Search

The multi-objective optimisation of high-speed rail profile with small radius curve is studied in the paper. A multi-objective mathematical model for rail profile optimisation of high-speed railway is established. The CN60 rail profile is parameterised into a series of generalised functions of design variables. In order to guarantee the smoothness of the rail profile and meet the maximum grinding depth of rail in China, the constraints are employed. The wheel-rail vertical clearance and equivalent conicity of wheelset are taken as objective functions, and a rail wear prediction programme is compiled. Contact line method is employed to complete the detection algorithm of wheel-rail contact points. Finally, NSGA-II Algorithm is adopted to solve the Pareto-optimal front of the optimisation model. A set of solutions are retrieved from the Pareto optimal front solution as the optimised profile. The optimised rail profile and the original rail profile are matched with the LMA wheel profile (a certain worn type of wheel profiles for EMU in China) respectively. It is testified that the rail profile could effectively reduce the rail wear and improve curving performance. The new method proposed in this paper can provide some reference for the optimisation design of high-speed rail profile with small radius curve. [ABSTRACT FROM AUTHOR]

Standard scheduled flight block time (SBT) setting is of great concern for Civil Aviation Administration of China (CAAC) and airlines in China. However, the standard scheduled flight block times are set in the form of on-site meetings in practice and current literature has not provided any efficient mathematical models to calculate the flight block times fairly among the airlines. The objective of this paper is to develop and solve a mathematical model for standard SBT setting with consideration of both fairness and reliability. We use whale optimization algorithm (WOA) and an improved version of the whale optimization algorithm (IWOA) to solve the SBT setting problem. A novel nonlinear update equation of convergence factor for random iterations is used in place of the original linear one in the proposed IWOA algorithm. Experimental results show that the suggested approach is effective, and IWOA performs better than WOA in the concerned problem, whose solutions are better compared to the flight block times released by CAAC. In particular, it is interesting to find that MSE, RMSE, MAE, MAPE and Theil of the reliability in 60%–70% range are always the smallest and the average fairness of airlines is better than that of 60%–75% range. The model and solving approach presented in this article have great potential to be applied by CAAC to determine the standard SBTs strategically. [ABSTRACT FROM AUTHOR]

Unlike the other fuzzy neural networks, in this paper the fuzzy system and the neural network are separated, and they are corresponding to structure identification and parameter identification. The fuzzy model is generated automatically by on-line clustering method and fuzzy support vector machines. This fuzzy model is not updated, but its modeling error is compensated by a neural network. The neural network acts as the parameter identification model. The benefits of this new method are the structure is simple, and the physical meanings of each part of the model are clear. For the neural compensator, a new stable and fast training algorithm is proposed. Finally, this modeling method is successfully applied to model a magnetic tube recovery ratio in a metal company in China. [ABSTRACT FROM AUTHOR]

Since the novel coronavirus (COVID-19) outbreak in China, and due to the open accessibility of COVID-19 data, several researchers and modellers revisited the classical epidemiological models to evaluate their practical applicability. While mathematical compartmental models can predict various contagious viruses' dynamics, their efficiency depends on the model parameters. Recently, several parameter estimation methods have been proposed for different models. In this study, we evaluated the Ensemble Kalman filter's performance (EnKF) in the estimation of time-varying model parameters with synthetic data and the real COVID-19 data of Hubei province, China. Contrary to the previous works, in the current study, the effect of damping factors on an augmented EnKF is studied. An augmented EnKF algorithm is provided, and we present how the filter performs in estimating models using uncertain observational (reported) data. Results obtained confirm that the augumented-EnKF approach can provide reliable model parameter estimates. Additionally, there was a good fit of profiles between model simulation and the reported COVID-19 data confirming the possibility of using the augmented-EnKF approach for reliable model parameter estimation. [ABSTRACT FROM AUTHOR]

With the information overload of user-generated content in microblogging, users find it extremely challenging to browse and find valuable information in their first attempt. In this paper we propose a microblogging recommendation algorithm, TSI-MR (Topic-Level Social Influence-based Microblogging Recommendation), which can significantly improve users' microblogging experiences. The main innovation of this proposed algorithm is that we consider social influences and their indirect structural relationships, which are largely based on social status theory, from the topic level. The primary advantage of this approach is that it can build an accurate description of latent relationships between two users with weak connections, which can improve the performance of the model; furthermore, it can solve sparsity problems of training data to a certain extent. The realization of the model is mainly based on Factor Graph. We also applied a distributed strategy to further improve the efficiency of the model. Finally, we use data from Tencent Weibo, one of the most popular microblogging services in China, to evaluate our methods. The results show that incorporating social influence can improve microblogging performance considerably, and outperform the baseline methods. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a two-dimensional numerical calculation algorithm for the water quality modeling in the Hengyang City section of the Xiangjiang River is researched considering the effect of the Dayuandu navigational key project. The research river is winding and has two branches resulted from an isle. The numerical calculation algorithm for the water quality modeling is set up on the basis of applying topographic map of the river course and the finite element method. The calculation result for the water quality modeling includes the concentration fields for various pollutants. The numerical calculation algorithm for the water quality modeling set up in this paper can he applied to shallow river with similar topographically complicated river course. Key words: two-dimensional river; water quality; numerical calculation algorithm. [ABSTRACT FROM AUTHOR]

Stock index forecasting is an important tool for both the investors and the government organizations. However, due to the inherent large volatility, high noise, and nonlinearity of the stock index, stock index forecasting has been a challenging task for a long time. This paper aims to develop a novel hybrid stock index forecasting model named BSO-GNN based on the brain storm optimization (BSO) approach and the grey neural network (GNN) model by taking full advantage of the grey model in dealing with data with small samples and the neural network in handling nonlinear fitting problems. Moreover, the new developed BSOGNN, which initializes the parameters in grey neural network with the BSO algorithm, has great capability in overcoming the deficiencies of the traditional GNN model with randomly initialized parameters through solving the local optimum and low forecasting accuracy problems. The performance of the proposed BSO-GNN model is evaluated under the normalization and nonnormalization preprocessing situations. Experimental results from the Shanghai Stock Exchange (SSE) Composite Index, the Shenzhen Composite Index, and the HuShen 300 Index opening price forecasting show that the proposed BSO-GNN model is effective and robust in the stock index forecasting and superior to the individual GNN model. [ABSTRACT FROM AUTHOR]

Artificial neural networks are sophisticated modelling and prediction tools capable of extracting complex, non-linear relationships between predictor (input) and predicted (output) variables. This study explores this capacity by modelling non-linearities in the hardiness-modulated burnout process with a neural network. Specifically, two multi-layer feed-forward artificial neural networks are concatenated in an attempt to model the composite non-linear burnout process. Sensitivity analysis, a Monte Carlo–based global simulation technique, is then utilised to examine the first-order effects of the predictor variables on the burnout sub-dimensions and consequences. Results show that (1) this concatenated artificial neural network approach is feasible to model the burnout process, (2) sensitivity analysis is a prolific method to study the relative importance of predictor variables and (3) the relationships among variables involved in the development of burnout and its consequences are to different degrees non-linear. Practitioner Summary: Many relationships among variables (e.g. stressors and strains) are not linear, yet researchers use linear methods such as Pearson correlation or linear regression to analyse these relationships. Artificial neural network analysis is an innovative method to analyse non-linear relationships and in combination with sensitivity analysis superior to linear methods. [ABSTRACT FROM AUTHOR]

Due to insufficient samples, the generalization performance of deep network is insufficient. In order to solve this problem, an improved U-net based image automatic segmentation and diagnosis algorithm was proposed, in which the max-pooling operation in original U-net model was replaced by the convolution operation to keep more feature information. Firstly, the regions of 128×128 were extracted from all slices of the patients as data samples. Secondly, the patient samples were divided into training sample set and testing sample set, and data augmentation was performed on the training samples. Finally, all the training samples were adopted to train the model. Compared with Fully Convolutional Network (FCN) model and max-pooling based U-net model, DSC and CR coefficients of the proposed method achieve the best results, while PM coefficient is 2.55 percentage lower than the maximum value in the two comparison models, and Average Symmetric Surface Distance is slightly higher than the minimum value of the two comparison models by 0.004. The experimental results show that the proposed model can achieve good segmentation and diagnosis results. [ABSTRACT FROM AUTHOR]

A unique commercial operation in China that delivers express parcels within the storage compartments (belly-holds) of highway passenger coaches is introduced. A new delivery mode, called ‘direct + transfer’ delivery, is proposed. On the basis of this mode, a model to optimize the delivery path is constructed by considering the parcel arrival patterns, coach departure times, and belly-hold capacity in the initial origin. The solution algorithm is designed. In a case study, the probability distribution function of the parcel arrival pattern is fitted, and the delivery paths of parcels from a city to other cities in a region in China are calculated and analyzed. [ABSTRACT FROM AUTHOR]

Two factors that affect satellite retrieval of Aerosol Optical Depth (AOD) are aerosol model assumptions and the separation of surface reflectance. NASA/MODIS Dense Dark Vegetation (DDV) algorithm has been proven valuable in deriving aerosol distribution and properties over land; however, it cannot be applied to bright targets. As a supplement to the DDV algorithm, an algorithm to retrieve AOD over urban areas in North China in winter is developed using MODIS data, including (1) the generation and analysis of adjacent clear-days surface reflectance using MOD09 product from 2007 to 2008, and (2) seasonal aerosol models derived from AERONET data in Beijing and Xianghe sites. Ground-based measurements using sun photometers were used to validate the retrieved AOD, and the correlation coefficient ( r) is up to 0.931. Especially for high AOD values (AOD>0.4), more retrievals meet the inversion accuracy. The temporal variations of retrieval errors over urban, rural and mountain regions were examined, and the results indicated that the variation of blue-band surface reflectance is less than 0.02 in a short period except for unusual weather conditions, the retrieval bias is under 0.08, and the relative error decreases as the AOD increases. [ABSTRACT FROM AUTHOR]

Background: There are many similarities and overlaps in clinical manifestations and ileocolonoscopic features between Crohn's disease (CD) and intestinal tuberculosis (ITB). Differentiation between CD and ITB is of great importance.Aim: To investigate the values of clinical and endoscopic findings in differential diagnosis between CD and ITB.Methods: Clinical and endoscopic features of a cohort of 130 cases of CD and 122 cases of ITB from June 2003 to February 2009 were retrospectively reviewed following predetermined criteria. Parameters were screened by logistic regression analysis. Furthermore, the diagnostic efficacy of screened parameters was analyzed by regression equation (mathematical model) and receiver operating characteristic curve (ROC curve).Results: The clinical features helpful in differentiating CD from ITB are hematochezia, intestinal surgery, perianal diseases, pulmonary tuberculosis, ascites, and positive of PPD skin test; the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of regression mathematical model established by clinical features were 90.3, 76.8, 83.8, 80.7, and 88.0%, respectively. The endoscopic features helpful in differentiating CD from ITB were rectum involved lesions, longitudinal ulcer, cobblestone appearance, fixed-open ileocecal valve, transverse ulcer, and rodent ulcer; the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of regression mathematical model established by endoscopic features were 82.9, 82.0, 82.5, 82.9, and 82.0%, respectively.Conclusions: It was proposed that a diagnostic algorithm based on available clinical and endoscopic regression equation could improve the current sensitivity, specificity, and accuracy in differentiating between CD from ITB. [ABSTRACT FROM AUTHOR]

Atmospheric correction is of great importance in quantitative remote sensing studies. However, many of the atmospheric correction algorithms proposed in the literature are not easily applicable in real cases. In order to develop a practical atmospheric correction algorithm, Moderate Resolution Imaging Spectroradiometer (MODIS) imagery is employed to obtain aerosol optical depth and the total atmospheric water vapour content, which are used to compute the transmittances in a dark object subtraction (DOS) model. An improved DOS atmospheric correction method combining MODIS imagery with the conventional DOS technique is proposed. A Landsat 7 Enhanced Thematic Mapper Plus (ETM+) image acquired on 21 October 2001 in Wuyi mountain, south-eastern China, and a CBERS 02 CCD image acquired on 24 August 2005 in Dunhuang, north-western China, were atmospherically corrected with this new approach. Various tests are performed, from spectral signature analysis, to vegetation index spatial profile and image information content comparisons, and by direct comparison with ground-measured reflectances, to evaluate the performance of the improved DOS model. The evaluation shows it can generally achieve a good atmospheric correction result. [ABSTRACT FROM AUTHOR]

A simple topographic correction approach, the Variable Empirical Coefficient Algorithm (VECA), was developed using theoretical and statistic analyses of the radiance values of remotely sensed data acquired for rugged terrain and the cosine of the solar illumination angle (cos i). Visual comparison and statistical analysis were used for evaluation of the proposed algorithm and the performance of the VECA approach was compared with 10 commonly used methods. The test site selected for this study is located on the south hill of the Qinling Mountain in Shanxi province, China, and the remotely sensed data used were from Landsat-7 Enhanced Thematic Mapper Plus (ETM+) images. The results indicate that the Cosine-T, Cosine-C, sun-canopy-senor (SCS) and Cosine-b correction have the problem of overcorrection, and the other corrections can be classed into three ranks: the VECA, b correction and C models performed the best, followed by the Teillet-regression correction model, and the SCS+C, Minnaert and Minnaert-SCS corrections performed the worst. The proposed VECA correction and the b correction are the most capable of removing the topographic effects of the ETM+ image. The VECA is not only simple in theory but also easy to operate, indicating that the VECA is an effective topographic correction tool in remote sensing techniques. [ABSTRACT FROM AUTHOR]