Search

This paper identifies possible solution to reduce amount data retrieved for purpose of network monitoring, while retaining the quality of information. Legacy methods used for network service monitoring data using and data retrieved by use of synthetic tests are usually decoupled – describing different contexts. As a result, there is too many monitored operational parameters on monitored devices and consequently too much measurement data exported from network service probes. Novel approach is suggested to perform heuristic analysis of the network service configuration and decomposition of collected data at the network edge. Objective is that amount of collected data can be reduced while at the same time quality of the presented information can be improved by providing clear correlation between network service and telemetry data.

It is every parent’s wish to protect their children from online pornography, cyber bullying and cyber predators. Several existing approaches analyze a limited amount of information stemming from the interactions of the child with the corresponding online party. Some restrict access to websites based on a blacklist of known forbidden URLs, others attempt to parse and analyze the exchanged multimedia content between the two parties. However, new URLs can be used to circumvent a blacklist, and images, video, and text can individually appear to be safe, but need to be judged jointly. We propose a highly modular framework of analyzing content in its final form at the user interface, or Human Computer Interaction (HCI) layer, as it appears before the child: on the screen and through the speakers. Our approach is to produce Children’s Agents for Secure and Privacy Enhanced Reaction (CASPER), which analyzes screen captures and audio signals in real time in order to make a decision based on all of the information at its disposal, with limited hardware capabilities. We employ a collection of deep learning techniques for image, audio and text processing in order to categorize visual content as pornographic or neutral, and textual content as cyberbullying or neutral. We additionally contribute a custom dataset that offers a wide spectrum of objectionable content for evaluation and training purposes. CASPER demonstrates an average accuracy of 88% and an F1 score of 0.85 when classifying text, and an accuracy of 95% when classifying pornography.

In recent years, gradual improvements in communication and connectivity technologies have enabled new technical possibilities for the adoption of chatbots across diverse sectors such as customer services, trade, and marketing. The chatbot is a platform that uses natural language processing, a subset of artificial intelligence, to find the right answer to all users’ questions and solve their problems. Advanced chatbot architecture that is extensible, scalable, and supports different services for natural language understanding (NLU) and communication channels for interactions of users has been proposed. The paper describes overall chatbot architecture and provides corresponding metamodels as well as rules for mapping between the proposed and two commonly used NLU metamodels. The proposed architecture could be easily extended with new NLU services and communication channels. Finally, two implementations of the proposed chatbot architecture are briefly demonstrated in the case study of “ADA” and “COVID-19 Info Serbia”.

This paper presents a novel approach for an Intrusion Detection System (IDS) based on one kind of asymmetric optimization which use any three already well-known IDS algorithms and Triple Modular Redundancy (TMR) algorithm together. Namely, a variable threshold which indicates an attack on an observed and protected network is determined by using all three values obtained with three known IDS algorithms i.e., on previously recorded data by making a decision by majority. For these algorithms authors used algorithm of k-nearest neighbors, cumulative sum algorithm, and algorithm of exponentially weighted moving average. Using a proposed method we can get a threshold that is more precisely determined than in the case of any method individual. Practically, using TMR we obtain a dynamically threshold adjustment of IDS software, which reduces the existence of false alarms and undetected attacks, so the efficiency of such IDS software is notably higher and can get better results. Today, Denial of Service attacks (DoS) are one of the most present type of attacks and the reason for the special attention paid to them in this paper. In addition, the authors of the proposed method for IDS software used a known CIC-DDoS2019 dataset, which contains various data recordings of such attacks. Obtained results with the proposed solution showed better characteristics than each individual used algorithm in this solution. IDS software with the proposed method worked precisely and timely, which means alarms were triggered properly and efficiently.

At the European level, a significant effort was exerted in order to define the regulatory framework for cyber security and establish Computer Emergency Response Teams (CERTs) to handle cyber threats and incidents. However, this topic is still underrepresented in the academic research, probably because of its novelty. Bearing this in mind, in this paper we reviewed the existing cyber security literature and discussed how the already existing methods could be used for providing more efficient CERT services.

Optimal charging of plug-in electric vehicles from the power grid requires the development of special algorithms. The presented system discloses one such algorithm used by server software for the optimal control of chargers for electric vehicles.

One of the essential activities for sustainable local economic development is continuous improvement of business environment which can be carried out through the business-friendly certification as objective benchmarking process, which is influenced by many factors - criteria that could be analyzed using multi-criteria decision-making methods. Determining criteria weights is the most important task regarding these methods for which a number of methodologies based on different approaches were developed. These methodologies could be generally divided into two groups: subjective and objective. Shortly, these methodologies quantify given preferences using knowledge of experts if they are subjective or using calculations from available data if they are objective. Methodologies from these two groups give different results in a wide range of values. Therefore, it is useful to create composite indicators using aggregation of both approaches in order to reduce the influence of their bad individual characteristics and, therefore, achieve a balanced symmetrical approach. The purpose of this paper is constructing one efficient model that solves a problem of the planning of sustainable local economic development in the Republic of Serbia. Our approach uses the aggregation of the entropy method, as one objective approach, and the analytical hierarchy process, as a subjective approach, in executing business-friendly certification process. The implementation of the proposed approach has been demonstrated as a part of a business-to-government (B2G) platform called “Multi-Criteria Support System for Analysis of the Local Economic Environment” in the City of Niš.

This paper presents Android-based SOS platform named SOSerbia for sending emergency messages by citizens in Serbia. The heart of the platform is SOS client Android application which is an easy and simple solution for sending SOS messages with unique combination of volume buttons. The proposed platform solves a lot of safety, security, and emergency problems for people who can be in dangerous situations. After a person presses a correct combination of buttons, a message with his or her location is sent to the operating center of the Serbian Police. The platform merges several appropriately combined advanced Android technologies into one complete solution. The proposed solution also uses the Google location API for getting user’s location and Media Player broadcast receiver for reading pressed buttons for volume. This logic can be also customized for any other mobile operating system. In other words, the proposed architecture can be also implemented in iOS or Windows OS. It should be noted that the proposed architecture is optimized for different mobile devices. It is also implemented with simple widget and background process based on location. The proposed platform is experimentally demonstrated as a part of emergency response center at the Ministry of Interior of the Republic of Serbia. This platform overcomes real-life problems that other state-of-the-art solutions introduce and can be applied and integrated easily in any national police and e-government systems.

In this paper, an analysis of undesired effects in multi-antenna MIMO transmitters such as PA nonlinearity, IQ imbalance and nonlinear crosstalk is presented. An impact of these effects on signal quality is demonstrated through simulations. The obtained results are given in numerical and graphical forms using metrics in time and frequency domains.

A novel generalized two dimensional (2-D) digital predistortion (DPD) architecture for concurrent dual-band transmitters is presented. The proposed architecture is based on simultaneous injection of in-band intermodulation (IM) and cross-modulation (CM) distortion products. A general fundamental-frequency model for concurrent dual-band transmitter is developed theoretically and proofed experimentally. An individual impact of each IM and CM distortion component is theoretically derived and analyzed. It is clearly proven by theoretical analysis and experiments that the proposed predistorter improves the in-band and out-of-band performances of both signals. The simulation and experimental studies are performed using various signal sets. The proposed predistorter does not depend on frequency separation between bands and has low computational complexity in comparison with concurrent dual-band DPD's state-of-the-art. In addition, it is clearly shown in experiments that when using iterative simultaneous injections, a phenomenon known as distortion compensation limit can be reduced. A presence of memory effects and their mitigation in frequency domain for each band of concurrent dual-band transmitter are also demonstrated in experiments.

U ovom radu analiziran je uticaj nelinearnosti relejne stanice sa fiksnim pojacanjem na performanse kooperativnog „pojacaj i proslijedi" sistema sa selektivnim kombinovanjem na odredisnom terminalu. Direktni link je izložen Rajsovom fedingu, a kooperativni link kombinovanom Rejlijevom/Rajsovom fedingu. Nelinearan pojacavac na relejnom cvoru je modelovan idealnim limiterom. Izvedeni su analiticki izrazi za vjerovatnocu otkaza i asimptotska granica kako za kooperativni link, tako i za kooperativni sistem generalno. Analiticki rezultati su verifikovani Monte Karlo simulacijama.

In this study, we investigated the impact of potential emission sources and transport pathways on annual and seasonal PM10 loadings in an urban area of Belgrade (Serbia). The analyzed dataset comprised PM10 mass concentrations for the period 2003-2015, as well as their chemical composition (organic/elemental carbon, benzo[a]pyrene, As, Cd, Cr, Mn, Ni, Pb, Cl(-), Na(+), Mg(2+), Ca(2+), K(+), NO3 (-), SO4 (2-), and NH4 (+)), meteorological parameters, and concentrations of inorganic gaseous pollutants and soot for the period 2011-2015. The combination of different methods, such as source apportionment (Unmix), ensemble learning method (random forest), and multifractal and inverse multifractal analysis, was utilized in order to obtain a detailed description of the PM10 origin and spatio-temporal distribution and to determine their relationship with other pollutants and meteorological parameters. The contribution of long-range and regional transport was estimated by means of trajectory sector analysis, whereas the hybrid receptor models were applied to identify potential areas of concern.

The effects of joint hardware impairments on the performance of fixed-gain amplify-and-forward (AF) relaying are studied. By considering IQ imbalance at the source and destination and the nonlinear relay the outage probability over Nakagami-m fading channels is derived, and the effects of fading and hardware impairments on the system are analysed. The analytical results are verified by Monte Carlo simulations.

A novel two dimensional (2-D) nonlinearity compensation digital predistortion (DPD) technique for concurrent dual-band transmitters is presented and experimentally verified. The technique improves an in-band and out-of-band performances of both signals. It does not depend on frequency separation between bands and has low memory requirements and computational complexity in comparison with state-of-the-art.

In this paper, an evaluation of unwanted effects in Multiple Input Multiple Output (MIMO) transmitters is described. Complete 2×2 and 4×4 MIMO Orthogonal Frequency Division Multiplex (OFDM) transmitters are simulated for the purpose of quantifying all potential unwanted effects such as Power Amplifiers' (PAs) nonlinearity, linear and nonlinear crosstalk, and IQ modulator imperfections. An experimental analysis of a 2×2 MIMO transmitter using two-tones and WCDMA signal is presented.

This paper presents compensation of all undesired effects (Power Amplifier (PA) nonlinearity, transmitter and receiver antenna crosstalk, before-PA nonlinear crosstalk, Multiple Input Multiple Output (MIMO) channel fading and crosstalk) in MIMO Orthogonal Frequency Division Multiplex (OFDM) wireless systems. It has been demonstrated that reduced-complexity Crossover Digital Predistortion (CO-DPD) algorithm on transmitter side and Matrix Inversion algorithm on receiver side can suppress almost all undesired effects introduced by transmitter, channel and receiver in 4×4 MIMO OFDM System that can be used in modern wireless system applications. A significant complexity reduction is achieved due to the fact that Digital Signal Processing (DSP) during CO-DPD process on transmitter side is done with real instead of complex numbers.

This paper presents analysis of nonlinear distortion and crosstalk compensation in Multiple Input Multiple Output (MIMO) OFDM wireless transmitters. This paper demonstrates that nonlinear crosstalk affects the performance of digital predistorter and it cannot be compensated by the conventional Memory Polynomial digital predistortion technique. Also, it has been shown that proposed CO-DPD technique can compensate the effect of nonlinear crosstalk in 2×2 MIMO OFDM wireless transmitters.

Summary In this paper, a fixed-gain amplify-and-forward relaying under non-ideal hardware is analyzed. The relaying system is impaired because of relay's power amplifier (PA) nonlinearity and in-phase and quadrature-phase (IQ) imbalance at a destination. Closed-form expressions for outage probability as well as ergodic capacity approximation and its upper bound are derived. Also, the outage probability and the ergodic capacity asymptotic expressions in the high signal-to-noise ratio are deduced. For the first time, the joint influence of PA nonlinearity and IQ imbalance on the system in terms of outage probability, symbol error rate, and ergodic capacity is investigated. The results are compared with the respect to soft envelope limiter and traveling-wave tube amplifier at the relay. Based on the analytical and the numerical results, important insights into the impact of IQ imbalance and nonlinearity of the aforementioned PA models on the system performance are gained as well as valuable information on the performance of practically deployed fixed-gain amplify-and-forward relaying system. Copyright © 2015 John Wiley & Sons, Ltd.

A new adaptive digital predistortion based on an iterative injections approach is experimentally verified using a 4G signal. An error vector magnitude and spectrum regrowth improvements are achieved, while at the same time not requiring large digital signal processing memory resources and computational complexity. Therefore, the method can be a strong candidate to become a part of modern predistorters for nonlinearity compensation in 4G wireless transmitters.