Pouriya Khaliliyan

Javad T. Firouzjaee, Pouriya Khaliliyan

Russia's attack on Ukraine on Thursday 24 February 2022 hitched financial markets and the increased geopolitical crisis. In this paper, we select some main economic indexes, such as Gold, Oil (WTI), NDAQ, and known currency which are involved in this crisis and try to find the quantitative effect of this war on them. To quantify the war effect, we use the correlation feature and the relationships between these economic indices, create datasets, and compare the results of forecasts with real data. To study war effects, we use Machine Learning Linear Regression. We carry on empirical experiments and perform on these economic indices datasets to evaluate and predict this war tolls and its effects on main economics indexes.

Seyed Sajad Tabasi, Reyhaneh Vojoudi Salmani, Pouriya Khaliliyan et al.

One of the fundamental questions about quasars is related to their central supermassive black holes. The reason for the existence of these black holes with such a huge mass is still unclear and various models have been proposed to explain them. However, there is still no comprehensive explanation that is accepted by the community. The only thing we are sure of is that these black holes were not created by the collapse of giant stars, nor by the accretion of matter around them. Moreover, another important question is the mass distribution of these black holes over time. Observations have shown that if we go back through redshift, we see black holes with more masses, and after passing the peak of star formation redshift, this procedure decreases. Nevertheless, the exact redshift of this peak is still controversial. In this paper, with the help of deep learning and the LSTM algorithm, we tried to find a suitable model for the mass of central black holes of quasars over time by considering QuasarNET data. Our model was built with these data reported from redshift 3 to 7 and for two redshift intervals 0 to 3 and 7 to 10, it predicted the mass of the quasar's central supermassive black holes. We have also tested our model for the specified intervals with observed data from central black holes and discussed the results.

Fatemeh Rezaei, Pouriya Khaliliyan, Mohsen Rezaei et al.

Recurrent Neural Networks are classes of Artificial Neural Networks that establish connections between different nodes form a directed or undirected graph for temporal dynamical analysis. In this research, the laser induced breakdown spectroscopy (LIBS) technique is used for quantitative analysis of aluminum alloys by different Recurrent Neural Network (RNN) architecture. The fundamental harmonic (1064 nm) of a nanosecond Nd:YAG laser pulse is employed to generate the LIBS plasma for the prediction of constituent concentrations of the aluminum standard samples. Here, Recurrent Neural Networks based on different networks, such as Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Simple Recurrent Neural Network (Simple RNN), and as well as Recurrent Convolutional Networks comprising of Conv-SimpleRNN, Conv-LSTM and Conv-GRU are utilized for concentration prediction. Then a comparison is performed among prediction by classical machine learning methods of support vector regressor (SVR), the Multi Layer Perceptron (MLP), Decision Tree algorithm, Gradient Boosting Regression (GBR), Random Forest Regression (RFR), Linear Regression, and k-Nearest Neighbor (KNN) algorithm. Results showed that the machine learning tools based on Convolutional Recurrent Networks had the best efficiencies in prediction of the most of the elements among other multivariate methods.

Javad T. Firouzjaee, Pouriya Khaliliyan

Oil companies are among the largest companies in the world whose economic indicators in the global stock market have a great impact on the world economy\cite{ec00} and market due to their relation to gold\cite{ec01}, crude oil\cite{ec02}, and the dollar\cite{ec03}. This study investigates the impact of correlated features on the interpretability of Long Short-Term Memory(LSTM)\cite{ec04} models for predicting oil company stocks. To achieve this, we designed a Standard Long Short-Term Memory (LSTM) network and trained it using various correlated datasets. Our approach aims to improve the accuracy of stock price prediction by considering the multiple factors affecting the market, such as crude oil prices, gold prices, and the US dollar. The results demonstrate that adding a feature correlated with oil stocks does not improve the interpretability of LSTM models. These findings suggest that while LSTM models may be effective in predicting stock prices, their interpretability may be limited. Caution should be exercised when relying solely on LSTM models for stock price prediction as their lack of interpretability may make it difficult to fully understand the underlying factors driving stock price movements. We have employed complexity analysis to support our argument, considering that financial markets encompass a form of physical complex system\cite{ec05}. One of the fundamental challenges faced in utilizing LSTM models for financial markets lies in interpreting the unexpected feedback dynamics within them.