Дисертації | Dissertations

The dissertation is devoted to the development of models, methods, and tools for data processing aimed at monitoring crop yields and integrating with Geographic Information Systems (GIS). As the global population grows, so does the need for food. Efficient agriculture can produce more food per unit of land, ensuring food security for an increasing number of people. Yield monitoring in the context of project management in agriculture is crucial for enhancing its efficiency. This process allows farmers to analyze the impact of various agronomic factors, such as soil type, fertilizer use, and water availability, on crop yields, facilitating resource optimization and reducing environmental impact. Moreover, monitoring is a critical tool for developing effective strategies for managing agricultural projects. Project management is becoming increasingly widespread in agriculture, as it promotes effective organization and management of agricultural projects, enhancing their productivity and profitability. In this context, yield monitoring serves as a fundamental tool for project management, providing valuable information for making informed decisions, planning, and controlling the execution of agricultural projects. Identifying the impact of external and internal factors on yield allows project managers to adapt strategies and optimize resources, ensuring the resilience and efficiency of agricultural initiatives. Thus, integrating project management in agriculture, supported by effective monitoring, opens new opportunities for enhancing productivity, adapting to climate change, fostering innovation, and achieving global food security. Therefore, scientific research on yield monitoring not only contributes to improving the productivity and efficiency of agricultural practices but also plays a key role in ensuring food security, sustainable development, and economic well-being on a global scale. This work addresses a critical task: the development of information technology that includes mathematical models, methods, and procedures for yield monitoring based on geoinformation data (scientific component), as well as the development of a yield monitoring information system that enables the automation of data collection, processing, and utilization of geoinformation data for yield forecasting (practical component). The object of the study is yield monitoring. The subject of the study is models, methods and information technology of yield monitoring based on interaction with Geographic Information Systems. The study aim is to develop models, methods and data processing procedures necessary for yield monitoring. Research Methods. The conducted research is based on methods of systems analysis, technical analysis, artificial intelligence, big data processing, and object-oriented programming. Scientific novelty of the obtained results: • For the first time, an integration model of artificial intelligence for yield monitoring has been developed, based on the combination of multispectral images and geoinformation data. This model integrates Convolutional Neural Networks and Recurrent Neural Networks to enhance the accuracy and sensitivity of monitoring. • The mathematical model of the relationship between phenological indicators and crop yields has been improved. Unlike other models, this combined model includes an adaptive threshold method for determining the membership of crop pixels and identifying the trend and seasonal components of the phenological indicators' time series. This improvement enhances the accuracy of forecasting. • The information technology for yield monitoring based on geoinformation data has been improved. The enhancement involves the use of a combined model of the relationship between phenological indicators and crop yields, as well as an integration model of artificial intelligence. Unlike other technologies, the developed technology takes into account a wider variety of data, which simplifies integration with Geographic Information Systems (GIS). • The methods for representing and storing geoinformation data have been further developed in terms of correlating key properties of agricultural objects with aerospace images of the locality. • Information technologies for project management have further developed in the aspects of monitoring and forecasting yields and integration with geographic information systems. The first chapter, an analysis of the scientific literature was conducted, which established that the use of digital images of geographical areas and the development of Geographic Information Systems (GIS) are becoming key in modern agriculture. This facilitates effective management of cultivated areas, analysis, and prediction of yields, especially in the context of the increasing demand for food against the backdrop of a growing global population. The advancement of technologies provides new opportunities for intensification and optimization in the agricultural sector. It was also established that neural networks are effective tools for yield prediction. They can model complex nonlinear dependencies in agronomic data and process satellite imagery and remote sensing data. It was discovered that no existing service or software combines all the necessary capabilities for crop area management: anomaly detection, identification of phenological changes, and yield estimation. It is shown that a crucial task is to create specialized software that would allow uploading and working with large archives of images and would have built-in methods for intelligent data processing and pattern recognition. The second chapter describes the use of aerospace imagery and time series analysis of images to determine phenological indicators and other important growth and health indicators of plants. The importance of using the NDVI index as a key indicator for assessing plant cover and yield is emphasized. An approach to data processing and analysis within the context of Geographic Information Systems is considered. The vast volume of geographical data requires reduction for computational processing. The chapter also covers the structure and organization of geodata in vector and raster formats, revealing their unique capabilities and limitations for representing and analyzing geographic information models. A conceptual model of the GIS for agricultural monitoring was developed. The system development is divided into four stages: defining objectives, describing functionality, implementation, and diagnostics. Each stage includes steps that facilitate the creation of an effective system for monitoring and managing agricultural crop yields. The importance of a systematic approach to the creation and use of Geographic Information Systems in agriculture is established. The third chapter describes a mathematical model of the relationship between phenological indicators and the yields of agricultural crops and biomonitoring, which considers multispectral field images for dynamic yield forecasting. The decomposition of phenological indicators into trend, seasonal, and random components is aimed at effective yield monitoring. The model includes image binarization steps to define crop areas using a threshold function and the Otsu method for selecting the optimal threshold value. The process of creating and training a hybrid neural network, integrating image data and soil information for yield prediction, is described. The network architecture includes convolutional neural networks (CNN) for image processing and fully connected layers for soil data analysis. This integration allows the network to consider diverse information, enhancing its ability to accurately predict yields. In the second phase, the network uses recurrent neural networks to analyze data sequences, adding the ability to account for temporal dependencies and context. The fourth chapter describes the development of a GIS-based yield monitoring information system to enhance the efficiency of the agricultural sector. The system's modular structure includes modules for data collection, storage, processing, visualization, and analysis, including the use of machine learning for forecasting and process optimization. An algorithm for implementing an artificial intelligence integration model for yield monitoring based on the combination of multispectral images and geoinformation data is described, which includes seven stages: data collection and preparation, neural network development, testing and validation, optimization, implementation in agricultural systems, and further analysis of results. Practical significance of the obtained results. The main scientific provisions of the dissertation have been elevated to the level of methodological generalizations and applied tools, enabling yield monitoring. The agricultural crop yield monitoring information system was validated through comparative analysis methods. Comparing the yield predictions for winter wheat, corn, and barley in the Chernihiv region for 2019 with the predictions using the WOFOST simulation model and data from the State Statistics Service of Ukraine for 2019 shows that the monitoring model can provide sufficiently accurate yield forecasts. It was established that yield is significantly determined by plant development in the first three months after emergence, highlighting the importance of monitoring during this period. The obtained practical results emphasize the potential and limitations of using yield monitoring information technology with Geographic Information Systems. The main provisions and results of the research have been implemented and applied in the activities of Yancheng Polytechnic College.

The dissertation is devoted to constructing methods, models and information technology for forming, evaluating and selecting diversification strategies for construction enterprises in conditions of uncertainty. The developed methods and models can be used to solve the current scientific and practical task of increasing the management efficiency and profitability of construction enterprises in conditions of insufficient information under the influence of technological, economic, political, social and other external factors, the consequences of which cannot be predicted. One of the methods that allow solving this problem is the diversification of the activities of construction enterprises. The relevance of the task of diversification for construction enterprises is based on several key factors. The first factor is the demand for the development of the construction industry in conditions of rapid economic growth in countries with favorable conditions. Rapid economic growth is manifested in an increase in the country's GDP, an improvement in the population's standard of living, an increase in employment, the development of infrastructure, an increase in the volume of trade and foreign investment, etc. The People's Republic of China is known for its impressive economic growth over the past decades. This achievement was possible due to the rapid pace of industrialization, an export-oriented approach to the economy, and the comprehensive implementation of reforms. Diversification can help businesses use their resources, such as human resources, equipment, and technology, more efficiently by expanding their applications in different markets or industries. Diversification can give a construction company a competitive advantage, providing it with a more flexible and adaptive business approach that will expand the range of services to meet the needs of different customers. However, the construction industry is known for its high vulnerability to economic fluctuations and changes in the market situation, economic situation, political turbulence and conflicts. That is why, in these conditions, several unresolved issues arise. More studies need to be conducted regarding including a separate diversification center in the company's organizational structure, whose activities aim to form, evaluate, and choose the company's diversification strategies. Also, in the case of horizontal integration, the influence of the choice of construction technologies and the choice of the values of the technical and economic parameters of construction on the choice of the diversification strategy of the construction enterprise has yet to be clarified. There needs to be sufficiently reliable methods of evaluating and selecting diversification strategies that would provide an opportunity to increase the profitability of construction companies. The creation of methods and models for forming, evaluating, and selecting diversification strategies for construction enterprises will increase their productivity and profitability and expand theoretical and practical developments in this direction. Therefore, this dissertation solves an important task, namely, the development of models, methods and information technology for choosing rational strategies for the diversification of construction companies, which is characterized by taking into account changes in the structure of organizational environments of companies and organically combines the entire range of activities of companies in conditions of uncertainty ( scientific component). Automating the evaluation and selection of diversification strategies is also solved. The developed methods and models are integrated into the relevant information technology (practical component). The object of the study is the processes related to the evaluation and decision-making regarding the choice of diversification strategies for construction companies in uncertain conditions. The subject of the research is the methods, models and information technology of managing the activities of construction companies in terms of forming, evaluating and choosing rational diversification strategies in conditions of uncertainty. Research methods. The research is based on knowledge presentation and processing methods, evaluation methods, monitoring of construction companies and their organizational structures, object-oriented programming, project management. The study aims to develop methods, models, and information technology for evaluating and choosing diversification strategies for construction companies to manage their activities in uncertain conditions. The scientific novelty of the obtained results: • for the first time, a model for choosing rational diversification strategies of construction companies is described based on an expert assessment of the technical and economic parameters of construction, which takes into account the most significant indicators and allows taking into account the advantages of participants in the construction process. • the method of evaluating diversification strategies of construction companies has been improved, which is distinguished by taking into account changes in the structure of organizational environments of companies, which is characteristic of conditions of uncertainty and allows to increase the efficiency of their management. • the method of forming diversification strategies has been improved, which takes into account the analysis of information about the activities of construction companies based on engineering and the concept of open sources, which is used to create a list of alternatives in the task of choosing rational strategies for the diversification of companies and allows expanding their management capabilities; • improved information technology for evaluating and choosing diversification strategies of construction companies in conditions of uncertainty, which is distinguished by taking into account the technical and economic parameters of construction and the advantages of participants in the construction process and allows expanding management capabilities and rationalizing the choice of diversification strategies of construction companies. • received further development of the conceptual presentation of the structural model of the organizational environment of construction companies, which takes into account the diversification of their activities and is distinguished by the fact that it organically combines the entire range of activities of project- oriented companies in conditions of uncertainty. The first chapter describes the peculiarities of the diversification of construction enterprises, the main concepts, types of diversification, and the possible effects of the diversification of activities. The relevance of the development of the construction industry and the diversification of the activities of construction companies are substantiated. The possible consequences after the diversification of the construction industry are characterized by conditions of uncertainty and risk: more effective use of human resources, equipment and technologies, risk reduction, intensification of post-war reconstruction (in Ukraine), an increase in the level of development of infrastructure, manufacturing and housing construction in countries with rapid economic growth (especially in the People's Republic of China). The well-known methods of multi-criteria decision-making are described, which motivate the application of decision-making strategies in the conditions of formation and evaluation regarding the diversification of the activities of the construction enterprise. It is indicated that since diversification strategies can have a significant number of evaluation criteria due to the presence of many stakeholders, financial needs, diversity and heterogeneity of the industry, the application of new or modification of known methods of multi-criteria decision- making can help solve the task of evaluating diversification strategies of construction enterprises. Since the task of assessing the diversification strategies of construction companies is complex and has many influencing factors, it is essential to develop information technology that would significantly simplify the work of the construction company's decision-maker or management team. In the second chapter, it is established that in the uncertain conditions in which construction companies operate, it is necessary to change the perception of the organizational environment of the construction company, which consists of the internal and external environment and task environment. These components of the same organizational environment were described with the caveat of the need to include a separate component corresponding to diversification tasks. Thus, because of the study, the conceptual presentation of the structural model of the organizational environment of construction companies, which takes into account the diversification of their activities and is distinguished by the fact that it organically combines the entire range of activities of companies in conditions of uncertainty, received further development. A formal presentation of construction technology and the task of choosing a construction technology is described. The choice of construction technology, in combination with the analysis of the competitive market and the analysis of technical and economic requirements for the task of diversification, makes it possible to thoroughly approach the formation of diversification strategies for the construction company. The concept of the formation of diversification strategies of construction companies is described, considering the principles of engineering, which takes into account six main stages from the formation of requirements for diversification activities to the evaluation of the results of implementing the diversification strategy in construction projects. A list of advantages from the formation of diversification strategies based on new principles is described: the ability to reflect complex diversification processes and management processes of construction companies in conditions of uncertainty, taking into account engineering; the ability to create, evaluate and implement diversification strategies and use a scientifically based selection of optimal diversification strategies that are aimed at increasing the profits of the construction company, increasing the credibility of the analysis of diversification data and the competitive market, using the concept of open data, etc. The third chapter describes the general task of the multi-criteria selection of diversification strategies for construction companies, which can be used in conditions of uncertainty when the external environment influences the company's activities: technological changes, political, economic, and other factors. The model for choosing rational diversification strategies of construction companies based on an expert assessment of construction's technical and economic parameters is described, which considers the most significant indicators and the advantages of participants in the construction process. These advantages and the features of diversification strategies are included in the indicators of the diversification center, which should be created in the construction company. The method of evaluating diversification strategies of construction companies has been improved, which is distinguished by considering changes in the structure of companies' organizational environments and allowing them to increase their management efficiency. This method is based on expert assessment and considers the opinions of all participants in the construction process: owners, developers, investors, general contractors, and designers. The method described for evaluating the diversification strategies of construction companies was verified using the example of a construction company in the People's Republic of China. The fourth chapter describes an improved information technology for evaluating and choosing diversification strategies of construction companies under conditions of uncertainty, which is distinguished by considering the technical and economic parameters of construction and the advantages of participants in the construction process and allows expansion management capabilities and rationalize the choice of diversification strategies of construction companies. The practical significance of the obtained results is that the developed methods, models and information technology for the formation, evaluation, and selection of diversification strategies of construction enterprises are an essential step in developing a theoretical and practical basis for ensuring sustainability and profitability of construction companies. The resulting tool is practically important for construction companies, holdings, and the construction industry. In the long term, using the developed methods and models will positively impact the development of the state's building industry. The main provisions and results of the research were implemented and applied in the activities of Yancheng Polytechnic College. The obtained results, theoretically and practically, serve as a basis for further scientific and applied research aimed at improving various aspects of the management of construction companies. Ensuring the sustainability of the development of construction companies and the organization of their diversification activities are the key signs of the sustainability of the development of the country's construction industry.

The dissertation is devoted to developing methods, models and information technology for monitoring the state of environmental pollution based on trend forecasting models, statistical fractal estimation, etc. The developed methods, models and information technology can be used to improve the efficiency of environmental management in the region, in particular in large cities, based on monitoring the level of pollution, the stability of pollution in the dynamics, the cyclicality of emissions, forecasting pollution levels for future periods and trends in future pollution levels. Developing models of methods and information technology for monitoring environmental pollution is urgent. First, creating effective technologies for monitoring pollution is key to preserving citizens' health and quality of life, particularly in large cities. Monitoring the level of pollution and developing effective control strategies are critical to preserving the health of citizens. Effective pollution monitoring systems can also lead to economic benefits, including reduced disease treatment costs, improved quality of life, and promoting sustainable development. some types of pollution, such as greenhouse gas emissions, can lead to climate change, which has global impacts on ecosystems and human society. Monitoring and reducing these emissions is important to preserve the climate and reduce its negative impacts. Many countries have legislation regulating the level of environmental pollution. Developing and implementing effective monitoring systems helps ensure compliance with these regulations and standards. In these conditions, several unresolved issues arise. There are no sufficiently developed systems that would be focused not only on measuring the level of pollution by various indicators but also on making a qualitative forecast and assessing the state of the environment in a particular area. The structure of the time series of environmental pollution parameters can be a valuable source of information on the stability of pollution in the dynamics, the cyclical nature of harmful emissions, and helps to effectively predict pollution levels for future periods and trends in future pollution levels. Thus, the creation of methods, models and information technology for monitoring the state of environmental pollution based on trend forecasting models and statistical fractal estimation will practically improve the efficiency of environmental safety management and ensure a higher quality of life for citizens. The results obtained in this paper expand the theoretical and practical developments in this area. Thus, this thesis solves an important task, namely, methods, models and information technology for monitoring the state of environmental pollution based on trend forecasting models, statistical fractal analysis, etc. The developed methods and models are practically integrated into the relevant monitoring information technology. The object of research is the processes associated with monitoring and forecasting environmental pollution parameters for environmental safety management. The subject of the study is methods, models and information technology for monitoring environmental pollution parameters based on trend forecasting models. Research methods. The research is based on methods of knowledge representation and processing, monitoring and evaluation methods, time series forecasting methods, and statistical fractal analysis of information system design methods. The study aims to develop methods, models, and information technology for monitoring environmental pollution parameters for environmental safety management. Scientific novelty of the results: •For the first time, a method of monitoring environmental pollution parameters based on a comprehensive model for predicting time series of pollution parameters for decision-making on environmental safety management is described. •The model for predicting time series of environmental pollution is improved, considering the aggregation of various prediction models formed based on a predictive statistical analysis of pollution indicators. The model differs from the known models by providing the ability to adapt the model parameters to changes in the state of the environment, which is especially important when using such models in environmental monitoring systems. •An improved model for assessing the state of the environment in the monitoring system, which, unlike the known ones, takes into account the results of comprehensive forecasting of time series of changes in pollution and can be a tool for ensuring environmental safety. •The information technology for monitoring environmental pollution parameters was improved, which is distinguished by taking into account the results of analysis and forecasting of changes in pollution parameters and offers an assessment of the state of the environment, which provides opportunities for quantitative assessment of the environmental situation in the region. •The direction of developing an environmental index based on the developed methods of monitoring and forecasting time series of pollution and characterized by the consideration of prospective pollution indicators, which can be used in urban environmental monitoring and conditions of environmental uncertainty, was further developed. The first section describes the basic concepts and features of environmental monitoring. The necessity to increase the efficiency of monitoring and the main approaches to their solution through the improvement of methods and technologies are substantiated. The analysis of the properties of time series of pollutants shows that they can be classified into three classes: substances with a pronounced seasonal component, substances with a pronounced trend, and random variables. Such a classification allows for a better selection of forecasting and data transformation methods that can be used more effectively for each class of substances. The problem of environmental monitoring has been formalized in two formulations: point and plane. The main stages of environmental monitoring are highlighted. These are collecting data on the history of the state, monitoring the current state and predicting the state of environmental pollution in the future. Approaches and requirements for technical means at each stage are proposed. A review of known systems for monitoring air, water and soil pollution is made. The importance of the technical component is shown. Fundamental differences and new trends in the use of innovative technologies for monitoring environmental pollution parameters are identified. A scientific hypothesis defines the author's vision of an environmental monitoring organization by combining software and hardware systems and using trend models to predict environmental pollution parameters. By formalizing the problem of environmental monitoring, the structure of the information system for environmental monitoring is proposed. The information system should include the following subsystems: a subsystem for collecting information about the state of the environment, a subsystem for storing and accumulating data, forecasting the state of the environment, and a subsystem for user interaction. It is indicated that constructing an air pollution monitoring system is also essential for the whole and safe operation of some critical infrastructure facilities, including power plants, processing and chemical plants, airports, tunnels and subways, etc. The second section describes a comprehensive model for forecasting time series of environmental pollution indicators, considering the aggregation of various forecasting models formed based on a predictive statistical analysis of pollution indicators and having an adaptive nature. The model differs from the known models by providing the ability to adapt the model parameters to changes in the state of the environment, which is especially important when using such models in environmental monitoring systems. The fractal analysis method of time series is described, which allows finding the Hurst index for use in the developed forecasting models and determining the presence of long-term memory, cyclicity, etc., in the time series. The complex forecasting model includes higher-order exponential smoothing, Holt, Winters, moving average, weighted moving average, and autoregressive models. All the parameters set in these models are related to the Hurst index, which is calculated based on the predictive fractal statistical analysis of the time series. The corresponding descriptions and justifications are given. Using such a model as part of an econometric system will help to more effectively predict and respond to possible changes in the values of pollution parameters. In particular, the persistence of the time series of pollution parameters may mean a stable upward or downward trend in pollution. Suppose the time series becomes close to random or ergodic. In that case, this may mean an emergency or that additional non-permanent emissions have appeared in the region that need to be monitored. The third section describes a method for monitoring environmental pollution parameters based on a comprehensive model for predicting time series of pollution parameters with the use of statistical fractal analysis. The method takes into account the results of statistical fractal analysis to determine the direction of the time series trend, which may indicate whether the amount of pollution is increasing or decreasing in the short term. The method also determines the average cycle length based on the V statistic, which establishes the presence of long-term memory in the time series and determines the reliability of the trend forecast calculation. In addition, the Hurst index determines whether emissions of harmful substances, particularly into the air, are stable. That is, it is shown that if the Hurst index of a time series indicates that the time series is close to random, the environmental situation in the area is unstable, and excessive emissions are possible. This means local governments and environmental services should respond to this situation to ensure environmental safety. The model for assessing the state of the environment in the monitoring system has been improved, which, unlike the known ones, takes into account the results of comprehensive forecasting of time series of pollution changes and can be a tool for ensuring environmental safety. The model establishes a comprehensive assessment of the state of the environment based on the method of monitoring environmental pollution parameters. The direction of developing an index of the state of the environment, based on the developed methods of monitoring and forecasting time series of pollution and characterized by the consideration of prospective pollution indicators, which can be used in urban environmental monitoring and conditions of environmental uncertainty, has been further developed. The fourth section describes the information technology for monitoring environmental pollution parameters, which is distinguished by taking into account the results of analysis and forecasting changes in pollution parameters and offers an assessment of the state of the environment, which provides opportunities for quantitative assessment of the environmental situation in the region. Information technology includes methods for collecting information, a method for monitoring environmental pollution parameters, a model for assessing the state of the environment in the monitoring system, a method for calculating the environmental condition index, time series forecasting models, a method for statistical fractal analysis of time series, etc. All of these components allow for a qualitative analysis of the region's environmental situation and predict its future change. The information technology for monitoring pollution parameters based on a monitoring method that uses a comprehensive forecasting model, time series trend prediction, and statistical fractal analysis was verified. The verification was carried out on the example of a time series of environmental pollution parameters in different districts of Beijing, which were recorded from 2013 to 2017. The calculated errors in forecasting and assessing the state of the environment show the effectiveness of the development of such information technology and the relevance of this development for use by the city's environmental services and government agencies. Acts on implementing the results of work within the framework of research projects of Yancheng Polytechnic College (Appendix A). The practical significance of the results obtained is that the developed methods, models, and information monitoring of environmental pollution parameters will improve the efficiency of managing the state's environmental state. The resulting tool is important practically for ecological services and public authorities. In the long term, using the developed methods and models will positively impact the development of environmental policy in the state. The main provisions and results of the research were implemented and applied in the activities of Yancheng Polytechnic College. The results obtained, both in theoretical and practical terms, serve as a basis for further scientific and applied research to improve and enhance various aspects of the state's environmental management.