No abstract

A wavelet-based model for stochastic analysis of beam structures is presented. In this model, the random processes representing the stochastic material and geometric properties are treated as stationary Gaussian processes with specified mean and correlation functions. Using the Karhunen-Loeve expansion, the process is represented as a linear sum of orthonormal eigenfunctions with uncorrelated random coefficients. The correlation and the eigenfunctions are approximated as truncated linear sums of compactly supported orthogonal wavelets, and the integral eigenvalue problem is converted to a finite dimensional eigenvalue problem. The energy-principle-based finite element approach is used to obtain the equilibrium and boundary conditions. Neumann expansion of the stiffness matrix is used to write the nodal displacement vector in terms of random coefficients. The expectation operator is applied to the nodal displacements and their squares to obtain the mean and standard deviation of the displacements. Studies show that the results obtained using this method compare well with Monte Carlo and semianalytical techniques.

No abstract

Stock investors have been making accurate predictions about the stock market in search of maximum profits. However, the stock market has a high degree of uncertainty, which makes it difficult to predict the development trend of the stock market. Existing stock prediction models generally improve the accuracy by changing the network structure and lack in-depth research on abnormal stock data. To solve this problem, we propose a logit-based stock prediction network LogNet, which uses the correctly predicted logits to measure the reliability of stock data, then calculate the confidence interval of the stock data, and use the credible data to make stock predictions. In addition, the model uses the theory of the Extremely Randomized Trees (ExtraTrees) theory to select the historical price data features of stocks. Experimental results show that LogNet has state-of-the-art performance on Twitter data and historical price datasets.

No abstract