Scientific Journal of Astana IT University
Not a member yet
250 research outputs found
Sort by
THE ARCHITECTURE OF DYNAMIC INTEGRATED INTELLIGENCE MODEL FOR MANAGING INNOVATION PROJECTS
Get PDFExisting Intelligence Models for managing innovative projects and programs have been explored. The competency-based approach is considered the basis for building a Dynamic Integrated Intelligence Model for managing innovative projects and programs. The proposed architecture of two groups of competence at a high level and five groups of Competencies lower level of the Dynamic Integrated Intelligence Model for Managing Innovation Projects. The Dynamic Integrated Intelligence model has two groups of high levels – Fluid intelligence and Crystallized intelligence. The lower-level model is presented by seven groups of interrelated competencies: strategic, managerial, emotional, social, cognitive, business, and technical. Each group of competencies of the Dynamic Integrated Intelligence Model is defined. The Dynamic Integrated Intelligence Model (DIIM) is a framework that helps individuals and organizations develop and enhance their ability to adapt to change and uncertainty. It is based on the idea that intelligence is not a fixed trait but rather a dynamic set of skills and abilities that can be developed and improved over time. By developing and enhancing these four components of intelligence, individuals, and organizations can become more adaptable, innovative, and resilient in the face of change and uncertainty. The dynamic integrated intelligence model can be applied in an Agile environment to enhance the cognitive and social-emotional skills of Agile team members. Applying the dynamic integrated intelligence model in an Agile environment can lead to better teamwork, enhanced problem-solving abilities, and improved project outcomes. The organization competence-based IPMA Delta model was used to assess the project team’s competence level. As an example of the application, the Dynamic Integrated Intelligence Model to the implementation of the double degree project of the Kyiv National University of Civil Engineering and Architecture and the Dortmund University of Applied Sciences
A BIBLIOMETRIC STUDY ON BLOCKCHAIN CONCEPT: A THEME ANALYSIS AND FUTURE DIRECTIONS FOR COMPUTER SCIENCE TRAINING
Get PDFThis paper aims to study the blockchain concept domain in the computer science field due to bibliometric study. Authors employed bibliometric and network analysis techniques to analyze existing literature. In total, 719 articles in the period of 2019 to August 2023 from the Web of Science (WOS) database were analyzed after applying search string, and criteria for inclusion and exclusion. Initial data screening involved the extraction of fundamental information, followed by data analysis based on co-occurrence, bibliographic coupling, and citation using special program software VOSviewer and R program. research areas "compute science" and "engineering". In addition to that, VOSviewer and R-based tools illustrate the application of text mining involves utilizing computational techniques to extract, analyze, and represent the key concepts and relationships within the field of blockchain technology. Data analysis primarily involved co-occurrence analysis, bibliographic coupling, co-authorship examination, citation analysis, and co-citation analysis. In the context of a blockchain concept thematic analysis, was applied clustering by coupling. Furthermore, it was conducted the thematic analysis to scrutinize the content of prior studies in the computer science field using clustering by coupling. Ranking of the authors, organizations, and countries was applied according to total link strength metric which was used to quantify the overall strength of connections between nodes within a network. Besides, citation analysis has also been conducted to assess the articles' ranking, considering both worldwide and localized citations. Bibliometric results indicate blockchain concepts within such thematic frameworks as access control scheme, identity management system, supply chain management, artificial intelligence integration, blockchain technology applications, and blockchain smart contract
MATHEMATICAL FRAMEWORK FORMULATION AND IMPLEMENTATION FOR HYPERSPECTRAL AEROSPACE IMAGES PROCESSING
Get PDFThis paper proposes a preprocessing algorithm for aerospace hyperspectral images based on a mathematical apparatus effectively applied in pre-compression transformation problems. In particular, several methods have been analyzed for hyperspectral image (signal) preprocessing from the point of view of digital signal processing algorithms. These mathematical methods are used for problems of filtering signals from noise of different natures and for compression and restoration of signals after their transmission through communication channels. The results of comparative analysis of preparatory processing of lossy compression algorithms based on wavelet analysis, discrete and orthogonal transforms are also given, demonstrating minimization of loss level of reconstructed decoded images. The performance of the proposed preprocessing algorithms with quality metrics is presented to evaluate the quality of the reconstructed hyperspectral aerospace images. The results of this study can be applied and used in the tasks of special processing of hyperspectral images, as well as fundamental knowledge of mathematical apparatuses of the proposed orthogonal preprocessing, considering the specificity of the data which is very important in obtaining images ready for compression for the subsequent identification of objects of the Earth's surface and using such mathematical transformations at the hyperspectral image preprocessing stage before compression provides efficient archiving of the obtained data, while reducing the communication channel load. Through the use of quality metrics of the reconstructed images, the preprocessing algorithm provides an understanding of the threshold of the peak signal-to-noise ratio value and the efficiency of its application to calculate and minimize the loss rate
DEVELOPMENT OF A MODEL FOR IMPLEMENTING A CASE METHOD FOR INTERACTIVE STUDY PROCESS MANAGEMENT MONITORING
Get PDFThe importance of this research topic lies in the need to gather, store, analyze and disseminate accurate information on the management status of educational institutions to guarantee the provision of quality educational services. This is particularly crucial in the current trend towards digitalizing educational work and utilizing the internet to facilitate practical management tasks. The study aims to construct a case method model to supervise educational process management outcomes. For that purpose, the study scrutinises the implementation methodologies of existing case models to monitor and analyse the situation without human intervention. Also, the investigation entails creating an implementation algorithm and a simulation model of an interactive case method to monitor educational activities. The formalized logical-semantic apparatus is used to address the research problems. The algorithm development and simulation modeling enabled correlation of the obtained answer with the assigned task, automating the results output. Generating answers in the case method involves considering rules based on the base word, answer keywords, and constraints (true/false). These elements are part of the thesaurus specific to the survey domain and are included in the test's base vocabulary. To test an answer against a question, each inductive step is viewed through a logical formula. Logical statements such as conjunction, disjunction, logical negation, implication, and equivalence are represented by formulas. This method enables the evaluation of the respondent's answer based on the nodes within the statement tree integrated into the test. The progression from the initial word to the node-connection generates an automated assessment of individual educational process management standards. This study enables the enhancement of automated monitoring capabilities for the University's educational process results. The research suggests the potential for developing models and algorithms to form question sets and enable individualized assessments based on the respondent's performance. As a consequence, the devised algorithm and simulation model for the interactive case approach are showcased. During the testing, the key words and example words were compared with the responses of the participants and specific results were obtained. Additional case vocabulary terms need to be added to address the limitations encountered during the model testing and the testing period
AN EFFICIENT APPROACH FOR THE IMPLEMENTATION OF THE GOBANG GAME USING ARTIFICIAL INTELLIGENCE METHODS
Get PDFGobang is one of the most ancient abstract strategy games for two players. The game is traditionally played on a board with black and white stones, where players take turns placing a colored stone on an empty intersection. The winner is the first player to form an unbroken chain of five stones, either horizontally, vertically, or diagonally. Although the rules of Gobang seem pretty straightforward, the game tree complexity is enormous since the board state is more intuitive than in other games. In this paper, we will implement an algorithm that will solve the Gobang game using artificial intelligence (AI) methods. The program will begin learning from scratch, then use self-play to produce training data, and eventually steadily build up its strength.
The present work first focuses on the implementation of the supervised learning algorithm in the identification procedure in order to identify the position of the current fallen piece. This will be achieved by utilizing image processing and a convolutional neural network. Then a Gobang game procedure will be implemented using a game search algorithm, in which the state of the game is judged by means of a human-set function. After that, the function of judging the game state in the above game search algorithm will be changed to an artificial neural network (ANN) model, since it is convenient to train a model with a small dataset. Finally, the reinforcement learning algorithm will be applied to learn the artificial neural network model so that the playing level of the Gobang game program can be continuously improved
TASKS AND METHODS OF TEXT SENTIMENT ANALYSIS
Get PDFThe purpose of this article is to study one of the methods of social networks analysis – text sentiment analysis. Today, social media has become a big data base that social network analysis is used for various purposes – from setting up targeted advertising for acosmetics store to preventing riots at the state level. There are various methods for analyzing social networks such as graph method, text sentiment analysis, audio, and video object analysis. Among them, sentiment analysis is widely used for political, social, consumer research, and also for cybersecurity. Since the analysis of the sentiment of the text involves the analysis of the emotional opinions expressed in the text, the first step is to define the term opinion. An opinion can be simple, that is, a positive, negative or neutral emotion towards a particular object or its aspect. Comparison is also an opinion, but devoid of emotional connotation. Towork with simple opinions, the first task of text sentiment analysis is to classify the text. There are three levels of classifications: classification at the text level, at the level of a sentence, and at the aspect level of the object. After classifying the text at the desired level, the next task is to extract structured data from unstructured information. The problem can be solved using the five-tuple method. One of the important elements of a tuple is the aspect in which an opinion is usually expressed. Next, aspect-based sentiment analysis is applied, which involves identifying aspects of the desired object and assessing the polarity of mood for each aspect. This task is divided into two sub-tasks such as aspect extraction and aspect classification. Sentiment analysis has limitations such as the definition of sarcasm and difficulty of working with abbreviated words
INVESTIGATION OF THE METHOD OF EVALUATING THE EFFECTIVENESS OF THE INFORMATION SECURITY SYSTEM BASED ON FUZZY INFERENCE
Get PDFAs organizations increasingly rely on digital technology to operate, protecting their information and data has become a critical concern. Information security systems are designed to safeguard digital assets against unauthorized access, use, disclosure, disruption, modification, or destruction. However, evaluating the effectiveness of an information security system can be challenging due to the complexity of the system and the diversity of threats it faces. In recent years, researchers have proposed using fuzzy inference to evaluate the effectiveness of information security systems. Fuzzy inference is a mathematical approach that can handle uncertain and imprecise information, making it well-suited for evaluating the effectiveness of information security systems. This research aims to develop a method for evaluating the effectiveness of an information security system based on fuzzy inference. The proposed method uses a set of performance indicators to measure the effectiveness of the system, such as the number of security incidents detected, the response time to security incidents, and the number of false positives and false negatives [1]. These indicators are then combined using fuzzy inference to generate an overall effectiveness score for the system. The proposed method will be evaluated using a real-world case study of an information security system deployed in an organization. The effectiveness score generated by the fuzzy inference method will be compared to the results obtained using traditional evaluation methods, such as the cost-benefit analysis or the return-on-investment analysis. The results of the study will demonstrate the effectiveness and usefulness of the proposed method for evaluating information security systems
APPLICATION OF MACHINE LEARNING FOR RECOGNIZING SURFACE WELDING DEFECTS IN VIDEO SEQUENCES
Get PDFThe paper offers a solution to the problem of detecting and recognizing surface defects in welded joints that appear during tungsten inert gas welding of metal edges. This problem belongs to the machine vision. Welding of stainless-steel edges is carried out automatically on the pipe production line. Therefore, frames of video sequences are investigated. Images of some welding defects are shown in the paper. An algorithm proposed by the authors is used to detect welding defects in the video sequence frames, the efficiency of which has been confirmed experimentally. The problem solution of welding defects recognition is based on the use of traditional machine learning methods: support vector machine and artificial neural network. To build classification models, a labeled dataset containing automatically extracted texture features from the areas of welding defects detected in the video sequences was created. An analysis was performed to identify the strength of the correlation of texture features between each other and the dependent variable in the dataset for dimensionality reduction of the feature vector. The models were trained and tested on datasets with different numbers of features. The quality of the classification models was evaluated based on the accuracy metric values. The best results were achieved by the classifier built using the support vector machine with a chi-square kernel on a training sample with two features. The build models allow automatic recognition of such welding defects as lack of fusion and metal oxidation. The computational experiments with real video sequences obtained with a digital camera confirmed the possibility of using the proposed solution for recognizing surface welding defects in the process of manufacturing stainless steel pipes
АНАЛИЗ ВЗАИМОДЕЙСТВИЯ ГЕТЕРОГЕННЫХ IOT-УСТРОЙСТВ В КИБЕРФИЗИЧЕСКОЙ СИСТЕМЫ
No full textThe article is devoted to the study of existing technologies regarding Internet of Things (IoT) device interaction in a heterogeneous network. Since each smart home appliance can be controlled by a customer who aims to find a cost-effective and easy-to-connect product for their own connected home, there are certain functional limitations for devices from distinct manufacturers that may decrease the intention to merge them all into a single network. A variety of proprietary protocols and communication standards embedded by vendors make their products unable to interact with other vendor devices if the connection standard used is not identical. Also, an IoT product design refers to its own functionality, mainly excluding the possibility of integration into other existing infrastructure. As IoT equipment emerges on the market, the complexity of its connection to a heterogeneous network corresponds to the firmware and the standard unification according to modern demands. It means that potential users might face the necessity of overcoming these issues to achieve high performance in terms of network interoperability. In general, an IoT gateway operating as a middleware might have the potential to enable a network with distinct communication models to operate without failure or data loss. This task requires the received data to be converted into the format in which the data is intended. This paper includes a comparative analysis of existing IoT device interaction standards, connection protocols, and data transfer technologies, evaluating their features for an effective adoption of the proposed network architecture, which can be used to improve the interoperability of heterogeneous IoT devices
OVERVIEW OF TRANSFORMER-BASED MODELS FOR MEDICAL IMAGE SEGMENTATION
Get PDFPremedical diagnostics is the process of examining survey results. Correct premedical diagnostics can improve the process of patient management and reduce the burden on the medical sector. Diagnostics of medical images such as computed tomography and X-ray are obligatory steps for further treatment. However, the shortage of clinicians causes delays in this step. We observed two state-of-the-art algorithms proposed for medical image segmentation: TransUnet and Swin-Unet. We conducted a theoretical comparison of algorithms in terms of the applicability of pre-hospital diagnostics according to quality and speed of training. The comparison is based on the original source of code provided by the authors of the original articles. We chose these two algorithms because they have similar U-form architecture, a high level of citation, and show competitive DICE scores on pictures of various human organs. Some architectural features were also important. Both models inherit key elements of U-net. TransUnet is a hybrid Transformer and CNN model. It consists of Transformer encoder and a convolutional decoder. Some additional computations are required in the bottleneck. Swin-Unet is a fully Transformer-based model. These architectural differences give rise to a difference in the number of trainable parameters. Generally, deeper architectures with a bigger number of parameters usually show better performance, however, according to our review, Swin-Unet has a smaller number of parameters and shows better DICE and Hausdorff Distance. It should be noted that the distribution between false positive and false negative predictions is important in medical image processing. It is crucial to avoid overloading the medical sector while also not missing any sick patients. Precision and recall can be used to evaluate the ratio of incorrect predictions. Therefore, we also observed the results of caries segmentation where precision and DICE were provided. In this specific case, TransUnet shows better DICE and recall values but worse precision