Search

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The forest area of Tibet ranks among the top in China, and the forest resources in Tibet play an important role in water conservation and ecological service. Therefore, it is of great significance to assess the assets of forest natural resources in this region. However, existing products and statistical data related to forest cover fail to meet the demands for the assessment of forest natural resource assets in this region, and it is necessary to explore a fine - scale forest classification method suitable for this region. Based on the cloud computing platform Google Earth Engine ( GEE ), this study constructed the temporal, spatial, spectral, and auxiliary feature sets of the forest coverage in Motuo County using the Landsat8 remote sensing images of 2015 and 2020, as well as field survey data, and the basic geographic data. Then, it conducted forest classification using the random forest ( RF) and classification and regression tree ( CART) algorithms. As indicated by the accuracy evaluation of the assessment results obtained using the two algorithms, the forest classification results of 2015 and 2020 obtained using the RF algorithm had relatively high accuracy, with overall classification accuracy of 0. 88 and 0. 87, respectively and Kappa coefficients of both greater than 0.8. The analyses of the areal and spatio - temporal characteristics of forest classification results show that: 1 Motuo County had a total forest area of 34 000 km ² in 2015, with a forest cover rate of up to 84. 63%, which was 2% less than that in 2020; 2 The forest resources in Motuo County are dominated by broadleaved forests, which are mainly distributed in Yarlung Zangbo Grand Canyon and low - altitude areas and accounted for 72. 27% and 75. 37% of the total forest area in 2015 and 2020, respectively. Coniferous forests accounted for 25. 96% and 23. 19% of the total forest area in 2015 and 2020, respectively and are concentrated in high - altitude areas, such as the Namcha Barwa and Gyala Peri peaks. This study determined the spatio - temporal distribution of the forests in Motuo County in 2015 and 2020 by developing a spatio - temporal -spectral classification method. It can provide a reference method for calculating specific forest cover indices SDGs and fill the gap of forest data of smaH zones. The obtained monitoring data will provide data support for the natural asset assessment and ecological function evaluation in Motuo County. [ABSTRACT FROM AUTHOR]

Numerical simulation technology is widely used in material forming process optimization and mold design. Although large volumes of simulation result data can be obtained, it is difficult to directly derive the relationship between the forming quality and the forming process parameters. To extract the potential knowledge latent in the simulation results, a systematic, robust, and efficient knowledge discovery technology is necessary, such as artificial intelligence technology, which has become one of the important research directions of material forming and processing. In this study the deep drawing process of a motorcycle fuel tank cover was taken as an example. A motorcycle fuel tank has complicated surfaces and local small fillets, and during its formation, the side wall and fillet are likely to wrinkle and rupture, respectively, because of local deep and uneven deformation. It is important to determine the forming parameters to produce high quality tank cover that satisfies the surface quality requirements. Compared with the iterative dichotomiser 3 (ID3) decision tree algorithm, the classification and regression decision tree (CART) algorithm is advantageous in terms of faster computation speed, higher stability, and supporting multiple segmentation of continuous data. Furthermore, compared with other algorithms such as support vector machines (SVM) and logistic regression (LR), using the CART decision tree algorithm, the decision tree diagram can be established, and knowledge rules can be visually extracted. Combining the artificial intelligence technology of CART decision tree and the model cross validation method of F1 score, Scikit-Learn, an open-source library of Python platform was used to carry out knowledge discovery from the numerical simulation results of the tank cover deep drawing process. The key forming process parameters of the tank cover, which are blank holder force, the height of the draw bead, and radius of the die fillet, were identified. The optimal eigenvalues and the optimal segmentation points of CART decision tree were selected according to the minimization criteria of Gini index, and the process rules were extracted from the CART decision tree of the forming quality index and the established process parameters. The tank cover drawing process example shows that the knowledge discovery technology based on CART decision tree theory is a feasible way to mine potential knowledge from the numerical simulation results of material forming process.

Objective: To evaluate the predictive role of pelvic floor muscle strength in postpartum period stress urinary incontinence. Methods: From April 2013 to March 2014, clinical data included pelvic floor muscle strength of 200 parturients who delivered in our hospital was analyzed. Predictors that reached significance in the bivariate analysis were entered into the classification and regression tree that identified interactions among them. Results: There was significant statistical difference between the two groups in comparing with chronic cough, prior SUI, newborn weight and new onset of SUI during pregnancy（P＞0.05）. Four predictors were identified, including PFM strength ≤ 35.5 cmH2O, prior SUI, newborn weigh ＞2988 g, and new onset of SUI during pregnancy. PFM strength was the strongest predictor. Conclusions: The forecasting model can screen out the high-risk population of postpartum stress urinary incontinence and provide early prevention. It makes sense of reducing postpartum stress urinary incontinence incidence. But to build a perfect model, further research is needed. [ABSTRACT FROM AUTHOR]

Salinization and alkalinization are two of important land degradation processes in flood area of the Yellow River in central China. A synthesized model for assessment of regional soil salinity was established based on multi-source data including soil salinity, topographical variable, the groundwater level and mineralization degree, vegetation and other factors to the soil salinization. A total of 101 soil columns were sampled from the study area using grid sampling method, and then analyzed for soil electrical conductivity (ECe) and other soil properties. Auxiliary data used in this study to interpret variability of soil salinization were Landsat 5 TM data, apparent electrical conconductivity (ECa) measured using an electromagnetic induction instrument (EM38), altitude derived from topographic map, the groundwater table and mineralization degree and soil pH. The spatial variability of soil salinity was assessed in Fengqiu County, Henan Province, China. Classification and regression tree was applied to obtain the relationships between ECe (0-120 cm) and the auxiliary data. The results showed that ECa accounted for the major proportion of model prediction from multi-source data in classification and regression tree model of total soil layer. Generally, ECaH (apparent soil electrical conductivity from EM38 horizontal mode) and spectral index (dvi: difference vegetation index, bi:soil index, int2: intentity, int1: intentity, ndvi: normalized difference vegetation index, si2: soil index and si1: soil index) were common variable for 0-60cm soil layer. For the 0-30 cm depth, plant index (ndvi and dvi), soil index (si1, si2 and bi) and intentity (int1 and int2) had the highest influence on the model prediction followed by ECa. Plant index (dvi) accounted of more than 50% for 0-60 cm soil layer used in the model. Meanwhile, for ⩾60-120 cm, ECaV (apparent soil electrical conductivity from EM38 vertical mode) was the most important variable used in regression tree model. Validation of the predictive models at each depth resulted in determination coefficient (R2 values) ranging from 0.52 to 0.65. The root mean square error (RMSE) value ranged between 0.72 to 1.27 dS/m. The model for the evaluation of the soil salinity of 0-60 cm was better than that of soil layer of ⩾60-120 cm. The mean of soil salinity varied from 1.26 to 1.61 dS/m from top to the bottom of soil profiles, and the soil salinity at the bottom was the highest in total soil profile, which indicated soil salinity accumulation at the bottom. ECe varied from 0.79 to 3.68 dS/m from top to the bottom of soil profiles. Coefficient of variation of soil salinity at each soil 1ayer was from 0.22 to 0.28 and exhibited the moderate spatial variability. The groundwater table varied from -14.0 m to -0.2 m. Coefficient of variation of groundwater table was 0.7 which exhibited the moderate spatial variability. The mean of groundwater electrical conductivity was 1.44 dS/m, which was similar to soil electrical conductivity. The mean of pH value varied from 8.88 to 9.28 and increased with increasing soil depth. Digital maps of ECa (horizontal and vertical modes) along with other environmental variables were used to predict the spatial distribution of ECe. The high values of soil salinity were mainly distributed in the northern and southern area along the Yellow river in the study area, especially the southeast region. The synthesized model based on multi-source data had high precision for assessment of regional soil salinity. Thus, the application of this technique provides a new method to improve soil salinization and soil quality in the flood area of the Yellow River in central China. [ABSTRACT FROM AUTHOR]