Eastern-European Journal of Enterprise Technologies最新文献

{"title":"Construction of a neural network for handwritten digits recognition based on TensorFlow library applying an error backpropagation algorithm","authors":"Tetiana Filimonova, H. Samoylenko, A. Selivanova, Yurii Yurchenko, Alexei Parashchak","doi":"10.15587/1729-4061.2023.293682","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.293682","url":null,"abstract":"The object of this study is a neural network for recognizing handwritten digits based on the TensorFlow library using the backpropagation algorithm. The main problem addressed is the development of an effective model with high recognition accuracy. Working on such a task is important as it allows understanding how algorithms and models can effectively work with real data and helps improve machine learning techniques. It has been determined that after 20 training epochs, the loss function is 0.105, and the recognition accuracy is 0.976, comparable to human recognition capability. The classification report indicates that the model is effectively trained on training data and demonstrates high accuracy on test data, capable of generalizing information to new examples. Visualization of recognition results confirms that the model correctly recognizes even poorly written digits. The results can be explained by the peculiarities of the model architecture, optimal selection of hyperparameters, and successful use of the backpropagation algorithm, which was not explicitly specified during model training. TensorFlow provided a convenient toolkit for implementing the neural network and optimizing its parameters. As a result, the model has a fairly high accuracy in image recognition. A significant feature of the results is the high recognition accuracy achieved through the optimal model architecture, correct choice of hyperparameters, and effective use of the backpropagation algorithm. Unlike models built using Keras and convolutional layers, the research model quickly learns, which is important, and does not compromise on accuracy. This result was made possible by the above features of model construction. The results could be practically applied in the field of handwritten character recognition, especially in automated document classification systems, in banking recognition systems, and in other areas where the accuracy of handwritten character recognition is essential","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"52 28","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139151064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a neural network model for training data on the effects of phosphorus on spring wheat growth","authors":"Saltanat Sharipova, Akerke Аkanova, N. Ospanova","doi":"10.15587/1729-4061.2023.292849","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.292849","url":null,"abstract":"A neural network was developed to predict the effect of phosphorus on spring wheat yields. The focus is on the neural network, including its structure, parameters, training methods and results related to phosphorus effects on spring wheat yields. An algorithm for developing a neural network model is also presented. The study was conducted to address the critical need for developing a neural network to predict the effect of phosphorus on spring wheat yields in the Republic of Kazakhstan. For data analysis, input data were used that cover the period from 2012 to 2022, including climatic indicators, regional features and phosphorus application. The target variable is spring wheat yield. To ensure the accuracy of the study, the data were preprocessed and standardized, and an outlier and variance analysis was performed. The developed neural network was trained and tested to obtain the best results. The mean squared error was used as a metric for evaluating the quality of forecasting. Additionally, indicators such as mean absolute error and coefficient of determination were considered. The results of the study showed an MSE of 7.12, indicating that the model agrees well with the data and makes accurate predictions, which also suggests its practical relevance. The correlation analysis of the features showed that phosphorus application and spring wheat yield have a positive relationship. These results can be very useful for agriculture and farming enterprises, as they allow optimizing phosphorus application to the soil and increasing wheat yields","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"11 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139152032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a social-oriented inclusive business model for strategic enterprise renewal","authors":"A. Kramarenko, A. Kvitka","doi":"10.15587/1729-4061.2023.292500","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.292500","url":null,"abstract":"Research object is a business model of enterprises’ strategic renewal in the areas of economy, environmental friendliness, and sociality. Key problem: the need to develop a business model for strategic renewal of enterprises, maximally adapted to the current challenges of the market and society. Based on the prerequisites for the evolution of traditional corporate strategies to a stakeholder approach, a business model for strategic enterprise renewal has been formed. The relative nature of companies’ business activity, transformation of analysis methods and approaches to decision-making, as well as key elements, vectors, and results of interaction within the developed business model are determined and justified. The possibilities of practical application of a social-oriented inclusive business model in the implementation of business analysis are shown. Interpretation of the research results: the social-oriented business model of enterprises’ strategic renewal is developed on the basis of systematization of the relative approach, theories of stakeholders and corporate philanthropy, the concept of \"charitable corporation\" and orientation to socially inclusive value instead of traditional shareholder value. Along with the traditional economic aspect of the business model, the environmental and social aspects are outlined. To adapt business models of enterprises to modern challenges, it is proposed to increase the use of qualitative analysis parameters in the implementation of strategic decisions, as well as to design the development of relations with key stakeholders. Practical significance: Certain parameters of the business model can be used by enterprises to conduct a critical analysis of their own business strategies and develop effective measures to adapt them to modern challenges","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"279 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139152620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determining quality indicators for projects of information protection of information activity objects","authors":"Vladimir Lutsenko, D. Progonov","doi":"10.15587/1729-4061.2023.291616","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.291616","url":null,"abstract":"The design and analysis of the effectiveness of modern integrated information protection systems (IIPS) is complicated by the influence of the designer's subjective decisions regarding methods and means of protection, the need to determine the quality criteria for the functioning of the designed objects. The work is aimed at improving the technology of automated design of IIPS by determining the quality of projects. When creating a database (DB) of objects with such \"qualitative\" performance indicators of information protection systems, it is possible to compare existing and new protection objects and to adjust the protection projects of existing objects. Moreover, the ontological properties of active and threat-resistant objects are taken into account. To illustrate the use of the methodology for determining and comparing the quality of projects, an example of comparing the quality of projects obtained in different ways is given. One way currently operating involves the use of expert evaluation of the quality of protection projects for existing facilities. The second way is intended for objects defined as objects of protection of the general structure (OPGS) and involves a principally objective assessment of design quality using known quality diagrams and control of Ishikawa and Pareto design consequences. As a result of the given example, it was determined that the quality of projects according to quality diagrams and control of design consequences should increase by more than two times. The proposed method of comparing the quality of information protection projects for different objects or different protection projects of one object allows to improve the process of creating information protection projects. At the same time, it is possible to exclude the human controller from the process of determining the reliability of object protection. It also allows you to automate the design process, reduce the time and cost of design costs","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"65 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139151832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The filament winding method’s finishing process impact on high-fidelity specimens: homogenity of density, fiber volume fraction, outer surface roughness and tensile strength","authors":"Herry Purnomo, T. Soemardi, Hendri D.S. Budiono, H. Wibowo, M. Ibadi","doi":"10.15587/1729-4061.2023.288025","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.288025","url":null,"abstract":"Filament winding is a widely used method for producing tubes and pressure vessels from composite materials. However, overlapping of fibers during the winding process can lead to rough surface and increased voids in the finished product. To improve the quality of CFRP materials produced through filament winding, the structure is cured either at room temperature or in an oven with a controlled heat profile, depending on the type of resin used. Various finishing techniques, including shrink tape, compression molding, and vacuum compression molding, have been attempted to improve the quality of the specimen. Among these techniques, vacuum compression molding has been found to deliver the best results in terms of surface roughness, with average roughness (Ra) values of 0.35 μm in the fiber direction and 0.61 μm in the transverse direction. This level of roughness is comparable to that achieved through milling machine manufacturing. Moreover, this technique ensures uniformity in fiber composition and volume fraction, achieving a homogeneous density of 1364.49 kg/m3 and the highest fiber volume fraction of 63 %. As a result, remarkable mechanical attributes, such as a tensile strength of 926.07 MPa and a stiffness of 21.35 GPa, can be obtained. In addition, by utilizing various finishing techniques, the tensile strength of these properties can be increased by up to 80 %. CFRP is a versatile material with unique characteristics, and selecting appropriate finishing techniques such as vacuum compression molding can significantly enhance its overall quality and mechanical properties. However, one drawback of the filament winding method is the poor outer surface finish which can be improved by vacuum compression molding","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"65 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139153296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing the optimal chemical composition of heat-resistant Cr-Ni steel for aerospace equipment","authors":"V. Mishchenko, Alona Kripak, D. Tonkonoh","doi":"10.15587/1729-4061.2023.288224","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.288224","url":null,"abstract":"The object of research in this work is the processes of forming the microstructure and mechanical properties of heat-resistant steels depending on their chemical composition. The microstructure and high-temperature mechanical properties of austenitic heat-resistant chrome-nickel steels of the proposed chemical composition were investigated in the work. The microstructure study determined the grain size and topography of inclusions in steels. Based on the results of mechanical tests, a multifactorial experiment was planned, which made it possible to establish the relationship between the mechanical properties of steels with alloying elements selected as factors. The obtained regression equations were used to estimate the quantitative influence of each alloying element on the corresponding mechanical properties. Analysis of the results of the experiment made it possible to determine the optimal chemical composition of steel for gas turbine engines used in the aerospace industry, as well as in the metallurgy of titanium production. It is shown that the state of solid solution and heat-resistant niobium and molybdenum carbides (chromium carbides dissolve at a temperature of 950 °C) are an important factor that significantly affects the structure, mechanical, and service properties of heat-resistant steel. The austenite structure is provided by the required amount of nickel. The resulting indicators of heat resistance of steels of different compositions, tested at temperatures of 850 °C, 950 °C, and 1050 °C, proved the superiority of steel with a higher content of carbon and chromium and a lower content of nickel. The mechanism of steel strengthening and the influence of alloying with carbon, chromium, and nickel on it have been determined. The optimal chemical composition of heat-resistant steel on an iron-nickel basis for operation at a temperature of 950 °C has been established","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"127 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139152920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of barium hexaferrite core–shell composites as high-performance microwave absorption by optimizing hydrothermal synthesis","authors":"E. Yustanti, A. Noviyanto, Annisa Nur Fauziah, Bachtiar Lubis, A. Trenggono, A. Taufiq","doi":"10.15587/1729-4061.2023.291064","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.291064","url":null,"abstract":"In conjunction with the enhancement of societal living standards and the rapid development of information technology, an extensive variety of high-capacity electronic devices are being introduced to the market. The heightened demands result in the generation of electromagnetic wave radiation, which poses a potential risk to human well-being. Barium hexaferrite (BHF) is one of the radar-absorbing materials (RAMs) that can absorb electromagnetic waves because it has a high anisotropic field. However, its drawbacks are narrow absorption and less stability. Molybdenum disulfide (MoS2), is the best candidate for the reinforcement of BHF. The study investigated the impact of increasing the thiourea, temperature, hydrothermal holding time, and sample thickness on reflection loss. This study used a two-step molten salt and hydrothermal synthesis to make a BaFe12O19@MoS2 core-cell composite. Two-step molten salt and hydrothermal synthesis methods created single-phase BaFe12O19@MoS2 core-cell composites that worked well. The results showed that adding MoS2 to BHF changed BHF's magnetic properties from hard to soft. Increasing the hydrothermal temperature up to 220 °C effectively reduced the reflection loss of BaFe12O19@MoS2. On a 2 mm thick sample containing 100 mmol thiourea, the study achieved an electromagnetic wave absorption of 99.97 % with a reflection loss of –35.41 dB (17.37 GHz). The results of this research can be applied to protect electronic devices vulnerable to signal interference from satellite radar systems at frequencies of 12–18 GHz","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"23 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139153836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Fe-13.8Cr-8.9Mn alloy for steel biomaterials","authors":"R. Kartikasari, A. Subardi, Rivan Muhfidin, Ihwanul Aziz, M. Effendy, Triyono Triyono, K. Diharjo","doi":"10.15587/1729-4061.2023.293009","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.293009","url":null,"abstract":"Traumatic, osteoarthritic, tumoral, and congenital bone issues impact human lives and health. The next generation of bone implants is made from biodegradable materials, including Fe-based materials with superior mechanical properties and high biocompatibility. However, efforts to inhibit the risk of inflammation and bacterial infection due to the biological response and corrosion properties of metals are a significant challenge.  This study aims to develop biomaterials based on Fe-Cr-Mn alloys to obtain superior physical and mechanical properties through plasma nitriding. Each sample was plasma-nitridated in a vacuum chamber at various temperatures of 250–450 °C for 3 hours at a pressure of 1.8 kPa. Several main tests were performed to investigate the effects of plasma nitriding, such as the chemical compositions of raw material, surface nitrogen contents, phase changes, thickness, hardness, and corrosion. Those parameters were then used to evaluate plasma nitriding's effectiveness, including observing the change in phenomena at each temperature treatment. The results indicated that forming the S phase on the surface of Fe-13.8Cr-8.9Mn alloy is a saturated solution of nitrogen in ɣ-Fe, where the nitrogen content on the surface increases with increasing nitriding temperature. The layer's surface hardness is uniform across its whole thickness, which reduces as the grade of raw material passes through the nitride layer. The highest hardness at a nitriding temperature of 450 °C reached 625.3 VHN. The findings showed that the corrosion rate decreased significantly, reaching the lowest value, 0.0018 mm/year, at a plasma nitriding temperature of 450 °C. Plasma nitriding could enhance the physical and mechanical properties of Fe-Cr-Mn alloy","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"39 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139153387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of recurrent neural networks for price forecasting at cryptocurrency exchanges","authors":"Victoria Tyshchenko, Svitlana Achkasova, Oleksii Naidenko, Serhii Kanyhin, Vlada Karpova","doi":"10.15587/1729-4061.2023.287094","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.287094","url":null,"abstract":"The study focuses on improving the quality of using recurrent neural networks (RNNs) to predict cryptocurrency prices. The formula of the target variable for the model based on the arithmetic mean is developed, which allows us to better take into account the dynamics of cryptocurrency exchanges. The factors affecting this variable were grouped into features based on the volume of daily cryptocurrency trading, the volatility of the relevant prices, and the pre-calculated and selected signals of technical indicators. As part of the study, an algorithm for processing daily data was developed for the model. The results obtained made it possible to create a holistic model for forecasting stock prices. Two recurrent neural networks were trained: one with a long short-term memory (LSTM) and the other with a recurrent gate unit (GRU). To determine the efficiency of the models, the analysis was carried out using two key indicators: the Sortino coefficient, which measures the relative risk/reward for each additional unit of unwanted volatility, and the Sharpe ratio, which measures the return on assets, subtracting the free risk. As a result, it was found that both models have similar results in terms of accuracy (~69 %). Still, the GRU-based model showed significantly better values of the Sortino coefficients (3.13) and Sharpe’s coefficient (2.45), which allows us to conclude that it is effective on cryptocurrency exchanges. At the same time, the LSTM model requires more parameters for training than the GRU model with an identical structure, which leads to a longer training time. The obtained scientific and practical results are aimed at more efficient use of recurrent neural networks in price forecasting on cryptocurrency exchanges","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135977851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing the technological modes of lamination of digital prints","authors":"Svitlana Havenko, Anna Dovhanych","doi":"10.15587/1729-4061.2023.288518","DOIUrl":"https://doi.org/10.15587/1729-4061.2023.288518","url":null,"abstract":"The intensive use of lamination technology for the decoration of printing prints made by various printing techniques, as well as a wide range of films, require solving an urgent problem – optimization of influencing factors to ensure the quality of laminated products. The objects of research were prints of inkjet and laser printing on paper, photo paper, and cardboard. A glossy film based on bio-oriented polypropylene BOPP was used for lamination. Studies of densitometric indicators of prints after lamination confirmed an increase in optical density by 0.28 units. This is especially true for inkjet prints. However, after lamination, all digital prints showed a tendency to improve colorimetric characteristics, namely an increase in the brightness of CMYK colors. The relationship between the technological regimes of lamination (speed and temperature) and the strength of the laminates, estimated by breaking and pressing forces, was established. To describe the dependence of the laminate strength on the temperature and speed of lamination, polynomial models were built that reproduce the values of the breaking and pushing forces of the laminate with satisfactory accuracy. The selected algorithm for calculating the parameter values of these models is based on the application of the Chebyshev approximation of the functions of many variables. The optimization models built will allow, if necessary, for making corrections in the technological process of laminating printing prints to ensure the predicted required quality and strength of laminates.","PeriodicalId":11433,"journal":{"name":"Eastern-European Journal of Enterprise Technologies","volume":"150 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135978018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}