Системні дослідження та інформаційні технології: міжнародний науково-технічний журнал, № 3
Постійне посилання зібрання
Переглянути
Нові надходження
Документ Відкритий доступ Basic algorithm for approximation of the boundary trajectory of short-focus electron beam using the root-polynomial functions of the fourth and fifth order(КПІ ім. Ігоря Сікорського, 2023) Melnyk, I.; Pochynok, A.Abstract. The new iterative method of approximating the boundary trajectory of a short-focus electron beam propagating in a free drift mode in a low-pressure ionized gas under the condition of compensation of the space charge of electrons is considered and discussed in the article. To solve the given approximation task, the rootpolynomial functions of the fourth and fifth order were applied, the main features of which are the ravine character and the presence of one global minimum. As an initial approach to solving the approximation problem, the values of the polynomial coefficients are calculated by solving the interpolation problem. After this, the approximation task is solved iteratively. All necessary polynomial coefficients are calculated multiple times, taking into account the values of the function and its derivative at the reference points. The final values of polynomial coefficients of high-order root-polynomial functions are calculated using the dichotomy method. The article also provides examples of the applying fourth-order and fifth-order root-polynomial functions to approximate sets of numerical data that correspond to the description of ravine functions. The obtained theoretical results are interesting and important for the experts who study the physics of electron beams and design modern industrial electron beam technological equipment.Документ Відкритий доступ Algorithm for simulating melting polar ice, Earth internal movement and volcano eruption with 3-dimensional inertia tensor(КПІ ім. Ігоря Сікорського, 2023) Matsuki, Yoshio; Bidyuk, PetroAbstract. This paper reports the result of an investigation of a hypothesis that the melting polar ice of Earth flowing down to the equatorial region causes volcano eruptions. We assumed a cube inside the spherical body of Earth, formulated a 3-dimensional inertia tensor of the cube, and then simulated the redistribution of the mass that is to be caused by the movement of melted ice on the Earth’s surface. Such mass distribution changes the inertia tensor of the cube. Then, the cube’s rotation inside Earth was simulated by multiplying the Euler angle matrix by the inertia tensor. Then, changes in the energy intensity and the angular momentum of the cube were calculated as coefficients of Hamiltonian equations of motion, which are made of the inertia tensor and sine and cosine curves of the rotation angles. The calculations show that the melted ice increases Earth’s internal energy intensity and angular momentum, possibly increasing volcano eruptions.Документ Відкритий доступ Intelligent information system of the city's socio-economic infrastructure(КПІ ім. Ігоря Сікорського, 2023) Lipianina-Honcharenko, Khrystyna; Bodyanskiy, Yevgeniy; Sachenko, AnatoliyAbstract. Urban development is an important problem that can be solved with the help of intelligent information systems. Such systems ensure efficient management of the city’s diverse infrastructure. The researchers developed a concept of such an information system based on a conceptual model and using data flow for intelligent decision-making. The system was tested for 1460 days in the city of Ternopil. The modelling results showed that the city’s central area is stable, with 50% of enterprises in the “growing” state and 70% of people in the “satisfactory” state. People often move to the northeastern and western zones due to higher levels of comfort and more affordable housing. However, the total distance of car trips has increased by 249%, negatively impacting the environment. The condition of enterprises in other zones is less stable with lower “growth” indicators, but there are zones with “stable” and “satisfactory” conditions.Документ Відкритий доступ Identification of lung disease types using convolutional neural network and VGG-16 architecture(КПІ ім. Ігоря Сікорського, 2023) Bukhori, S.; Verdy, B. Y. N.; Eka, Y. R. Windi; Januar, A. P.Abstract. Pneumonia, tuberculosis, and Covid-19 are different lung diseases but have similar characteristics. One of the reasons for the worsening of disease in lung sufferers is a diagnosis that takes a long time. Another factor, the results of the X-ray photos look blurry and lack contracture, causing different diagnostic results of X-ray photos. This research classifies lung images into four categories: normal lungs, tuberculosis, pneumonia, and Covid-19 using the Convolutional Neural Network method and VGG-16 architecture. The results of the research with models and scenarios without pre-trained use data with a ratio of 9:1 at epoch 50, an accuracy of 94%, while the lowest results are in scenarios using data with a ratio of 8:2 at epoch 50, non-pre-trained models, accuracy by 87%.Документ Відкритий доступ A concatenation approach-based disease prediction model for sustainable health care system(КПІ ім. Ігоря Сікорського, 2023) Tharageswari, K.; Sundaram, N. Mohana; Santhosh, R.Abstract. In the present world, due to many factors like environmental changes, food styles, and living habits, human health is constantly affected by different diseases, which causes a huge amount of data to be managed in health care. Some diseases become life-threatening if they are not cured at the starting stage. Thus, it is a complex task for the healthcare system to design a well-trained disease prediction model for accurately identifying diseases. Deep learning models are the most widely used in disease prediction research, but their performance is inferior to conventional models. In order to overcome this issue, this work introduces the concatenation of Inception V3 and Xception deep learning convolutional neural network models. The proposed model extracts the main features and produces the prediction result more accurately than traditional predictive models. This work analyses the performance of the proposed model in terms of accuracy, precision, recall, and f1-score. It compares the proposed model to existing techniques such as Stacked Denoising Auto-Encoder (SDAE), Logistic Regression (LR), MLP, MLP with attention mechanism (MLP-A), Support Vector Machine (SVM), Multi Neural Network (MNN), and Hybrid Convolutional Neural Network (CNN)-Random Forest (RF).Документ Відкритий доступ Uncertainties in data processing, forecasting and decision making(КПІ ім. Ігоря Сікорського, 2023) Levenchuk, L. B.; Tymoshchuk, O. L.; Guskova, V. H.; Bidyuk, P. I.Abstract. Forecasting, dynamic planning, and current statistical data processing are defined as the process of estimating an enterprise’s current state on the market compared to other competing enterprises and determining further goals as well as sequences of actions and resources necessary for reaching the goals stated. In order to perform high-quality forecasting, it is proposed to identify and consider possible uncertainties associated with data and expert estimates. This is one of the system analysis principles to be hired for achieving high-quality final results. A review of some uncertainties is given, and an illustrative example showing improvement of the final result after considering possible stochastic uncertainty is provided.Документ Відкритий доступ Investigation of computational intelligence methods in forecasting at financial markets(КПІ ім. Ігоря Сікорського, 2023) Zaychenko, Yu.; Zaichenko, He.; Kuzmenko, O.Abstract. The work considers intelligent methods for solving the problem of shortand middle-term forecasting in the financial sphere. LSTM DL networks, GMDH, and hybrid GMDH-neo-fuzzy networks were studied. Neo-fuzzy neurons were chosen as nodes of the hybrid network, which allows to reduce computational costs. The optimal network parameters were found. The synthesis of the optimal structure of hybrid networks was performed. Experimental studies of LSTM, GMDH, and hybrid GMDH-neo-fuzzy networks with optimal parameters for short- and middleterm forecasting have been conducted. The accuracy of the obtained experimental predictions is compared. The forecasting intervals for which the application of the researched artificial intelligence methods is the most expedient have been determined.Документ Відкритий доступ Research on hybrid transformer-based autoencoders for user biometric verification(КПІ ім. Ігоря Сікорського, 2023) Havrylovych, M. P.; Danylov, V. Y.Abstract. Our current study extends previous work on motion-based biometric verification using sensory data by exploring new architectures and more complex input from various sensors. Biometric verification offers advantages like uniqueness and protection against fraud. The state-of-the-art transformer architecture in AI is known for its attention block and applications in various fields, including NLP and CV. We investigated its potential value for applications involving sensory data. The research proposes a hybrid architecture, integrating transformer attention blocks with different autoencoders, to evaluate its efficacy for biometric verification and user authentication. Various configurations were compared, including LSTM autoencoder, transformer autoencoder, LSTM VAE, and transformer VAE. Results showed that combining transformer blocks with an undercomplete deterministic autoencoder yields the best performance, but model performance is significantly influenced by data preprocessing and configuration parameters. The application of transformers for biometric verification and sensory data appears promising, performing on par with or surpassing LSTM-based models but with lower inference and training time.Документ Відкритий доступ Augmented security scheme for shared dynamic data with efficient lightweight elliptic curve cryptography(КПІ ім. Ігоря Сікорського, 2023) Dharmadhikari, Dipa D.; Tamane, Sharvari C.Abstract. Technology for Cloud Computing (CC) has advanced, so Cloud Computing creates a variety of cloud services. Users may receive storage space from the provider as Cloud storage services are quite practical; many users and businesses save their data in cloud storage. Data confidentiality becomes a larger risk for service providers when more information is outsourced to Cloud storage. Hence in this work, a Ciphertext and Elliptic Curve Cryptography (ECC) with Identity-based encryption (CP-IBE) approaches are used in the cloud environment to ensure data security for a healthcare environment. The revocation problem becomes complicated since characteristics are used to create cipher texts and secret keys; therefore, a User revocation algorithm is introduced for which a secret token key is uniquely produced for each level ensuring security. The initial operation, including signature, public audits, and dynamic data, are sensible to Sybil attacks; hence, to overcome that, a Sybil Attack Check Algorithm is introduced, effectively securing the system. Moreover, the conditions for public auditing using shared data and providing typical strategies, including the analytical function, security, and performance conditions, are analyzed in terms of accuracy, sensitivity, and similarity.Документ Відкритий доступ Academician Glushkov’s legacy: Human capital in the field of cybernetics, computing, and informatics at Igor Sikorsky Kyiv Polytechnic Institute(КПІ ім. Ігоря Сікорського, 2023) Zgurovsky, M. Z.Abstract. The role of academician Viktor Glushkov in the creation of scientific schools in the field of cybernetics, computing, and informatics at the Igor Sikorsky Kyiv Polytechnic Institute, which became a powerful national center for training specialists in this field, is considered. The significant influence of academician Hlushkov’s ideas on the formation of generations of scientists, who to this day continue to build a digital society in Ukraine and far beyond its borders, is shown.