It is generally known that QoE reflects the actual customer experience of network services. This parameter is not limited to network performance, but also includes aspects of customer behavior, ISP brand reputation, service standards and cost. That is why, in order to meet the needs of customers, providers should regularly determine the current quality of service to subscribers, which definitely correlates with QoE. To establish these relationships, it was decided to use machine learning models. In this regard, the paper recommends applying a machine learning model called Random Forest for data analysis, where the stages of analysis are considered in detail, taking into account historical information about QoS and QoE, respectively. In the course of the study, it was possible to test the method of QoE prediction based on QoS parameters based on machine learning algorithms. It was established that the applied methods allow to reduce the amount of data without losing the accuracy and efficiency of the calculations performed by the machine learning model. Thus, the presented approach can be applied by telecommunication providers and mobile operators in their activities for continuous monitoring of user satisfaction with the provided services.
In this paper, we introduce a scalable, AI-driven chatbot designed for real-time diagnostics in Industry 4.0 manufacturing plants. By incorporating Google Dialogflow and a plant-specific knowledge graph, the chatbot enables seamless interaction with users while requiring minimal reconfiguration when adapting to new environments. The integration of BERT in the back-end empowers the chatbot to efficiently identify errors. Furthermore, a self-learning module continuously scans the manufacturing execution system (MES) database for new errors, generating learning data for the automatic re-training of the BERT-based neural network. Although there are opportunities for refinement, the chatbot exhibits significant potential as a scalable, supplementary first-line support system in the manufacturing sector.
Food safety and quality are extremely important for consumer satisfaction. Eggs are an important source of protein worldwide and occupy an important place in many industries. Therefore, detecting and preventing damage that may occur in the egg production process is of great importance in terms of both protecting the health of the consumer and reducing the costs in the egg industry. However, the suitability and quality of eggs for consumption depends on various external factors throughout their journey. Among these factors, physical damage is one of the most common and important. In the egg industry, damage to eggs and therefore not being able to reach the consumer is an important cost factor. This means a great loss, especially for businesses that produce on an industrial scale. Damage detection and prevention methods can help reduce these losses. In this study, a dataset containing a total of 569 images in three classes was used to detect egg damage. There are three classes in the dataset named crack, empty and good. For the classification of images, VGG16 and VGG19 models from CNN (Convolutional Neural Network) architectures were used with transfer learning method. As a result of the classification, 93.8% classification success was obtained from the VGG16 model and 95.1% from the VGG19 model. F1 Score, precision and recall metrics of the classification performance of the model were also analyzed. By considering the advantages and disadvantages of detecting egg damage in the image, a basis for future studies in this field has been established.
An optimal control system for the production of mineral fertilizers in a fluidized bed granulator has been built. The main control channel is the dependence of the coolant temperature and the temperature of the granules. The criterion of optimality for the control system is obtained. The transfer function was obtained using the MATLAB System Identification package. The transition to the vector-matrix model is made. The Riccati equation is solved. The main factors influencing the process are identified and a control system with LQR-regulator is created, which meets the requirements of stability, dynamics and reliability. A transient process is obtained, which brings the temperature of the granules to a given level in 364 K. The transition process with LQR-regulator lasts 18.7 seconds, which is a real value for regulators of this type.
In this investigation, we present a new method of Author Identification (AI) based on two different modalities: Transcript Text (TT) and Speech Signal (SS). This research work is performed on a corpus of several discourses given by Famous Politicians in English (FPOL corpus). The originality of this work is that we use both Speech Signal and its Text Transcript during the classification process. That is, 14 famous politicians are considered, where 6 are female politicians and 8 are male politicians. The first analysis uses the text modality based on three classifiers and three features: Character 3Grams, Character 4Grams and Words, while the second analysis is based on those textual features in association with the average Pitch (Fo) of the speech signal modality. The proposed association uses a logical filtering based on the average Pitch range in order to correct the errors of identification if any. The experiments of author identification conducted on the FPOL corpus show that the association of the two modalities enhances considerably the identification performances. The average accuracy improvement brought by the speech modality is about 5% for character 3Grams and 4Grams, and it is about 12% of improvement for words.
The rationality and benefits of software model-driven development (MDD) continue to be the subject of studies and debates, both scholarly and among practitioners. This study argues the usefulness of applying a UML profile as an MDD artefact. The developed UML profile intends to model the Web service selection process by non-functional properties with the Logic Scoring of Preference (LSP) method. The primary profile's stereotypes determine the concepts of Web service quality criterion and LSP aggre-gators. The models created using the proposed profile were validated by the MagicDraw tool, and their effectiveness was confirmed when the actual model-driven development of the software application.
Today's world is rapidly changing, and educational institutions face many challenges that have yet to be solved. One of these tasks is the optimal organization of support for students in the matter of their future employment. The authors of this article consider the development and implementation of the Cross-Universities-Business (CUB) platform on the base of the Digital Education Ecosystem (DEE) to be the optimal solution to this problem. To check the relevance of this idea, the authors conducted a survey, the purpose of which was to find out the attitude of employers from different countries to the implementation of the CUB platform. The results of the survey showed a positive attitude of employers towards the project, although they highlighted some additional issues and tasks that will need to be resolved during the work.
In Japan, many in-home exercise programs have appeared to improve the motor function of the elderly through self-care. However, a challenging point always exists in evaluating the process of exercise programs quantitively and non-invasively for further reflecting the health status. As a preliminary progress, we present and discuss a vision-based novel method on edge that aims to evaluate an in-home exercise program in this paper. Our key idea is to integrate multiple different vision-based pre-trained models. In the proposed method, we mainly integrate and call multiple pre-trained models to recognize human facial, skeletal, and hand movements with edge computing. Also, we propose to evaluate an in-home exercise program process from the Euclidean distance, velocity, and angle of the two-dimensional coordinates of feature points in the time series. Through experiments, we estimate the physical health status from the analysis of body movements in the elderly.
The unprecedented development of blockchain technology has sparked a wave of innovation in payment systems areas. Blockchain offers a decentralized, secure, and transparent platform for conducting transactions. It does not have any additional intermediaries, such as banks. Blockchain provides many advantages and encourages the qualitative transformation of payment systems, offering new opportunities to create efficient and low-cost payment systems. However, blockchain-based payment systems are still in their infancy, and rooms for improvement still exist in their implementation. This paper proposes using the non-fungible token to interest customers and provide them with additional options when paying with a blockchain-based payment system.
Systems that utilise biological data typically necessitate a module with the capacity to analyse biomedical data. This article investigates the problem at the specified location and outlines the potential solutions at our disposal. Then, we'll examine the deployed technology. This technology has the potential to be bundled as a container for a microservice architecture and provides data analysis capabilities. Each module must contain fundamental features and capabilities, such as fuzzy machine learning and data mining methods. Similarly, this component must be able to generate an accurate report based on the results of its analysis. The primary benefit of such a system is its modularity, which enables quick adaptations and expansion for various data types, as well as simpler adaptation of the modules to newer technologies.
This paper dwells upon the solution of the task of creating the voice assistant to control the personal computer based on Windows in English using third-party language engines and the voice recognition models. The Python programming language, the Speech Recognition and PyTorch library are used to solve this problem. The article analyzes similar programs, tells about the stages of software development, demonstrates the program demo version example and analyzes the prospects for project work. The created model for speech recognition, which was developed during the implementation of this research has the following results as average loss 0.4305, average WER 0.3428 and average CER 0.121629.
The article presents an approach to pollution data for EU countries correlated to the Summary Innovation Index (SII). The analysis is based on data from 2015 to 2020. It compares pollution with health problems and deaths, and innovation. As it will be shown, it is a significant issue for EU countries. The approach is connected with $CO_{2}$ emission and its influence on health and people's attitudes toward pollution and climate change.
The work is dedicated to the analysis of algorithms and software tools for scanning web applications with the aim of detecting vulnerabilities according to OWASP top 10. Incorrect or insecure programming can lead to the emergence of vulnerabilities that can be exploited by malicious actors to gain unauthorized access to data or render applications inoperable, thereby violating confidentiality, integrity, and availability. The main objective of this research is to analyze existing algorithms and software capable of automatically scanning web applications for vulnerabilities such as “code injection” and “insecure design”. The work presents an overview of existing vulnerabilities in web applications, specifically “code injection” and “insecure design”, as well as describing the main approaches and methods used for their detection. Subsequently, scanning algorithms based on the identified approaches and methods are developed and discussed their implementation.
Multi-objective decision systems for the management, monitoring and control of complex processes require the application of new methods and models of abstraction and formal description based on intelligent computing structures to ensure optimal overall decision-making. These computing structures can be built on the basis of Multi-Agent systems. In this paper it is proposed the development of a Multi-Objective Based Multi-Agent Decision-Making System that ensures the process of searching for the optimal solution based on genetic algorithms and its application in the decision-making process. The Multi-Agent system features a distributed computing structure consisting of lots of heterogeneous data processing nodes. The functionality of agents is described based on mathematical models and sequence diagram, which explains the interaction between the set of Agents. The structure of the decision-making system is presented on two levels of abstraction: the Multi-Agent level of production and management, and the Information level of communication, storage and data processing.
The experience of wide use of stepper motors as drives is considered and investigated. The main goal of this research is the development of technical and algorithmic tools that implement information technology to determine the error and adequacy of the Simulink model based on a single- board Arduino controller. A measurement scheme has been developed that provides an unambiguous relationship between the error of determining the angular position of the shaft and the error of direct measurement of linear displacement. To simulate the engine operation process in the Matlab environment, it was carried out using a single-board Arduino Uno Rev 3 controller. To increase the accuracy of measuring small angles and angular displacements, a metrological scheme of laser beams was used, which converts the angular displacement into a linear one, the accuracy of which is regulated. An analytical expression for determining the angle of rotation based on the linear movement of the beam point along the ruler has been constructed, which clearly demonstrates the influence of the main factors on its angle error. With the help of a computer, the values of the angles were set according to the research program, and the angles of actual rotation of the shaft were experimentally measured. According to the results of the conducted experiment, a comparison of the estimation error of the shaft rotation angle samples was made and their statistical difference was determined. The technology of experimental determination of the statistical difference of the stepper motor model what was built in the Matlab environment by instruments of Simulink are presented. This technology transparently demonstrates the influence of the main factors on its value.
The paper presents the approach to identify fake signatures based on the image analysis. The problem is related with the forensics operations in order to distinguish handwritten signatures made by the human from the machine-originated counterfeits. The identification system is based on the selected artificial intelligence-based classifiers and processes features extracted from the signature images. The source material comes from either human or the 5-dimensional printer, being able to mimic a hand with the pen writing on the sheet of paper. Each image is then processed by the profilometer to extract important information allowing for distinguishing the original signature from the false one. Features include attributes related with the pen's position and inclination, obtained through the Fourier and wavelet transformations. The identification is then made by the intelligent classifier. For the project multiple algorithms were selected and tested regarding their accuracy, such as multilayered perceptron, decision tree or k Nearest Neighbors classifier. Presented experimental results show the ability of the system to support human during the task of the signature authenticity verification.
We discuss a dual band Complementary Split Ring Resonator (CSRR) based Rectangular Dielectric Resonator Antenna (RDRA). The proposed design operates at 2.3 GHz and 2.6 GHz resonance frequencies respectively. The dual band operation is achieved by using CSRR unit cell in the ground of the proposed antenna along with the Dielectric Resonator (DR). The Dielectric Resonator Antenna (DRA) is excited using a simple microstrip feed line. The 2.3 GHz resonance frequency is obtained by excitation of the CSRR unit cell while the 2.6 GHz resonance frequency is achieved by the excitation of the DRA. The proposed design is simulated using Computer Simulation Technology (CST) software. The antenna has high gain of 6.86 dBi at 2.3 GHz and high gain of 6.4 dBi at 2.6 GHz respectively. Considering the overall performance, the proposed DRA has good characteristics for the WiMAX and LTE wireless applications.
The main idea of the article is that the decision support object may possess declarative knowledge, but when it comes to executing technological tasks or solving complex technological problems, it requires procedural knowledge. In other words, having information about what needs to be done (declarative knowledge) might not be enough to ensure error-free execution. Practical knowledge of how to perform tasks (procedural knowledge) is equally crucial. In summary, the proposed study aims to build an intellimedia automated system (IMAS) based on Olson's theory, with a focus on providing decision support that incorporates both declarative knowledge and procedural (algorithmic) knowledge. The objective is to help users tackle technological problems more effectively, minimize errors in their actions, and improve overall problem-solving outcomes.
The BBC micro:bit is used worldwide as a computer hardware tool for teaching Informatics. Slovakia is no exception, and a significant part of lower secondary and high schools teach with micro:bits. In most cases, it starts with simple programs and basic hardware, which are then extended with a variety of additional components. We decided to not only extend the components but also the teaching and to link Informatics with the subject of Biology. The research goal was to find out if it is possible to link Biology and Informatics through a micro:bit project so that students understand that nature and technology can form an interplay. We have made this link in the framework of automatic irrigation with the help of the Smart Home Kit.
Regional monetary integration is traditionally considered from two perspectives: the similarity of participants and the overall efficiency of the union, with the latter favoring diversity among members. European states are both pioneers and benchmarks of currency unions, providing a good platform for research into both phenomena. A cluster analysis of indicators of nominal convergence was conducted to assess the homogeneity and heterogeneity of the European region. The effectiveness of existing currency integration was evaluated using gravity modeling. The research found that there are noticeable processes of convergence between European states according to the selected indicators. This convergence is even more evident when compared to former USSR members, who were once a single state. Additionally, the processes of currency integration in Europe have been accompanied by a significant strengthening of intra-regional trade. However, the influence of monetary integration is considered to be positive, but not crucially significant.
