Abstract: This work introduces the Extracted Tags - EXTags, a short form of data extracted from a massive amount of multimodal human motion data for efficient human motion analysis. EXTags describe the only crucial space-time features from motion data in a certain period. We demonstrate how such brief representation might be a handful in an analysis of the patient transport situation from the point of view of the ergonomics of transporting people.

Keywords: Tag Detection; Motion Analysis; Ergonomics in Healthcare

Abstract: Fault detection problems in dynamic objects and their localization are a very critical and rather challenging tasks for many practical applications. The Kalman-filter technology is used for these purposes most often. The correct operation indicator of the specified filter is the innovation process to be represented as a normal uncorrelated stochastic process with zero mean value and a priori calculated covariation matrix, except the specified conditions, are violated in case of unforeseen perturbations. The aim of the presented work is to develop a method allowing to restore the normal performance of the Kalman filter in the presence of uncertain disturbances. This aim is attained by applying a special one-to-one transformation of the output equation of the testing system, as a result of it, the disturbance component is modified by the extrapolation equation of the state vector dynamic system. This feature will be used in the sequel when modified Kalman filter is applied to the transformed system. The properties of the obtained filter concerning the stability of estimation errors, their convergence, and optimality are discussed. The efficiency of the method has been verified by the method of statistical modeling on a test example of a third-order dynamic system.

Keywords: states estimation; linear dynamic systems; Kalman filter; uncertain structure perturbations

Abstract: This study deals with the research and development of the optimal design of a small floating hydroelectric power plant by theoretical analysis and the subsequent conceptual design of the optimal variant. A computational fluid dynamics (CFD) system is used for theoretical analyses of flow, flow around, free surface properties, and motion of bodies in the water. The aim of this study is to identify the optimal geometry and construction of a small floating hydroelectric power plant. In the study, five different versions of floating pontoons are designed and analysed in the first phase. CFD analysis is used to determine the choice of the most suitable concept, which is further modified based on the calculation results. The result of the study is the design of a suitable design solution, which obviously achieves higher efficiency compared to a conventional water wheel. Finally, the further direction of research is presented, with a focus on maximising the performance and further optimisation of the small floating hydroelectric power plant structures.

Keywords: optimisation; power plant; computational fluid dynamics (CFD); water wheel; hydraulic power

Abstract: It is becoming increasingly clear to professionals and leaders, in the economic sphere, that logistics and logistical approach are now not only a service area, but also clearly, part of a competitive winning strategy. We can see the benefits of system, both in the supply chain and in the flow actions of value-creating processes. Lean, is one of the most comprehensive and respected philosophies of value-creating process development, which now weaves the organization of resupply through its wide range of tools, including external relations on more and more levels. We have good reason to ask, what can be used to make the internal and external development of needs even more transparent and plastic? It is extremely important, that the consistency of demand and production is established in a customer-centered approach, which must be experienced by all participants, even those who are not directly related to the customers or their needs. In the meantime, in the growing competition between companies, the product itself is no longer the most important, but the services associated with it, for which we will need additional production information with the highest efficiency and economies of scale. At the same time, customer expectations are changing at a faster pace than ever, which requires not only extreme flexibility and preparedness, but also immediate (up-to-date) information. Considering of all this, this study looks for the technology to help display and monitor consumption, in a controlled way. This helps targeting the goals and identify workers, within the current situation, thus demonstrating the significance of visualization, through live examples. Our main question is to look at the “whats” and “whys” of visualization and once knowing that, we will also be better equipped to perform the visualization.

Keywords: Visualization; Visual Management; Consumption Control; Logistics; Lean

Abstract: Nowadays, technology is advancing rapidly in parallel with developments. The traditional concept of machine loses its function and is replaced by particular devices with spherical geometry such as spherical electric motors and brain stimulation systems. Consequently; the calculation of self-inductance (Lii) and mutual inductance (Mij) coefficients in the spherical coordinate system with analytical or semi-analytical methods has become one of the major research topics in recent years. In this study, the terms of B, E, and A for multi-winding coils were calculated analytically by using the single-winding coil approach. The same geometries were calculated with the assumption of axial symmetry in ANSYS Maxwell using finite element analysis (FEA). The obtained results with the FEA and analytical calculations were compared. Finally, two concentric coil geometries with magnetic core with radius r1 were determined, the variation of the self-inductance (Lii) and mutual inductance (Mij) coefficients of the determined geometries based on the γ angle in spherical coordinates were calculated analytically. Simulation studies were conducted by creating 3D models of coil geometries in ANSYS Maxwell program. An experimental setup that can be produced with 3-dimensional (3D) printers has been designed and constructed compatibly with the determined geometries. The variation of Lii and Mij coefficients with γ was studied experimentally after the production of necessary coil windings. At the end of the study, it was observed that the analytical results collected for the mutual inductance Mij and the self-inductance coefficient Lii were consistent with each other by comparing the FEA and experimental results.

Keywords: Spherical coordinates; Magnetic field; Maxwell's equations; Analytical solution; Finite element analysis (FEA); Mutual inductance; Self-inductance

Abstract: The current analysis is based on the concept that the proper quality of a particular type of alloy, such as half-hard cast irons and their properties, are determined by chemical composition and a proper melting and alloying processing, as well as, a special nodulizing treatment, assuring the graphite’s nodular form. This analysis follows several key aspects of the manufacturing of half-hard cast iron rolls (also called "ductile iron rolls"), using the multivariate statistical research used as modelling approach upon the industrial data. In this sense, several results of a complex study on the half-hard cast iron rolls are presented, regarding the cumulative influences of several chemical components of the half-hard cast iron (Phosphorus, Sulphur and Magnesium), upon the Hardness, which is the common method of testing rolls, for the quality and predicted wear properties. The performed research herein has generated a number of multi-component regression equations and correlation coefficients, determined to the 3rd and 4th dimension spaces. Also generated are several regression surfaces and correlative level curves, which define proper technological areas. For the multiple regression equations and for the graphical addenda the Matlab software was used.

Keywords: cast iron rolls manufacturing; hardness; Phosphorus; Sulphur; Magnesium; multivariate regression analysis; regression equation; correlation charts

Abstract: The natural frequencies of aircraft jet engine parts are necessary knowledge in the design, safety and operation of the jet engine. The presented article is focused on the area of determining natural frequencies of the turbine blade of the jet engine. The article describes three different methods for determining the natural frequencies of jet engine blades. Acoustic method, method of determining natural frequencies by measuring the vibrations using an accelerometer and determination of natural frequencies by finite element method (FEM) modal analysis. The principles of each method are described in Sections 3 and 4. In Section 5, the achieved results of individual measurements are described. In the conclusion area, Section 6 of this work, the authors describe the results achieved between the various methods and their advantages/disadvantages.

Keywords: natural frequency; turbine blade; frequency measurement; vibration measurement; acoustic measurement; vibrodiagnostic

Abstract: This research work is aimed directly at the study of network traversal, for the design of vehicle dynamics and driving test programs. The work can be applied more widely to the qualification of test tracks. In addition to general modelling, this method can also be used to investigate the formation of loops in order to take into account, the sub-routes, multiple times. An important area of its application is the more comprehensive analysis of complex loads, as well as, the development of learning algorithms, which can be achieved by repeating multiple traversals of certain track sections within a series of measurements, and can be used for the development of on-board vehicle systems. The mathematical modelling is presented through the application of the geometric graph and subgraphs of the track. The properties of the Markov model extracted from the connection matrix of the large-scale network model are also presented. In this way, the modelling is extended to the application of the connection matrix of the large-scale network model as well. The modelling and computational details are demonstrated by means of a computer based, algebraic program. This modelling and the results of the calculations, will allow the further development of a test program design and related evaluation methods.

Keywords: Study of network traversal; mathematical modelling; connection matrix; Markov model; computer algebra; test program design; evaluation method

Abstract: An increasing number of defects in software, damages the quality and reliability of that software. The detection of defective instances is becoming increasingly important, and current detection techniques require a great deal of improvement. However, Machine Learning (ML) techniques are effectively used, to detect defects in software. The primary purpose of ML techniques in Software Defect Prediction (SDP) is to predict defects, according to historical data. Establishing a critical SDP model on high-dimensional and limited data is still a challenging task. Thus, in this paper, we proposed an approach to detect defective modules in software using enhanced Convolutional Neural Networks (CNNs). The paper aims to identify the defective instance using the enhanced deep learning method. Our experiments are based on Within Project Defect Prediction (WPDP), where K-fold cross-validation is performed. The proposed approach has been evaluated on nineteen open-source software defect datasets, with respect to different evaluation metrics. Empirical results show that our proposed approach is significantly better than Li's CNN and standard ML model. In addition, we performed the Scott-Knot ESD test, which shows the effectiveness of our proposed approach.

Keywords: Software defect; CNN; Deep learning

Abstract: Machine learning models have been tested on countless classification problems in the past. However, there is little information available on how well they perform when the task is learning abstract concepts, that are difficult to understand, even for humans. The object of this research was to find the best model for capturing the concepts of white-collar and blue-collar jobs, based on unstructured job ads, in Serbian. These concepts have become very difficult to define in the modern job market, since there are now many factors besides the required level of formal education, that determines the category of a job.

Keywords: document classification; natural language processing; neural networks; support vector machines; Serbian

Abstract: Contaminated water became a major issue for our country over the last few decades. One of the main reasons behind this scenario is urbanization and industrialization. Every industry should have an Effluent Treatment Plant (ETP) for treating industrial wastewater and safe disposal to the environment. We implement a system that monitors whether an industry uses ETP or not. To monitor ETP, we need to monitor the untreated wastewater quality. The traditional way offers us a method that is time-consuming and inefficient. To solve this problem, we adopt a model based on Wireless Sensor Networking (WSN), which allows us to keep track of the water quality parameters in real-time. This paper proposes a water quality monitoring system that uses WSN and Internet of Things (IoT) based devices to monitor different parameters of water: temperature by a temperature sensor, turbidity by a turbidity sensor, and pH by a pH sensor. Moreover, the microcontroller of Arduino Uno R3 collects the parameter values from these sensors and transmits the values to the IoT based cloud server using the GSM module. The GSM module is also used to alert the supervisors by sending SMS in case of an emergency. Integrating modules such as sensors, Arduino Uno R3, GSM module, enhances the purpose of the desired system. Finally, we calculate the Water Quality Index (WQI) for the pH and turbidity data to report the water quality status. Also, we compare the WQI status with our cloud status, and it shows excellent performance.

Keywords: water quality; wireless sensor networking; IoT; smart sensor; GSM module; Real-time; plant monitoring; artificial intelligence

Abstract: Li-ion batteries have become a widespread solution for modern energy storage systems, both for e-mobility and stationary storage. SOC and SOH estimation of batteries has great importance from both technical and economic aspects. There are many ways to estimate SOC and SOH with different complexity and accuracy rates, our paper focuses mostly on SOH. At first, this paper gives a brief review of possible methods of SOH determination. From these methods, one way is developed to measure an indicator related to SOH, and from the indicator estimating it. In our paper, we analyzed the connection between SOH and self-discharge for different time periods. The capacity degradation was measured with a high current, that closely resembles modern e-mobility applications. After that, from our experimental data, with the measured self-discharge, the final best-estimated SOH value in the range of ± 3% is achieved.

Keywords: battery; Li-ion; state-of-health; self-discharge; degradation

Abstract: Due to the direct observation of the Heat Transfer Coefficient at the surface of the metallic components under quenching is practically impossible, indirect methods based on measuring the cooling curves in certain points inside the workpieces, and numerical integration of their thermodynamic model mean a viable approach. The complexity of the necessary calculations can be considerably reduced by the use of symmetric cylindrical samples made of an alloy of particularly simple thermal properties defined in the standard ISO 9950. In spite of that the complexity is still large enough. In the present approach it is reduced by applying a simple formal, qualitative model of the cooling process, the efficient Newton-Raphson algorithm and a Fixed Point Iteration approach to obtain approximate preliminary results. This approach requires only very limited computational capacities. Besides for making rough estimations, due to its simplicity, the method may be useful in the education.

Keywords: Heat Transfer Coefficient; Newton-Raphson Algorithm; Banach’s Fixed Point Theorem; Fixed Point Iteration; Quenching