Abstract: Within the framework of this article, the Staking-ensemble of methods for analyzing academic statistics is proposed, which makes it possible to increase the effectiveness of implementing academic monitoring tasks. The relevance of the topic is the need to develop a distributed information and analytical system that integrates information resources and general principles of models and methods of monitoring the infrastructures of academic facilities based on education statistics. Education statistics is a system of indicators characterizing quantitative and qualitative changes taking place in the field of education which makes it possible to obtain information for each level of education on the number of educational institutions, the contingent of students, characteristics of the internal efficiency of the learning process, data on admission to educational institutions, graduation of specialists, quantitative and qualitative characteristics of the teaching staff, the state of the material and technical base of educational institutions. The object of the study is the system of formation of statistical data in education. The subject of the study are the approaches of combining intelligent methods of data analysis. The idea of the work is the use of modern methods of data processing in the implementation of academic monitoring in order to successfully solve the tasks of the state program for the development of education. The goal of the study is to develop an algorithm for Staking-ensemble methods for analyzing academic statistics to improve the effectiveness of academic monitoring tasks. The scientific novelty of the research is the staking-ensemble for analyzing education statistics, which aggregated the following 3 types of intellectual models: the Bayes algorithm, the decision tree algorithm, and the neural network. The practical importance of the research results lies in the applicability of the proposed Staking-ensemble algorithm for solving the problems of information and analytical support of management decision-making when tracking the business processes of monitoring, controlling and forecasting the state of distributed academic objects at various levels of training, management and functioning.

Keywords: academic statistics; analysis of indicators; Staking-ensemble algorithm; combination of intellectual methods

Abstract: This paper investigates the dynamic parametric estimation of a solar cell system, by using balancing composite motions optimization (BCMO). The BCMO technique was first online published in 2019, the main idea is to balance composite motion properties of individuals in solution space, to equalize global and local searchability. To evaluate the performance of BCMO, experimental tests are carried out in photovoltaic cell parameters estimation of R.T.C.France which is collected under 1000 W/m2 at 33oC, by changing the population size of BCMO. And then, the performance of BCMO is compared with wellestablished parameters estimation methods in terms of convergence speed, computation time, and RMSE value. The results demonstrate that the proposed approach can be accurately estimated for photovoltaic model parameters.

Keywords: Balancing Composite Motions Optimization (BCMO); Photovoltaic Model; Parametric Estimation

Abstract: Offering human machine interfaces capable of handling cultural variation in speech is an exciting topic in cognitive info-communication. From a machine learning point-of-view, this paper examines Automatic Speech Recognition (ASR) with respect to transcribing interactions occurring in a language environment where a particular dialect of a pluricentric language is spoken. Conservative retraining, transfer learning, multi-task training, matrix factorization, i-vector based techniques as well as adversarial and teacherstudent training are all considered suitable approaches for the adaptation of deep neural acoustic models in ASR. Facing a problem of adaptation for accented speech, which method should be preferred? Comparing these techniques is often complicated, as different experiments are carried out on diverse datasets and within various frameworks. It is also worthwhile analysing possible combination of such techniques within complex systems. The objective of this work is to systematically compare and analyse a number of domain adaptation techniques for ASR using the same framework, in order to allow for a fair comparison on adapting US English acoustic models for particular accents. Our results indicate that, when properly hyperparametrized and carefully regularized, the easiest approaches, requiring less complexity and reduced computational power, can perform equally well as the more complex ones.

Keywords: human-machine interaction; speech recognition; adaptation; dialect; conservative training

Abstract: Handwriting and Drawing are functional tasks involving physical and cognitive processes. Recently they have been investigated for detecting cognitive and motor disorders. In this work, handwriting/drawing features are investigated for identifying connections with personality traits. For this purpose, an experiment comprising seven handwriting/drawing tasks has been administrated to 78 young adults (mean age=24.6 ± 2.4 years) equally balanced by gender. Handwriting and Drawing activities - both on and close to the paper - had been recorded online through a digitizing tablet able to measure handwriting and drawing features such as pressure, speed, dimension, and inclination of each pen-stroke on the paper. Participants were asked to fill the Big Five Personality Questionnaire (BFQ) and according to the scores obtained for each of the 5 dimensions and 10 Big Five sub-dimensions, were partitioned into three categories: low, typical, and high. To evaluate whether the recorded handwriting/drawing features are connected with personality traits ANOVA repeated measures have been performed with gender and group category (low, typical, and high) as between and the listed handwriting/drawing features as within factors. The analyses show significant differences among low, typical and, high BFQ scores for the main Big Five dimensions and the ten Big Five sub-dimensions, indicating that personality traits can be revealed by a quantitative analysis of the proposed handwriting/drawing features.

Keywords: Personality traits; Big Five; Handwriting and drawing tasks; Graphology

Abstract: In this work, the impact resistance of an aluminium-rubber sandwich composite plate under impact loading is investigated using experimental and numerical approaches. The experimental tests were carried out using a perforation gas gun for a wide range of impact velocities from 40 m/s to 120 m/s and for two different temperatures 20°C and 150°C. Based on experimental results, the failure mode, initial/residual velocity curves and the ballistic limit velocities of aluminium under different temperatures were analysed. The effect of rubber reinforcement layer thickness in the aluminium sandwich was also evaluated. It was found that the composite plate with 9 mm of rubber provides higher performance in terms of energy absorption than that of 3 mm thick, which is demonstrated by approximately 10% reduction in the ballistic limit. In contrast, an increase in temperature considerably reduces these ballistic performances. It was also found that petaling is a typical failure mode in the perforation process. The rubber has an effect on the failure pattern of both aluminum plates. In addition, a thermomechanical model using a finite element method was developed to simulate the response of the aluminum-rubber composite plate under a high energy rate loading condition. The numerical results show a good agreement in relation to the experimental results in terms of failure mechanism, number of petals and energy absorption.

Keywords: aluminium-rubber sandwich panel; pneumatic gas gun; high strain rates

Abstract: Hyperelastic materials are widely used in many industries. Their use requires thorough knowledge of their strength parameters over a wide temperature range. However, determination of the parameters of hyperelastic materials is still a challenge. Therefore, the paper presents research methodology allowing determination of the properties of hyperelastic materials in a wide range of stretch and temperatures (from +50°C to -25°C) on the example of NBR (nitrile butadiene rubber) and CR (chloroprene rubber) elastomers. On the basis of physical premises, a hyperelastic constitutive model was also modified through introducing an explicit dependence of strain energy on temperature, allowing an accurate reflection of the properties of the tested materials. The material parameters of the adopted strain energy functions for the NBR and CR were determined with R2 not less than 0.999.

Keywords: elastomers; polymers; uniaxial tension; temperature effects; failure

Abstract: In August of 2020, the United Nations reported that the COVID-19 pandemic had affected 1.6 billion learners, in more than 190 countries and on all continents [1]. The closing of schools and other learning spaces impacted an astonishing 94% of the world’s student population. These sudden school closures, at all levels, had the immediate and unprecedented effect of triggering a mass migration to emergency remote teaching. While mass vaccinations have enabled educational institutions to reopen and students to return to classrooms in the Fall of 2021, the educational disruption caused by the COVID-19 pandemic is far from over. Higher education must now permanently transition from reductionist, emergency remote learning systems to permanent, holistic online learning platforms. In order to better understand this transition, an online survey was delivered to diverse groups of international students attending Corvinus University and ESSCA School of Management, at the beginning and end of the Spring 2021 semester. The analysis of this survey, strongly indicates that the home and social environments of University, had a significant impact on the student’s learning aptitudes.

Keywords: higher education; COVID-19; emergency online learning; learning experience; sentiment analysis

Abstract: PWM-driven feedback systems are known for demonstrating the multistable behavior within the stability margins of a nominal operating mode. With the transition of the system to the stable coexisting mode, the ripples of the variables increase and the overall efficiency deteriorates; therefore, it is an undesired behavior. We study the possibility of controlling multistability on the model of a chopper-fed DC drive. The proposed control takes the form of short forcing, temporarily moving the margins between the basins of attraction of the coexisting modes and thus driving the system to the nominal mode of operation. We also propose a universal control strategy, combining different types of short forcing, that are applied in a repeated manner with different settings. The latter control strategy overcomes unpredictability of the system’s behavior caused by the fractal basin boundaries, and also, by external disturbances or noise.

Keywords: DC drive; multistability; basin of attraction; control of multistability

Abstract: For most users, everyday objects are connected to the Internet, using their computational capabilities to form a whole entity, called the IoT (Internet of Things). This article deals with the creation of an available IoT device, with which we will be able to classify the emotional states of the user. Using existing technical solutions and methods that use approaches based on the application of sensors while maintaining their non-invasiveness, we have created such a device. In the analysis of the current state, we describe the possibilities of classifying human emotions, existing classification methods and how the measured data are related to human emotions. Next, we describe the methods used to analyze the collected human physiological signals. We propose a complex system for measuring physiological human signals and subsequent recognition of emotional states. We describe the composition of the proposed system, as well as the specific hardware and software used. At the end, we focus on the functionality and testing of the proposed system. Finally, we perform several measurements, where we evaluate their results and the reliability of the proposed system.

Keywords: Internet of Things; emotions; data; sensors; heart rate; facial recognition

Abstract: Nowadays, due to fast-increasing economic development, the current available road infrastructure is more and more crowded, which creates frustration for the people using them. In the current research, a model is proposed for authorities, companies and individuals, to choose the best available route(s) and road sections(s) for improvement measures, optimal delivery or commuting. In the proposed model, a fuzzy signature rule base, is introduced for commuters, which distinguishes all the relevant factors during commuting. The actual decision process is based on various input data, such as peoples’ habits, assumptions and preferences and various other factors.

Keywords: fuzzy signature rule bases; personal preferences; route selection

Abstract: In this time of digitalization, leaders have to face new challenges and concentrate on engaging subordinates, due to the hybrid working conditions. One of these challenges is the Digital Competence Expectations for Public School Leaders, published in 2021, by the Digital Pedagogical Development Working Group. The emerging importance of engagement is supported by a great deal of scientific research. However, it is still questionable… what directly determines engagement and affects subordinates in the engaging process? Our review aims to analyze the characteristics of engaging leadership and leaders’ behavior, which contributes to the engagement of coworkers. Taking the challenges of the digital world into consideration, we make some practical suggestions for future leaders and HR professionals, in order to strengthen their organizations and retain valuable employees.

Keywords: engaging leadership; engagement; digital workplace; empowerment; HR solutions; leadership practice

Abstract: This article introduces the operation of a previously developed Emotional Pattern Generator and its user-centered validation, through the use of an emotion-driven design case study. As the primary work, various geometric patterns were generated by an in-house Emotional Pattern Generator (EmPatGen) that was successfully developed in MatLab to generate patterns based on user preferences. 33 individuals participated in this eye-tracking study, in order to fully comprehend the complexity of the fuzzy logic of the EmPatGen system. The participants were required to select a geometric pattern from a 3x3 palette, based on a situation, with the assistance of personas designed to indicate emotions during the tasks. Eye-tracking results contributed to a comprehensive understanding of the cognitive processes underlying pattern selection, allowing for the user-centric improvement of the applied pattern generator. For instance, it was discovered that female factors played a more significant role in the selection activities; therefore, the fuzzy logic of the generator presented in this article could be improved through a series of user-centered experiments.

Keywords: Eye-tracking; Emotional Design; Pattern Design; Interdisciplinary Research; Design for Experience

Abstract: Ensuring the safety of the equipment, its environment and most importantly, the operator during robot operations is of paramount importance. Robots and complex robotic systems are appearing in more and more industrial and professional service applications. However, while mechanical components and control systems are advancing rapidly, the legislation background and standards framework for such systems and machinery are lagging behind. As part of a fundamental research work targeting industrial robots and industry 4.0 solutions for completely automated slaughtering, it was revealed that there are no particular standards addressing robotics systems applied to the agri-food domain. More specifically, within the agri-food sector, the only standards existing for the meat industry and the red meat sector are hygienic standards related to machinery. None of the identified standards or regulations consider the safety of autonomous robot operations or human-robot collaborations in the abattoirs. The goal of this paper is to provide a general overview of the regulations and standards (and similar guiding documents) relevant for such applications, that could possibly be used as guidelines during the development of inherently safe robotic systems for abattoirs. Reviewing and summarizing the relevant standard and legislation landscape should also offer some instrumental help regarding the foreseen certification procedure of meat processing robots and robot cells for slaughterhouses in the near future.

Keywords: robotic meat processing, robot standardization, agri-food robotics