Scientific Journal of Astana IT University

14-23

Authors: Sharipa Temirgaziyeva, Batyrkhan Omarov

Road sign recognition is one of the most important steps drivers can take to avoid dangerous roads or accidents. The purpose of the research work is to develop a recognition system, increasing the classification accuracy of the model, using deep learning methods of Road sign recognition system for drivers in real time on the road. Stages of road sign image classification were carried out, and other authors’ solutions were analyzed. In addition, in this work, the convolutional neural network (CNN) method with the help of deep learning was used to create a system for identifying and recognizing road signs. The proposed road sign recognition system can work in real time to recognize the image of road signs. In this paper, a model is trained using deep learning of 43 different road signs using existing datasets and collected local road signs. A traffic sign detection and recognition system is presented using an 8-layer convolutional neural network, which acquires different functions by training different types of traffic signs. In previous studies, models were trained using simple machine learning algorithms, but the relevance of this study is that a CNN model was trained for a classification task based on convolutional neural networks using deep learning. As a result of the study, classification accuracy of 95% was obtained using deep learning methods. As a novelty of the work, it is possible to note the diversity of the convolutional network methods used to increase the efficiency of the used data set and model training algorithms, the variety of received road signs and algorithms for its recognition, as well as the achievement of a high accuracy rate. This allowed the system to overcome the limited accuracy and performance issues caused by environmental factors, and to be more versatile and accurate than most modern systems.

34-44

Authors: Arailym Tleubayeva, Assar Maidanov, Arina Kantayeva

Traditional street lighting systems receive data about daylight levels and adjust the lighting. However, in such conditions, energy consumption increases since the sensors of such systems receive data on only one indicator, which is daylight. Therefore, a suitable automated intelligent lighting system model is needed. Intelligent lighting systems can adjust the brightness of the light not only based on natural data but also based on the movement of vehicles and people. This paper describes the development, implementation, and testing of a smart lighting system model to increase energy efficiency and high reliability. This system is controlled by a microcontroller programmed to control the lighting and receive data from sensors for processing with good efficiency. Distributed sensors record environmental conditions such as daylight and traffic. Photoresistors change resistance in daylight to light up the streets at night. The HC-SR501 infrared motion sensor detects objects emitting infrared radiation (heat) in the controlled motion zone and sends a signal to the microcontroller. The intelligent lighting system uses LEDs, which consume less energy and achieve high efficiency. Calculations show that the efficiency of using these lamps is almost 70%, compared to what is used in conventional street lighting systems.

55-64

Authors: Dinara Kaibassova, Margulan Nurtay, Ardak Tau, Mira Kissina

Due to the popularity of the easiest way to obtain personal information among attackers, phishing detection is becoming a popular area for research aimed at countering the implementation of such attacks. Malicious website detection is essential to prevent the spread of malware and protect end users from victims. Unfortunately, malicious URL detection still needs to be better understood due to a lack of features and inaccurate classification. Possible sources were examined in order to investigate the subject. Based on the collected information from previous studies, this study is devoted to solving the problem of detecting phishing websites using Ensemble Learning. The aim of the work is to choose the most optimal algorithm for classifying phishing websites using gradient boosting algorithms. AdaBoost, CatBoost, and Gradient Boosting Classifier were chosen as Ensemble Learning algorithms and were used to improve the efficiency of classifiers. Practical studies of the parameters of each algorithm for finding the optimal classification model are given. Research and experiments were carried out on a dataset containing information extracted from the contents of a URL: main URL, domain, directory, and file. A thorough Exploratory Data Analysis (EDA) was carried out, as a result of which the main dependencies and patterns of determining phishing resources were identified using correlation analysis. ROC AUC Score was chosen as an evaluation metric for the algorithms. The best result for predicting phishing websites was demonstrated by the AdaBoost Classifier algorithm, with an average ROC AUC score of 99%. The results of the experiments were illustrated in the form of graphs and tables.

81-88

Authors: Ardabek Khompysh, Nursulu Kapalova, Kunbolat Algazy, Kairat Sakan

This article presents one of the main transformations of symmetric block ciphers used to protect confidential information, a new method for obtaining a non-linear S block, and an analysis of the results obtained. The S-box obtained by this method can be used as a nonlinear transformation in block cipher algorithms to protect confidential data transmitted over an open channel. In most well-known works in the field of analysis and synthesis of modern block symmetric ciphers, S-box is used as a mathematical apparatus for cryptographic Boolean functions. In this case, each S-box is represented by a set of composite Boolean functions whose properties characterize the efficiency of the nonlinear substitution node. Substitution nodes for modern symmetric primitives, including key unfolding functions, are usually implemented as replacement tables. Considering that in most modern block symmetric ciphers for introducing round keys, the encryption algorithm uses a linear operation (bitwise addition modulo 2), S-blocks are the only elements responsible for the cryptographic stability of block encryption algorithms. The required number of rounds of block symmetric ciphers is selected taking into account the results of the cryptographic analysis performed, provided that the properties of S-boxes are specified. As the main criteria and performance indicators, the balance and nonlinearity of composite Boolean functions are used; strict avalanche criterion (SAC), propagation criterion; algebraic degree; the value of the autocorrelation function. In this article, a study was made of the nonlinearity and strict avalanche criterion (SAC) of the S-box used in the block symmetric encryption algorithm. The results of the study were compared with the S-boxes of modern cryptographic algorithms and showed good results.

101-112

Authors: Alua Myrzakerimova, Katerina Kolesnikova, Mugulsum Nurmaganbetova

Today, the importance of information support for various medical technologies has increased significantly. The use of modern information technologies is becoming a critical factor in the development of most branches of knowledge and areas of practice, so the development and implementation of information systems is an urgent task. The clinical decision support system provides clinicians and stakeholders with individualized patient assessments and recommendations to assist in the clinical decision-making process. Knowledge-based information systems are widely used in medicine around the world. Modern technical capabilities make it possible to reach a qualitatively new level of presentation of the course of the disease, namely, based on appropriate mathematical models, to model the typical development of the pathological process in a particular disease, to speed up the process of diagnosing and receiving recommendations on treatment protocols. In Kazakhstan, there is no variety of decision support systems in medicine, especially in the process of diagnosing diseases. The purpose of this study is to develop the structure of an automated system for diagnosing diseases. The Unified Modeling Language (UML) is used as a design tool. The structure of the automated system is presented; the main components and key terms are considered. A mathematical model of diagnostics is shown (in the example of diseases of intestinal and pancreatic insufficiency) based on decision-making methods with fuzzy initial data. A diagram of the data flows of the system is presented. Thus, the paper proposes the structure of an automated system that will contribute to high-quality diagnostics due to an effective method of system organization and the use of fuzzy set theory methods.

122-138

Authors: Serik Omirbayev, Aidos Mukhatayev, Andrii Biloshchytskyi, Sapar Toxanov, Adil Faizullin, Svitlana Biloshchytska

The article considers the creation of structural model for the system of development of methodological competence of IT-discipline teachers based on continuing education with the description of the structure of microservices subsystems. To implement the proposed conceptual model the paper proposes a software architecture based on the use of classical service-oriented design pattern “Model-View Separation” (separation of model objects from the graphical interface objects with the user) and provides for interaction with the database, the composition of its main packages is detailed. Logical and physical service-oriented models of basic classes of objects of subject area and auxiliary objects (services) have been developed. The article also proposes a relational database structure based on the use of metadata tables, directories, and operational data in a relational database management system environment. Methods and mechanisms for data protection and replication are proposed and justified, considering the specifics of system operation in higher education institutions. The article aims to develop insurgents and mechanisms of creation of information technology improvement of the system of higher education and creation and operation of integrated flexible software tools to support the mixed system of organization of educational process, as well as increasing the effectiveness of the introduction of a mixed system for the organization of the educational process on the basis of the use of the latest technical means of training and documentation, ensuring free access of students to teaching and methodological resources, сontent and criteria for the assessment of knowledge in disciplines and modules, data recording, and partial compensation for the increased workload of teachers and staff through the automation of assessment, registration and assessment processes. A task-oriented model for managing technical problems in the implementation of the information system for the development of teachers’ methodological competence is also proposed, and a conceptual framework for managing these problems has been developed from the perspective of considering projects as a set of objects and subjects. Technical problems in projects are shown to be obstacles to moving in the right direction, created by random events, uncertainties, and changes. A mathematical model of the change in resistance value caused by technical problems has been developed and methods to counteract these problems have been proposed.