Regression analysis, in statistic a modelling, is a set of statical processes that can be used to estimate the relationship between a dependent variable, commonly known as the outcome or response, and more independent variables generally called predictors of covariant. On the other hand, autoregression, which is based on regression equations, is a sequential model that uses time to predict the next step data from the previous step. Given the importance of accurate modelling and reliable predictions. in this paper we have analyzed the most popular methods used for data prediction. Nonlinear autoregressive methods were introduced, and then the machine deep learning approach was used to apply prediction based on a selected input data set. The mean square error was calculated for various artificial neural networks architecture to reach the optimal architecture, which minimized the error. Different artificial neural network (ANN) architectures were trained, tested, and validated using various regressive models, a recommendation was raised according to the obtained and analyzed experimental results. It was shown that using the concepts of machine deep learning will enhance the response of the prediction model.

One of the biggest problems that humans are faced with today is pollution and climate change. Pollution is not a new phenomenon and remains a leading cause of diseases and deaths. Mining, industrialization, exploration and urbanization caused global pollution, whose burdens are shared by developed and undeveloped countries alike. Awareness and stricter laws in the developed countries have contributed to environmental protection. Although all countries have paid attention to pollution, the impact and severity of its long-term consequences are being felt. There is a cause-and-effect link between the pollution of air, water and soil and the environment. This research aimed to prove that the main function of the philosophy of science is to have a functional understanding of knowledge, which views knowledge as a tool for prediction. Prediction is the function or mission of science or the goal that must be achieved if the scientific project is successful. In other words, prediction is the final harvest of description and interpretation. In addition, science is primarily concerned with the prediction of events that have occurred in the universe. A mature prediction is what science provides to validate scientific models. This paper introduced the concepts of using machine learning techniques to enhance the prediction process results. Pollution data set and the negative effects of polluted air data were used. We built, trained and tested various models in order to find the optimal model, which could enhance the results of the prediction process.

Diagnosis, reporting and proper analysis of occupational diseases among railway workers and crew remain unsatisfactory so far. This paper focus on utilizing the concepts of human factors and ergonomics (HFE) for improving the quality of care provided to railway workers, in particular, railway transportation crews. The high level of morbidity in this category of workers makes it important to search for new methods and innovative approach for improve the quality of decision-making related to the risks of the development of occupational diseases in railway crews. The paper aims to develop a method for the prediction and diagnoses of occupational diseases of railway crew workers, this will allow gathering decision rules necessary for improving the quality of medical care provided to crew and preventive strategies based on best practices. The decision rules obtained in the work take into account various risk factors associated with the design and working conditions in the cab of a locomotive in combination with other factors that may increase the risk of the occurrence and development of occupational diseases for workers of locomotive crews that is caused by poor or inappropriate working conditions. The authors investigated the various risks causing occupational diseases, and extrapolate the relationships revealed to railway workers in order to forecast high risk of occupational diseases among railway crew.

The paper offers the obtained quantitative assessment of the performance and energy parameters of a process system composed of an asynchronous motor, a fluid-handling machine and a pipeline when using two methods of performance control, in particular, throttling and speed control methods. Taking into account nonlinearity of mathematical representation of fluid-handling machines and asynchronous drive motors, the starting conditions were analysed using nonlinear differential calculus. The calculations for the models were performed using the MATLAB software package. Transient profiles of flow and head, stator current, angular frequency and torque of an asynchronous motor were obtained at pump startup and control of pump capacity. It has been found that the developed mathematical model of a process system composed of an asynchronous motor, a fluid-handling machine and a pipeline allows obtaining quantitative estimation of the performance and energy parameters of the unit when using two methods of the pump capacity control. The use of frequency method allows to decrease the pump rotation speed and significantly reduce the power consumed by the unit and provide energy-saving mode of operation, the economic efficiency of which depends on the range of feed control.

This study investigates the operational performance of a solar power plant (SPP) in the after math of the damage, focusing on the combined impact of physical equipment damage and environmental changes. A comparative analysis of Maximum Specific Hourly Average Power (MSHAP) was conducted for the 2021 (pre-damage) and 2022–2023 (post-damage) periods. The results reveal a significant decline in power output across all investigated solar angles (16.5°–61.9°), with raw MSHAP discrepancies ranging from –15.3% to –24.3%. By accounting for a systematic reduction in solar radiation (SR) due to increased atmospheric pollution from combustion products, it was determined that the net performance loss attributable specifically to hardware degradation settled between –12.2 % and –21.0 %.To enhance the accuracy of generation forecasting under these conditions, multivariate linear regression models were developed to estimate adjustment coefficients (ksp.h.avg) based on solar altitude (α) and azimuth (γ). The statistical analysis confirmed high model adequacy, with coefficients of determination (R2) reaching 0.884 for pre-noon and 0.802 for post-noon periods. Furthermore, correction factors for partial shading during sunrise and sunset were established with R2 values exceeding 0.94. These findings provide a methodological basis for optimizing SPP operation and predicting energy yields in regions affected by large-scale industrial or military-induced environmental stress.