The primary purpose of trading in stock markets is to profit from buying and selling listed stocks. However, numerous factors can influence the stock prices, such as the company's present financial situation, news, rumor, macroeconomics, psychological, economic, political, and geopolitical factors. Consequently, tremendous challenges already exist in predicting noisy stock prices. This paper proposes a hybrid model integrating the singular spectrum analysis (SSA) and the backpropagation neural network (BPNN) to forecast daily closing prices in stock markets. The model first decomposes the stock prices into several components using the SSA. Then, the extracted components are utilized for training BPNNs to forecast future prices. Compared with the BPNN, the hybrid SSA-BPNN model demonstrates a better predictive performance, indicating the SSA's ability to extract hidden information and reduce the noise effect of the original time series.

No abstract

Reliable capillary pressure data are required for reservoir simulation and fluid flow characterization in porous media. The capillary pressure is commonly measured in the laboratory, which is costly, challenging, and accompanied by measurement uncertainties, especially for low-permeability core samples. Besides laboratory measurements, two-dimensional (2D) rock images reveal another prospect to obtain capillary pressure curves. This paper presents a new integrated approach combining image processing and fractal theory to infer the capillary pressure curve from 2D rock images in low-permeability sandstone. Our approach’s unique feature is its new representation of the pore structure based on information extracted from 2D cross-sections using image processing techniques (i.e. image segmentation and watershed partitioning). Furthermore, we derived an innovative analytical fractal model to calculate the capillary pressure from the newly proposed pore system representation. A new tortuous length equation is introduced to eliminate the developed fractal models’ dependency on the straight capillary length. The pore fractal dimension is computed using the box-counting method from the processed 2D image. The tortuosity fractal dimension is obtained from solving the developed fractal equations of porosity and permeability with the corresponding laboratory measurements. Additionally, a procedure for inferring capillary pressure from multiple cross-sections is proposed. The good accuracy in predicting capillary pressure for five low-permeability sandstone core samples demonstrates the developed approach’s robustness.

Capillary pressure is a crucial input in reservoir simulation models. Generally, capillary pressure measurements are expensive and time-consuming; therefore, there is a limitation on the number of cores tested in the laboratory. Accordingly, numerous capillary pressure models have been suggested to match capillary pressure curves and overcome this limitation. This study developed a new fractal capillary pressure model by depicting the porous system as a bundle of tortuous triangular tubes. The model imitates the pores’ angularity, providing a more accurate representation of the pore system than smooth circular openings. Moreover, triangular tubes allow the wetting phase to be retained in the tube’s corners. A genetic algorithm was employed to match the capillary pressure curves and obtain the proposed model’s parameters. Capillary pressure data of eight low-permeability sandstone samples from the Khatatba formation in the Western Desert of Egypt were utilized to test the proposed model. The results revealed that the developed model reasonably matched the laboratory-measured data.

<span>The main objective of stock market investors is to maximize their gains. As a result, stock price forecasting has not lost interest in recent decades. Nevertheless, stock prices are influenced by news, rumor, and various economic factors. Moreover, the characteristics of specific stock markets can differ significantly between countries and regions, based on size, liquidity, and regulations. Accordingly, it is difficult to predict stock prices that are volatile and noisy. This paper presents a hybrid model combining singular spectrum analysis (SSA) and nonlinear autoregressive neural network (NARNN) to forecast close prices of stocks. The model starts by applying the SSA to decompose the price series into various components. Each component is then used to train a NARNN for future price forecasting. In comparison to the autoregressive integrated moving average (ARIMA) and NARNN models, the SSA-NARNN model performs better, demonstrating the effectiveness of SSA in extracting hidden information and reducing the noise of price series.</span>