Accurate and fast building feature extraction is of great significance for construction of smart cities. Polygonal features and linear features are the most fundamental geometric information, which can accurately reveal building structural characteristics. This study first conducted comparative analysis of surface feature detection using three distinct approaches: Euclidean clustering, random sampling consistency algorithm and regional growth method, followed by quantitative performance comparison. For edge characterization, the linear features were detected by normal vector and approximate curvature estimation,respectively, and the effects of them were compared and analyzed. Experiments show that the regional growth method demonstrated superior precision of surface feature extraction compared to other methods, whereas the approximate curvature estimation enhanced continuity of smoothness of linear characteristics. The methods adopted in this study for accurate and efficient detection of building features has considerable application value for subsequent reconstruction of building models.

Based on the scale of urban park green space system and the scale of urban park plant community in Huainan City, the carbon sequestration capacity and benefits of urban park green space landscape pattern and internal plant community were analyzed using landscape pattern index method and i - Tree model, and the key ways to promote the carbon sink benefits of park green space were put forward. The results show that: (1) There are few specialized parks in the park green spaces of Huainan City but they have a relatively large area, while there are many garden parks with a small area. The number of comprehensive parks and community parks is small, and the spatial distribution is uneven. The aggregation index (AI), landscape shape index (LSI) and average shape index (MSI) are small, resulting in less carbon sink benefit. (2) Most of the tree species are of medium and small diameter classes, which are planted recently, so their carbon sink capacity is not fully exerted. (3) The annual carbon storage of 1 010 trees in the research area is 203. 42 t, with a total benefit of 187 146. 4 yuan; the annual carbon sequestration is 15. 62 t, with a total benefit of 14 370. 4 yuan. The tree species with the higher per-plant benefits are Styphnolobium japonicum, Sapindus saponaria, Liriodendron chinense，while those with lower per-plant benefits are Ginkgo biloba and Acer palmatum.

Analyzing the main influencing factors of the construction industry in the Yellow River Basin and scientifically predicting future carbon emission trends is an important part of achieving ecological protection and high-quality development in this region. The panel data of nine provinces (autonomous regions) in the Yellow River Basin from 2005 to 2021 were selected to analyze the influencing factors based on the extended STIRPAT model, and the forecast models were established to analyze the carbon emission trends under various scenarios. The results show that the total population, urbanization rate, total output value of the construction industry, per capita disposable income, and carbon emission intensity promote the growth of carbon emissions. Conversely, the energy structure inhibits the growth of carbon emissions. Although carbon emissions vary across different scenarios, all scenarios indicate the attainment of carbon peak by 2030. Notably, the scenario of maintaining stable population and economic development together with rapid technological advancements has the most significant carbon reduction effect, which is most conducive to the green and low-carbon development of the Yellow River Basin.

Taking the influencing factors of carbon emissions in the construction industry as the clustering index, the provinces with similar characteristics were divided into three clusters. The random forest algorithm was used to identify the key factors affecting the carbon emissions of each type of construction industry. The STIRPAT model was constructed to predict carbon emissions under three different scenarios(baseline, extensive and low-carbon) by adjusting the relevant influencing factors. The results show that there are large differences in carbon emissions among different types of provinces. Category 1 and Category 2 have great potential for carbon emission reduction. It is necessary not only to accelerate the upgrading of industrial structure and energy structure transformation, but also to pay attention to the impact of economy and technology on carbon emissions in the construction industry. The peak time varies. The provinces in Category 1 will reach peaks around 2032, 2032 and 2030 under the baseline, extensive and low-carbon scenarios respectively. Provinces in Category 2 can only reach the peak in 2032 under the low-carbon scenario. Provinces in Category 3 can peak their carbon emissions around 2030 under any scenario.

Through a comprehensive analysis of relevant literatures and in combination with questionnaire survey, a list of influencing factors on the vulnerability of the assembly building supply chain is derived. With the help of the principles of system dynamics, a feedback diagram model of assembly building supply chain vulnerability is constructed. Through qualitative analysis (using the feedback loop analysis method) and quantitative analysis (using fuzzy hierarchical analysis), the influencing factors of vulnerability of the assembly building supply chain were ranked in order of importance. Specific suggestions are proposed for each link of the supply chain to reduce the vulnerability of the assembly building supply chain.

In the field of natural language processing, sentiment analysis is a key task to understand the emotional tendency of text, but polysemy and insufficient semantic feature extraction often lead to difficulties in analysis. This study proposes a BERT-BiLSTM-KAN (BBK) model aimed at solving these problems. First, BERT model pre-training technology is used to convert Chinese text into high-dimensional matrix vectors to fully capture the contextual information of words, phrases,and sentences. Subsequently,the bidirectional semantic features of the text are further extracted through the BiLSTM model to enhance the model's sensitivity to time series information. On this basis, the KAN model is introduced to replace traditional linear weights with learnable activation functions at the edges, which improves the model's ability to handle data fitting and complex feature representation. Experimental results show that the BBK model has significantly improved precision, recall and F1 score, verifying its effectiveness and superiority in Chinese text sentiment analysis.

With the development of object detection and re-identification algorithms, multi-object tracking (MOT) has made rapid progress. However, tracking multiple athletes with similar appearances and nonlinear movements in team sports remains a pressing challenge. Current motion-based tracking algorithms typically employ the Kalman Filter to predict target motion, but they struggle to handle nonlinear movements and mutual occlusions among multiple targets effectively. To address this, we propose a MOT framework based on improved OC-SORT and motion information estimation, utilizing the Transformer architecture as a motion predictor instead of the Kalman Filter. We introduce historical trajectory embeddings to extract spatiotemporal features from sequences of previously detected bounding boxes. During the association phase between current detections and historical trajectories, accurate matching is achieved u-sing the Hungarian algorithm based on Buffered Intersection Over Union (BIoU). Furthermore, we design different post-processing procedures for three team sports, basketball, soccer, and volleyball, to effectively handle athletes' nonlinear movements on the field. Experimental results show that the proposed method achieves HOTA score of 77. 3% and IDF1 of 78. 2% on the SportsMOT public dataset, outperforming other state-of-the-art methods. This demonstrates the effectiveness and robustness of the proposed framework in MOT tasks for various team sports，including basketball，soccer，and volleyball.

The UI design and user interaction optimization of the smart energy cloud platform have become a key research direction to improve the overall value of the system, but the current interface design still needs to be improved in terms of functionality and visibility. In this study, the analytic hierarchy process (AHP) and the fuzzy comprehensive evaluation method (FCE) were used to construct the UI evaluation model, and the user interface (UI) design of the platform was systematically evaluated and optimized. AHP was used to weigh the design factors, and the FCE model was employed to evaluate the three UI design schemes to screen out the best one. Combined with the user heatmap data, the visual design of the high-click area was optimized, and the platform score was increased from 82.396 to 87.471. The research results verify the effectiveness of the combination of AHP and FCE in the evaluation and optimization of platform UI design, and provide a scientific basis and practical reference for the user experience improvement of other intelligent cloud platforms.

Oxygen reduction reaction (ORR) is the core reaction of proton exchange membrane fuel cell(PEMFC), but its slow oxygen reduction kinetics constrains the energy conversion efficiency of the fuel cell. Single-atom catalysts (SACs) are considered to be effective catalysts for catalyzing the oxygen reduction reaction due to their high atom utilization, but their insufficient active sites and low 4e- selectivity lead to low catalytic efficiency. Cu clusters with different sizes were stretcher-loaded onto the singleatom catalyst Cu@BN using density-functional theory (DFT) calculations to construct Cux/Cu@BN (x=4, 13) composite catalysts in order to investigate the effect of the loading of the clusters on the catalytic oxygen reduction efficiency of Cu@BN single-atom catalysts. The results show that there is a more pro-nounced orbital hybridization between the h-BN carrier and Cu, suggesting that the strong interaction be-tween them makes the catalyst more stable; the cluster-anchored Cu@BN enhances the adsorption and activation of O2 from the active site Cu, with the largest O -O bond length elongation and the largest charge transfer for the adsorbed Cu4/Cu@BN. It is concluded that the loading of Cu clusters can significantly improve the catalytic efficiency of Cu - based monoatomic catalysts，especially Cu4/Cu@BN exhibits the best catalytic performance for the oxygen reduction reaction.

In order to solve the problem of formaldehyde (HCHO) volatilizing into the air and polluting the environment, a new type of highly efficient adsorbent was studied, and density functional theory (DFT) was used to calculate the influence of boron nitride (BN) nanocages of different sizes on the adsorption performance of HCHO. Firstly, BN nanocages of different sizes, namely B12N12、B16N16, and B24N24, were constructed. The HOMO and LUMO energy levels of the three nanocages were analyzed and compared, and it was found that B12N12 had the minimum energy level difference with HCHO. Therefore, charge transfer between B12N12 and HCHO was more likely to occur. In addition, the bond length formed by B12N12 and HCHO was the shortest (1.663 ), and the absolute value of adsorption energy was the largest (0.653 eV), indicating that B12N12 had stronger adsorption and activation capacity for HCHO. Finally, by calculating the density of states,it is found that there is a more obvious orbital hybridization between B12N12 and HCHO, and the charge transfer is the highest, reaching 0. 332 e-, indicating that the strong interaction between them makes the adsorption effect more significant. In summary，B12N12 with a smaller size shows great potential in formaldehyde removal.

Vapor injecting could effectively improve thermodynamic performance for heat pump with high temperature rise. The performance of medium/high temperature air-source heat pump using vapor injection need to be conducted. A simulation model of the vapor injection heat pump with an economizer is established to analyze influence of parameters (temperature, injection ratio) on cycle performance. Parameter optimization and comparative evaluation of three typical medium-and high-temperature working conditions are carried out under different cycle temperature spans. The results indicate that vapor injection could increase the heat rejection and COP of heat pump, but it has limited effect on reducing compressor exhaust temperature for isentropic working fluids. There exists an optimal branch evaporation temperature that maximizes the COP of the system. The optimal value is greatly influenced by the cycle temperature span and is less affected by the type of working fluid. The corresponding injection pressure is equivalent to the arithmetic square root of the cycle high and low pressures. Increasing the injection ratio is beneficial to improving cycle performance, but the maximum upper limit of the injection ratio is re-stricted by the heat transfer temperature difference of the economizer, and the type of working fluid and cycle temperature span have a significant impact on the maximum allowable injection ratio. The performance improvement effect of vapor injection on large cycle temperature span is more significant. Under condensing temperature of 60℃ and 90℃，COP is improved by 4% and 16% for R1234ze(E)，respectively.

In order to objectively evaluate the academic quality of the Journal of Shandong University of Technology (Natural Science Edition) and optimize the publishing strategy, based on the Annual Report for Chinese Academic Journal Impact Factors (Natural Science) (2020—2024),the main evaluating indicators of the Journal of Shandong University of Technology (Natural Science Edition) from 2019 to 2023 were analyzed statistically, including impact factors, journal mass index, half-life, annual Web download rate, publication delay, article volume, and manuscript sources. The results indicate that the Journal of Shandong University of Technology (Natural Science Edition) showed rising trends in composite impact factor, composite 5-year impact factor, journal mass index, and annual Web download rate, which were significantly higher than the average of similar journals and indicated strong academic influence. In 2024,the Journal of Shandong University of Technology (Natural Science Edition) was selected for the first time as a RCCSE Chinese core academic journal and an excellent scientific and technological journal in Chinese universities. However, there are certain shortcomings in terms of cited half-life, total download volume, publication delay, and manuscript source. Based on the analysis results, some suggestions are presented such as optimizing the selection of topics and column settings，improving the editing and proofreading process，expanding high-quality manuscript sources and striving for policy support from the university，in order to continuously improve the journal quality and extend its academic influence.