Intelligent Data Analysis Research Articles

A cascade ensemble-learning model for the deployment at the edge: case on missing IoT data recovery in environmental monitoring systems

In recent years, more and more applied industries have relied on data collection by IoT devices. Various IoT devices generate vast volumes of data that require efficient processing. Usually, the intellectual analysis of such data takes place in data centers in cloud environments. However, the problems of transferring large volumes of data and the long wait for a response from the data center for further corrective actions in the system led to the search for new processing methods. One possible option is Edge computing. Intelligent data analysis in the places of their collection eliminates the disadvantages mentioned above, revealing many advantages of using such an approach in practice. However, the Edge computing approach is challenging to implement when different IoT devices collect the independent attributes required for classification/regression. In order to overcome this limitation, the authors developed a new cascade ensemble-learning model for the deployment at the Edge. It is based on the principles of cascading machine learning methods, where each IoT device that collects data performs its analysis based on the attributes it contains. The results of its work are transmitted to the next IoT device, which analyzes the attributes it collects, taking into account the output of the previous device. All independent at-tributes are taken into account in this way. Because of this, the proposed approach provides: 1) The possibility of effective implementation of Edge computing for intelligent data analysis, that is, even before their transmission to the data center; 2) increasing, and in some cases maintaining, classification/regression accuracy at the same level that can be achieved in the data center; 3) significantly reducing the duration of training procedures due to the processing of a smaller number of attributes by each of the IoT devices. The simulation of the proposed approach was performed on a real-world set of IoT data. The missing data recovery task in the atmospheric air state data was solved. The authors selected the optimal parameters of the proposed approach. It was established that the developed model provides a slight increase in prediction accuracy while significantly reducing the duration of the training procedure. However, in this case, the main advantage is that all this happens within the bounds of Edge computing, which opens up several benefits of using the developed model in practice.

Tecnologias de fala e a variação de pronúncia do russo no contexto de VoiceInteraction

This article aims to describe the work conducted at VoiceInteraction, a company specialized in speech processing solutions, with a particular focus on automatic transcription using a Hybrid Automatic Speech Recognizer (ASR). The primary objective revolved around studying the phonetic characteristics of the Russian language, encompassing four main tasks: describing the phonetic-phonological inventory, validating news transcriptions, validating a previously created lexicon, and integrating filled pauses into the ASR. This work contributed to the Artificial Intelligence and Advanced Data Analysis for Authority Agencies (AIDA) project, funded by the European Commission under the Horizon 2020 program, by transcribing the data in the Russian language.

ADM: Appraiser Decision Model for Empowering Industry 5.0-Driven Manufacturers toward Sustainability and Optimization: A Case Study

Whilst it was thought that Industry 4.0 (I 4.0) would support sustainable growth, it overlooked or misinterpreted many current sustainability issues, which gave rise to the Industry 5.0 (I 5.0) agenda. Such a revolution facilitates sustainable development through its three dimensions. Therefore, I 5.0 promotes more effective management of business environment as supply chain resources. Although artificial intelligence (AI) and big data analytics (BDA) are becoming more well-liked in the context of supply chains, research to this day is fragmented into research streams that are mostly determined by the publishing outlet. This study appraises the ability of these techniques in manufacturing enterprises toward sustainability based on a set of criteria. Hence, we identified the criteria which related to AI and BDA. The various techniques as entropy and weighted sum models of multi-criteria decision-making (MCDM) techniques are working under the authority of single values neutrosophic sets (SVNSs) to enhance and boost these techniques in uncertain situations. The constructed appraiser decision model (ADM) is applied to real enterprises to validate this model.

The impact of business intelligence, big data analytics capability, and green knowledge management on sustainability performance

This paper aims to study the determinants that affect sustainability performance in manufacturing companies and the impact of business intelligence and big data analytics capability on performance considering the moderating role of green knowledge management. An online questionnaire survey was conducted with 488 ISO14001-certified manufacturing companies in Malaysia to test the framework developed in this study. Nonprobability sampling was used in this study. A total of 283 responses were received, whereby the data was then analyzed using structural equation modeling via SmartPLS 4 software. The results indicated that the significant factor determining big data analytics capability is business intelligence, and the positive outcome of big data analytics capability is sustainability performance. Big data analytics capability also plays a mediating role in the positive relationship between business intelligence and sustainability performance, whereby green knowledge management does not moderate the relationship between big data analytics capability and sustainability performance. Even though business intelligence has a substantial impact on sustainability performance, the relationship is not stronger when the level of green knowledge management changes. This research provides awareness to manufacturing companies on the critical factors contributing to big data analytics capability and its outcomes on corporate sustainability performance.

Investigating applications of Artificial Intelligence in university libraries of Pakistan: An empirical study

This study aims to investigate the applications of Artificial Intelligence (AI) in the university libraries of Pakistan. Following the explanatory sequential mixed-methods approach, this study was completed in two phases. In the first phase, quantitative data was collected from 237 university librarians from across Pakistan. In the second phase, 10 purposefully selected university librarians were interviewed. The results reveal that Pakistani university libraries are using limited AI-based library services including text-to-speech and speech-to-text technologies, Google Assistant to search by voice command, Radio Frequency Identification (RFID) system for self-checkout, check-in, and security purposes, and intelligent data analysis for collection management. This study explored key factors that influence implementation of AI applications including highly integrated technological infrastructure, funding/cost associated with AI, collaboration between AI experts and professionals, and library users' feedback. The major identified challenges were the requirement of a highly networked and integrated environment, lack of budget, high cost of AI technologies, and lack of staff expertise. This study claims to implement the first comprehensive survey of AI applications in Pakistani university libraries at the national level. The research findings would support library and university administrators to integrate AI applications in libraries not only in Pakistan but also in other developing countries.

An Automated Nanowell-Array Workflow for Quantitative Multiplexed Single-Cell Proteomics Sample Preparation at High Sensitivity

Multiplexed and label-free mass spectrometry–based approaches with single-cell resolution have attributed surprising heterogeneity to presumed homogenous cell populations. Even though specialized experimental designs and instrumentation have demonstrated remarkable advances, the efficient sample preparation of single cells still lags. Here, we introduce the proteoCHIP, a universal option for single-cell proteomics sample preparation including multiplexed labeling up to 16-plex with high sensitivity and throughput. The automated processing using a commercial system combining single-cell isolation and picoliter dispensing, the cellenONE, reduces final sample volumes to low nanoliters submerged in a hexadecane layer simultaneously eliminating error-prone manual sample handling and overcoming evaporation. The specialized proteoCHIP design allows direct injection of single cells via a standard autosampler resulting in around 1500 protein groups per TMT10-plex with reduced or eliminated need for a carrier proteome. We evaluated the effect of wider precursor isolation windows at single-cell input levels and found that using 2 Da isolation windows increased overall sensitivity without significantly impacting interference. Using the dedicated mass spectrometry acquisition strategies detailed here, we identified on average close to 2000 proteins per TMT10-plex across 170 multiplexed single cells that readily distinguished human cell types. Overall, our workflow combines highly efficient sample preparation, chromatographic and ion mobility–based filtering, rapid wide-window data-dependent acquisition analysis, and intelligent data analysis for optimal multiplexed single-cell proteomics. This versatile and automated proteoCHIP-based sample preparation approach is sufficiently sensitive to drive biological applications of single-cell proteomics and can be readily adopted by proteomics laboratories.

Comparative analysis of the topics of scientific publications in the field of artificial intelligence in international and Russian journals

Aim. To perform a comparative analysis of the topics and volumes of publication activity in the field of artificial intelligence (AI) of Russian authors in journals indexed in such databases as the Russian Science Citation Index (RSCI) and WoS/Scopus, in relation to the fields of AI technologies, scientific directions and organisations of the place of work.Tasks. To create a list of publications by authors with Russian affiliation in journals indexed in WoS/Scopus, including those categorised as Q1 and Q2 quartiles, as well as in the proceedings of A* level conferences, the topics of which are related to the AI sphere; to create a list of publications by Russian researchers devoted to the AI topics in journals indexed in RSCI, including those categorised as Q1; to carry out a comparative analysis of the topics and structure of publications by Russian authors in journals indexed in WoS/Scopus and RSCI in relation to the fields of AI technologies, groups of scientific specialties, and organisations of the authors’ place of work.Methods. The methodology of the study is based on expert analysis of publications in scientific journals indexed in WoS/Scopus, including Q1 and Q2 quartiles, in proceedings of A* level conferences, scientific journals indexed in RSCI for 2017–2021, the subject matter of which relates to the field of AI, based on selections from open databases of publications using libraries and packages for data processing and analysis. The criterion for attributing an article to the AI subject was the presence of word combinations from the fields of AI technologies and subtechnologies in the search fields “publication title” and (or) “Keywords”, “Abstract”.Results. Comparison of highly rated WoS/Scopus, Q1, Q2, A* and RINC K1 publications shows that among WoS/Scopus, Q1, Q2, A* publications “Machine learning: knowledge representation, ontology, interpretation, explanation” (32 %) and “Computer vision” (30 %) dominate. Among RINC Q1 publications, “Responsible Artificial Intelligence (ethics and philosophy, legal regulations, security)” (34 %), “Machine learning: knowledge representation, ontology, interpretation, explanation” (28 %) and “Intelligent analysis of data and processes, making sense of patterns” (13 %) dominate.Conclusions. The analysis of publication activity of Russian authors in relation to AI topics on the basis of comparison of scientific publications from WoS/Scopus and RINC databases can serve as an information basis for selection of AI competence centres and formation of lists of best practices in the field of AI.

An Explainable AI Approach to Agrotechnical Monitoring and Crop Diseases Prediction in Dnipro Region of Ukraine

Abstract The proliferation of computer-oriented and information digitalisation technologies has become a hallmark across various sectors in today’s rapidly evolving environment. Among these, agriculture emerges as a pivotal sector in need of seamless incorporation of high-performance information technologies to address the pressing needs of national economies worldwide. The aim of the present article is to substantiate scientific and applied approaches to improving the efficiency of computer-oriented agrotechnical monitoring systems by developing an intelligent software component for predicting the probability of occurrence of corn diseases during the full cycle of its cultivation. The object of research is non-stationary processes of intelligent transformation and predictive analytics of soil and climatic data, which are factors of the occurrence and development of diseases in corn. The subject of the research is methods and explainable AI models of intelligent predictive analysis of measurement data on the soil and climatic condition of agricultural enterprises specialised in growing corn. The main scientific and practical effect of the research results is the development of IoT technologies for agrotechnical monitoring through the development of a computer-oriented model based on the ANFIS technique and the synthesis of structural and algorithmic provision for identifying and predicting the probability of occurrence of corn diseases during the full cycle of its cultivation.

Fast Attack Detection Method for Imbalanced Data in Industrial Cyber-Physical Systems

Abstract Integrating industrial cyber-physical systems (ICPSs) with modern information technologies (5G, artificial intelligence, and big data analytics) has led to the development of industrial intelligence. Still, it has increased the vulnerability of such systems regarding cybersecurity. Traditional network intrusion detection methods for ICPSs are limited in identifying minority attack categories and suffer from high time complexity. To address these issues, this paper proposes a network intrusion detection scheme, which includes an information-theoretic hybrid feature selection method to reduce data dimensionality and the ALLKNN-LightGBM intrusion detection framework. Experimental results on three industrial datasets demonstrate that the proposed method outperforms four mainstream machine learning methods and other advanced intrusion detection techniques regarding accuracy, F-score, and run time complexity.

S1686 Using Business Intelligence Data Analytics to Improve Scheduling of Urgent and Non-Urgent Gastroenterology Clinic and Endoscopies in a Large Safety-Net Hospital

S1686 Using Business Intelligence Data Analytics to Improve Scheduling of Urgent and Non-Urgent Gastroenterology Clinic and Endoscopies in a Large Safety-Net Hospital

METHOD OF CREATING AN INFORMATION SYSTEM FOR MONITORING INFECTIOUS PATIENTS

In the context of the COVID-19 pandemic, infectious disease information systems are widely used and promoted to prevent the spread of the pandemic (mainly in the form of mobile applications). Many countries have offered their apps to improve contact tracing and thus reduce the number of infections. However, the level of adoption of such applications has been and remains relatively low, which, obviously, given their massive use and effectiveness, has been largely influenced by issues related to privacy and anonymity, as well as the perception of potential users of the price-benefit ratio. Thus, the task of creating information systems for monitoring infectious patients is still relevant today. Therefore, our study is devoted to the development of a method and an information system for monitoring infectious patients.
 The article develops a method for creating an information system for monitoring infectious patients, which, unlike the known ones, is based on intelligent analysis of data on the geolocation of patients and contact persons, and provides the ability to design an information system for controlling infectious patients. The purpose of the information system for monitoring infectious patients is to prevent the spread of epidemics and pandemics by tracking patient contacts and reducing the number of infections. The tasks of the information system for monitoring infectious patients are to track the self-isolation of infectious patients and their contacts, identify the most "infected" buildings, districts, cities, etc. based on intelligent analysis of data on infectious patients and their contacts.
 The designed mobile-oriented information system for monitoring infectious patients can be used to prevent the spread of the pandemic by tracking contacts and reducing the number of infections. The design of screen forms, reports, implementation, testing and commissioning of the information system for monitoring infectious patients will be carried out by the authors in the course of their further research.

Optimization study of intelligent decision-making system for coal processing plant based on big data analysis

Abstract Optimizing the intelligent decision-making system of coal processing plants is better to improve the economic efficiency of coal processing plants and realize the high-quality development of coal processing plants. In this paper, an integrated intelligent decision-making platform for a coal processing plant is constructed based on big data technology, and the intelligent data analysis techniques of the platform are optimized by using an improved whale optimization algorithm and BP neural network. Examples analyze the optimized crude coal slurry and flotation systems’ processes, and the economic benefits are analyzed. From the optimization of the crude coal slurry sorting system, the ash content in the 0.25mm particle size region was reduced from 55.37% to 13.12%, and the ash content in the −0.125mm particle size region was reduced from 42.68% to 15.96%. From the flotation system optimization, when the flotation time increases from 120s to 180s, the ash content increases from 16.27% to 17.19%, and then to 240s, the ash content increases to 19.44%. Using the integrated intelligent decision-making platform can achieve a net increase in revenue of 4,276,800 yuan for the crude coal slurry sorting system and a net increase of 11,274,200 yuan for the flotation system. This shows that the integrated intelligent decision-making platform can improve the coal processing plant’s quality and efficiency and promote intelligent production.

Meta In-Context Learning: Harnessing Large Language Models for Electrical Data Classification

The evolution of communication technology has driven the demand for intelligent power grids and data analysis in power systems. However, obtaining and annotating electrical data from intelligent terminals is time-consuming and challenging. We propose Meta In-Context Learning (M-ICL), a new approach that harnesses large language models to classify time series electrical data, which largely alleviates the need for annotated data when adapting to new tasks. The proposed M-ICL consists of two stages: meta-training and meta-testing. In meta-training, the model is trained on various tasks that have an adequate amount of training data. The meta-training stage aims to learn the mapping between electrical data and the embedding space of large language models. In the meta-testing stage, the trained model makes predictions on new tasks. By utilizing the in-context learning ability of large language models, M-ICL adapts models to new tasks effectively with only a few annotated instances (e.g., 1–5 training instances per class). Our contributions lie in the new application of large language models to electrical data classification and the introduction of M-ICL to improve the classification performance with the strong in-context learning ability of large language models. Furthermore, we conduct extensive experiments on 13 real-world datasets, and the experimental results show that the proposed M-ICL improves the average accuracy over all datasets by 19.06%, 12.06%, and 6.63% when only one, two, and five training instances for each class are available, respectively. In summary, M-ICL offers a promising solution to the challenges of electrical data classification.

Methodology for Assessing the Digital Transformation of Libraries

Due to the paucity of comprehensive studies in the field of library digitalization, a brief description of the methodology for assessing the digital transformation (DT) of libraries is presented. The problem is considered according to various components. Domestic and foreign approaches to the study of the level of DT are described. The stages of assessing the level of digital maturity of libraries (analysis of the socio-professional background of digital maturity, functional benchmarking of digital maturity of specific libraries, intellectual data analysis and replication of best practices, data-driven sectoral management with the use of artificial intelligence and revision of regulations) are substantiated. The levels of digital maturity of libraries (readiness for DT, activity of DT, innovativeness of DT) have been defined. The aim of the study is to develop a methodology for comprehensive assessment of libraries’ digital maturity at the general and corporate levels, and to propose tools for assessing the level of digital maturity of specific libraries. Recommendations for processing the results obtained using modern software and hardware tools are given. For the first time a formula for quantitative assessment of digital maturity of libraries using indices is proposed. The presented variant of the matrix for assessing digital maturity of technological processes includes the main library processes as components of digital maturity and expands the understanding of functional benchmarking aimed at comparing the results of digital maturity of specific libraries.Based on the study, the following conclusions are drawn. 1. To manage DT, it is necessary to organize continuous monitoring of digital maturity of libraries, i.e. their readiness for DT, activity of DT, innovativeness of DT expressed in criteria and indicators agreed with the professional community. 2. The results of monitoring should become an important component of management decision-making based on digital data (data-driven approach) and forecasting of both positive and negative trends as a result of intelligent data analysis. 3. The analysis of the digital maturity level of libraries will make it possible to create appropriate rankings, as well as dashboards (interactive visualisation dashboards), which have increased visibility, decision-making power and motivate libraries to achieve goals in DT.

Machine Learning-Driven Remote Sensing Applications for Agriculture in India—A Systematic Review

In India, agriculture serves as the backbone of the economy, and is a primary source of employment. Despite the setbacks caused by the COVID-19 pandemic, the agriculture and allied sectors in India exhibited resilience, registered a growth of 3.4% during 2020–2121, even as the overall economic growth declined by 7.2% during the same period. The improvement of the agriculture sector holds paramount importance in sustaining the increasing population and safeguarding food security. Consequently, researchers worldwide have been concentrating on digitally transforming agriculture by leveraging advanced technologies to establish smart, sustainable, and lucrative farming systems. The advancement in remote sensing (RS) and machine learning (ML) has proven beneficial for farmers and policymakers in minimizing crop losses and optimizing resource utilization through valuable crop insights. In this paper, we present a comprehensive review of studies dedicated to the application of RS and ML in addressing agriculture-related challenges in India. We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and evaluated research articles published from 2015 to 2022. The objective of this study is to shed light on the application of both RS and ML technique across key agricultural domains, encompassing “crop management”, “soil management”, and “water management, ultimately leading to their improvement. This study primarily focuses on assessing the current status of using intelligent geospatial data analytics in Indian agriculture. Majority of the studies were carried out in the crop management category, where the deployment of various RS sensors led yielded substantial improvements in agricultural monitoring. The integration of remote sensing technology and machine learning techniques can enable an intelligent approach to agricultural monitoring, thereby providing valuable recommendations and insights for effective agricultural management.

Practice and Case Analysis of Enterprise Financial Accounting Transformation into Management Accounting

This paper will provide a comprehensive analysis of the practice of transforming corporate financial accounting into management accounting. Firstly, we will introduce the basic concepts and objectives of financial accounting and management accounting, and discuss why companies need to transition from traditional financial accounting to management accounting. Next, we will delve into the key focus areas for companies during the implementation of management accounting. As market competition intensifies, traditional financial accounting is no longer sufficient to meet the decision support and strategic planning needs of corporate management. More and more companies are shifting towards management accounting; however, they often face a series of challenges in implementing it. Despite these challenges, the transformation to management accounting also brings many opportunities for companies. In the digital age, combining advanced technologies such as artificial intelligence and big data analytics with management accounting can bring new competitive advantages to businesses. The transformation of corporate financial accounting into management accounting is an undeniable trend that cannot be overlooked.

Individualizing Medicinal Therapy Post Heart Stent Implantation: Tailoring for Patient Factors.

The field of cardiovascular medicine is undergoing a transformative shift towards personalized medicinal therapy, particularly in the context of post stent implantation. This narrative review explores the significance, challenges, and future directions of individualized treatment strategies for patients with coronary stents. The review highlights the pivotal role of personalized approaches in optimizing treatment efficacy and minimizing adverse events. Real-world clinical studies and trials underscore the importance of tailoring antiplatelet therapy based on platelet function testing, genetic testing, and risk scoring. These studies reveal that personalized medicinal treatment improves clinical outcomes by balancing preventing thrombotic events and mitigating bleeding risks. Challenges, including cost, test availability, patient adherence, and ethical considerations, are discussed in depth, shedding light on the complexities of implementing personalized approaches. Technological advancements, including omics data integration, artificial intelligence, and big data analytics, shape the future of personalized medicinal therapy. These tools enable precise pharmacogenomic selection of medications and the development of integrated risk-scoring systems. Patient engagement and education are also central, with empowered patients and remote monitoring contributing to collaborative decision-making. In conclusion, the narrative review underscores that personalized medicinal therapy post stent implantation holds immense promise for revolutionizing cardiovascular care. By embracing a comprehensive approach that considers genetics, clinical factors, and patient preferences, healthcare providers can optimize treatment outcomes and improve patient quality of life. The evolving landscape of personalized medicine offers a glimpse into a future where tailored treatment strategies become the cornerstone of precision cardiovascular care.

Integrating Artificial Intelligence and Big Data into Smart Healthcare Systems: A Comprehensive Review of Current Practices and Future Directions

The COVID-19 pandemic has unveiled both the vulnerabilities and resilience of global healthcare systems, sparking a surge in innovation, including the accelerated adoption of Artificial Intelligence (AI) and big data analytics. This paper provides a comprehensive examination of the incorporation of these technologies within the advancement of contemporary, intelligent healthcare systems, with a keen focus on their potential to transform health management globally. This study explores the roles of AI and big data in bolstering the adaptability, efficiency, and productivity of healthcare services while also empowering individuals with actionable insights for enhanced health outcomes. Besides identifying key opportunities for AI and big data synergies within smart medical systems - encompassing disease detection and prevention, personalized medicine, resource allocation, and healthcare accessibility - this study delve into the critical ethical considerations accompanying their use. These include the essential principles of explainability, trustworthiness, privacy, security, and healthcare equity. Emphasis is placed on the importance of transparent, accountable, and ethically robust implementation strategies to ensure the responsible deployment of these technologies. Furthermore, the inherent privacy and security challenges associated with big data and AI in healthcare are addressed, detailing potential risks such as data breaches, data misuse, and patient confidentiality threats. Also, this study highlights the significance of incorporating privacy-preserving techniques, such as differential privacy and federated learning, in AI and big data analytics. This paper proposes a forward-looking paradigm for embedding AI and big data analytics within the core infrastructure of smart healthcare systems, outlining best practices and providing recommendations to leverage their transformative potential effectively and ethically. The insights and findings offered aim to guide future research, policy, and implementation efforts focused on harnessing the power of AI and big data to enhance global health resilience, stimulate innovation, and drive constructive change within the realm of intelligent medical facilities.

A strategy study based on artificial intelligence data analysis of rural governance into tourism industry development research

Abstract Exploring the strategy of integrating rural governance into tourism industry development is to provide industrial support to realize rural revitalization. This paper introduces recurrent neural networks and long and short-term memory neural networks under deep learning techniques, including their specific structures and basic principles, starting from artificial intelligence grading techniques. The basic principle of the attention mechanism is explained, and the components of the basic attention mechanism model structure and the steps of processing data are given. The ATT-LSTM analytical prediction model is jointly constructed using the attention mechanism and the long and short-term memory neural network, and the model’s prediction process and overall structure are given. The ATT-LSTM analysis model was used to analyze the data related to developing rural governance integrated tourism industry using county S as an example. From the satisfaction data, the percentages of very good, good, average, and poor ratings are 9.32%, 24.51%, 39.28%, and 26.89%, respectively. In terms of promotion and publicity, the percentage of visitors introduced by friends and family increased from 25.64% in 2017 to 33.58% in 2020, an increase of 30.97%. This shows that the use of artificial intelligence technology can effectively analyze the impact related to the integration and development of rural governance and the tourism industry and should be complemented by industrial advantages and natural resources to tap into local folk culture and thus promote the prosperous development of the tourism industry.

Review of Estimating and Predicting Models of the Wind Energy Amount

Obtaining wind energy for the production of electric energy plays a key role in overcoming the problems associated with climate change and the dwindling reserves of traditional types of energy resources. The purpose of this work is to analyze current methods of energy estimation and forecasting, to consider the main classifications of forecasts and methods used in their construction and to review the main types of mathematical distributions used to calculate the speed and power of wind flow, depending on specific geographical conditions. In recent years, there has been an increase in the capacity of modern wind generators, which has significantly improved the efficiency of wind energy parks. The initial stage in determining the feasibility of involving a particular energy source in the overall energy system of the region is a preliminary assessment of the energy potential, allowing one to determine the possible percentage of substitution of traditional energy. To solve such a problem, it is necessary to use models of energy supply. Evaluation of wind as a resource creates certain difficulties in modeling because this resource is stochastic and variable. In this regard, this paper proposes to consider various models for estimating wind energy potential, which can be classified into empirical models and models based on the application of modern intelligent data analysis technologies. The paper presents an analysis of the existing models for estimating the amount of energy, which can be used in a system designed to determine the most optimal configuration of the energy system based on the use of different conversion technologies most relevant to the case under study, and it also serves as the basis for creating digital twins designed to model and optimize the operation of the projected energy complex.