Scientific Journal of Astana IT University
Not a member yet
250 research outputs found
Sort by
FORECASTING ELECTRICITY CONSUMPTION: CASE STUDY IN ASTANA
Get PDFThis paper presents time series forecasting models Forecaster Autoreg and Neural Network for predicting electricity consumption in the city of Astana. Given the limited natural resources and the need to reduce the impact on the environment due to global climate change, energy efficiency remains an urgent problem requiring the search for scientifically sound and effective solutions. One of the ways to address this problem is the use of machine learning methods to predict electricity demand. In this study, a time series dataset was explored containing data on electricity consumption (measured in MW) in the city of Astana during the period from January 1, 2020 to December 31, 2020 in an hourly interval. These data were used to utilize a model that predicts the electricity demand for the next day with an accuracy of every hour. To improve the accuracy of forecasting, additional factors such as air temperature and wind speed were included. This is since Astana experiences a sharply continental climate and high windiness. Including these factors allows for accounting for their influence on the electricity demand and thus achieving more accurate forecasting. A neural network model was utilized for this purpose, as it can uncover complex dependencies and patterns in the data, thereby aiding in achieving more precise predictions of electricity consumption. The accuracy and reliability of forecasts were evaluated by error indicators such as Average Absolute Error (MAE) and Average Absolute Percentage Error (MAPE), and the results showed that the models can provide accurate forecasts with low errors
INFORMATION-LOGICAL MODEL OF EDUCATION OPTIMIZATION IN REMOTE MODE
Get PDFThe educational optimization process is widely researched in the theoretical aspect. Analyzing existing sources made it possible to highlight the research issues: the need to create an optimizing distance studying model, in which work with weaker students becomes possible both within the educational process and in individual or group independent work. The study aims to develop an information-logical model for optimizing distance studying. This model should provide for the learning process organization in such a way as to strengthen the weaknesses of students, reveal their potential and focus on the comprehensive development of knowledge and skills. The task formalization is carried out using the Hungarian algorithm and Boolean variables. The main work limitation is the operation with integers. Discreteness manifests itself already at the modelling stages in many problems, for example, when working with Boolean variables. An example with the most straightforward information model construction using the logical functions "true/false" with the transition to a chain of matrices is given. It demonstrates the studying optimization algorithm and presents an expanded information-logical model. The presented model was preliminary tested in one of the academic groups of the S. Seifullin Kazakh Agro Technical Research University. Students' knowledge inspections were carried out at the approbation beginning. Then a student group working on a student project was divided into subgroups according to the algorithm. The knowledge inspection showed an 11.3% improvement in results at the work's end. Further research on this topic may consist of expanding the presented model's capabilities and developing appropriate modules for knowledge control and algorithmization of related tasks
SYSTEMATIZATION OF INTERNATIONAL AND DOMESTIC EXPERIENCE IN PROJECT MANAGEMENT AIMED AT ADAPTING PUBLIC-PRIVATE PARTNERSHIPS TO THE IMPLEMENTATION OF SUSTAINABLE ENERGY DEVELOPMENT PROGRAMS
Get PDFEuropean countries are recognized leaders in the use of public-private partnerships in project management for large-scale infrastructure projects, including those that contribute to energy efficiency in various sectors of the economy. Their experience is a useful example for Ukraine in its quest for energy independence and economic stability. Establishing partnerships with business will increase the resources of the state and promote the involvement of the private sector in the implementation of profitable and image projects for both stakeholders. The development of mechanisms and recommendations for the development of public-private partnership (PPP) should be preceded by an analysis of international experience in creating a favorable and attractive environment in which public-private partnerships can be intensified. Since energy efficiency is the key to the successful functioning of the economy of any state, it is necessary, creating the conditions for the successful functioning of public-private partnership,to develop programs and projects to improve energy efficiency, which will be implemented under the PPP on a priority basis
PERFORMANCE COMPARISON OF NEURAL NETWORKS IN GRAVITATIONAL LENSING DETECTION
Get PDFA gravitational lens is a distribution of matter, such as dark matter halos, galaxies, or quasars, between a distant light source and an observer that can bend the light from the source as the light travels toward the observer. Nowadays, it is slightly complicated to identify gravitational lenses without powerful computing devices and groups of scientists working together. In addition, future surveys will have orders of magnitude more data and more lenses to find. With up-to-date algorithms such as neural networks, detecting and classifying them for a single human being will be possible. The neural networks described in this paper make the first steps in that direction. The primary purpose of this work was to develop three different neural networks and determine which one could detect gravitational lensing more quickly and precisely. For training, testing, and validation we used a dataset of 2000 images. Half of these images were downloaded from Bologna Lens Factory, a database of simulated gravitational lenses based on galaxies lensed by galaxies (i.e., no clusters and no quasars). We simulated the second half of the images using Python-based code to simulate mock strong lensed galaxies. We used Python-based code to mock strong lensing with different source parameters. Next, we built three types of artificial neural networks and compared their efficiency. Firstly, we developed a fully convolutional neural network (CNN) and a fully connected neural network (FCNN). The third neural network was a combination of these two approaches. In this algorithm, the FCNN layer replaced the last layer of CNN. Next, we compared the learning rates of these algorithms and applied all neural networks to validation images. As a result of the study, we determined which of the developed neural networks fit better for searching gravitational lenses.
DEVICE FOR DETERMINING THE VALUE OF THE STEADY-STATE ELECTRICITY IN THE PRIMARY CIRCUIT USING A REED SWITCH AND A MICROPROCESSOR
Get PDFThis article discusses an innovative device designed to determine the value of the steady-state current in the primary circuit of electrical installations using reed switches and a microprocessor without the use of current transformers. The typical structure of relay protection devices is considered. The main elements are presented. When choosing a primary converter, a reed switch was taken, because it has certain advantages over current transformers. As part of the research, experimental installations for measurements were assembled. They made it possible to emulate the real conditions in which the relay protection devices have to function, unnecessary and to depict the characteristics of future devices. The code is presented that allows the microprocessor device to function according to the laid down algorithm. A device on a reed switch and a microprocessor is presented, whichallows transmitting a certain amount of current in the primary circuit in digital form (binary code) to the microprocessor protection. The presented measuring device made it possible to implement a method for determining the magnitude of the steady-state short-circuit current
A DEEP LEARNING MODEL FOR PNEUMONIA DETECTION FROM X-RAY IMAGES
Get PDFThe World Health Organization estimates that more than four million deaths oc- cur annually due to pneumonia and other diseases associated with air pollution, and the lat- est COVID-19 virus has dramatically increased the percentage of pneumonia cases. Over 150 million people get infected with pneumonia on an annual basis, especially children under 5 years old. There’s also a global shortage of radiologists in both developing and developed countries. Over 2/3 of people on earth do not have access to radiologists. According to the Association of American Medical Colleges, the U.S. is projected to have a shortage of 17,000 to 42,000 radiologists by 2033. Currently, the development of artificial intelligence and machine learning technologies, as well as the accumulation of large volumes of medical images, make it possible to create automated systems for analyzing medical images. The article presents a simple sequential model based on deep learning methods (convolutional neural networks) that helps detect pneumonia. X-ray images of the Women’s and Children’s Medical Center in Guangzhou were used for the model. The development of the pneumonia diagnostic program was carried out in Python. Training the neural network took 26 minutes and 12 epochs. The results obtained in the test data are: recall: 96%; precision: 92%; accuracy: 92%; and f1: 94% for pneumonia cases. This is no less than the result proposed in many popular works. The mod- el significantly reduces the burden on radiologists, helps them make decisions and save time, allows them to evaluate the quality of their work, and reduces the likelihood of medical errors
REALISATION OF MPC ALGORITHM FOR QUANSER QUBE-SERVO
Get PDFThis paper offers an in-depth look into the design and implementation of a Model Predictive Control (MPC) algorithm for the QUANSER QUBE-SERVO system. The QUBE-SERVO is a sophisticated laboratory experimental setup consisting of a servo motor, an encoder, and a rotary module. This combination provides a robust platform for investigating and testing various control strategies. In particular, the central focus of this study is the usage of the MPC algorithm for controlling the position of the QUBE-SERVO’s rotary disc load module.
The MPC algorithm plays a pivotal role in this application by predicting the future behaviors of the system, and controlling the system by minimizing an objective function over a defined finite horizon. This makes it a versatile and effective tool for controlling complex systems.
One of the key challenges in practical control applications is maintaining system stability in the presence of disturbances and uncertainties. To this end, we propose a MPC algorithm designed specifically to stabilize the QUBE-SERVO under such conditions. The functionality of this algorithm is not limited to the QUBE-SERVO system alone, and can be extended to other control systems exhibiting similar characteristics.
The effectiveness of the proposed MPC algorithm is rigorously tested through simulation studies. These studies involve subjecting the QUBE-SERVO to various reference signals and disturbances. The results of the simulations provide strong evidence of the algorithm’s capability to effectively track reference signals, while also rejecting disturbances and uncertainties, thereby corroborating its efficacy for the QUBE-SERVO application.
Moreover, the original MPC algorithm was enhanced to improve its performance for trajectory tracking tasks. We also discuss the integration of the MPC algorithm within the MatLAB and LabVIEW programming environments, which served as the base platforms for designing and running the simulations in this project.
This paper, therefore, presents a comprehensive and practical approach for the successful implementation of the MPC algorithm in the QUANSER QUBE-SERVO system, and demonstrates its potential for wider application in similar control systems
METHODS OF NAVIGATING ALGORITHMIC COMPLEXITY: BIG-OH AND SMALL-OH NOTATIONS
Get PDFThis article provides an in-depth exploration of Big-Oh and small-oh notations, shedding light on their practical implications in the analysis of algorithm complexity. Big-Oh notation offers a valuable tool for estimating an upper bound on the growth rate of an algorithm's running time, whereas small-oh notation delineates a lower limit on this growth rate. The piece delves into a comprehensive examination of various complexity classes that emerge through the application of Big-Oh notation, underscoring the significance of small-oh notation as it complements and enriches complexity analysis.
In the realm of programming and computer science, the employment of these notations holds paramount importance. They empower developers and researchers to make informed decisions regarding algorithm selection and optimization. It is crucial to recognize that while complexity analysis is a vital facet of effective programming, ongoing research endeavors may yield more refined methodologies and approaches within this domain.
By understanding and harnessing the power of Big-Oh and small-oh notations, professionals can effectively evaluate algorithm efficiency and scalability. This knowledge equips them with the ability to design and implement algorithms that meet specific performance criteria, which is pivotal in the ever-evolving landscape of technology and computation. As pushing the boundaries of what is possible in the field of algorithm design is being continued, these notations remain invaluable tools for navigating the complex terrain of algorithmic analysis and optimization.
By embracing Big-Oh and small-oh notations, professionals can finely assess algorithmic efficiency, ensuring they meet performance criteria in the evolving technological landscape. These notations remain indispensable for algorithmic analysis
DEVELOPMENT OF A LINEAR REGRESSION MODEL BASED ON VEGETATION INDICES OF AGRICULTURAL CROPS
Get PDFThe article is devoted to the study of vegetation indices for assessing the productivity of agricultural crops of the North Kazakhstan Agricultural Experimental Station (NKAES) LLP. The research was carried out using a modern software package for processing satellite images, EOS Land Viewer. The work used images from the Landsat 8 (USA) and Sentitel 2 (European Space Agency) spacecraft. Digitized Earth remote sensing data for the last 3 years are presented, showing changes in the amount of moisture reserves on the territory of NKAES LLP. Time series of distribution of the studied coefficients were constructed according to different phases of active vegetation biomass in the study area. The resulting time series made it possible to identify annually repeating patterns, a linear trend of increasing and decreasing NDWI and NDVI on the territory of the NKAES LLP.
Review of studies over the past 5 years, published in highly rated foreign journals, on various vegetation indices, including indices designed to assess moisture content in vegetation and soil. It is noted that the first normalized water index, NDWI, using the SWIR infrared channel, unlike the widely used NDVI vegetation index, actually penetrates 80% of the atmosphere.
Analysis of the obtained NDWI allowed us to identify dry, moderately dry and fairly humid periods on the territory of the NKAES LPP from 2020 to 2023. Based on the research carried out, the feasibility of using normalized difference water indicators and normalized vegetation indices for further use in forecasting yields in the conditions of the North Kazakhstan region is substantiated. Next, using vegetation indices and additional agrometeorological factors, a linear model for predicting crop yields was developed. The coefficient of determination of the resulting model is 0.90 which indicates that the selected trend line reliably approximates the process under study
SYSTEMATIC DATA PROCUREMENT IN AN OWL-EMBEDDED INFORMATION AND ANALYTICAL FRAMEWORK FOR THE MONITORING OF WATER RESOURCES IN THE ILE-BALKHASH BASIN
Get PDFThe world is facing an escalating water shortage crisis, with dire consequences for ecosystems, human health, and socio-economic development. This article explores the multifaceted nature of the water shortage problem of Ile-Balkhash basin that falls under the jurisdiction of the Balkhash-Alakol Republic of Kazakhstan, its underlying causes, and the complex web of challenges it presents. The predicament in the Ile-Balkhash basin is a complex interplay of various factors. Climate change has led to erratic precipitation patterns, exacerbating the problem. The simultaneous rise in population places additional stress on the already limited water resources. Moreover, inefficient water management practices have perpetuated the issue, hindering the equitable distribution of water. The challenge of conducting a comprehensive basin analysis is a formidable task due to the numerous variables and indicators involved. It demands an enormous amount of time and effort. To address this issue, a web application framework integrated with the Web Ontology Language database, allowing for the execution of advanced queries to extract valuable insights from various objects and indicators, has been developed. The database underpinning this system is meticulously compiled, drawing upon data from the Hydrological monitoring of water bodies and the National Hydrometeorological Service of the Republic of Kazakhstan. These sources provide critical data that forms the bedrock of the analysis. Recognizing the importance of data storage and management in this endeavor, integrated components have been established. These components play a pivotal role in structuring the diverse data sources and maintaining their currency. The water shortage issue in the Ile-Balkhash basin serves as a stark reminder of the urgency with which such crises must be addressed. The tools and methods offer hope and underscore global water management sustainability