Journal of Problems in Computer Science and Information Technologies

TIME SERIES FORECASTING MODELS OF NON-SCHEDULED PASSENGER AIR TRANSPORTATION

2024-08-14T12:30:50+00:00

The change in the time series of non-scheduled passenger air transportation is random and variable, which creates a number of problems in forecasting the demand for this type of transportation. In calculations based on trend models, it is usually not possible to take into account all extraneous factors affecting non-scheduled passenger air transportation. For this reason, the accuracy and practical significance of the forecast are low. Considering the mentioned facts, this paper investigates the application of combined autoregressive integrated moving average (ARIMA) and support vector machine (SVM) methods to improve the accuracy of charter air transportation demand forecasting. ARIMA and SVM models usually complement each other in forecasting due to their inherent characteristics. These features include detecting temporal dependencies and trends, as well as handling non-linear relationships within historical data. The integration of these methods aims to obtain optimal forecast results using the time series analysis of the ARIMA model and the non-linear relationship detection feature of the SVM model. The obtained results emphasize the ability of ARIMA-SVM models to adapt to the dynamic demand patterns of non-scheduled air transportation and also offer a number of efficient ideas for the optimization of operational strategies and resource allocation in this field. The theoretical-practical results of this study, conducted with ARIMA and SVM methods, will be effective in the field of non-scheduled passenger air transportation.

IMPROVING MEDICAL DIAGNOSIS WITH A HYBRID BALANCING TECHNIQUE

2024-09-05T12:04:38+00:00

The issue of class imbalance in medical data poses a significant challenge for developing robust machine learning models aimed at medical diagnosis. A characteristic feature of such data is the substantial dominance of instances belonging to majority classes (e.g., healthy patients or those with common diseases) over instances representing rare conditions. This disproportion leads to machine learning models trained on such data being prone to systematic classification errors, predominantly predicting the most frequent class. Consequently, the ability of models to accurately identify rare cases is severely diminished. This paper proposes a hybrid class-balancing algorithm that combines Inverse Quadratic Radial Undersampling (IQRBU) and genetic oversampling to address this issue. The integration of these two methods within a single algorithm achieves an optimal balance between preserving information and enhancing the representation of rare classes. Experimental results conducted on several medical datasets demonstrated the effectiveness of the proposed approach. The obtained results showed that the hybrid algorithm significantly improves classification metrics, such as the F1-score and accuracy. These findings underscore the potential of our approach to enhance the reliability and precision of medical diagnostic systems.

A COMPARATIVE ANALYSIS OF MACHINE LEARNING CLASSIFIERS FOR STROKE PREDICTION

2024-09-23T10:35:34+00:00

Stroke, a major global health concern, is characterized by sudden neurological deficits and impaired cerebral function. Advancements in technology and the integration of medical records offer opportunities to enhance stroke care and diagnosis. By mining and analyzing electronic health records, valuable insights into the interdependencies of stroke risk factors can be gained, aiding in prediction. This research provides a comprehensive review of the application of machine learning classifiers in stroke prediction, considering various techniques, features, and performance measures utilized in previous studies. The novelty of this work is to emphasize the potential of machine learning classifiers in improving stroke prediction, with a focus on feature selection, data pre-processing, and model evaluation. The aim is to shed light on the strengths and limitations of different classifiers, including Decision Trees, AdaBoost, and Gradient Boost, and their performance metrics in stroke prediction. By achieving this goal, effective stroke risk assessment models can be developed, leading to improved patient outcomes through early intervention and targeted preventive measures. The findings reveal that machine learning classifiers, particularly AdaBoost and Gradient Boost, show promising performance in stroke prediction. These classifiers demonstrate high recall rates and balanced F1 scores, indicating their efficacy in identifying individuals at risk of stroke. This research contributes to the growing body of knowledge in stroke prediction and highlights the potential of machine learning techniques in enhancing stroke care. The integration of machine learning classifiers with stroke prediction holds great promise in improving patient outcomes. By harnessing the power of electronic health records and utilizing appropriate techniques and features, healthcare providers can enhance their ability to identify and intervene in stroke cases, ultimately leading to better preventive measures and care strategies.

APPLICATION OF PINN AND THE METHOD OF DIFFERENTIAL CONSTRUCTION OF ADAPTIVE ONE-DIMENSIONAL COMPUTATIONAL GRIDS

2024-09-23T10:22:07+00:00

This paper presents an approach to constructing adaptive one-dimensional computational grids using the Beltrami equation and Physics-Informed Neural Networks (PINNs). The main focus is on exploring the potential for precise control of grid node density through the control function ω(s), which allows the grid to adapt to the local features of the problem. The Beltrami equation used, being a key component of the method, regulates the distribution of nodes by modifying the function’s derivatives depending on the values of the control function. The effectiveness of this approach is demonstrated through examples involving one and two regions of node clustering.

The results showed that the PINN method combined with the Beltrami equation allows for the creation of computational grids with a high degree of adaptation to given conditions, providing detailed modeling in critical regions. This approach has advantages over traditional numerical methods, as integrating physical laws in the grid construction process minimizes numerical errors and improves modeling accuracy. The use of neural networks offers flexibility in model tuning and the ability to account for complex nonlinear dependencies. The discussion of the results highlights the potential of using PINNs for adaptive grid construction in various fields requiring precise and efficient modeling. In conclusion, this study confirms that the combination of the Beltrami equation and PINNs is a powerful tool for adaptive grid construction, opening new possibilities for numerical modeling of complex physical processes.