Pulmonary emphysema is a complicated disease caused by irreversible damage to the wall of the pulmonary alveoli and causes 5% of the total mortality worldwide. This paper presents the development of an artificial neural network (ANN) for the diagnosis of pulmonary emphysema. Following biomarkers were used for the development of the ANN: AAT (alphal-antitrypsin), FEV1 (forced expiratory volume in 1 second), FVC (forced vital capacity) and FEV1/FVC (ratio forced expiratory volume in 1 second / forced vital capacity). The dataset consisted of 300 patients: 210 healthy subjects and 90 subject with disease. The neural network has 4 input parameters and 1 output parameter. For the final architecture, a neural network with 13 neurons in hidden layer was chosen based on the training results. The developed ANN has shown good performance and has a potential for use in this field.

This paper focuses on the problem of diagnosing polycystic ovary syndrome (PCOS), which is one of the leading disorders of the female endocrine system. Although the incidence of this syndrome is quite high, physicians and patients still often encounter problems in their detection, as well as with the ineffectiveness of prescribed therapy. For the development of expert system, a database containing following parameters was used: oligo ovulation, anovulation, free testosterone, free androgen index (FAI), calculated bioavailable testosterone, androstendione, dehydroepiandrosterone, ovarian volume, number of follicles, obesity. The presented dataset contains 1000 samples distributed in two categories: (1) heatlhy subjects and (2) subjects with disease. The purpose of the developed system is to classify instances with polycystic ovary syndrome using artificial neural networks (ANN s). The overall performance evaluation of the system resulted with accuracy of96.1 %, sensitivity of96.8% and specificity of90% indicating significant potential of ANNs in this field. Since the system predicted a total of 157 positive and 23 negative, this leads us to the result that the sensitivity of our system is 96.8%, specificity 90% and accuracy 96.1 %.

The aim of this paper is to investigate the state of performance of audit firms registered in the Republic of Serbia, as well as the factors that manage performance. The research is based on the entire population of audit firms, based on financial reports for the period 2019-2020. that are publicly available. The performance of audit firms will be investigated from the aspect of profitability performance, where the indicators of return on assets nad return on equity is most often used. Performance analysis will be presented through descriptive statistical analysis. Performance management will be analyzed in terms of the impact of independent factors on ROA and ROE. The following will be defined as independent factors: the size of the audit firm, liquidity, indebtedness, belonging to the big four, growth and the like. The research of the influence of independent factors on the dependent variables of the performance of audit firms will be conducted on the basis of regression analysis. The results of descriptive analysis should indicate the state and trend of performance of audit firms, while the results of regression analysis should indicate the nature of the factors that drive the performance of audit firms.

While examining biomedical signals, signal classification as well as measurements, quantifications and their assessment is very important for studying different diseases and disorders. Through this paper, we have focused on different signals and biomedical devices, whose purpose is to give high quality information about diseases and disorders in prenatal age. The main focus was on ultrasound techniques and the relationship between 2D, 3D and 4D ultrasound, on Doppler ultrasound, cardiotocography, KANET test, and in general, comparison of standardized and automated techniques. Purpose of this paper is to compare some of the available techniques used to assess the fetus in the womb, how they advance through time and whether they are being automated.

The primary focus of this paper review is to summarize the most important facts and findings regarding the use of Artificial Intelligence (AI) in the modeling, processing and analysis of biomedical data and to give an insight on the contributions of AI, Machine learning and Deep learning to the field of medicine. This study compiled and analyzed work published in the period between 1986 and 2021 related to the use of AI in medicine, its various applications and historical development, with a focus on papers published from 2015 until today, due to the accumulation and development of newer technologies. Out of a total of 117 papers reviewed, 52 were selected for a more detailed analysis and presented in a table summarizing the key points, advances, advantages and disadvantages of AI, its subfields and algorithms. The goal of this paper was to extract the most famous AI learning algorithms, past and current, and focus on the methods of modeling, processing and analysis by which these algorithms operate and perform tasks in order to help doctors and experts better understand the underlying mechanisms behind biological processes, and in some cases, even replace humans in data classification, identification, diagnosis and prediction of different conditions associated with diseases.

As a consequence of the progress of the modern mobile medicine, wearable technologies, especially ECG wearables tend to become indispensable part of peoples' lives. As applications and devices for tracking cardiac electrical activity are rapidly entering the market, it is important to compare individual ECG wearable devices. This review takes a systematic approach on the analysis of wearable ECG devices. It provides a detailed introduction on the updated methods, to create a comparison between individual features of devices, and to evaluate techniques for fall risk assessment, diagnosis, and prevention. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) instructions were used as a report standard. In an effort to collect the appropriate data, various databases were queried together with specific subject-oriented keywords. This was combined with different inclusion and exclusion criteria to find the relevant data. To further improve the data gathering and reduce bias, a Zotero tool was used. The results of this paper show the comparison of the different devices and their features. All findings can be observed in the table and in words. As information for the QardioCore are scarce, all six authors consolidated on the VitalCore being the most accurate ECG wearable device, as its sensitivity and specificity are the highest. Recent advances in wearable ECG devices allow for more trouble free out of clinic fall risk assessment, detection and prevention. As people tend to prefer the comfort of their home over doctors, such progress will assure the everyday emerging of new wearables.

In this paper, a measurement campaign for off-body communications in an indoor environment is investigated for a set of on-body antennas. The channel impulse response was measured with the user approaching and departing from an off-body fixed antenna using two user dynamics, standing at fixed positions and walking. The processing of the measurement data allowed to evaluate system loss statistics. Different antenna configurations are classified in terms of mobility and visibility depending on the on-body antenna placement. A dependence on distance is found for the antennas with the lowest mobility (chest and head), while no significant dependence is found for the antennas with the highest mobility (arms and legs). Regarding the standard deviation of system loss, higher values are found in walking scenarios (above 1.0 dB) compared to the standing ones (below 0.6 dB) showing a clear dependence on mobility.

This paper presents an Artificial Nerual Network (ANN) for identification of postmenopausal women who are at high risk for developing osteopathy. While 800 patients took part in the study, 180 were used for network training. The following parameters were used: T-score (from −2,5 to −4), Age, Blood calcium level (<1,9 mmol/L), Blood vitamin D level (<20 ng/ml), Hip fracture, Spine fracture, Joint fracture, Glucocorticoids use, Smoking status, and BMI. The network has 10 input parameters and 1 output parameter. For the final architecture of expert system, a neural network with 20 neurons in hidden layer was chosen based on the training results. The signal from each neuron from hidden layer is directed to neuron in output layer, where this neuron processes the signal and gives desired output of the network. The sensitivity was 97,5%, specificity 70%, and accuracy 94,44%.

Education and society always lag behind technical state of the art achievements. General computer literacy needed decades to become the part of public acceptance after computers become available. Smart phones enters our life and becomes an extension of the human body yet we still do not know how to properly apply them in education. Artificial intelligence is an exciting technology that adapts educational experiences to different learning groups, teachers and tutors. Intelligent Management Systems (IMS) are not a novelty in education though. There have been many experiments, but they have all somehow stalled due to immature technology or misinterpretation. We can now see a new impetus for AI in education, and its impact will soon be very noticeable. In education, AI can: personalize learning, connect and create innovative learning content, perform tutoring in intelligent tutoring systems, is used to help pupils with special needs, help teachers assess, give students access to learning content, and translate educational content from different languages, removing language barriers. This article will explore the different possibilities of using AI in education and its use in education.

By delivering end-to-end latencies down to 5ms, data rates of up to 20Gbps, and ultra-high reliability of 99.999%, 5G is extending the capabilities of numerous industry verticals, including the Transport & Logistics (T&L). As the T&L industry has a pivotal role in modern production and distribution systems, it is expected to leverage 5G technology to significantly increase efficiency and safety in the T&L operations, through automating and optimizing processes and resource usage. However, to be able to truly benefit from 5G, the design, the development, as well as the management, of T&L services need to specify and include 5G connectivity requirements, and the features that are tailored to the specific T&L use cases. To this end, in this paper we introduce the concept of Network Applications (NetApps), as the fundamental building blocks of T&L services in 5G, which simplify the composition of complex services, abstracting the underlying complexity and bridging the knowledge gap between the vertical stakeholders, the network experts, and the application/service providers, while specifying service-level information (vertical specific) and 5G requirements (5G slices and 5G Core services). In this paper, we exemplify the concept of NetApps leveraging one of the VITAL-5G use cases, which provides faster and safer operations of vessels in the port of Galati, the largest port on the Danube River.

The COVID-19 pandemic has accelerated the process of digital transformation of higher education institutions. In a very short period, teachers and students abruptly switched to digital environments, which they had not used until then. As online teaching is very different from traditional teaching, teachers and students are faced with numerous new challenges. Online teaching requires a specific environment that primarily implies the availability of adequate technology as well as the skills that both teachers and students should have. Some higher education institutions have completely switched to online mode, while others have practiced a combined (online and offline) mode. The aim of this paper is, based on a questionnaire developed by Bernard et al. (2007), to examine the level of online skills, readiness for online learning and learning initiatives, attitudes about online learning, as well as the desire for online interaction with teachers and colleagues by the surveyed students.

The success of a company depends on the employees, so the challenge for managers is to monitor their needs continuously and find ways to encourage them to work and achieve goals. By using a combination of compatible material and non-material techniques within motivation strategies, managers link long-term company goals and rewarding employees for work and achievements. The aim of this paper is to get insight into the used motivation techniques and strategic approach to motivation in companies in the Federation of BiH (FBiH). The survey was conducted in early 2019 and covered 63 companies. The most commonly used material motivation techniques are salaries, bonuses, and paid leave, and the most commonly used nonmaterial techniques are appropriate working hours, information on work results and the possibility of advancement. Almost half of the managers state that there are established rules for motivating employees in their companies, slightly more than ¼ point out that there is an established plan for motivating employees that is continuously implemented. Only a part of the surveyed companies, have a continuous, systematic way of monitoring employee motivation. Assessing motivation and taking corrective action is most often carried out by top management, two or more times a year. The results indicate that some companies in the FBiH have not yet realized that the human factor is a key factor in achieving better business results. In order for motivation to be truly effective, it must be approached in a planned and continuous manner.

—The power system state estimation (SE) algorithm estimates the complex bus voltages based on the available set of measurements. Because phasor measurement units (PMUs) are becoming more widely employed in transmission power systems, a fast SE solver capable of exploiting PMUs’ high sample rates is required. To accomplish this, we present a method for training a model based on graph neural networks (GNNs) to learn estimates from PMU voltage and current measurements, which, once it is trained, has a linear computational complexity with respect to the number of nodes in the power system. We propose an original GNN implementation over the power system’s factor graph to simplify the incorporation of various types and numbers of measurements both on power system buses and branches. Fur-thermore, we augment the factor graph to improve the robustness of GNN predictions. Training and test examples were generated by randomly sampling sets of power system measurements and annotated with the exact solutions of linear SE with PMUs. The numerical results demonstrate that the GNN model provides an accurate approximation of the SE solutions. Additionally, errors caused by PMU malfunctions or the communication failures that make the SE problem unobservable have a local effect and do not deteriorate the results in the rest of the power system.