The construction of information resource management system is a promotion for upgrading industrial structure and enhancing independent innovation capability. Based on the city-level data of a region from 2010 to 2022, the evaluation index system of information resource management system and regional economic development mode is established, and the variables are measured according to the collected data using gray correlation analysis method. Then double machine learning method is applied to explore the influence effect of information resource management system on regional economic development model. The baseline regression analysis reveals that the information resource management system can promote the regional economic development model, with a regression coefficient of 0.029, and the conclusion still holds after the stability test. The heterogeneity results show that regions with better economic foundation (0.067) and peripheral cities (0.036) are more significantly affected by the positive spillover effect of the information resource management system. This paper combines machine learning algorithms with traditional causal inference to explore the role path of information resource management system to promote regional economic development model, which provides empirical evidence and decision-making reference for promoting regional economic development.

With the rapid development of the global cruise transportation industry and the worldwide increase of cruise ship transportation year by year, fire accidents on passenger and roll-on/roll-off ships (P/ROCs) pose a serious threat to economic properties. The article establishes a fire model of a passenger-roller ship carrying electric vehicles using the basic equation of dynamics, a large eddy simulation model, and a mixed fraction combustion model. The mesh division is used to improve the solving accuracy of the kinetic equations. The fire simulation conditions of the electric vehicle carried by a passenger-roller ship are designed to analyze the fire combustion characteristics of the passenger-roller ship transported in terms of wind speed, fire intensity, and ignition power in multiple dimensions using the FDS simulation software as a carrier. Based on the YOLOv5s network and combined with the improved non-great suppression algorithm, a statistical model for target detection of electric vehicles carried by a passenger-roller ship is designed, and the corresponding loss function is designed. When the external ambient wind speed was increased from 0.5 m/s to 6.5 m/s, the maximum temperature at the fire center of the electric vehicle carried by the passenger-roller ship was reduced from 883.93°C to 748.57°C. The improved YOLOv5s model has the highest mAP of 96.67% on the target detection of EVs after fire damage and an accuracy of 92.96% for counting the number of EVs after fire. The state of electric vehicles after fire damage can be obtained under fire dynamics simulation, and the target detection and quantity counting of electric vehicles can be effectively realized by combining deep learning technology.

Background: Ultraviolet radiation (UVR) causes premature skin aging. Litchi seed (LS) is considered a natural plant extract with potential antioxidant, anti-aging and anti-inflammatory properties. However, the mechanisms of LS’s protective effects on skin photoaging remain unclear. Objective: This study aims to perform a rapid and efficient virtual screening of the main targets and possible mechanisms of the protective effect of LS on skin photoaging through network pharmacology, bioinformatics and molecular docking. Methods: The primary active compounds and their corresponding targets of LS were obtained from the TCMSP, STP, and UniProt databases. Concurrently, photoaging-related targets were mined from the GEO, GeneCards, and OMIM databases. “LS-photoaging” targets were identified using Venn diagrams created with R software. Protein-protein interaction (PPI) networks and “compound-target-disease” networks were constructed and analyzed using Cytoscape. GO and KEGG pathway enrichment analyses were then performed to predict the protective mechanisms of LS against skin photoaging. Finally, key targets and active compounds were validated through molecular docking using AutoDock Vina. Results: The screening identified 368 targets of LS active compounds and 872 photoaging-related targets. Network topology analysis revealed 87 common targets, with AKT1, IL6, TP53, and CASP3 as core targets. Enrichment analysis reveals that LS can modulate the ROS/MAPK/AP-1 pathway, thereby inhibiting inflammatory responses and reducing oxidative stress, which leads to a decrease in pro-inflammatory factors. Additionally, it promotes collagen restoration by suppressing the expression of MMPs. Molecular docking validation demonstrated a strong binding affinity between the core targets and the key compounds. Conclusion: LS shows potential for treating photoaging by counteracting inflammation and oxidative stress, regulating collagen and lipid metabolism, and inhibiting apoptosis.

The Tradable Green Certificate (TGC) system scientifically guides renewable energy investment by internalising the positive externalities of renewable electricity. With the promotion of energy transition, the demand for TGC has increased significantly, and the scale of market players has gradually expanded. Market players will imitate other players’ trading strategies for reasons such as herd mentality, which is manifested as herd behaviour. If TGC market players ignore high-quality information and blindly imitate the behaviour of other players, it will limit the diffusion of effective information in the market and reduce the pricing efficiency of the market. Therefore, this paper explores the emergence law of herd behaviour in the TGC market based on a hybrid system dynamic model, with a view to providing theoretical and methodological support for the immediate identification of market risk. This paper portrays the emergence process of herd behaviour of TGC trading subjects, and analyses the emergence law through multi-scenario computational experiments. The results show that (1) herd behavior will emerge from all kinds of strategy subjects and there is a positive feedback relationship between the emergence speed and the return difference between subjects. (2) The emergence of herd behaviour of fundamental strategy subjects has scale and structural effects, and only when the initial imitation scale of such subjects reaches 40% or the market share is less than 50%, will the emergence of herd behaviour, and the depth of its emergence shows an ‘S’ type growth. (3) The herd mentality and the weakening of cognitive bias of TGC trading subjects will reduce the emergence speed of herd behaviour, but have almost no effect on the depth of emergence.

This paper studies integrated process planning and scheduling (IPPS), a typical workshop scheduling problem, and mainly investigates the uncertain problems in the actual industrial production process. Then, we introduce the theoretical knowledge of interval numbers and adopt the interval number comparison method. Specifically, interval numbers are used to replace the determined processing time, and uncertain IPPS problems are modeled based on the interval number theory. Based on this, a hybrid particle swarm algorithm is proposed to solve the uncertain IPPS. Meanwhile, the genetic operator is introduced to improve its ability to deal with combined optimization problems. The above theoretical results are applied to the process planning and scheduling of a mechanical workshop, thus verifying the effectiveness of the proposed method.

Rural digitalization and rural tourism are important tasks to achieve the goal of rural revitalization strategy, and researching whether there is a connection between them and the degree of association is helpful to accelerate the transformation of rural digitalization and promote the quality and upgrading of rural tourism. This paper constructs an evaluation system of rural digitalization and rural tourism, adopting 253 counties in China as samples to measure the development differences between regions of the two systems. A coupled coordination model is applied to explore the relationship between the two systems and reveals the distribution characteristics of the level of coupling and coordination in China. The findings show that the difference in the overall score of rural digitalization between counties is greater than that of rural tourism industry. There is a high degree of coupling between rural digitalization and rural tourism systems, and the two systems are currently at a barely coordinated stage in China. In addition, the degree of coordination varies significantly between counties, presenting a phenomenon of higher coupling coordination in the eastern coastal region, intermediate in the central and western inland regions, and lower in the northwest. This paper supports and validates some results of rural development projects in the research area to provide theoretical and decision support for coordinating rural digitalization and rural tourism services.

A fault diagnosis method for wind turbine gearbox based on adaptive probability random forest is proposed to address the issue of noise pollution in SCADA data of wind turbine gearbox. Firstly, SMOTE oversampling is used to balance sample categories, and then CART is trained and classified by constructing multiple balanced subsets. The sample error rate represents the weight of sample ambiguity, and the label uncertainty is determined. Monte Carlo simulation is used to calculate the mean distribution of features, which is fused with each sample instance to obtain the uncertainty of sample features. Utilizing adaptive labels and sample uncertainties as inputs to probabilistic random forest can enhance the ability to manage feature noise and label noise, thereby improving the robustness of fault diagnosis. Conduct an experimental evaluation using the SCADA dataset of wind turbine gearbox. The results show that this model outperforms other methods in terms of false alarm rate, false alarm rate, and F1 rating metrics when dealing with missing values, Gaussian noise, and label noise in the dataset, as compared to other methods. This method is of great significance for improving the accuracy and robustness of wind turbine gearbox fault diagnosis.

This paper focuses on the coupling and coordinated development of provincial sports industry and tourism industry. In view of the integration trend of the two as the pillar of the tertiary industry and driven by relevant policies, in view of the insufficient quantitative and regional comparison of existing studies, data from 31 provinces from 2014 to 2021 were selected for analysis. The connotation mechanism of coupling coordination is explained from the economic, social, ecological and cultural levels, and the system including industrial scale and structural indicators is constructed, and the coupling coordination degree model is used to calculate. The results show that the coupling coordination degree of the country is rising in a step, with the eastern starting point being high, the central part making great progress and the western part growing fast. The types of industrial development vary between regions and over time. The global Moreland index shows that there are significant autocorrelation and clustering in the space, the local “high-high” cluster in the east and part of the middle, and the “low-low” cluster in the west. Further, suggestions were put forward to strengthen policy guidance, optimize industrial structure, promote the development of talents and technology, and strengthen the protection and utilization of ecological culture, so as to provide decision-making reference for industrial upgrading and sustainable development of regional economy.

Traditional construction project cost estimation methods rely on expert experience and statistical models, which are difficult to handle complex data and multimodal features effectively and have low prediction precision. This paper constructs an intelligent building engineering cost estimation model that combines subtractive clustering, a self-learning mechanism, and convolutional neural networks (CNN) to address this problem. In the data preprocessing stage, subtractive clustering is applied to optimize multimodal data, screen key features, and eliminate redundant information. Subsequently, the model parameters are dynamically adjusted according to the error feedback through a self-learning mechanism to improve its adaptability to diverse construction projects. In the feature extraction and estimation stage, the CNN module is combined to extract deep features from images, texts, and numerical data to achieve high-precision estimation. The experimental results show that the model in this paper outperforms traditional methods in terms of MSE (mean-square error), MAE (mean absolute error), R² (coefficient of determination), MAPE (mean absolute percentage error), with the mean values being 73.18, 8.33, 0.9477, and 5.33%, respectively. In summary, the model in this paper demonstrates superior precision, adaptability, and robustness in construction project cost estimation.

Foreign direct investment plays a more important role in China’s economic development. This paper examines the impact of FDI on China’s GDP and analyzes regional variability through OLS and quantile regression models. Then the spatial correlation-Moran, I scatter plot is used to visualize the clustering pattern of regional units. The analysis shows that FDI has a significant positive effect on China’s high economic growth at the 25% quantile. However, the higher the economic growth rate, the margin of positive effect of FDI on economic growth gradually decreases. China’s regional economic development is characterized by a dualistic structure. The elasticity coefficient of FDI in the eastern region is 0.099, and that in the western region is 0.05. Therefore, FDI has a greater impact on the eastern region than on the western region. With the development of China, foreign investment began to discrete, gradually spreading from coastal areas to inland areas.