Search

Urban tunnel traffic has its inherent charateristics, such as frequently periodical traffic congestion/blocking, tidal phenomenon, large traffic flow and population, complicated traffic confluences and cross-flowing intertwined sections. Unlike ordinary roads, the potential fire scenarios are quite different and the consequences of fire are extremely severe in urban tunnel. The study adopts theoretical calculation, formula derivation, traffic survey, random sampling simulation to explore the probability distribution of urban tunnel fire. MATLAB is used to realize the numerical simulation of a million fire scenarios under different working conditions. The results identify the major factors affecting two-lane tunnel vehicle ignition model and three-lane model respectively. The probability of six combustion scales ( 5 MW , 20 MW , 25 MW , 30 MW , 40 MW and 60 MW ) is higher than that of others, and with the increase of combustion scale, the probability decreasing exponentially. The ratio of truck to bus has a significant impact on the probability of large-scale fire. And truck fire and bus fire have a risk of igniting vehicles in adjacent lanes. The research results provide a basis for the design parameters of evacuation safety in practical engineering. [ABSTRACT FROM AUTHOR]

Pseudostellariae heterophylla, an important medicinal plant, has been shown to suffer from serious replanting disease that causes significant declines in both yield and quality. The objective of this study was to isolate the soil-born pathogen and antagonistic microorganism for investigation of the relationship between these microorganism and consecutive monoculture problems of P heterophylla. In this study, we isolated the bacteria with different morphology from P heterophylla rhizosphere soil, detected the pathogenicity of these bacteria to P heterophylla plantlet and antagonistic ability to Fusarium of P heterophylla biotype, identified their species and analyzed their abundance with qRT-PCR in rhizosphere soil of different planting years. We isolated Enterobacter sp1 and Burkholderia sp1 from P heterophylla rhizosphere soil, and found Enterobacter sp1 possessed the pathogenicity to P heterophylla plantlet and Burkholderia sp1 was antagonistic for Fusarium of P heterophylla biotype. However, Burkholderia sp1 was not the antagonistic microorganism to Enterobacter sp1. The growth of Enterobacter sp1 was stimulated by phenolic acids at a certain concentration nearly closed to that in P heterophylla rhizosphere soil, which increased as planting years of P heterophylla increased. On the contrary, the phenolic acids had no promoting effect on the growth of Burkholderia sp1. And with the increase of planting years, the abundance of Burkholderia sp1 decreased and abundance of Enterobacter sp1 increased in the P heterophylla rhizosphere soil. The results indicated that harmful microorganisms increase and beneficial microorganisms decrease, which were mediated by the accumulated autotoxins in rhizosphere soil of consecutively monocultured P heterophylla, and hence leads to the imbalance of microbial community structure and the degradation of soil ecological function. So several abatement methods, such as crop rotation, specific microbial fertilizer and organic matter, could be used to improve the structure and functional diversity of microbial community, and overcome the obstacles of continuous cropping. © 2015 Friends Science Publishers [ABSTRACT FROM AUTHOR]

1. Chronic active lesions volume increase, reflecting the lesions activity between the two MRI scans. 2. Nine models based on three methods (ReliefF, LASSO, and RFE) and three classifiers (LR, RF and SVM) were built and evaluated. 3. SVM classifier with ReliefF algorithm had the best prediction performance (AUC = 0.857). 4. The radiomics-based machine learning model can help predict evolution of unenhanced MS lesion on FLAIR images. Background: The volume change of multiple sclerosis (MS) lesion is related to its activity and can be used to assess disease progression. Therefore, the purpose of this study was to develop radiomics models for predicting the evolution of unenhanced MS lesions by using different kinds of machine learning algorithms and explore the optimal model. Methods: In this prospective observation, 45 follow-up MR images obtained in 36 patients with MS (mean age 32.53±10.91; 23 women, 13 men) were evaluated. The lesions will be defined as interval activity and interval inactivity, respectively, based on the percentage of enlargement or reduction of the lesion >20% in the follow-up MR images. We extracted radiomic features of lesions on FLAIR images, and used recursive feature elimination (RFE), ReliefF algorithm and least absolute shrinkage and selection operator (LASSO) for feature selection, then three classification models including logistic regression, random forest and support vector machine (SVM) were used to build predictive models. The performance of the models were evaluated based on the sensitivity, specificity, precision, negative predictive value (NPV) and receiver operating characteristic curve (ROC) curves analyses. Results: 135 interval inactivity lesions and 110 interval activity lesions were registered in our study. A total of 972 radiomics features were extracted, of which 265 were robust. The consistency and effectiveness of model performance were compared and verified by different combinations of feature selection and machine learning methods in different K-fold cross-validation strategies where K ranges from 5 to 10, thus demonstrating the stability and robustness. SVM classifier with ReliefF algorithm had the best prediction performance with an average accuracy of 0.827, sensitivity of 0.809, specificity of 0.841, precision of 0.921, NPV of 0.948 and the areas under the ROC curves (AUC) of 0.857 (95% CI: 0.812–0.902) in the cohorts. Conclusion: The results demonstrated that the radiomics-based machine learning model has potential in predicting the evolution of MS lesions. [ABSTRACT FROM AUTHOR]

Purpose: To develop deep learning models based on four-dimensional computed tomography angiography (4D-CTA) images for automatic detection of large vessel occlusion (LVO) in the anterior circulation that cause acute ischemic stroke., Methods: This retrospective study included 104 LVO patients and 105 non-LVO patients for deep learning models development. Another 30 LVO patients and 31 non-LVO patients formed the time-independent validation set. Four phases of 4D-CTA (arterial phase P1, arterial-venous phase P2, venous phase P3 and late venous phase P4) were arranged and combined and two input methods was used: combined input and superimposed input. Totally 26 models were constructed using a modified HRNet network. Assessment metrics included the areas under the curve (AUC), accuracy, sensitivity, specificity and F1 score. Kappa analysis was performed to assess inter-rater agreement between the best model and radiologists of different seniority., Results: The P1 + P2 model (combined input) had the best diagnostic performance. In the internal validation set, the AUC was 0.975 (95%CI: 0.878-0.999), accuracy was 0.911, sensitivity was 0.889, specificity was 0.944, and the F1 score was 0.909. In the time-independent validation set, the model demonstrated consistently high performance with an AUC of 0.942 (95%CI: 0.851-0.986), accuracy of 0.902, sensitivity of 0.867, specificity of 0.935, and an F1 score of 0.901. The best model showed strong consistency with the diagnostic efficacy of three radiologists of different seniority (k = 0.84, 0.80, 0.70, respectively)., Conclusion: The deep learning model, using combined arterial and arterial-venous phase, was highly effective in detecting LVO, alerting radiologists to speed up the diagnosis., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Peng, Liu, Yao, Wu, Li, Dai, Gu, Yao, Li, Chen and Wang.)