Adaptive neuro-fuzzy inference system (ANFIS) it is a type of neural network that combines the strengths of both fuzzy logic and artificial neural networks. ANFIS is particularly useful in stock trading because it can handle uncertainty and imprecision in the data, which is common in stock market data. In stock trading, ANFIS can be used for a variety of purposes, such as predicting stock prices, identifying profitable trades, and detecting stock market trends. One of the key advantages of using ANFIS for stock trading is that it can handle both linear and non-linear relationships in the data. This is particularly useful in the stock market, where the relationships between different variables are often complex and non-linear. ANFIS can also be updated and retrained as new data becomes available, which allows it to adapt to changing market conditions. Therefore, the main hypothesis of this work is to understand whether it is possible to predict the dynamics of prices for stocks of companies in the electric vehicle (EV) sector using technical analysis indicators. The purpose of this work is to create a model for predicting the prices of companies in the EV sector. The technical analysis indicators were processed by several machine learning models. Linear models generally perform worse than more advanced techniques. Decision trees, whether fine or coarse, tend to yield poorer performance results in terms of RMSE, MSE and MAE. After conducting a data analysis, the ANFIS and Bayesian regularization back propagation Neural Network (BR-BPNN) models were seen to be the most effective. The ANFIS was trained for 2000 epochs which yielded a minimum RMSE of 5.90926

Among the many problems in machine learning, the most critical ones involve improving the categorical response prediction rate based on extracted features. In spite of this, it is noted that most of the time from the entire cycle of multi-class machine modeling for sign language recognition tasks is spent on data preparation, including collection, filtering, analysis, and visualization of data. To find the optimal solution for the above-mentioned problem, this paper proposes a methodology for automatically collecting the spatiotemporal features of gestures by calculating the coordinates of the found area of the pose and hand, normalizing them, and constructing an optimal multilayer perceptron for multiclass classification. By extracting and analyzing spatiotemporal data, the proposed method makes it possible to identify not only static features, but also the spatial (for gestures that touch the face and head) and dynamic features of gestures, which leads to an increase in the accuracy of gesture recognition. This classification was also carried out according to the form of the gesture demonstration to optimally extract the characteristics of gestures (display ability of all connection points), which also led to an increase in the accuracy of gesture recognition for certain classes to the value of 0.96. This method was tested using the well-known Ankara University Turkish Sign Language Dataset and the Dataset for Argentinian Sign Language to validate the experiment, which proved effective with a recognition accuracy of 0.98.

Designing secure electronic voting systems that truly protect voter privacy, ensure vote accuracy, and allow independent verification continues to pose serious difficulties. Many current cryptographic approaches require excessive computational resources and use encryption keys that are too large for practical implementation. This paper proposes modifications to the Chaum, Pedersen and Cramer, Franklin, Schoenmakers, and Yung voting protocols by integrating elliptic curve cryptography (ECC), which offers stronger security per bit and more compact key representations. The use of ECC allows for reduced parameter sizes while maintaining resistance against known attacks, including those targeting the discrete logarithm problem. We present detailed adaptations of these protocols on elliptic curves and demonstrate how they preserve core security properties such as vote secrecy, universal verifiability, and resistance to double voting under a more efficient cryptographic framework. Our findings contribute to the development of scalable, high-assurance e-voting mechanisms suitable for modern digital infrastructures. The presented modifications significantly enhance the scalability and efficiency of e-voting systems without compromising cryptographic strength.

В процессе применения технологии есть несколько взаимосвязанных этапов. Сначала из текста выбирается информация, имеющая смысловое значение. Затем они приводятся в определенную структуру и включаются в онтологическую модель. На последнем этапе между этими данными устанавливаются семантические связи в результате формирования внутренней структуры онтологической системы. Кроме того, метод был протестирован на онтологической модели, описывающей административно-географические особенности Казахстана. Опыт показал, что этот подход может быть эффективно применен не только в конкретной области, но и в других областях, таких как здравоохранение, многомерный анализ текстовых данных. Результаты исследования показали, что предложенный подход позволяет систематизировать сложные текстовые структуры и вносить их в базу знаний. В этой области этот метод может играть особенно важную роль в разработке интеллектуальных систем, особенно в проектах, предназначенных для автоматической обработки и интерпретации сложных знаний.