban safety & security management.

To improve the accuracy of human thermal injury assessment and protect rescuers' safety in thermal radiation environments，a coupled heat and mass transfer model of skin-microenvironment-firefighting clothing system was proposed to predict skin burn injuries under dynamic conditions. Based on mechanism of heat and moisture transfer in porous media，the periodic movement of fabric caused by human activities and its impact on heat and mass transfer in the skin-microenvironment-firefighting clothing system were considered. Furthermore，the proposed model was used to simulate skin temperature，time of skin burn，and the distribution of temperature and humidity in the fabric layers for both dry and wet cases in real time. The results show that the relative error between simulated values predicted by the model and the experimental measurements presented in the literature is only 3.79%. When exposed to 8.5 kW/m² thermal radiation environments，the time to second-degree burn for the dry case is 33.7 s earlier than that for the wet case. When firefighters approach a 20 kW/m² radiant heat source at a speed of 1 m/s，the heat transferred is impeded by the increase in thermal layer thickness. This extends the time for second-degree burns to occur by 10.9 s and reduces the heat absorbed by the skin surface by 20%. When the air gap thickness in the microenvironment is the same as the amplitude of the periodic motion of fabric，the skin temperature increases rapidly and fluctuates significantly，and the time to second-degree burn occurs 43.7 s earlier. Human body movement and moisture in fabric layers affect heat transfer process between the human body and thermal environment，thereby their impact on the accuracy of rescue assessments cannot be ignored.

To enhance the ability to cope with reservoir landslide hazard risks under extreme climate，a framework for multi-dimensional scientific observation and hydrometeorological early warning was constructed using multi-source monitoring data and machine learning algorithms. The spatiotemporal pattern and main controlling factors of landslide deformation were identified by analyzing the multi-annual observations of the two landslide cases，involving Sentinel-1，global navigation satellite system (GNSS) surface displacement and fiber optic (FO) strain. Leveraging the boosting decision tree (BDT) algorithm，a hydrometeorological early warning method based on slip zone real-time strain (RTS) was proposed，and the generalized framework of monitoring，early warning and emergency management strategies for reservoir landslides was systematically discussed. The results indicate that landslides with different deformation mechanisms show different spatiotemporal deformation characteristics，and landslide activities are closely related to localized anti-sliding treatment measures. Landslide kinematics are characterized by subzone-independent displacements and their drivers，which are highly correlated with hydrometeorological extremes. The RTS-based early warning model provides specific hydrometeorological thresholds，emphasizing the emergency response-oriented landslide monitoring and early warning concept.

During the attack of public health emergencies，the surge in material demand in isolated communities leads to a series of problems，i.e.，serious shortfalls in supply，fairness of distribution and special distributional needs. To address this issue，a multi-period，multi-type，cross-regional emergency material dynamic allocation problem was studied based on a hierarchical distribution network of "material supply point-distribution center-isolated community". Especially，the demand time windows were applied to characterize the realistic requirements of isolated communities for the delivery time，and the special needs of some vulnerable groups，e.g.，aging populations，were considered. Thus，a multi-objective non-linear dynamic program was developed by integrating the three dimensions of considerations：economy，material distribution satisfaction rate and distribution equity. In view of the multi-objective structure，the Epsilon constraint algorithm was used to solve the proposed model，and the material allocation during the attack of public health emergencies in Shanghai was taken as a case study to analyze the Pareto front of the optimal solutions and conduct the sensitivity analysis on some key parameters in the model. The results show that，under the constraint of limited emergency material supply，the material allocation strategy considering the aging populations helps to prioritize the material supply of vulnerable groups. However，it also contributes to an increase in the unfairness rate of the isolated communities as a whole. For the material allocation strategy considering the delivery time windows of isolated communities，the total operation cost of the cross-regional distribution network and the unmet rate of the material demand in the isolated communities are high，but the overall distribution of supplies in the system is relatively fair，and it could better meet the needs of isolated communities in terms of delivery of supplies，which provides a useful reference for the decision makers to balance the individual demand and the overall interests.

In order to solve problems of land shortage and transmission line construction in the old urban area，taking the underground goaf of Xiuwu North power transmission substation as the research object，on the basis of clarifying the basic geological conditions and mining conditions of the underground goaf of the transmission substation，SBAS-InSAR monitoring was used to study the development characteristics of surface subsidence. The evolution characteristics of surface subsidence of the transmission line through the mining right area were quantitatively analyzed. The influence of goaf settlement，inclination and curvature on the transmission line of the substation was evaluated. The results show that the maximum average settlement rate of the surface of the study area is -53.6 mm/a，and the location of this area coincides with the location of Guhanshan mine，and the subsidence is consistent with coal mining，and the settlement rate of the tower position is between -16.5--0.3 mm/a. The average settlement rate of No. 11 and No. 35 towers are significantly greater than those of other positions，with the average settlement rates of -15.88 and -16.21 mm/a respectively. The historical tracing of the deformation law shows that the maximum cumulative subsidence occurs at the end of the monitoring period，which is -104.91 and -106.97 mm respectively. According to the most unfavorable principle，it is concluded that the actual monitoring and predicted settlement of the unfavorable points of the interannual deformation rate of the tower in each region during the service life is less than 400 mm，and the maximum inclination and curvature of the tower are 1.2 mm/m and the curvature is 0 mm/m²，which are all within the specified minimum allowable value. The surface of the transmission line crossing the mining rights area is in a safe and stable state.

To investigate the impact of different injection source gases on the adsorption and diffusion behavior of methane (CH₄) in coal，three types of gases were selected: hot gas power generation exhaust (heat injection，multi-component)，carbon dioxide (CO₂) at room temperature (strong adsorption，single component)，and nitrogen (N₂) at room temperature (weak adsorption，single component). Using giant canonical Monte Carlo (GCMM) and molecular dynamics (MD) methods，these gases were mixed with CH₄ and injected into coal to analyze the adsorption conditions. Based on a fixed amount of CH₄，the changes in diffusion behavior were analyzed after injecting each of the three gases. The results show that with the increase of gas injection ratio，the reduction of CH₄ adsorption capacity under CO₂ injection condition is gradually greater than that under thermal power generation tail gas condition，showing better inhibition performance than thermal power generation tail gas. In contrast，although the adsorption capacity of CH₄ decreases after N₂ injection，it is always greater than the previous two. In terms of diffusion，with the increase of gas injection ratio，the diffusion coefficient increases first and then decreases，and the coefficient is always larger than before gas injection，and the displacement gas mainly promotes CH₄ diffusion. Under N₂ injection，the diffusion coefficient of CH₄ is the highest and the decrease is the smallest，and the promoting effect is the most obvious. Under the condition of CO₂ injection，the diffusion coefficient of CH₄ decreases the most and the promoting effect is the weakest. Therefore，the selection of hot tail gas from gas-fired power generation for CH₄ displacement is more cost-effective.

In order to effectively control low-frequency vibrations in engineering practice，the structure and the formation mechanism of the band gap were analyzed，and the finite element method was employed to investigate the influencing factor of the band gap in combined periodic cross-isolation trenches. Subsequently，this study analyzed vibration isolation performance using the model experiment. The results show that the band gap characteristics of the combined periodic cross-isolation trenches are mainly influenced by the periodic constant，the depth of the channel，the elastic modulus of soil and the filling medium. With the increase of the period constant，combined periodic cross-isolation trenches are more likely to obtain the low-frequency band gaps，but the bandwidth narrows. By increasing the depth，the low-frequency band gap with a larger bandwidth can be obtained，and the number of band gaps increases. With the increase of elastic modulus，the boundary frequency of the band gap migrates to high frequency synchronously，and a more low-frequency and wider band gap can be obtained by filling the medium. The experimental results show that the maximum attenuation amplitude of acceleration in the band gap range reaches 0.001 24 m/s²，the average amplitude attenuation ratio in the band gap is 0.206 2，and the maximum attenuation degree reaches 98.4%. The combined periodic cross-isolation trenches have remarkable vibration isolation performance.