Artificial neural networks find extensive applications in various fields, including complex robotics, computer vision, and classification tasks. They are designed to mimic the highly complex, nonlinear, and parallel computational abilities of the hum...

Partial differential equations are a branch of engineering mathematics that in the last decades in the scientific field has played a very important role in solving certain engineering problems. In this paper, we have applied a kind of partial differential equations when examining the influence of microwaves. We have observed the phenomena occurring in one part of the electromagnetic spectrum in the frequency range of 1 GHz-100 GHz as an aggravating factor in signal transmission by telecommunication water, which was the starting point for research on this topic. The reason for isolating this area is contained in the specific technique that characterizes it. One of the types of partial hyperbolic equations is the telegraphic equation, whose solution eliminates problems related to the transmission line. The graphical interpolation of the telegraph equation is given in the Matlab Engineering Matrix Laboratory. Only the parts of mathematically important functions are derived in the paper and the final results are presented in order to represent our starting differential equation as telegraphic.

The real estate market has a major impact on the economy and everyday life. Accurate real estate valuation is essential for buyers, sellers, investors, and government institutions. Traditionally, valuation has been conducted using various estimation models. However, recent advancements in information technology, particularly in artificial intelligence and machine learning, have enabled more precise predictions of real estate prices. Machine learning allows computers to recognize patterns in data and create models that can predict prices based on the characteristics of the property, such as location, square footage, number of rooms, age of the building, and similar features. The aim of this paper is to investigate how the application of machine learning can be used to predict real estate prices. A machine learning model was developed using four algorithms: Linear Regression, Random Forest Regression, XGBoost, and K-Nearest Neighbors. The dataset used in this study was collected from major online real estate listing portals in Bosnia and Herzegovina. The performance of each model was evaluated using the R² score, Root Mean Squared Error (RMSE), scatter plots, and error distributions. Based on this evaluation, the most accurate model was selected. Additionally, a simple web interface was created to allow for non-experts to easily obtain property price estimates.

This paper explores the applications of stochastic methods in the field of artificial intelligence (AI), focusing on their contribution to optimization, learning, and decision-making. By employing stochastic models, we enable AI to effectively handle uncertainty, unpredictability, and data variation. We analyze how stochastic processes can improve the convergence of algorithms in training deep neural networks and optimizing parameters. Additionally, we investigate the applications of stochastic simulations in assessing the performance of machine learning algorithms in real-world conditions. Through this study, we highlight the key advantages and challenges of stochastic methods in the field of artificial intelligence. Furthermore, we explore how stochastic methods allow artificial intelligence models to better adapt to changing circumstances and unpredictable situations, thereby increasing their robustness and applicability in the real world. We analyze the impact of stochastic elements on decision-making processes, examining how these properties contribute to the adaptability of systems in dynamic environments. By reviewing relevant studies and experiments, this research provides insight into how stochastic methods contribute to the evolution of artificial intelligence, opening new perspectives for understanding and improving the performance of models in real-world scenarios. This paper contributes to a broader understanding of the role of stochastic processes in the field of artificial intelligence, emphasizing the potential for further development and applications in various domains

This paper shows an analysis how to calculate proper bandwidth for VoIP calls after proper dimensioning PSTN network. For this purpose, we use Erlang B and extended Erlang B formulas. Further, we have developed a software tool to calculate proper numbers of the circuits on the PSTN side (using our bandwidth calculator) and after that, bandwidth on the IP. By another word, traffic analysis will be conducted to VoIP networks considering impact of many factors on the bandwidth: voice codec, samples, VAD, RTP compression. The regression analysis is used to show trends of the subscriber behavior in the future (for specific category of subscribers). Finally, simulation results are compared with data obtained by bandwidth calculator.