Zsolt Csaba Johanyák

John von Neumann University, Kecskemét, Hungary · Department of Information Technology

With the evolution of the automotive industry and telecommunication technologies, an increasing number of vehicles are connected to achieve the intelligent transportation system (ITS) framework. The safety of road users is a major concern in ITS. A Vehicular ad hoc network (VANET) is an innovative technology that provides a wide range of services f...

Nowadays manufacturing systems are strongly dependent on data transfer and network connection. Therefore, information technology systems serving modern industrial environments have to provide a high level of reliability, redundancy, maintainability as well as a centralized monitoring. In order to meet these requirements, one should carefully design...

Intelligent Transportation Systems and particularly vehicular adhoc networks (VANETs) play a key role in enabling Smart Cities as well as improving and maintaining road safety. VANETs are distributed networks built from moving vehicles on the road. Each vehicle of the network has an embedded IEEE 802.11p interface to support the interaction between...

Nowadays, mobile applications are developed for more and more areas, providing great help for our everyday lives. When designing a mobile application, the first important decision to make is to choose the targeted platform. Is it only phone or tablet as well? Should the app run on Android or iOS, or should it be available on both mobile operating s...

The most used technology for ITS (Intelligent Transportation System) is VANET (Vehicular Ad-hoc NETworks) which is a subclass of MANET (Mobile Ad-hoc NETworks).VANET enables wireless communication between vehicles as well as RSU (Road Side Units), by using the standard 802.11p channels bandwidth to transmit all sort of information to each vehicle,...

A significant advantage of Software-Defined Networks (SDNs) over traditional networks is the ability to directly control network behavior and direct communication with network elements. These options are useful and provide us with a quicker, more effective response in critical situations. Of course, they do not relieve us of the task of designing a...

Az ipari informatikai rendszerek működése megköveteli a magas szintű megbízhatóságot, redundanciát, karbantarthatóságot és biztonságot, ezért törekedni kell olyan technológiák alkalmazására, melyek biztosítják ezeket. A cikk bemutat olyan hálózati megvalósításokat, melyek egy Ipar 4.0-s rendszer kialakításához szükségesek lehetnek.

It is common problem with complex software systems that although usually they work as intended, after some time of usage security-critical flaws poop up. In order to alleviate this problem, this paper aims to demonstrate the application potential and benefits of the Fault Tree Analysis (FTA) which is a widely used method in quality assurance. FTA i...

A sparse fuzzy rule base provides low complexity and low memory requirements for the fuzzy system. Automatic fuzzy model generation from sample data involves two main tasks. These are structure determination and parameter identification. In this paper, we present a new approach that initially generates two rules, then gradually adds new rules to th...

Due to the exponentially growing number of mobile devices connected to the Internet, the current 4G LTE-A mobile network will no longer be able to serve the nearly 5 billion mobile devices. With the advent of the fifth generation, however, the number of cybercrimes may increase. This requires building an architecture that can adequately protect aga...

In most cases, a dataset obtained through observation, measurement, etc. cannot be directly used for the training of a machine learning based system due to the unavoidable existence of missing data, inconsistencies and high dimensional feature space. Additionally, the individual features can contain quite different data types and ranges. For this r...

The automotive industry is one of the most dynamically growing fields of the manufacturingarea. Besides this, it has very strict rules concerning safety and reliability. In our work, our aim is to point out the importance of the automotive industry (based on statistics) and the rules in connection with risk and root cause analysis. The most importa...

Heretofore, most network equipment had to be configured individually by connecting manually into it. This approach is time consuming for large networks and prone to human errors. The Software Defined Networking paradigm defines several standards and protocols in order to read the network states and act on its configuration from distant servers. The...

A megfigyelésekből szerzett nagy mennyiségű adat legtöbb esetben nem alkalmazható azonnal közvetlenül egy számítási intelligencián alapuló modell tanítására, mivel a gyakorlatban szinte elkerülhetetlen az, hogy hibás, inkonzisztens vagy hiányos adatokat tartalmazzon az adathalmaz. Emellett a különböző jellemzők értékei nagyon eltérő típusúak vagy n...

This study describes 5G, the latest wireless technology that is currently under development. It will ensure increased bandwidth as well as newer and higher quality antennas. 5G is actually about further developing 4G/LTE. Due to the rapidly growing number of network devices, the current LTE technology will soon be unsatisfactory in terms of quality...

We are convinced that the learning process could be a lot more interesting and more interactive for young people with the help of modern technologies. The presence and the usage of the smartphones is natural for today’s young generations, although they do not use their inherent potential for example for educational purposes. Eddie is a hybrid of a...

FRI methods are less popular in the practical application domain. One possible reason is the missing common framework. There are many FRI methods developed independently, having different interpolation concepts and features. One trial for setting up a common FRI framework was the MATLAB FRI Toolbox, developed by Johany\'ak et. al. in 2006. The goal...

Allocating university resources, especially defining the number of necessary student groups and laboratory classes is a hard task without knowing the exact number of students who will enroll in the given courses. This number usually depends on the exam results of the prerequisite courses. However, the planning of the next term has to be done some m...

FRI methods are less popular in the practical application domain. One possible reason is the missing common framework. There are many FRI methods developed independently, having different interpolation concepts and features. One trial for setting up a common FRI framework was the MATLAB FRI Toolbox, developed by Johanyák et. al. in 2006. The goals...

Inter-vehicular communication (IVC) has become a reality driven by navigational safety requirements and by the investments of car manufacturers and public transport authorities. Thanks to the availability of radio communication equipment like radio interface, access points, spectrum, and standards, vehicular ad-hoc networks (VANETs) set the stage f...

Automatic fuzzy system generation from sample data is a common task in fuzzy modeling. Here usually first an initial system is created using clustering, grid partitioning or other approaches and next, the parameters of the system are optimized based on the difference between the sample output and the output of the fuzzy system. The software being p...

In this paper, first the travel and delay times in a road ending in a traffic light are determined under different traffic flows and traffic light cycles using a microscopic traffic simulator. The obtained results are analyzed and compared with the results of other models reported in the literature. In addition, the optimal traffic light cycle time...

Összefoglalás A szoftver által definiált hálózatok (SDN) egy meglehetősen új hálózati megoldás. Az SDN szétválasztja a vezérlő síkot és az adatsíkot. Három fő résszel rendelkezik: az adatsíkkal, a vezérlő síkkal és az alkalmazási síkkal. Az alkalmazási sík tartalmazza a programozási nyelveket. Ezen nyelvek használatával a felhasználó vezérelheti és...

Particle swarm optimization (PSO) based optimization algorithms are simple and easily implementable techniques with low computational complexity, which makes them good tools for solving large-scale nonlinear optimization problems. This paper presents a modified version of the original method by combining PSO with a local search technique at the end...

Urban traffic is continuously increasing and therefore especially in peak-hours an optimized traffic light system can provide significant advantages. As a step towards developing such a system this paper presents a fuzzy model that estimates the average delay times on a road that ends at an intersection with traffic lights. The model was created ba...

Modern vehicles are equipped with a wide variety of sensors, on-board computers and different devices supporting navigation and communication. These systems aim the fulfilment of various demands on the improvement of traffic safety, traffic/route optimization, passenger, comfort, etc. Inter-vehicle and vehicle-infrastructure communication plays an...

Software-Defined Networking (SDN) is a new network approach. The SDN most important innovation is the separating the control plane and data plane. The network devices only responsible for the packet forwarding, the control functions are implemented in the upper layer. The SDN has three layers: the data layer, the control layer and management layer....

A vállalati informatikai rendszerek védelme érdekében gyakran alkalmaznak hálózati támadásokat detektáló úgynevezett Behatolás Érzékelő Rendszereket (IDS - Intrusion Detection System). Legnagyobb előnyük az IDS-eket használó hálózatoknak, hogy egy támadás bekövetkezésének észlelési ideje nagymértékben lecsökken, hiszen a rendszer automatikusan küld...

Computer networks are frequently targeted by various hostile activities independently of their scale (home, small business, enterprise network). System administrators often employ special tools called honeypots as bait in order to discover, understand, and deflect malicious activities and to identify their actors. This task can be done either by a...

In course of the design and implementation of computer networks important aspects are the usability, manageability, and configurability. The new paradigm of Software Defined Networks (SDN) ensures the fulfilment of these requirements. SDN separates the control plane and the data plane to facilitate network implementation. Thus the data plane of the...

Intrusion detection systems (IDSs) can provide an effective solution for the information security needs of a company. Well configured IDSs are able to automatically recognize attacks that target either networks or hosts. IDSs can be categorized based on different aspects or properties. The intrusion detection approach is one of the most important p...

Software-Defined Networking (SDN) offers solutions for several difficulties of network configuration and control by separating the control logic of the network from the underlying hardware components and applying a logical centralization. Having software in focus the services and features offered by the used programming languages play a key role in...

There are several technologies and methods for the security related design, management and maintenance of computer laboratories of educational institutions. In order to ensure the continuous availability and the proper maintainability it is crucial to protect the operating systems of the workstations as well as the whole network against internal an...

Software engineering education has to deal with different challenges nowadays in Hungary. While the number of job offers in this field is continuously increasing the students' interest in programming shows a declining trend. The recognition of the problem led to several initiatives trying to address the existing lack of software engineers and stude...

Virtualization in Network Administration Education

Az informatikai hálózatok megvalósítása során nagy hangsúlyt kell fektetni a könnyű kezelhetőségre, hatékonyságra, és a biztonságára. Fontos szempont még a könnyű felügyelhetőség és konfigurálhatóság. A Software Defined Networking (SDN) vagy szoftver által definiált hálózat paradigma pontosan ezt a lehetőséget nyújtja. Ez egy napjainkban egyre jobb...

Összefoglalás A számítógépes hálózatok biztonságára különös hangsúlyt kell fektetni a rendszermenedzsment során. Figyelni kell a biztonságos adatáramlásra mind a kimenő, mind a bemenő forgalom esetében. Ebben hatékony segítséget nyújthatnak a forgalomirányítóknál alkalmazott Access Control List-ek (ACL). A cikk célja az, hogy ismertesse az ACL-ek...

Intrusion detection systems (IDSs) play an important role in the defense of the companies’ IT systems. These systems provide automated protection against a variety of attacks and intrusions. Without them in several cases system administrators are not able to recognize in time high degree attacks and thus effective defense and intervention actions c...

This paper proposes a Particle Swarm Optimization (PSO) based tuning for fuzzy controllers. The applicability of the proposed solution is demonstrated by tuning a simple fuzzy cruise control. The algorithm is used for the tuning of the input-output gains as well as the tuning of the sets included into the consequent parts of the fuzzy rules. The re...

The prediction of the number of students who will pass or fail the exams in the case of a subject can be very useful information for resource allocation planning purposes. In this chapter, we report on the development of a fuzzy model, that based on the previous performance of currently enrolled students, gives a prediction for the number of studen...

The performance of a fuzzy controller is determined in a great amount by the underlying rule base. In this paper, we present tuning methods implemented in our rule base identification and tuning toolbox. The toolbox is easy-to-use Matlab based software with graphical user interface. All the implemented tuning methods support the creation of low com...

Swarm intelligence has become an intensively studied research area in the last few years. Gathering of mobile robots is one of its basic topics that aims the assembly of the scattered robots on the smallest possible area. In this chapter, we present a new and effective algorithm for this task supposing an obstacle-free plan, limited visibility, and...

Evaluating students' work cannot be always fully automatized. In case of narrative responses or assignment sheets only general scoring guidelines and principal aspects can be set. The teachers try to follow them; however, the final decision is mainly based on their expertise. In such situations the evaluator often feels some kind of uncertainty whi...

Fuzzy rule interpolation based on subsethood values is a low complexity FRI method. In this paper, we present its enhanced version that makes possible the weighting of the individual rules. Thereby FRISUV becomes better tuneable and adaptable. Keywords: fuzzy rule interpolation, FRISUV, clonal selection

Melt volume-flow rate (MVR) is one of the most important quality indicators of composite materials, which depends on the proportion of the component materials. This paper reports the development of a low complexity fuzzy model that describes the relation between percentage amount of multiwall carbon nanotube (MWCNT), acrylonitrile-butadiene-styrene...

Nature inspired algorithms proved to be very advantageous in several application areas. This paper presents the application of the clonal selection algorithm (originated from the functioning of the vertebrate's immune system) for the tuning of fuzzy inference systems. The proposed solution was tested in case of SISO and MISO systems with two differ...

Artificial Immune System (AIS) algorithms make possible the development of systems that can work similarly to the human immune system by emulating or copying its protection methods. They can be applied in field of information technology and other engineering sciences (medical systems, computer networks, simulations, etc.) as well. In this paper, af...

Parameter optimization is a key step during the creation of a fuzzy rule based system. It also has a determining effect on the resulting system’s performance. In this chapter, we examine the performance of several fuzzy systems obtained by applying two different optimization methods. In each case we start from an initial rule base that is created u...

Parameter tuning is an important step in automatic fuzzy model identification from sample data. It aims at the determination of quasi-optimal parameter values for fuzzy inference systems using an adequate search technique. In this paper, we introduce a new hybrid search algorithm that uses a variant of the cross-entropy (CE) method for global searc...

Fuzzy rule interpolation (FRI) methods could be advantageous tools for fuzzy inference owing to their capability to reason in sparse rule bases as well. The fuzzy rule interpolation by the least squares method (LESFRI) like most of the available techniques is designed so that it can be implemented easily only by using the traditional structure base...

Rule base optimization is a key step in fuzzy model identification that determines the performance of the fuzzy system. In this paper, we examine two optimization solutions, i.e. the cross-entropy method and a hill climbing approach based heuristic method. They are used and compared in case of four benchmarking problems. In each case the initial ru...

This paper comprehensively analyzes Fuzzy Rule In-terpolation and extrapolation Techniques (FRITs). Because extrapolation techniques are usually exten-sions of fuzzy rule interpolation, we treat them both as approximation techniques designed to be applied where sparse or incomplete fuzzy rule bases are used, i.e., when classical inference fails. FR...

Ground-level ozone is a dangerous pollutant for which the prediction of the concentration could be of great importance. In this paper, we present and compare three fuzzy models aiming the forecasting of ground-level ozone concentration. The models apply Takagi-Sugeno, respective LESFRI fuzzy inference techniques and were generated using the ANFIS m...

Alpha-cut based calculations are widely used in fuzzy arithmetic and fuzzy rule interpolation based reasoning. One of the key issues of the successful development of these applications is the availability of a toolbox that makes possible the quick and efficient calculation of the α-cuts' endpoints. In this paper, after reviewing some basic theoreti...

A sparse fuzzy rule base offers low complexity and low memory demand for a fuzzy system. Its automatic generation from sample data involves two main tasks, i.e. the structure definition and the parameter identification. In this paper, we present a novel approach that starts with two rules and incrementally creates new rules followed by the identifi...

sszefoglalás: A fuzzy halmazelmélet számos gyakorlati alkalmazásánál (pl. fuzzy aritmetika, egyes fuzzy következtetési eljárások) a számításokat ún. α-vágatok segítségével végzik. A sikeres megvalósítás egyik kulcskérdése egy olyan eljáráskészlet megléte, aminek segítségével gyorsan és hatékonyan meghatározhatók a vágatok végpontjai. Cikkünkben néh...

Nowadays thermoplastic composites are commonly used owing to their good mechanical properties, which can be ensured only by the proper mixing of different types of materials. In this paper, we present the results of our studies regarding the fuzzy modeling of the relation between the yield strength and the amount of the used components (ABS, polyca...

In case of non-automated examinations the evaluation of students’ academic achievements involves in several cases the consideration of impressions and other subjective elements that can lead to differences between the scores given by different evaluators. The inherent vagueness makes this area a natural application field for fuzzy set theory-based...

Alpha-cut based calculations are widely used in fuzzy arithmetic and fuzzy rule interpolation based reasoning. One of the key issues of the successful development of these applications is the availability of a toolbox that makes possible the quick and efficient calculation of the α-cuts' endpoints. In this paper, after reviewing some basic theoreti...

Fuzzy rule interpolation methods make possible the development of fuzzy rule based systems applying a low complexity and compact rule base that contains only the most relevant rules. They are able to infer even in those regions of the antecedent space where there are no applicable rules. In this paper, we present a novel method called Fuzzy Rule In...

The evaluation of narrative student responses contains always vague elements that originate from the fact that the students performance cannot be clearly ranked in one or another category, which makes this area a natural application field for fuzzy set theory based solutions. This paper presents a new evaluation method that allows taking into consi...

Fuzzy logic achieved an important role on the areas of the conditioning, control technique and guidance in the 20th century, and it had gained more and more significance recently on the area of function approximation applications as well. Fuzzy logic based applications do not require always a full coverage of the input space by the rule base, they...

Thermoplastic composites are widely used in various areas. In several cases their applicability is determined by their mechanical properties that depend on the proper mixing of the component polymeric materials. In this paper two low complexity fuzzy models are presented that have been developed for the prediction of Charpy impact strength and yiel...

The evaluation of students’ academic performance in cases when a totalautomated scoring is not possible can result in quite significant differences between themarks given by different evaluators or at different occasions. The problem partly can betraced back to the uncertainty in the opinion or the evaluator that cannot be expressed properly in the...

Fuzzy systems applying a sparse rule base and a fuzzy rule interpolation based reasoning method are popular solutions in cases with partial knowledge of the modeled area or cases when the full coverage of the input space by rule antecedents would require too many rules. In several practical applications there is no human expert based knowledge; the...

Fuzzy systems built on sparse rule bases apply special inference techniques. A large family of them can be described by the concept of the general methodology of the fuzzy rule interpolation (GM) [1]. Accordingly to this the conclusion is produced in two steps. First a new rule is interpolated corresponding to the position of the reference point of...

Approximate fuzzy reasoning methods serve the task of inference in case of fuzzy systems applying sparse rule bases. This paper reviews four one-step methods according to a general condition set for fuzzy rule interpolation methods [5], which is brought together from an application-oriented point of view.

The application of fuzzy rule interpolation (FRI) methods in fuzzy models can reduce the complexity of the fuzzy model significantly. In case of automatic model generation this reduced complexity also leads to quicker convergence of the fuzzy model. The goal of this paper is the detailed investigation of a fuzzy model construction in a real world p...