Contemporary Approaches Research Articles

Improving life quality via mandibular reconstruction: Innovations and techniques – A literature review

Mandibular abnormalities can arise from a range of causes, including illnesses, trauma to the face, and surgical excision of tumors. These conditions can significantly affect daily activities such as eating, speaking, and even grooming. These functions are impaired without appropriate repair, which has a major negative impact on an individual's quality of life. Mandibular reconstruction aims to preserve facial symmetry and allow patients to regain their normal ability to chew food by restoring both the structure and functionality of the jaw. A successful restoration also takes into account elements such as the positioning of implants to restore oral function and, in certain cases, the reconnecting of the inferior alveolar nerve to enhance feeling.Mandibular reconstruction has undergone a revolutionary change in technique over the years. These developments are still ongoing, with the goal of improving patient recovery and outcomes. This article highlights the continuous attempts to improve surgical techniques and integrate new technologies for improved patient care. It gives a general review of the historical evolution, contemporary approaches, and prospective future possibilities in mandibular reconstruction.

Medical Image Segmentation

Medical image segmentation is a critical component in the development of computer-aided diagnosis and treatment planning systems. This paper provides a comprehensive survey of recent advances in segmentation techniques applied to various imaging modalities, including Magnetic Resonance Imaging (MRI). Traditional methods such as thresholding, region-growing, and active contours are reviewed alongside contemporary machine learning-based approaches, particularly deep learning models. The survey emphasizes the growing dominance of convolutional neural networks (CNNs) and their variants, including U-Net and Fully Convolutional Networks (FCNs), which have shown remarkable success in handling complex medical imaging challenges. Additionally, the paper discusses hybrid methods that combine classical techniques with artificial intelligence to improve accuracy and robustness in segmentation tasks. Key challenges such as class imbalance, boundary delineation, and computational efficiency are also highlighted. Future directions, including the integration of multi-modal data and advancements in self-supervised learning, are explored as potential solutions to overcome current limitations in medical image segmentation.

OPTIMISATION OF STRATEGIES FOR WORKING WITH COUNTERPARTIES AND RISK MANAGEMENT AT UTILITY INFRASTRUCTURE ENTERPRISES

The objective of this paper is to examine and enhance strategies for managing relationships with counterparties and mitigating risks in utility infrastructure enterprises. The paper seeks to analyse contemporary approaches and challenges faced by these enterprises, offering recommendations for improving their strategies in counterparty interactions and risk management. Ultimately, the goal is to enhance operational stability, competitiveness, and sustainable development in a dynamic business environment. Methodology. The research presents a critical review and analysis of the existing risk management and counterparty strategies employed by utility infrastructure enterprises. The methodology comprises an examination of current practices, the identification of key problems, and an evaluation of modern approaches, including digital transformation, process automation, and innovative management methods. By synthesising existing research and case studies, the paper identifies the strengths and weaknesses of various strategies and recommends improvements. Results. The analysis identified several key challenges faced by utilities in managing counterparties and risks, including inadequate risk management systems, outdated business processes and poor communication. Process automation, digital transformation and improved stakeholder integration are identified in the document as critical factors for optimising operations. It also emphasises the importance of careful selection of counterparties, performance monitoring and staff development to mitigate risks and foster better partnerships. Practical implications. The recommendations set forth in the paper provide actionable strategies for utility infrastructure enterprises to optimise their management of counterparties and risks. The implementation of these strategies, including the utilisation of digital tools, enhanced internal communication and a focus on staff development, can facilitate improvements in efficiency, risk management and long-term sustainability for utility companies. These recommendations are particularly beneficial for those in managerial or decision-making roles who are seeking to navigate the complexities of a rapidly evolving business environment. Value / Originality. This paper makes a significant contribution to the field by offering a comprehensive analysis of the strategies available for optimising counterparty relations and risk management in the utility sector. The value of this approach lies in its integration of modern technological solutions with traditional risk management practices. By offering practical, research-based recommendations, the paper addresses current gaps in the literature and provides new insights into how utility enterprises can better manage both internal and external challenges.

Enhancing Fuel Economy in Heavy-Duty Trucks: A Contemporary Approach

This article reviews the effect of load-based speed control (LBSC) and gear-down protection (GDP) features on fuel consumption in heavy-duty trucks. These two electronic features, developed by Cummins Inc., are major developments in the field of engine management for optimum fuel economy. LBSC controls engine speed based on operating conditions, while GDP encourages operation in top gear for maximum fuel economy. Their mechanisms, benefits, and combined impact on fuel consumption and driver behavior are discussed. The discussion also involves challenges and future developments in this field. Research indicates that LBSC and GDP can offer significant improvements in fuel savings, up to 7% improvement in fuel efficiency. LBSC and GDP contribute to cutting fuel consumption and serve as virtual driver trainers, contributing to more efficient driving behavior. This article concludes that LBSC and GDP are important tools that help fleet managers reduce operation costs and environmental impact within the trucking industry.

Therapeutic Modulation of the Microbiome in Oncology: Current Trends and Future Directions.

Cancer is a predominant cause of mortality worldwide, necessitating the development of innovative therapeutic techniques. The human microbiome, particularly the gut microbiota, has become a significant element in cancer research owing to its essential role in sustaining health and influencing disease progression. This review examines the microbiome's makeup and essential functions, including immunological modulation and metabolic regulation, which may be evaluated using sophisticated methodologies such as metagenomics and 16S rRNA sequencing. The microbiome influences cancer development by promoting inflammation, modulating the immune system, and producing carcinogenic compounds. Dysbiosis, or microbial imbalance, can undermine the epithelial barrier and facilitate cancer. The microbiome influences chemotherapy and radiation results by modifying drug metabolism, either enhancing or reducing therapeutic efficacy and contributing to side effects and toxicity. Comprehending these intricate relationships emphasises the microbiome's significance in oncology and accentuates the possibility for microbiome-targeted therapeutics. Contemporary therapeutic approaches encompass the utilisation of probiotics and dietary components to regulate the microbiome, enhance treatment efficacy, and minimise unwanted effects. Advancements in research indicate that personalised microbiome-based interventions, have the potential to transform cancer therapy, by providing more effective and customised treatment alternatives. This study aims to provide a comprehensive analysis of the microbiome's influence on the onset and treatment of cancer, while emphasising current trends and future possibilities for therapeutic intervention.

Comprehensive Pain Management in Total Joint Arthroplasty: A Review of Contemporary Approaches

Background: Total hip and knee arthroplasties are among the most effective and widely performed procedures in modern medicine, providing substantial benefits to patients with end-stage osteoarthritis. These surgeries have transformed the treatment of degenerative joint disease, significantly enhancing functionality and quality of life for patients. Despite considerable advancements in surgical techniques and postoperative care, managing postoperative pain remains a major challenge, impacting both clinical recovery and patient satisfaction. The persistence of postoperative pain as a barrier to recovery underscores the need for improved pain management strategies. Methods: A comprehensive narrative review of the literature was conducted, focusing on the physiological mechanisms underlying surgical pain, the role of anesthesia techniques, and the development of multimodal pain management approaches used in total joint arthroplasty. This review emphasizes the components of modern multimodal strategies, which combine multiple pharmacologic and non-pharmacologic methods to address the various mechanisms of postoperative pain. Results: Current pain management strategies employ a dynamic, multimodal approach that covers the perioperative period. These strategies aim to optimize pain control while minimizing side effects. They incorporate a range of methods, including nerve blocks, non-opioid analgesics, opioids, and non-pharmacologic techniques such as physical therapy. However, evidence regarding the efficacy and optimal combinations of these interventions varies widely across studies. Conclusions: This variation has led to inconsistent pain management practices across institutions. To standardize and improve care, this paper presents the authors’ institutional pain management model, offering a potential framework for broader application and adaptation in the field of joint arthroplasty.

Advances in smart nanotechnology-supported photodynamic therapy for cancer.

Cancer has emerged as a formidable challenge in the 21st century, impacting society, public health, and the economy. Conventional cancer treatments often exhibit limited efficacy and considerable side effects, particularly in managing the advanced stages of the disease. Photodynamic therapy (PDT), a contemporary non-invasive therapeutic approach, employs photosensitizers (PS) in conjunction with precise light wavelengths to selectively target diseased tissues, inducing the generation of reactive oxygen species and ultimately leading to cancer cell apoptosis. In contrast to conventional therapies, PDT presents a lower incidence of side effects and greater precision in targeting. The integration of intelligent nanotechnology into PDT has markedly improved its effectiveness, as evidenced by the remarkable synergistic antitumor effects observed with the utilization of multifunctional nanoplatforms in conjunction with PDT. This paper provides a concise overview of the principles underlying PS and PDT, while also delving into the utilization of nanomaterial-based PDT in the context of cancer treatment.

Employing Evolutionary Computing and Hybrid Artificial Neural Networks to Improve Drug Discovery

An ultimate relevant translational scientific endeavour that contributes to human vulnerability and happiness might be the creation and advancement of medications. Fast drug discovery procedures necessitate using contemporary computational approaches to tackle pharma data's complexities and high complexity. By combining Evolutionary Computing with Hybrid Artificial Neural Networks (EC-HANNs), this research introduces a novel strategy for optimizing and speeding up the drug development process. To handle various drug-target relations, predict the efficacy of compounds, and discover more accurate potential medications, the proposed model employs EC to evolve the computational construction and hyperparameters of HANNs in real-time. This innovation makes the model a flexible framework. Through repeated refinement of EC- HANN designs, the EC Module uses Particle Swarm Optimization (PSO) to choose the best configuration for individual drug discovery tasks. The model's distinctive feature is that it dynamically adjusts the network configuration to match the details of each drug discovery activity by using PSO to optimize the HANN's architecture and hyperparameters. Regarding sequential biological data, the HANN Module employs Convolutional Neural Networks (CNNs) to glean features for pattern recognition over time. By extracting high-level spatial information from genetic data, CNN can better identify prospective medication candidates. When tested on several benchmark datasets, the proposed framework demonstrates superior performance over traditional neural networks across the board regarding prediction accuracy, convergence speed, and model durability. As a powerful tool, this hybrid approach can simplify drug discovery, leading to more efficient drug development.

A risk-based approach to mitigating the Gen(AI) challenge to assessment integrity

In the evolving landscape of higher education, emerging technologies such as Generative AI (GenAI) present both opportunities and challenges. The rapid increase in access to, and sophistication of, GenAI poses significant challenges for our institution and the wider sector (Bearman & Luckin 2020, Bobula 2024, Chan & Hu 2023). The most immediate of these challenges is the increased risk to the existing approaches used to assure that students achieve the stated outcomes of their learning experiences. Director of Higher Education Integrity Unit, TEQSA, Dr Helen Gniel argues ‘We are entering an age where institutions can no longer ensure the integrity of every single assessment, and it makes sense to think at that bigger level […] what are the mechanisms that you have in place to be confident that an individual has demonstrated the learning outcomes to receive that degree’(TEQSA information request: AI risk mitigation, webinar, 21 March 2024). While higher education institutions are exploring opportunities to realise the potential benefits of GenAI, our immediate focus is on mitigating these risks. This poster describes institutional Programmatic Assessment Security Project (PASP) at the University of Newcastle (UON), a pioneering four-stage initiative designed to address academic integrity risks associated with inappropriate uses of GenAI in summative assessment (Lodge 2024). Academic integrity risks in this context refers to the potential for students to engage in academic misconduct by using GenAI tools in ways that violate institutional policies or ethical standards for assessment. These risks pose a threat to the validity and reliability of summative assessments, potentially compromising the integrity of academic qualifications and the learning process itself. Led by the central teaching and learning support unit, in collaboration with the Artificial Intelligence Working Group (AIWG) a group of expert practitioners and academic stakeholders at UON, the PASP aims to secure assessments across a program of study, assuring student attainment of program learning outcomes. This innovative approach aligns with the sector’s focus on programmatic assessment and supports compliance with regulatory requirements, including TEQSA’s mid 2024 request for institutions to submit a detailed action plan to mitigate the risks that GenAI poses to the integrity of awards (TEQSA 2024). This poster showcases exemplary innovation in practice through the PASP, advancing research and practice in technology-enhanced learning (TEL). The PASP employs a risk-based approach, identifying seven risk factors for inappropriate student use of GenAI in assessment tasks. The first step in this project involved Course Coordinators completing an Assessment Reflection Survey, guiding them to reflect on individual assessment tasks in relation to these risk factors. The survey data were then used to compile an understanding of the varying levels of assessment risk across the institution’s programs. The PASP will deliver a defined series of secure assessments, delivered at key moments across a program of study to assure student attainment of program learning outcomes. This poster provides insight into UON’s contemporary and agile approach to TEL and assessment redesign, with potential for staff at other institutions to adopt similar responses.

Digitalization of Adjustment and Maintenance Processes for Optimizing Energy Consumption in the Oil and Gas Sector

This article examines the impact of digitalization on adjustment and maintenance processes in the oil and gas sector aimed at optimizing energy consumption. Modern technologies such as big data analysis, the Internet of Things (IoT), and Machine Learning (ML) algorithms are discussed, highlighting how they assist companies in reducing energy consumption and enhancing operational efficiency. Examples of the implementation of these solutions in major companies are provided, demonstrating significant reductions in energy costs and equipment downtime. The advantages of contemporary approaches over traditional adjustment and maintenance methods are emphasized.

OGC API: Ldproxy, an Updated and Contemporary Approach to Geodata Provision in Disaster Mapping

Abstract. Natural disaster occurrences have been rising for the past decades. It causes severe damage both in human properties and lives. To minimize the risk caused by disaster and accelerate the recovery, the accessibility of geospatial data is critical. WebGIS utilizes the internet to make the geospatial data accessible to a wider audience. In addition, the emergence of novel standards from OGC APIs also accelerates the accessibility of geospatial data. However, the abundance of Geospatial data requires a better performance of the webGIS. Ldproxy as a tool that follows OGC API standards could be an alternative to traditional tools such as Geoserver. This study focuses on developing a WebGIS application for accessing disaster-related geospatial data and evaluating the performance of Ldproxy in comparison to Geoserver. The method is to build a Single Page Application (SPA) using open-source data from Google Earth Engine (GEE) and OpenStreetMap (OSM). The functionalities of the webGIS enable users to retrieve OSM and GEE data and examine the impact of the disasters. The performance of Ldproxy and Geoserver is tested using Google Light House for comparison. The parameters that are tested are Speed Index, Total Blocking Time, Time to Interactive, Max Potential First Input Delay, Network Server Latency, and Total Byte Weight. As a result, Ldproxy shows slower performance in NSL compared to Geoserver. However, it offers an mvt feature format that makes the feature data can be loaded more efficiently and quickly.

A new strategy based on multi-source remote sensing data for improving the accuracy of land use/cover change classification.

Land Use/Cover Change (LUCC) plays a crucial role in sustainable land management and regional planning. However, contemporary feature extraction approaches often prove inefficient at capturing critical data features, thereby complicating land cover categorization. In this research, we introduce a new feature extraction algorithm alongside a Segmented and Stratified Principal Component Analysis (SS-PCA) dimensionality reduction method based on correlation grouping. These methods are applied to UAV LiDAR and UAV HSI data collected from land use types (e.g., residential areas, agricultural lands) and specific species (e.g., tree species) in urban, agricultural, and natural environments to reflect the diversity of the study area and to demonstrate the ability of our methods to be applied in different classification scenarios. We utilize LiDAR and HSI data to extract 157 features, including intensity, height, Normalized Digital Surface Model (nDSM), spectral, texture, and index features, to identify the optimal feature subset. Subsequently, the best feature subset is inputted into a random forest classifier to classify the features. Our findings demonstrate that the SS-PCA method successfully enhances downscaled feature bands, reduces hyperspectral data noise, and improves classification accuracy (Overall Accuracy = 91.17%). Additionally, the CFW method effectively screens appropriate features, thereby increasing classification accuracy for LiDAR (Overall Accuracy = 78.10%), HIS (Overall Accuracy = 89.87%), and LiDAR + HIS (Overall Accuracy = 97.17%) data across various areas. Moreover, the integration of LiDAR and HSI data holds promise for significantly improving ground fine classification accuracy while mitigating issues such as the 'salt and pepper noise'. Furthermore, among individual features, the LiDAR intensity feature emerges as critical for enhancing classification accuracy, while among single-class features, the HSI feature proves most influential in improving classification accuracy.

Implementing an adaptive reuse on industrial buildings: a proposal for transforming Erbil’s Silo in Kurdistan-Iraq into a hotel

Industrial buildings, serving as markers of cultural heritage, connect our cultural identity from the past through the present and into the future. Unfortunately, many of these buildings lose their identity when they are converted into another function. Through the case study analysis (the Silo of Erbil City), a qualitative method is employed to examine design strategies and spatial transformations in recent adaptive reuse projects of existing structures. Through the literature review, this research investigates the importance of adaptive reuse and heritage buildings, underscoring their historical and theoretical underpinnings, and subsequently examines contemporary approaches to architectural criteria towards habitation for existing structures in the public, creative, and cultural domains. The study findings identify common fundamental elements of industrial heritage adaptive reuse and innovative design strategies applied in recent adaptive reuse projects, highlighting the potential to transform neglected or vacant abandoned buildings into urban open spaces. The study uses a comprehensive methodology involving case study analyses and diverse data collection techniques. The case study properties are the structural systems, natural lighting, and the surrounding open spaces. As a result, a hotel with a multipurpose hall, and a museum dedicated to the history of the Silo have been proposed, aiming at conserving the valuable heritage in this industrial area as well as providing an alternative perspective for the adaptive reuse of industrial structures in Erbil city. Finally, the implications of the research for the economic and social dimensions of urban development lie in understanding and promoting sustainable preservation strategies. This work is considered the first step for future research in Iraq, specifically in Kurdistan Region. The research concludes that the Silo of Erbil is one of the successful examples of the process of reusing buildings. It also concludes that less intervention in reusing a building can protect the building identity.

A Content Analysis Study of Distortion's Influence on Drum and Bass Music Production

This study uses content analysis and draws upon aesthetic theory and technological determinism as theoretical frameworks to explore contemporary approaches to the use of distortion within drum and bass production. To achieve this, it investigates online video tutorials created by professional drum and bass producers and online content creators in order to extract insights into their common working practice when using distortion in their work. The analysis highlights a prevalent use of aggressive distortion to transform bass timbres, which is a trend originating in the 1990s that continues to shape the genre's evolving aesthetic. This research provides unique insights into the evolution. and impact of distortion and shows how established techniques persist while subtly evolving within the ever-changing production ecosystem.

THE EVOLUTION OF MOZART'S VOCAL STYLE: AN ANALYSIS BASED ON CHURCH MUSIC

This article examines the stylistic influences shaping Mozart’s sacred music, offering an in-depth analysis of its evolution. It identifies two distinct styles: the Salzburgian and contemporary approaches. The Salzburgian style is defined by brevity, counterpoint, and tonal unity, adhering to traditional liturgical requirements. Meanwhile, the contemporary style reflects the influence of secular music, with larger structures, concertante melodies, and thematic contrasts drawn from symphonic and operatic works. A comparison between Mozart’s two Lauretian litanies, Litaniae Lauretanae KV 109 and KV 195, illustrates his compositional development. The earlier litany demonstrates simplicity and compactness, while the later piece shows increased complexity, operatic influence, and a more intricate orchestral role. The analysis highlights how Mozart blended sacred music's formal rigor with expressive elements from operatic and instrumental traditions, creating a distinctive style that paved the way for future innovations in liturgical music. By drawing from contrapuntal traditions and integrating operatic expressiveness, Mozart's sacred works reflect his genius in synthesizing diverse influences into a cohesive and innovative musical language.

Rainmaking: Observed with social systems theory

AbstractThis article examines contemporary efforts to control climate change through the lens of social systems theory, particularly by drawing comparisons to rain dances and shamanic rituals. It argues that modern climate control strategies bear functional similarities to archaic rituals aimed at influencing weather patterns, despite the absence of direct causality. Using Niklas Luhmann's concepts of autopoietic systems and functional equivalence, the article demonstrates that both historical and contemporary approaches to climate influence rely on blame‐shifting mechanisms and the social production of scapegoats, with failure often attributed not to the rituals or solutions themselves but to noncompliance or impurity among participants. The originality of this article lies in its application of social systems theory to link contemporary climate control strategies with ancient rituals, positioning them as functionally equivalent social phenomena. By drawing comparisons between shamanistic practices, corporate consulting, and global climate governance, the article provides a unique lens for understanding that the primary function of modern climate efforts may be to regulate social behaviour rather than achieving concrete natural environmental outcomes.

Perspectivas contemporâneas sobre marcas: um estudo sobre abordagens e dinâmicas na comunicação

This study investigates contemporary approaches researchers in Communication use to study brands, reflecting on the multifaceted and dynamic concept of this theme. A systematic analysis of 77 articles published in Brazilian journals from 2018 to 2023 found and discussed five main thematic axes: culture and social values, economy and market, ethics and social responsibility, audience experience, and visual identity and symbolism. Results point to a wealth of perspectives that show the complexity of the subject and the possibility of approaching it in various ways.

Impact of active case finding for tuberculosis with mass chest X-ray screening in Glasgow, Scotland, 1950-1963: An epidemiological analysis of historical data.

Community active case finding (ACF) for tuberculosis was widely implemented in Europe and North America between 1940 and 1970, when incidence was comparable to many present-day high-burden countries. Using an interrupted time series analysis, we analysed the effect of the 1957 Glasgow mass chest X-ray campaign to inform contemporary approaches to screening. Case notifications for 1950 to 1963 were extracted from public health records and linked to demographic data. We fitted Bayesian multilevel regression models to estimate annual relative case notification rates (CNRs) during and after a mass screening intervention implemented over 5 weeks in 1957 compared to the counterfactual scenario where the intervention had not occurred. We additionally estimated case detection ratios and incidence. From 11 March 1957 to 12 April 1957, 714,915 people (622,349 of 819,301 [76.0%] resident adults ≥15 years) were screened with miniature chest X-ray; 2,369 (0.4%) were diagnosed with tuberculosis. Pre-intervention (1950 to 1956), pulmonary CNRs were declining at 2.3% per year from a CNR of 222/100,000 in 1950. With the intervention in 1957, there was a doubling in the pulmonary CNR (RR: 1.95, 95% uncertainty interval [UI] [1.81, 2.11]) and 35% decline in the year after (RR: 0.65, 95% UI [0.59, 0.71]). Post-intervention (1958 to 1963) annual rates of decline (5.4% per year) were greater (RR: 0.77, 95% UI [0.69, 0.85]), and there were an estimated 4,599 (95% UI [3,641, 5,683]) pulmonary case notifications averted due to the intervention. Effects were consistent across all city wards and notifications declined in young children (0 to 5 years) with the intervention. Limitations include the lack of data in historical reports on microbiological testing for tuberculosis, and uncertainty in contributory effects of other contemporaneous interventions including slum clearances, introduction of BCG vaccination programmes, and the ending of postwar food rationing. A single, rapid round of mass screening with chest X-ray (probably the largest ever conducted) likely resulted in a major and sustained reduction in tuberculosis case notifications. Synthesis of evidence from other historical tuberculosis screening programmes is needed to confirm findings from Glasgow and to provide insights into ongoing efforts to successfully implement ACF interventions in today's high tuberculosis burden countries and with new screening tools and technologies.

СУЧАСНІ КОНЦЕПТУАЛЬНІ ПІДХОДИ ДО КАТЕГОРІЇ «АГРОСФЕРА»

An analysis of contemporary scientific approaches to defining the category of «agrosphere» has been conducted. The features of its content, components, and main aspects of sustainable development have been examined. The importance of the agrosphere for ensuring food security, economic growth, social well-being, and environmental preservation has been substantiated. Based on the aforementioned approaches, an author's definition of the researched category has been formulated, according to which the agrosphere is a complex system that integrates land use and agro-production, their economic, social, and environmental aspects, functioning based on sustainable land management, aimed at ensuring food security, sustainable development, and societal well-being. The agrosphere should include: all elements of agricultural production; the economic component; the social component; the environmental direction; and the institutional aspect. It is important to understand that the agrosphere is not static but continuously evolves under the influence of various factors. For the sustainable development of the agrosphere, it is necessary to implement innovative technologies and practices, invest in infrastructure and human capital, create favorable conditions for the development of the agro-industrial complex, and ensure compliance with environmental norms and standards. Only through the combined efforts of the state, business, and the public can a stable and promising agrosphere be created. Being a life-supporting system, it ideally corresponds to the principles of the sustainable development concept. And it is precisely on the foundations of sustainability that its progress should occur.

IDENTIFICATION AND LOCALIZATION OF VULNERABILITIES IN SMART CONTRACTS USING ATTENTION VECTORS ANALYSIS IN A BERT-BASED MODEL

Context. With the development of blockchain technology and the increasing use of smart contracts, which are automatically executed in blockchain networks, the significance of securing these contracts has become extremely relevant. Traditional code auditing methods often prove ineffective in identifying complex vulnerabilities, which can lead to significant financial losses. For example, the reentrancy vulnerability that led to the DAO attack in 2016 resulted in the loss of 3.6 million ethers and the split of the Ethereum blockchain network. This underscores the necessity for early detection of vulnerabilities. Objective. The objective of this work is to develop and test an innovative approach for identifying and localizing vulnerabilities in smart contracts based on the analysis of attention vectors in a model using BERT architecture. Method. The methodology described includes data preparation and training a transformer-based model for analyzing smart contract code. The proposed attention vector analysis method allows for the precise identification of vulnerable code segments. The use of the CodeBERT model significantly improves the accuracy of vulnerability identification compared to traditional methods. Specifically, three types of vulnerabilities are considered: reentrancy, timestamp dependence, and tx.origin vulnerability. The data is preprocessed, which includes the standardization of variables and the simplification of functions. Results. The developed model demonstrated a high F-score of 95.51%, which significantly exceeds the results of contemporary approaches, such as the BGRU-ATT model with an F-score of 91.41%. The accuracy of the method in the task of localizing reentrancy vulnerabilities was 82%. Conclusions. The experiments conducted confirmed the effectiveness of the proposed solution. Prospects for further research include the integration of more advanced deep learning models, such as GPT-4 or T5, to improve the accuracy and reliability of vulnerability detection, as well as expanding the dataset to cover other smart contract languages, such as Vyper or LLL, to enhance the applicability and efficiency of the model across various blockchain platforms. Thus, the developed CodeBERT-based model demonstrates high results in detecting and localizing vulnerabilities in smart contracts, which opens new opportunities for research in the field of blockchain platform security.