a borítólapra  Súgó epa Copyright 
Acta polytechnica HungaricaVolume 16, Issue No. 1. (2019.)


  • Laszlo Ratgeber ,
    Zdravko Ivankovic ,
    Zoran Gojkovic ,
    Zoran Milosevic ,
    Branko Markoski ,
    Anja Kostic-Zobenica :
    Video Mining in Basketball Shot and Game Analysis7-27en [762.61 kB - PDF]EPA-02461-00086-0010

    Abstract: The aim of this study is to analyze the footage of basketball games presented to viewers on television. It includes a wide range of activities from identifying players, determining their position, recognizing the ball, hoops, as well as analyzing the shots and determining shot efficacy. The player detection is based on mixture of non-oriented pictorial structures. The detection of body parts is performed by the Support Vector Machines (SVM) algorithm. This paper contains algorithms for detecting player positions of the court, ball position detection and determination of shot. It is achieved by detecting court position and applying spatial transformation. It also includes detection of shot, detection weather shot was successful and position from which shot was taken. All algorithms are tested in large number of frames from different basketball games.

    Keywords: video mining; basketball; shot recognition

  • Anita Kolnhofer-Derecskei ,
    Regina Zs. Reicher ,
    Ágnes Szeghegyi :

    Abstract: Every single day we spend one hour, on average, with travelling and this value has not changed for decades. According to the Hungarian timescale statistics, approximately one hour per day, on average, has been spent on travelling for the last 30 years. The world, however, has changed a lot in 30 years and one the best examples for this is the quick sequence of generations. Currently, there are at least four generations at the same time. The current study briefly introduces each generation, then discusses the differences and preferences in the travelling habits of generations who are present in the labor market. The aim of this study is to give a structured preliminary research plan, based on the state of the art. Therefore, the problems of further empirical research is reasoned and a well-structured research plan can be specified. Later, this conceptual model helps us to study and understand travel habits and preferences of various generations.

    Keywords: travel habits; generations; preference; literature review; research plan

  • Nemanja Maček ,
    Saąa Adamović ,
    Milan Milosavljević ,
    Miloą Jovanović ,
    Milan Gnjatović ,
    Branimir Trenkić :

    Abstract: This paper presents an approach to designing secure modular authentication framework based on iris biometrics and its’ implementation into mobile banking scenario. The system consists of multiple clients and an authentication server. Client, a smartphone with accompanying application, is used to capture biometrics, manage auxiliary data and create and store encrypted cancelable templates. Bank’s authentication server manages encryption keys and provides the template verification service. Proposed system keeps biometric templates encrypted or at least cancelable during all stages of storage, transmission and verification. As templates are stored on clients in encrypted form and decryption keys reside on bank's authentication server, original plaintext templates are unavailable to an adversary if the phone gets lost or stolen. The system employs public key cryptography and pseudorandom number generator on small-sized templates, thus not suffering from severe computational costs like systems that employ homomorphic encryption. System is also general, as it does do not depend on specific cryptographic algorithms. Having in mind that modern smartphones have iris scanners or at least high-quality front cameras, and that no severe computational drawbacks exist, one may conclude that the proposed authentication framework is highly applicable in mobile banking authentication.

    Keywords: mobile banking; authentication; biometrics; iris; cryptography

  • Adam B. Csapo :

    Abstract: The Spiral Discovery Network (SDN) was recently proposed as a tool for automated parametric optimization based on the Spiral Discovery Method. SDN can be seen as a heuristic optimization approach that offers tradeoffs between exploration and exploitation without having recourse to explicit gradient-based feedback information (unlike classical neural networks) and without requiring hand-coded representations of metaheuristic constructs such as genotypes (unlike genetic algorithms). In this paper, the properties of the SDN model are further explored, and two extensions to the model are proposed. The first extension corrects a shortcoming of the original model and has to do with the assignment of credit among different output components based on the most recent performance of the model at any given time. The second extension consists of using multiple SDN cells in a hierarchical architecture, which enables a fuller and more effective exploration of the parametric space. The improvements provided by the two extensions are validated on the same set of simulations discussed in earlier work.

    Keywords: Spiral Discovery Network; Spiral Discovery Method; Non-convex optimization; Exploration versus exploitation

  • Krisztián Bálint ,
    Dragan Cvetković ,
    Márta Takács ,
    Ildikó Holik ,
    Alex Tóth :

    Abstract: In the present paper, an extension of the Bitcoin (BTC) structure is introduced, with a proprietary and unique DLCC (Digital Learning Chain Structure) blockchain, through which an automated bursary payment system could be constituted, which has, until this day, never been implemented at universities. Thus, an alternative is offered to achieve a bursary payment system, operating in a fully automatic, periodically repeating manner, never requiring supervision. In the DLCC blockchain, specifically, in the Smart Contract, the terms of contract are kept, concerning the bursaries, terms agreed by both parties (students and universities alike). A great advantage of the DLCC system is that it is able to extract the required grades from the electronic grade book, thus supervising the students’ progress throughout the semesters. Upon reaching the end of each semester, if the student qualifies, meeting the requirements, the system will transfer the required quantity of cryptocurrency from the university’s account automatically to the student's account.

    Keywords: Bitcoin; Smart Contract; Digital Learning Chain Structure

  • Lantos Béla ,
    Zsófia Bodó :

    Abstract: High level kinematic model-based control of vehicles is an often used technique in the presence of a driver. Existing robust low level linear (speed, steering, brake, suspension etc.) control components are available in cars which can be influenced using the outputs of the kinematic control as reference signals. If problems arise then the driver can modify the internal control based on the visual information of the path and the observed car motion. In case of unmanned ground vehicles (UGVs) this modification is no more evident. In the paper an approach is presented to estimate the errors in real UGV situations where the road-tire contacts generate special sliding effects in behavior of the UGV. These effects are considered as disturbances and are involved in both the kinematic and dynamic models. The novelties of the paper are the consideration of the sliding effects in the kinematic control and the application of sophisticated nonlinear methods for low level dynamic control. It is demonstrated by simulation that high level kinematic control based approaches can cause lateral errors in the order of 1m. In the experiments three types of low level dynamic controls were considered: i) a simplified one using the steering angle of kinematic control, ii) nonlinear input-output linearization (DGA method), and iii) flatness control. They can supply the sliding angle information for the kinematic control.

    Keywords: Kinematic Control, Sliding Effects, UGV, Kinematic and Dynamic Coupling, Path Following, Input-Output Linearization, Flatness Control

  • Juan Lata-García ,
    Francisco Jurado ,
    Luis M. Fernández-Ramírez ,
    Pablo Parra ,
    Víctor Larco :

    Abstract: The increase in the production of energy through renewable energies and the reduced predictability of meteorological variables leads to consider reliable energy storage systems to ensure the constant supply of energy and the stabilization of the network. This paper studies four commercial energy storage systems for energy supply to an island by using photovoltaic panels and hydrokinetic turbine as primary energy sources. The technical characteristics of the energy storage systems are compared with respect to capacity shortage, autonomy storage and expected life storage, and the economic analysis is carried out. The system with li-ion batteries has 15 year expect life storage, the fuel cell based system has the highest storage autonomy 253 hr, and the pump hydro storage system has the lowest levelized cost of energy 0.178 $/kWh with 7 year expect life storage.

    Keywords: energy storage; hybrid system; off-grid applications; renewable energy

  • Ivica Nikolić ,
    Isidora Miloąević ,
    Nenad Milijić ,
    Aca Jovanović ,
    Ivan Mihajlović :

    Abstract: Although the production of copper and its usage has been known for thousands of years, the search for the optimal process of its production is still in progress. The removal of the negative impacts of a certain technology could cost more, over a period of time, than the initial investment in the selection of the optimal technology process which would consider these effects. Hence, the selection should be supported by the innovative and modern tools, such as the applying of the multi-criteria analysis. This paper presents the implementation of the PROMETHEE/GAIA methodology for the ranking of the appropriate technological pyrometallurgical smelting process for the copper concentrate based on the eleven parameters which recognize the economic, ecological and technical aspects of the technological process. The implementation of the multi-criteria decision-making presented in this paper can be deemed as a contribution to the decision making tools, that is, to the one who makes a decision on the selection of the appropriate technological facility for smelting of the copper concentrates. The decision-makers faced with the practical need of evaluating and selecting the most appropriate technological process for pyrometallurgical copper extraction will get the greatest benefit from this multi-criteria model. The innovative contribution of this paper is also presented in the obtained model which systematically analyzes the ecological, economic and technical parameters of the copper extraction process.

    Keywords: technological process; pyrometallurgical processes; ranking, PROMETHEE/GAIA

  • Lajos Izsó ,
    Miklós Antalovits ,
    Sándor Suplicz :

    Abstract: The objective of this paper was to summarize the measurable indicators of the impact of eight year application of the SOL safety event analysis methodology in the period of 2007-2015 in a nuclear power plant in Hungary. The theoretical framework of this paper consists of the (1) “Swiss-Cheese Model”, (2) the “socio-technical system model”, (3) the organizational learning approach, and (4) the concept of safety culture. The selected broad spectrum of methods corresponds to the approach of progressing from the actual state of the safety culture - via covering the SOL related experiences and opinions of the most involved employees, middle and top managers, and training experts as well - towards the whole community of the NPP. As the results of widespread questionnaire surveys, focus group interviews and anonymous intranet-based inquiry methods it can be stated that the overwhelming majority of the respondents considered the application of the SOL methodology as useful and supporting the safety-related organizational learning. It was also found, however, that in the respondents’ opinion the utilization of the - otherwise correct and deeply penetrating - results of SOL analyses is still to be improved.

    Keywords: SOL; safety event analysis; nuclear power plant

  • Ravi Kumar Mandava ,
    Katla Mrudul ,
    Pandu R Vundavilli :

    Abstract: In the past few years, studies of biped robot locomotion and navigation have increased enormously due to its ease in mobility in the terrains that are designed exclusively for the humans. To navigate the biped robot in static and dynamic environments without hitting obstacles is a challenging task. In the present research, the authors have developed a hybridized motion planning algorithm that is, fast marching method hybridized with regression search (FMMHRS) methodology. In this work, initially the fast marching algorithm has been used to observe the environment and identify the path from start to final goal. Later on, the regression search method is combined with the fast marching method (FMM) algorithm to optimize the path without hitting any obstacles. The main objective of the present research work is to generate the path for both the static and dynamic scenarios in simulation and in a real environment. To conduct the testing of the proposed algorithm, the authors have chosen an 18-DOF two legged robot that was developed in our laboratory.

    Keywords: Biped robot; static and dynamic environment; fast marching method; regression search

  • Dragan Jočić ,
    Ivana ©tajner-Papuga :

    Abstract: Aggregation operators with an annihilator are in the focus of a significant number of research papers due to their applicability in both theoretical and practical areas of mathematics. Therefore, the main topic of this paper is distributivity and conditional distributivity for some classes of aggregation operators with this property. The characterization of all pairs (F, G) of aggregation operators that are satisfying distributivity law, on both whole and restricted domain, where F is a S-uninorm from Umin, and G is a t-norm or a uninorm from Umin or Umax is given.

    Keywords: aggregation operator; annihilator; t-norm; uninorm; S-uninorm; distributivity; conditional distributivity

  • Daniela Stănescu ,
    Mircea Stratulat ,
    Romeo Negrea ,
    Ioana Ghergulescu :
    Cover Processing-based Steganographic Model with Improved Security227-246en [1.04 MB - PDF]EPA-02461-00086-0120

    Abstract: Steganography uses specialised techniques to conceal messages in different cover objects such as image or video so that only the sender and receiver know of the message’s existence and are able to decipher it. Previous research conducted in the area has mainly focused on steganography and steganalysis techniques. This paper proposes a new model for steganography called Cover Processing-based Steganographic Model (CPSM) that processes the cover objects and transmits them in a way to improve the security of steganographic objects. A comprehensive demonstration based on information theory proves that CPSM provides improved security in terms of lower relative entropy as compared to previous models from the literature. Moreover, experimental tests show a decrease of the relative error between the cover and steganographic objects of up to 14%.

    Keywords: steganographic model; cover processing; secret communication; security improvement; entropy