Search

This paper presents a comparative analysis of two methods for planning and coordinating the movement of robot manipulators in dynamic environments: a neural network-based approach for solving dynamic production scenarios and the rapidly exploring random trees algorithm. The study aims to enhance the trajectory planning of robot manipulators by leveraging the strengths of intelligent systems. The neural network method is designed to perceive the environment, generate accurate control commands, and adapt to changing conditions in real-time. The paper the processes involved in environmental analysis, collision avoidance, and control signal generation for actuators, with an emphasis on the neural network architecture tailored for these tasks. The results demonstrate that the neural network approach offers significant improvements in adaptability and efficiency, providing a robust solution for optimizing automated processes in dynamic production environments. [ABSTRACT FROM AUTHOR]

The paper presents the development of a hybrid neural network architecture, BAFUNet, designed for the segmentation of spine MR images in the context of medical diagnostics. The architecture builds upon the classical U-Net, integrating atrous spatial pyramid pooling module in the bottleneck and a two-round fusion module in the skip connections to address challenges such as various object scales and unclear boundaries in medical images. The work describes the design of the proposed BAFUNet architecture, its implementation, and the experimental results. A comparative analysis was performed against classical U-Net and ResUNet++, demonstrating the relationship between the proposed architectural enhancements and segmentation performance. The evaluation was carried out using Dice score and Jaccard score metrics on the SPIDER dataset, a publicly available lumbar spine magnetic resonance imaging dataset. The results indicate that the BAFUNet architecture achieves a slight but consistent improvement in segmentation performance, with an average Dice Score increase of 0.003-0.005 compared to baseline models, highlighting its potential applicability in automated medical diagnostics. [ABSTRACT FROM AUTHOR]

This paper introduces advanced copula-based methods for the nonparametric detection and characterization of wideband radar signals. The research focuses on developing signal detection algorithms that are invariant to changes in the probability density function of the sounding or reflected signals, employing multiscale analysis techniques and copula-based statistics. Two primary approaches are explored: multiscale analysis using wavelet transforms and rank-based signal detection with copulabased ambiguity functions. Simulation results confirm the effectiveness of the proposed approaches. The research demonstrates that integrating rank-based methods with copula-based statistics significantly improves the detection and analysis of wideband radar signals, particularly in complex scenarios where signals exhibit intricate dependency structures. This comprehensive detection framework is well-suited for handling high-dimensional radar signal data, enhancing accuracy and reliability under varied conditions. Future work will focus on optimizing copula selection and permutation strategies to further improve performance. [ABSTRACT FROM AUTHOR]

This paper is devoted to enchasing existing multi-view semi-supervised ensemble learning algorithms by introducing a cross-view consensus. A detailed overview of three state-of-the-art methods is given, with relevant steps of the training highlighted. A problem statement is formed to introduce both semi-supervised framework and consider the semi-supervised learning in the context of optimization problem. A novel multi-view semi-supervised ensemble learning algorithm called multi-view semisupervised cross consensus (MSSXC) is introduced. The algorithm is tested against 5 synthetic datasets designed for semi-supervised learning challenges. The results indicate improvement in the average accuracy of up to 10% in comparison to existing methods, especially in low-volume, high density scenarios. [ABSTRACT FROM AUTHOR]

The paper analyses the existing methods and best international practices for creating a system of professional standardisation in the field of cybersecurity and information protection. It is shown that at present, a new List of professions has been formed in accordance with the needs of the labour market in the field of cybersecurity and information protection. For the first time in many years, on the initiative of a comprehensive group of specialists at the State Special Communications Service of Ukraine, changes were made and new professions were added to the classifier of professions DK - 003: 2010 in the field of cybersecurity and information protection (Amendments #10, Order of the Ministry of Economy No. 810 dated 25.10.21; Amendments #11, Order of the Ministry of Economy No. 5573 dated 29.12.22). According to the Amendments for 2024, the total number of cybersecurity professions in Ukraine is 27 professions and 46 qualifications. According to the "Classifier of Occupations" DK 003:2010 and in accordance with the best international practices, the said list of occupations was formed on the basis of the implementation of the best international professional standards, namely, taking into account the European Cybersecurity Skills Framework (ECSF ENISA, ECSF role profile). Also, the paper provides conceptual and methodological recommendations for the formation of a basic model of the content of professional standards, namely, the creation of the content of competencies, knowledge, skills and abilities of the professional standard "Head of a structural unit for information security and cyber defence". The material presented is considered with the aim of analysing and providing practical recommendations on methods and procedures for the implementation and development (adaptation to national requirements) of professional standards (hereinafter referred to as PS) and their corresponding qualifications in accordance with the approved Amendments to the National Classifier of Occupations "Classifier of Occupations" DK 003:2010 (Amendments No. 10, Order of the Ministry of Economy No. 810 of 25.10.2021; Amendments No. 11, Order of the Ministry of Economy No. 5573 of 29.12.2022). This material presents an example in accordance with the European Cybersecurity Skills Framework (ECSF) and in accordance with the Classifier of Occupations DK 003:2010 and the National Qualifications Framework of Ukraine. [ABSTRACT FROM AUTHOR]

Landmine detection is one of the most innovative applications of unmanned aerial vehicles that became possible due to rapid development of both aerial vehicles equipped by different optical cameras and sensors using different physical principles, and object classification and detection methods, including machine learning and especially deep learning. Optical detection is an essential part of the overall landmine detection process that can be performed either separately or in combination with data processing from other types of cameras or sensors. The development of deep convolutional neural networks has dramatically changed the landscape of optical detection by making them de-facto choice number one for the majority of object classification, detection and segmentation tasks. However, the deterrent factor in the case of landmine detection is limited availability of appropriate data for training that different researchers try to overcome in different ways. The assessment of necessary amount of training data for any particular object detection problem still remains an experimental task. Despite several years of development in this area, still there is a shortage of research based on real landmine imagery obtained from unmanned aerial vehicles, so currently any public effort in this direction is valuable and works as an inspiration for new researchers. This paper describes such a study, namely its first iteration in which popular open-source tools are used to build detection pipeline and estimation of their efficiency is done using limited amount of data. It is shown that the problem of limited amount of training data can be effectively overcome by data augmentation and iterational process of training optical landmine detector is demonstrated. The effectiveness of open-source tools and libraries for neural networks training, object detection and dataset preparation is also demonstrated. [ABSTRACT FROM AUTHOR]

The efficiency and safety of civil aviation heavily depend on the robust performance of avionic systems, which provide essential communication, navigation, and surveillance capabilities for flight operations. To sustain the requisite level of reliability in these complex systems, a methodological foundation for their design and modernization is critical. This paper presents a comprehensive framework for the Avionics Management System, emphasizing systematic component analysis and developmental methodologies. This framework includes a multidisciplinary approach that integrates advanced principles, theories, models, and methods drawn from current achievements in information technology, artificial intelligence, mathematical statistics, and decision-making theory. It also considers societal needs, economic trends, and future developmental prospects. Proposed approach ensures that AMS not only addresses immediate operational requirements but is also adaptable to future technological evolutions, thus supporting the life cycle of avionic systems from conception through to utilization. The proposed framework is poised to guide the industry in achieving higher levels of system reliability and maintenance efficiency, with potential implications for the broader realm of civil aviation and its everadvancing technological landscape. [ABSTRACT FROM AUTHOR]

This paper explores the relevance of protecting information systems from ransomware in the context of the rapid development of cybercrime, especially in the context of the war in Ukraine. The article focuses on the shortcomings of traditional anti-virus solutions and the need to introduce new technological solutions for effective monitoring of network traffic. One of the proposed solutions is the use of an enhanced Berkeley Packet Filter (eBPF), which allows detecting potentially malicious activity without interfering with the operating system kernel. The importance of solving this problem cannot be overestimated, given the severe consequences of ransomware attacks, which can range from the loss of important data to complete paralysis of the enterprise infrastructure. It is also noted that the eBPF can play an important role in developing mechanisms for detecting, analyzing and countering cyber threats, which is significant for both theoretical research and practical application in the field of cybersecurity. The rest of the article reveals the issues of using eBPF to monitor the activities of ransomware and detect it in network traffic. A comprehensive approach to evaluating machine learning algorithms that can be used to analyze data collected by eBPF is proposed, with an emphasis on the support vector machine (SVM) algorithm as the most suitable for detecting ransomware. The paper also evaluates the effectiveness of SVM in comparison to other tools, which emphasizes its advantages for cybersecurity tasks. The article concludes with a discussion of the possibilities of implementing eBPF in the practical field of cybersecurity, in particular, its impact on improving the efficiency of security systems, reducing incident response times, and ensuring more dynamic and flexible security management. The authors emphasize that solving this problem iis of significant importance for the scientific community and practical application, suggesting new directions for further research in the field of cybersecurity. [ABSTRACT FROM AUTHOR]

The use of voice control of unmanned aerial vehicles is relevant due to the ease of practical use and new opportunities. This technology allows one to simplify the interface, making it more intuitive and natural. However, the quality and intelligibility of speech signals indoors can be significantly impaired by noise and reverberation. Therefore, before using voice technologies, it is desirable to take into account the effect of interferences by preliminary assessment of their parameters. In this paper, an algorithm for estimating the boundary (truncation time) between the informative and non-informative parts of the room impulse response, which allows obtaining believable estimates of the reverberation time, is proposed. The proposed algorithm is two-stage. At the first stage, "rough" envelope of the room impulse response is calculated using the detector-integrator, which allows one to find an approximate value of truncation time and construct an approximate envelope of room impulse response using backward integration method to obtain an approximate estimate of the reverberation time. In the second stage, output data of the first stage are used to refine the truncation time and reverberation time estimates. Experimental tests using recordings of real room impulse responses testify to the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The paper searches the work process of a ship agent - providing a set of representation services and ensuring compliance with the interests of a vessel located in a sea port for the purpose of loading/discharging of cargo and/or for other purposes. Agents organize and coordinate the arrival, staying and departure of vessels from the seaport. In the paper, the agency service of ships in sea ports is presented as one consisting of three stages of the work of a ship agent - operations that are carried out before the arrival of the vessel in the port, during the stay of the vessel in the port and after her departure. The events that fixed the beginning and end of each stage are defined. The agency service process is rather complex due to the large number of third parties to be involved in the procedures and formalities that allow a vessel to arrive in the port and depart. Such a process is accompanied by the issuing of a number of documents that the agent must fill in in order to inform all interested parties. The main time of the vessels' stay in the port are cargo handling - loading and discharging operations. During this period, agency service includes non-stop control of cargo handling, considering the interests of the shipowner. The three stages of the process under consideration are formalized in their mutual dependence and mutual conditioning using the apparatus of temporal logic. Their clear coordination in time ensures the coordination of the process in general, because only the timeliness and correctness of each stage of the agency service process and its completion allow the next stage to begin. The presented process was formalized with the help of temporal logic operators, which can establish cause-and-effect relationships between the stages and ensure the continuity of the process and the interconnection of the stages themselves. A set of documents necessary for the start, execution and completion of each of the stages has been defined. Some of the documents are external to the ship agent, some are issued directly by him, but each of them is key in the implementation of certain operations in the process of agency service. [ABSTRACT FROM AUTHOR]

The development of transport technologies today requires not only the creation of bases for the optimal technical use of vehicles, their technical operation, but also their maintenance and repair. One of the main tasks of transport technologies is the search for new promising scientific directions and their implementation in practice, as well as ensuring the effective use of the latest technologies and innovative methods for the construction or repair of water transport facilities. In this respect, the use of epoxy-based polymer composites is promising. They are characterised by improved adhesive and cohesive properties compared to other known oligomers, which determines the wide range of their application in water transport. In order to improve the properties of epoxy-based adhesives, additives of different physical nature are introduced into the epoxy matrix at the initial stage of moulding. This paper investigates the effect of the modifier d-ascorbic acid on the thermal properties of epoxies to obtain a material intended for the restoration of ship loading mechanisms. Based on the dynamics of heat resistance as a function of d-ascorbic acid concentration, the optimum content of the additive in the epoxy compound was determined, which is 1,25...1,50 pts.wt.for 100 pts.wt.of epoxy resin. The introduction of a modifier into the epoxy oligomer provides composites with the highest heat resistance values of all the materials studied. The heat resistance values increase from 341 K (for the epoxy matrix) to 352...354 K. The mechanism of increasing the heat resistance of an epoxy matrix in the presence of a modifier is substantiated, which involves the interaction of epoxy resin with an additive and a hardener as a result of chemical reactions. As a result of the reactions of structure formation of the compound based on epoxy oligomer and modifier in the presence of polyethylene polyamine, mainly strong chemical bonds of C-O, NH2, O-NH2, N=O, N-O-H, C=N type are formed, which largely determine the increase of cohesive strength of the newly formed modified epoxy matrices. It should be noted that it is the cohesive strength of the matrix that determines the thermal resistance of the material at elevated temperatures. It was found that the maximum glass transition temperature (333 K) was observed for the modified material containing d-ascorbic acid at 1,5 pts.wt. At this level of additive, the maximum values of both heat resistance and glass transition temperature were observed compared to the original epoxy matrix (327 K). At this modifier concentration, the crosslinking of the compound forms the most cross-linked structural network of an amorphous polymer with the highest number of chemical bonds. [ABSTRACT FROM AUTHOR]

The paper presents the results of determining the amplitude-frequency characteristic of the Z14XEP engine vibration of the Opel Astra G (F69) at idle speed depending on the steering wheel position. The opposite of changes in the values of the amplitude and frequency of mechanical vibrations of the engine on its supports was determined: an increase in amplitude and a decrease in frequency under the condition of the beginning of the movement of the hydraulic fluid through the power cylinder of the hydraulic booster. The actuation of the hydraulic boost system with an electric pump drive generally causes an increase in the amplitude of engine oscillations by 24.2% in the longitudinal and vertical planes, which occurred before the fluid was replaced, and by 14.4% after its replacement. It was determined that, regardless of the state of the hydraulic fluid at the beginning of its circulation through the cavities of the amplifier's power cylinder, the frequency of mechanical vibrations of the engine decreases in the longitudinal and vertical planes by 25%. In the transverse plane, the oscillation frequency is reduced by 35%, except when the hydraulic fluid is changed, when the oscillation frequency remains unchanged. It has been established that the quality of the hydraulic fluid of the power steering system significantly affects the change in mechanical vibrations of the engine only when the steering wheel is deviated from the neutral position. It was determined that a decrease in the viscosity of the new hydraulic fluid by 8.3% compared to the fluid that was replaced causes changes only in the amplitude of engine oscillations. In the longitudinal plane, the oscillation amplitude decreases by 13.3%, in the vertical plane - by 15.1%, and in the transverse plane, the oscillation increases by 25.4%. Reducing the viscosity of the hydraulic fluid used reduced the resistance to its movement through the holes, channels and pipelines of the power steering system and reduced the power take-off to drive the power steering pump. [ABSTRACT FROM AUTHOR]

The paper examines the process of increasing the functional properties of coatings made from powders of self-fluxing alloys by using the method of electric contact sintering. It has been shown that the adhesive strength of the coatings is high. with the base is ensured by the formation of a wide diffusion zone on the side of the base. There is no liquid phase at the coating-part boundary. This indicates that, unlike surfacing, during electrical contact sintering there is no overheating and no mixing zone of the coating material with the metal of the part. X-ray study of the phase composition of coatings shows that under optimal conditions of electric contact sintering, the carbides present in the original powder are mainly retained in the sintered layer, which indicates the preservation of the hereditary properties of the coating material during electric contact sintering. The effect of grinding the carbide phase makes it possible to obtain sintered layers with evenly distributed carbide inclusions, which helps to increase the wear resistance of coatings. Carbide particles have a specific acute-angled shape, which indicates the preservation of the original properties and structure of the coating material during electrical contact sintering. Impulse temperature-force influence in the process of coating formation during electric contact cauterization leads to the dispersion of solid phase particles, which helps to increase the microhardness and wear resistance of the obtained coatings by 2-3 times. The developed technology for obtaining coatings from self-fluxing alloy powders by electric contact sintering leads to a decrease in the cost of manufacturing and restoration of parts due to the replacement of alloy steel with low-carbon steel with coatings from SFP SFS while increasing the resource of parts by 3-5 times. [ABSTRACT FROM AUTHOR]

This paper analyzes the effectiveness of the developed voice control system for robotics based on MFCC and GMM-SVM under the influence of interference in the communication channel. The system allows characterizing individual features of speech signals with their subsequent classification and making a reliable decision on the interpretation and execution of voice commands by robotic equipment. The proposed voice control system for robotics based on MFCC and GMM-SVM is implemented using the following technologies: 1) selection of active speech areas by calculating the short-term energy and the number of zero crossings between adjacent frames of the speech signal; 2) adaptive wavelet filtering of the speech signal, where it is necessary to generate threshold values, which will reduce the impact of additive noise; 3) selection of recognition features, which are used as mel-frequency cepstral coefficients; 4) classification of recognition features based on mixtures of Gaussian distributions and the support vector method using the linear Campbell kernel and the principal component method with a projection on latent structures, which will reduce errors of the 1st and 2nd kind. [ABSTRACT FROM AUTHOR]

Soil parameters monitoring is vital for different areas such as climatological and ecological studies, agriculture, etc. Large scale measurement systems are based on satellite technologies however their spatial and temporal resolutions still must be improved for real-time measurement tasks and control of local areas. Such systems also require in-situ measurements for calibration. It rises the need of local sensor networks development. The paper proposes a soil monitoring system which allows measuring temperature and humidity. Wireless communication between sensors and data collection unit allows to form sensor array at required area without additional cables. Usage of thermal noise method allows to perform measurement of both parameters with a single sensor which allows to avoid soil moisture content changes due to absence of local soil heating which could be caused by probing currents in other methods. Proposed method also allows to increase measurement accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a nano circuit of a full one-bit adder on the proposed five-input majority element. This innovative full adder design is used to development of a four-bit adder based on it. We offer a new single-bit full adder and a four-bit adder nano circuit in quantum-dot cellular automata technology. The proposed design four-bit adder utilizes only 231 quantum cells in a 0.49 µm2 area. It has a reduction in the number of cells, delay and energy dissipation at 1 K compared to the existing works. The QCADdesigner version 2.0.3 tool implements the developed quantum-dot cellular automata full adder and four-bit adder circuits. The implementation results show that the developed quantum-dot cellular automata full adder and four-bit adder circuits have an improvement over other quantum-dot cellular automata full adder circuits. [ABSTRACT FROM AUTHOR]

This paper explores the relevance of protecting information systems from ransomware in the context of the rapid development of cybercrime, especially in the context of the war in Ukraine. The article focuses on the shortcomings of traditional anti-virus solutions and the need to introduce new technological solutions for effective monitoring of network traffic. One of the proposed solutions is the use of an enhanced Berkeley Packet Filter (eBPF), which allows detecting potentially malicious activity without interfering with the operating system kernel. The importance of solving this problem cannot be overestimated, given the severe consequences of ransomware attacks, which can range from the loss of important data to complete paralysis of the enterprise infrastructure. It is also noted that the eBPF can play an important role in developing mechanisms for detecting, analyzing and countering cyber threats, which is significant for both theoretical research and practical application in the field of cybersecurity. The rest of the article reveals the issues of using eBPF to monitor the activities of ransomware and detect it in network traffic. A comprehensive approach to evaluating machine learning algorithms that can be used to analyze data collected by eBPF is proposed, with an emphasis on the support vector machine (SVM) algorithm as the most suitable for detecting ransomware. The paper also evaluates the effectiveness of SVM in comparison to other tools, which emphasizes its advantages for cybersecurity tasks. The article concludes with a discussion of the possibilities of implementing eBPF in the practical field of cybersecurity, in particular, its impact on improving the efficiency of security systems, reducing incident response times, and ensuring more dynamic and flexible security management. The authors emphasize that solving this problem iis of significant importance for the scientific community and practical application, suggesting new directions for further research in the field of cybersecurity. [ABSTRACT FROM AUTHOR]

This article is devoted to the intellectual processing of text information for the purpose of detecting rail news. To solve the given task, the use of deep graph neural networks is proposed. Fake news detection based on user preferences is augmented with deeper graph neural network topologies, including Hierarchical Graph Pooling with Structure Learning, to improve the graph convolution operation and capture richer contextual relationships in news graphs. The paper presents the possibilities of extending the framework of fake news detection based on user preferences using deep graph neural networks to improve fake news recognition. Evaluation on the FakeNewsNet dataset (a subset of Gossipcop) using the PyTorch Geometric and PyTorch Lightning frameworks demonstrates that the developed deep graph neural network model achieves 94% accuracy in fake news classification. The results show that deeper graph neural networks with integrated text and graph features offer promising options for reliable and accurate fake news detection, paving the way for improved information quality in social networks and beyond. [ABSTRACT FROM AUTHOR]