The project envisages the creation of a complex system that integrates advanced technologies of machine learning and natural language processing for media content analysis. The main goal is to provide means for quick and accurate verification of information, reduce the impact of disinformation campaigns and increase media literacy of the population. Research tasks included the development of algorithms for the analysis of textual information, the creation of a database of fakes, and the development of an interface for convenient access to analytical tools. The object of the study was the process of spreading information in the media space, and the subject was methods and means for identifying disinformation. The scientific novelty of the project consists of the development of algorithms adapted to the peculiarities of the Ukrainian language, which allows for more effective work with local content and ensures higher accuracy in identifying fake news. Also, the significance of the project is enhanced by its practical value, as the developed tools can be used by government structures, media organizations, educational institutions and the public to increase the level of information security. Thus, the development of this project is of great importance for increasing Ukraine's resilience to information threats and forming an open, transparent information society.

The increase in value of security and privacy is compounded by the rapid advancements in the digital landscape sprouting new problems in information security. This research explores the use of artificial intelligence (AI) to enhance cybersecurity and to strengthen data protection. This research aims to first assess and critically evaluate the potential of applying AI methods to improve predicting, mitigating, and resolving cyber threats while addressing important ethical issues. Specifically, it wants to determine AI’s advantages compared to traditional cybersecurity ways and the plausible technological risks and ethical implications associated with its use. We show that AI tools, especially machine learning and deep learning, can greatly aid the threat detection and response automation. The rise of AI, however, brings forth new vulnerabilities and necessitates stronger ethical frameworks to preclude their misuse. This study offers a balanced view of potential with AI and hazards. The results emphasize the importance of AI in securing both the cybersecurity and data protection portfolio, and urge strongly for ethical standards to be met and the research to be continued in order to mitigate risks and promote responsible AI integration.

The aim of the paper is the development of a design catalog and sustainability analyses of road layers. In this paper, the material and thickness of the layers for three different traffic load classes will be determined based on the pavement design of the Hungarian and Pakistani standards. This was achieved using the Hungarian design method and the AASHTO method adopted by the National Highway Authority in Pakistan. "This will enable engineers in the field to choose pre-established designs from the catalog.". The forefront of pavement design is the direction in which ongoing research endeavors in the field are guiding us. The empirical design, as outlined in the AASHTO 1993 version, relies on statistical models derived from road tests. Moving beyond this, the mechanistic-empirical design involves assessing stresses and strains alongside empirical models, such as the MEPDG approach. Looking ahead, a mechanistic design encompasses models based on mechanics and represents the frontier where researchers are advancing the future of pavement design. The Hungarian pavement design method (eÚT 2-1.202:2005, 2005) primarily relies on mechanistic-empirical pavement design principles. However, it limits practicing engineers to choosing predefined designs from the catalog. The Comparison was carried out between Hungarian and Pakistani pavement designs. Subsequently, comparative calculations between GRT and SBS will be made for CO2 emissions and other sustainability parameters. To achieve this aim, the Pavement LCA tool by the US Department of Transportation Federal Highway Administration was employed.

The redundancy of a multichannel data transmission system increases its reliability. During the operation of the system, it is necessary to diagnose and switch failed channels. To solve this problem, the set of input signals of the system is considered as a vector signal, whose scalar components are the coordinates of the vector in a given dimensional space. The diagnosis is performed using a scalar criterion, whose relative simplicity is ensured by the linearity of the signal transformations applied. To minimize the total probability of diagnostic error, the task of optimizing the tolerance on the diagnostic parameter is solved. The possibility of technical implementation of the proposed method is shown based on matrix transformations of the system's input and output signals. The system efficiency was assessed according to the "reliability-cost" criterion. Scientific novelty of the work consists in the fact that analytical expressions for matrix transformations of input and output vector signals of a multichannel data transmission system have been developed. Realization of these transformations provides diagnostics of the system according to the developed scalar criterion both in the test mode and in the mode of functioning as intended. 

Accurate stock price prediction is crucial for financial markets, where investors and analysts forecast future prices to support informed decision-making. In this study, various methods for integrating two advanced time series prediction models, Gated Recurrent Unit (GRU) and Neural Basis Expansion Analysis Time Series Forecasting (N-BEATS), are explored to enhance stock price prediction accuracy. GRU is recognized for its ability to capture temporal dependencies in sequential data, while N-BEATS is known for handling complex trends and seasonality components. Several integration techniques, including feature fusion, residual learning, Ensemble learning and hybrid modeling, are proposed to leverage the strengths of both models and improve forecasting performance. These methods are evaluated on datasets of ten stocks from the S&P 500, with some exhibiting strong seasonal or cyclic patterns and others lacking such characteristics. Results demonstrate that the integrated models consistently outperform individual models. Feature selection, including the integration of technical indicators, is employed during data processing to further improve prediction accuracy.

Polycystic Ovary Syndrome (PCOS) is a common endocrine disorder that affects women of reproductive age, leading to hormonal imbalances and ovarian dysfunction. Early detection and intervention are vital for effective management and prevention of complications. This study compares PCOS prediction using the XGBoost machine learning model against four traditional models: Logistic Regression (LR), Support Vector Machine (SVM), Decision Trees (DT), and Random Forests (RF). LR and SVM achieve accuracies of 95% and 96%, respectively, demonstrating strong predictive capabilities. In contrast, DT had a lower accuracy (82%), indicating limitations in PCOS data complexity. RF showed competitive performance with 96% accuracy, underscoring its effectiveness in ensemble learning. XGBoost achieves 98% accuracy with its parameter configuration. The scale pos weight parameter adjusts the positive class weight in imbalanced datasets, addressing under representation by assigning more weight to the minority class, and thereby improving the training focus. The gradient boosting framework incrementally builds models to address complex feature interactions and dependencies, enhancing the accuracy and stability in predicting intricate PCOS dataset. This analysis highlights the importance of advanced machine learning models such as XGBoost for accurate and reliable PCOS predictions. This research advances PCOS prediction, demonstrates the potential of machine learning in healthcare, and clarifies the strengths and limitations of different algorithms with complex medical datasets.

Introducing an innovative approach to stress detection through multimodal data fusion, this study addresses the critical need for accurate stress level monitoring, essential for mental health assessments. Leveraging diverse data sources—including audio, biological sensors, social media, and facial expressions—the methodology integrates advanced algorithms such as XG-Boost, GBM, Naïve Bayes, and BERT. Through separate preprocessing of each dataset and subsequent feature fusion, the model achieves a comprehensive understanding of stress levels. The novelty of this study lies in its comprehensive fusion of multiple data modalities and the specific preprocessing techniques used, which improves the accuracy and depth of stress detection compared to traditional single-modal methods. The results demonstrate the efficacy of this approach, providing a nuanced perspective on stress that can significantly benefit healthcare, wellness, and HR sectors. The model's strong performance in accuracy and robustness positions it as a valuable asset for early stress detection and intervention. XG-Boost achieved an accuracy rate of 95%, GBM reached 97%, Naive Bayes achieved 90%, and BERT attained 93% accuracy, demonstrating the effectiveness of each algorithm in stress detection. This innovative approach not only improves stress detection accuracy but also offers potential for use in other fields requiring analysis of multimodal data, such as affective computing and human-computer interaction. The model's scalability and adaptability make it well-suited for incorporation into existing systems, opening up opportunities for widespread adoption and impact across various industries.

Big Data is a new class of technology that gives businesses more insight into their massive data sets, allowing them to make better business decisions and satisfy customers. Big data systems are also a desirable target for hackers due to the aggregation of their data. Hadoop is used to handle large data sets through reading and writing application programs on a distributed system. Hadoop Distributed File System is used to store massive data. Since HDFS does not safeguard data privacy, encrypting the file is the right way to protect the stored data in HDFS but takes a long time. In this paper, regarding privacy concerns, we use different compression-type data storage file formats with the proposed user-defined function (XOR-Onetime pad with AES) to secure data in HDFS. In this way, we provide a dual level of security by masking the selective data and whole data in the file. Our experiment demonstrates that the whole process time is significantly smaller than that of a conventional method. The proposed UDF with ORC, Zlib file format gives 9-10% better performance results than 2DES and other methods.  Finally, we decreased the load time of secure data and significantly improved query processing time with the Hive engine.

Aiming at the problems of large information loss and feature loss in the similarity design of high-dimensional panel data in clustering, a new panel data clustering method was proposed, which named an adaptive clustering method for panel data based on multi-dimensional feature extraction. This method defined "comprehensive quantity", "absolute quantity", "growth rate", "general trend" and "fluctuation quantity" of samples to extract features, and the five features were weighted to calculate the samples comprehensive distance. On this basis, ward method is used for clustering. This method can greatly reduces the loss of effective information. To verify the effectiveness of the method, cluster empirical analysis was conducted using GDP panel data from 31 regions in China, and the clustering results were compared with those of other clustering models. The experimental results showed that the proposed model was more interpretable and the clustering results were better.

Fifth-generation (5G) wireless communication systems employ millimeter-wave (mm-wave) frequency bands to achieve a very broad spectrum for high data rate transmission. To meet the system requirements, the best design of antenna arrays with superior performance is essential. Thus, in this paper, the design and performance analysis of single element, 2 x 1, and 4 x 1 metamaterial inspired millimeter-wave antenna (MIA) arrays are proposed. The antenna elements are designed using Rogers’ 5880 as a substrate material with a 2.2 dielectric constant and thickness of 0.35 mm to operate at a center frequency of 38 GHz. The simulated design of the single, 2 x 1, and 4 x 1 MIA arrays return loss, bandwidth, gain, voltage standing wave ratio (VSWR), and total efficiency are: -82.95 dB, -67.1 dB, -69.12 dB; 1.971 GHz, 2.278 GHz, 4.704 GHz; 7.36 dBi, 9.11 dBi, 11.4 dBi; 1.001432, 1.0009, 1.0007; and 95.55 %, 94.01 %, 95.87. As compared to other works, improved performance has been achieved by considering the effect of meta-materials on the radiator and at the ground of microstrip patch antennas (MPA). The selected type of meta-materials alters the current distribution of the radiating patch that enhances the fringing fields at the edge of MPAs, which inspires the radiation of antennas and reduces the surface wave loss at the radiators’ ground plane. The proposed MIA antenna arrays have improved upon the drawbacks of traditional MPAs and fulfill the requirements of 5G communication systems.