Scientific Journal of Astana IT University
Not a member yet
250 research outputs found
Sort by
THE TASK OF CHOOSING PARTNERS FOR THE ORGANIZATION OF COOPERATION IN THE FRAMEWORK OF SCIENTIFIC AND EDUCATIONAL PROJECTS
Get PDFThe primary objective of this article is to establish a set of fundamental criteria for the selection of scientific partners for collaborative research efforts. Achieving this objective entails addressing the challenge of identifying criteria that are both objective and universally applicable, capable of encompassing various fields of scientific research, such as natural sciences, technical sciences, and economic sciences, among others.
One such criterion, applicable to scientists, may involve assessing their publication activity within specific research areas that align with the objectives of the relevant scientific research or international projects. In the contemporary landscape of scientific research, there is a growing urgency to enhance the effectiveness of research endeavors and to foster efficient collaboration within scientific communities. This is particularly vital for organizations oriented towards project-based research.
In the formation of research project teams, a conventional approach is to select partners from the pool of scientists possessing the requisite qualifications and experience in the execution of such projects. A widely accepted yardstick for evaluating the outcomes of scientists' research endeavors is the citation metrics associated with their publications. Typically, these metrics take the form of scalar values. While this approach offers several advantages, it is not without its limitations. One notable drawback is the potential loss of information when converting raw data into scalar metrics, and the existence of certain edge cases where the parameter remains unchanged despite variations in the number of citations and publications.
Hence, it is pertinent to explore the development of new methodologies or modifications to existing ones that can effectively evaluate the results of scientists' research activities while mitigating these limitations.Начало формы The article describes the criteria for the search and selection of partners for joint scientific research. This will make it possible to effectively form teams for narrowly focused scientific research or international collaboration projects in interdisciplinary scientific projects such as the European Horizon Program or educational projects such as the Erasmus plus program. Also, the proposed solution will allow the formation of small teams for joint scientific publications. It is imperative to acknowledge that the process of partner selection is predominantly driven by a consideration of the knowledge, whether it be novel or foundational, possessed by prospective partners who are entrusted with the execution of a project. It becomes crucial to delineate the specific criteria governing partner selection which can vary contingent upon factors such as the typology of partners, the nature of project tasks, the depth of knowledge possessed, and related contextual variables. A vital underpinning for the formation of project consortia is the mathematical conundrum of choice which furnishes a formal rationale for the judicious selection of a particular partner
ANALYSIS OF METHODS FOR DETECTING FACES IN AN IMAGE
Get PDFIn this article, computer vision is considered as modern technology of automatic processing of graphic images, and the relationship between the terms “computer vision” and “machine vision” is investigated. A diagram of a typical computer vision system is given and the possibility of using a system based on an artificial neural network for image analysis is considered. The article analyses the current situation with the use of computer vision systems and the possibility of its application. This article presents face recognition algorithms for existing categories, including: empirical method; feature method – invariant feature; use the template specified by the developer for identification; study the method of detecting the system by external signs. The empirical method of “top-down knowledge-based methods” involves creating an algorithm that implements a set of rules that image segments must satisfy in order to be recognized as faces. Feature-invariant approaches (Feature-invariant approaches) based on bottom-up knowledge constitute the second group of face detection methods. The methods of this group have the ability to recognize faces in different places as an advantage. Use the template set by the developer for identification (template matching method). Templates definespecific standard images of face images, for example, describing the attributes of different areas of the face and their possible mutual positions. A method for detecting faces by external signs (a method for performing the training stage of the system by processing test images). The image (or its fragments) is somehow assigned a calculated feature vector, which is used to classify the image into two categories – human face/non-human face
ЕND-TO-END SPEECH RECOGNITION SYSTEMS FOR AGGLUTINATIVE LANGUAGES
Get PDFWith the improvement of intelligent systems, speech recognition technologies are being widely integrated into various aspects of human life. Speech recognition is applied to smart assistants, smart home infrastructure, the call center applications of banks, information system components for impaired people, etc. But these facilities of information systems are available only for common languages, like English, Chinese, or Russian. For low-resource language, these opportunities for information technologies are still not implemented. Most modern speech recognition approaches are still not tested on agglutinative languages, especially for the languages of Turkic group like Kazakh, Tatar, and Turkish Languages. The HMM-GMM (Hidden Markov Models - Gaussian Mixture Models) model has been the most popular in the field of Automatic Speech Recognition (ASR) for a long time. Currently, neural networks are widely used in different fields of NLP, especially in automatic speech recognition. In an enormous number of works application of neural networks within different stages of automatic speech recognition makes the quality level of this systems much better. Integral speech recognition systems based on neural networks are investigated in the article. The paper proves that the Connectionist Temporal Classification (CTC) model works precisely for agglutinative languages. The author conducted an experiment with the LSHTM neural network using an encoder-decoder model, which is based on the attention-based models. The result of the experiment showed a Character Error Rate (CER) equal to 8.01% and a Word Error Rate (WER) equal to 17.91%. This result proves the possibility of getting a good ASR model without the use of the Language Model (LM)
METHOD OF COORDINATION OF MOTION OF SWARM ROBOTIC SYSTEMS
Get PDFMaintaining a specific geometric pattern is essential in various applications where groups of autonomous robots must follow a given path. Proper organization of the geometric pattern can lead to several benefits such as cost reduction, increased system reliability, and efficiency while providing a reconfigurable and flexible structure of the system. Military missions and traffic systems are examples where maintaining certain geometric patterns are widely used. However, little is known about how to develop an effective algorithm that guarantees collision avoidance and obstacle avoidance while maintaining the geometric pattern. This paper presents an algorithm for movement with a certain geometric structure of a group of autonomous mobile robots that maintains the required geometric pattern and ensures the avoidance of collisions and obstacles. The proposed algorithm is behavior-based and utilizes a set of rules that allow the robots to navigate around obstacles and avoid collisions. The algorithm's performance is demonstrated through simulations in a variety of scenarios with different numbers of robots and geometric patterns. The algorithm proposed in this paper provides an effective solution for controlling a group of autonomous mobile robots to maintain a certain geometric pattern. The proposed algorithm has the potential to be utilized in numerous applications where multiple robots must work together to achieve a common goal while maintaining a specific formation. The use of behavior-based approach and obstacle avoidance rules ensures that the robots avoid collisions and obstacles while maintaining the required patter
COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORTMS TO IDENTIFY EXTREMIST TEXTS IN THE KAZAKH LANGUAGE
Get PDFThe article explores various models and methods employed in classifying text content with the aim of identifying destructive information within social networks. The study focuses on utilizing machine learning techniques, such as support vector machines, naive Bayes classifiers, random tree methods, decision tree, k-Nearest Neighbors algorithm, logistic regression, gradient boosting to identify extremist texts. The research findings showcase the effectiveness of these methodologies in the identification process.
The article also offers an overview of existing research, methodologies, and software products in the analysis of extremist texts, emphasizing the importance of case-based learning, deductive learning models, and automated data collection and analysis. Additionally, the article provides an overview of existing research, methods, and software products within the field of analyzing extremist texts. It highlights the significance of case-based learning and the use of deductive learning models, as well as automated data collection and analysis techniques. These approaches contribute to the overall understanding and detection of extremist content.
The article further discusses the relevance and future prospects of the presented research. It emphasizes the need to expand the corpus of documents studied, enabling a more comprehensive analysis of texts, including those in photo, audio, and video formats. The development of complex models for recognizing hidden extremist propaganda is also identified as a key direction for future work.
By addressing these areas of focus, the research presented in the article aims to advance the field of identifying and combating extremist content within social networks. The incorporation of advanced techniques and technologies is crucial to effectively detect and address the presence of such content in various forms and formats
DETERMINATION OF THE OPTIMAL CONTROLLABLE KEY INDICATOR OF CALL CENTER IN ORDER TO INCREASE EFFICIENCY FOR GENERATING INCOME
Get PDFThis paper focuses on call centers, which have become a common means of communication with potential customers in various companies. Specifically, this paper analyzes call center data and the importance of assessing key indicators for evaluating call center performance. The questions this paper addresses are the criteria for evaluating call center quality and the methods for analyzing call center data. Previous research has shown the significance of call centers as the "face of the company," with the quality of their work reflecting how efficiently a company will serve its customers ' requests in the future. The main goal of this paper is to fill a gap in previous research by identifying the main controlled key indicator for call center quality and to suggest ways to improve efficiency. By using analytical methods to examine call center data, this paper identifies the most important criteria for call center quality and provides recommendations for enhancing service quality.
The main findings of this paper show the importance of call center operator performance in determining call center performance which affects company revenue. By evaluating key indicators such as the number of operators, this paper demonstrates how call centers can reduce service costs and improve efficiency. During the analysis using call center data for two years, it turned out that the company had expenses 1/3 of the total amount of maintenance compared to the previous year, which is not effective in terms of economy. Operational planning has a direct impact on operators’ costs and the main cost component is the hourly cost of operators. If optimal planning turns out to be at least 10% better than the arrangement set in the call center, company will save a good amount. The significance of this paper lies in its potential to improve the quality of service in call centers and its contribution to the field of customer service management. By providing insight into the importance of call center efficiency, this research offers recommendations for predicting the optimal number of operators to improve the customer experience with reducing service costs
DEEP RECURRENT NEURAL NETWORKS IN ENERGY DEMAND FORECASTING: A CASE STUDY OF KAZAKHSTAN'S ELECTRICAL CONSUMPTION
Get PDFThe critical transformation of the energy sector demands innovative approaches to ensure the reliability and efficiency of energy systems. In this pursuit, this study delved into the potential of Deep Recurrent Neural Networks (DRNNs) for forecasting energy demand, using a comprehensive dataset detailing Kazakhstan's electrical consumption over a span of two years. Traditional statistical models have historically played a role in energy demand prediction, but the growing intricacy of the energy landscape calls for more advanced solutions. The paper presented a comparison of the DRNN with other traditional and machine learning models and highlighted the superior performance of DRNNs, especially in capturing complex temporal relationships.
The energy sector is confronting unprecedented challenges due to population growth and the integration of diverse energy sources, leading to increased demand and system strains. Accurate energy demand prediction is essential for system reliability. Traditional models, though widely used, often overlook intricate variables like weather patterns and temporal factors. Through rigorous methodology, encompassing exploratory data analysis, feature engineering, and hyperparameter optimization, an optimized DRNN model was developed. The results demonstrated the DRNN's exceptional capability in processing complex time-series data, as evidenced by its attainment of an R-squared value of 83.6%. Additionally, it achieved Mean Absolute Errors and Root Mean Squared Errors of less than 2%. However, there were noticeable deviations in some predictions, suggesting areas for refinement. This research underscores the significance of DRNNs in energy demand prediction, highlighting their advantages over traditional models while also noting the need for ongoing optimization. The findings underscore DRNN's promise as a robust forecasting tool, pivotal for the energy sector's future resilience and efficiency
INNOVATIVE DEVELOPMENT OF EDUCATIONAL SYSTEMS IN THE BANI ENVIRONMENT
Get PDFThe rapid advancement of technology and the ever-changing global landscape have presented unique challenges and opportunities for educational systems worldwide. The introduction of the BANI (Brittle, Anxious, Nonlinear, Incomprehensible) framework as a response to the volatile and unpredictable nature of contemporary environments has further emphasized the need for innovative approaches to education. This paper explores the innovative development of educational systems within the BANI environment, focusing on the integration of emerging technologies, pedagogical strategies, and learner-centred approaches. The paper begins by providing a comprehensive overview of the BANI framework and its implications for educational systems. It highlights the key characteristics of the BANI environment, including its inherent brittleness, anxiety-inducing nature, nonlinearity, and incomprehensibility. The formal model of interaction between projects and the BANI environment can assess innovation project value for future optimisation. Furthermore, it elucidates the potential consequences of neglecting to adapt educational systems to these volatile conditions, emphasizing the importance of innovation in education. Drawing upon recent research and theoretical frameworks, the paper explores various innovative approaches to educational development in the BANI environment. It discusses the integration of emerging technologies, such as artificial intelligence, virtual reality, and augmented reality, into teaching and learning processes. Moreover, it investigates the implementation of learner-centred development strategies that foster critical thinking, problem-solving skills, creativity, and adaptability. The paper addresses the role of educators and institutions in supporting innovative development within the BANI environment. It emphasizes the need for professional development programs that empower educators to leverage emerging technologies and implement learner-centred approaches effectively. Key management of innovative project principles in the BANI environment is defined in the paper. Additionally, it highlights the significance of collaboration among educational stakeholders, including policymakers, administrators, teachers, students, and parents, to foster an ecosystem that nurtures innovation in education. The paper discusses potential challenges and ethical considerations associated with the innovative development of educational systems in the BANI environment. It explores issues related to equity, privacy, data security, and the digital divide, emphasizing the importance of responsible and inclusive approaches to educational innovation. Contributes to the existing literature by providing insights and recommendations for the innovative development of educational systems within the BANI environment. By embracing emerging technologies, learner-centred pedagogies, and collaborative efforts, educational systems can better prepare learners to thrive in uncertain and rapidly changing contexts
USING A VIRTUAL TWIN OF A BUILDING TO ENSURE SECURITY IN EDUCATIONAL INSTITUTIONS
Get PDFThis research paper delves into the exploration of computer vision technology and digital twins as a means to enhance security measures in educational institutions. The study primarily focuses on the creation of a virtual replica of the first floor of a school and the integration of a person detection algorithm with the existing surveillance cameras. By leverag- ing the capabilities of the digital twin and real-time monitoring, comprehensive surveillance of the premises becomes feasible, resulting in simplified security operations. The paper sheds light on the significant potential of training neural networks for specific security tasks, such as the identification of weapons or the detection of anomalies in human behavior. These trained neural networks can be seamlessly integrated into the digital twin, thus ensuring public safety within the educational environment. The findings of this study provide substantial evidence for the effectiveness of computer vision technology and digital twins in bolstering security measures. The ability to create a virtual representation of the school’s first floor enables com- prehensive monitoring and surveillance, aiding in the prevention and prompt response to se- curity incidents. The integration of person detection algorithms further enhances the system’s capabilities by automatically identifying and tracking individuals within the premises. Addi- tionally, the deployment of neural networks for specialized security tasks adds an extra layer of protection, enabling the identification of potential threats and the detection of abnormal behavior patterns. By employing computer vision technology and digital twins, educational institutions can establish an advanced security infrastructure that optimizes monitoring, en- hances situational awareness, and ensures a safer environment for students, staff, and visitors. The research presented in this paper highlights the tremendous potential and practical impli- cations of these technologies in the realm of educational security
GESTURE RECOGNITION OF MACHINE LEARNING AND CONVOLUTIONAL NEURAL NETWORK METHODS FOR KAZAKH SIGN LANGUAGE
Get PDFRecently, there has been a growing interest in machine learning and neural networks among the public, largely due to advancements in technology which have led to improved methods of computer recognition of objects, sounds, texts, and other data types. As a result, human-computer interactions are becoming more natural and comprehensible to the average person. The progress in computer vision has enabled the use of increasingly sophisticated models for object recognition in images and videos, which can also be applied to recognize hand gestures. In this research, popular hand gesture recognition models, such as the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Support Vector Machine (SVM) were examined. These models vary in their approaches, processing time, and training data size. The important feature of this research work is the use of various machine learning algorithms and methods such as CNN, LSTM, and SVM. Experiments showed different results when training neural networks for sign language recognition in the Kazakh sign language based on the dactyl alphabet. This article provides a detailed description of each method, their respective purposes, and effectiveness in terms of performance and training. Numerous experimental results were recorded in a table, demonstrating the accuracy of recognizing each gesture. Additionally, specific hand gestures were isolated for testing in front of the camera to recognize the gesture and display the result on the screen. An important feature was the use of mathematical formulas and functions to explain the working principle of the machine learning algorithm, as well as the logical scheme and structure of the LSTM algorithm