Aleksandar Neskovic

• University of Belgrade

This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern...

This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include b...

Two outdoor base station macrocell/microcell topologies in operational Global System for Mobile communications (GSM) and Universal Mobile Telecommunications Service (UMTS) networks are compared with respect to average Electromagnetic Field (EMF) exposure over population in an area. A novel joint metric is used, accounting for exposure from both bas...

Apstrakt-U radu je izvršena analiza promene intenziteta električnog polja koje potiče od mikro LTE (Long Term Evolution) bazne stanice, čije je merenje vršeno tokom sedam dana. Merenje je vršeno u frekvencijskom opsegu downlink smera komunikacije na centralnoj učestanosti od 1835 MHz. Realizacija intenzivnih merenja je izvršena u realnim uslovima r...

In this paper, the impact of the network architecture on signal quality in the fourth generation of the public mobile network is analyzed. The analysis was performed using RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), SINR (Signal to Interference plus Noise Ratio) and throughput parameters in indoor environment....

Overlapped fingerprints are often found in latent fingerprints lifted from crime scenes and in live-scan fingerprint images when the surface of fingerprint sensors contains residues of fingerprints of previous users. Such overlapped fingerprints must be separated before they can be processed by a fingerprint matcher, which has led to the creation o...

This chapter describes the problem of segmentation of overlapped fingerprints, which is a required prerequisite step in the fingerprint processing pipeline, performed before the processes of fingerprint separation and subsequent verification. Overlapped fingerprints segmentation is usually performed manually, and only recently there have been (semi...

This chapter describes a convolutional neural network (CNN)-based approach for overlapped fingerprint mask segmentation. The CNN classifies each image block within the overlapped fingerprint image into three classes—background (B), single fingerprint (S), and overlapped fingerprint (O). The proposed segmentation method has been successfully tested...

This chapter presents fundamental concepts and terminology associated with latent fingerprint processing, with particular reference to overlapped latent fingerprints. It introduces the matching process itself, including classical manual latent fingerprints matching procedures. It also presents the design of a modern automated latent fingerprints ma...

This chapter describes a machine learning based approach for overlapped fingerprint separation. The algorithm works in a block-based fashion: after producing an initial estimation of the orientation fields present in the overlapped fingerprint image, it uses a neural network to separate the mixed orientation fields, which are then post-processed to...

This chapter presents an overview of existing image datasets that can be used for evaluating approaches for overlapped fingerprint separation. It gives special attention to the Vlatacom dataset, created by the authors and publicly available, which consists of 120,000 synthetically overlapped test images (and the associated masks), with and without...

U radu je analiziran uticaj arhitekture mreže na kvalitet signala u okviru četvrte generacije javne mobilne mreže. Analiza je izvršena pomoću parametara RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality) i realno ostvarivog protoka podataka. Parametri kvaliteta signala su prikupljeni merenjem pomoću TEMS Investigation...

This Springerbrief presents an overview of problems and technologies behind segmentation and separation of overlapped latent fingerprints, which are two fundamental steps in the context of fingerprint matching systems. It addresses five main aspects: (1) the need for overlapped latent fingerprint segmentation and separation in the context of finger...

Individual exposure to electromagnetic field (EMF) originating from a user device when using different services over WLAN (Wireless Local Area Network), GSM (Global System for Mobile communications), and UMTS (Universal Mobile Telecommunications Service) technologies in different radio conditions is analyzed. The most common types of traffic were c...

Overlapped fingerprints can be potentially present in several civil applications and criminal investigations. Segmentation of overlapped fingerprints is a required step in the process of fingerprint separation and subsequent verification. Overlapped fingerprint segmentation is performed manually (and the resulting manually drawn masks are a require...

Fingerprint matching is a widely used process to aid in crime scene investigation, where fingerprint fragments are often found on objects and surfaces. In such cases, the lifted fingerprints (called latents) are usually of poor quality and often appear overlapped and against a noisy background. These aspects make latent fingerprint – especially ove...

Overlapped fingerprints are often found in latent fingerprints lifted from crime scenes and in live-scan fingerprint images when the surface of fingerprint sensors contains residues of fingerprints of previous users. Such overlapped fingerprints usually cannot be processed accurately by contemporary commercial fingerprint matchers, which has led ma...

This paper presents a novel method for fingerprint ROI (region of interest) segmentation using Deep learning technique — Convolutional Neural Networks. Experimental results, obtained using a publicly available test database of 200 fingerprint images in two variations — with and without Gaussian noise, demonstrate that this method is competitive wit...

The aim of this paper was the efficiency improvement of methods for measurement of electric field strength in the vicinity of base stations, which was achieved in two areas: procedure for using shorter time intervals of averaging (comparing to 6min that standards stipulate) and model for the conversion from mono-axial measurements to isotropic case...

In this paper an experimental performance analysis of the second, third and fourth generation of public mobile networks is presented. The voice and data services are tested and quality of service parameters are considered in the analysis. Measurements are performed in indoor environment and real microcell of the specific radio technology is analyse...

This article is the first thorough study of average population exposure to third generation network (3G)-induced electromagnetic fields (EMFs), from both uplink and downlink radio emissions in different countries, geographical areas, and for different wireless device usages. Indeed, previous publications in the framework of exposure to EMFs general...

This deliverable presents the validations and proofs of concept of methodologies and technical solutions elaborated in the LEXNET project. Part-A details the developed EMF measurement tools and their characterization. Different methods for the Exposure Index (EI) assessment are implemented and demonstrated in various environments. In Part-B, a set...

This deliverable presents the validations and proofs of concept of methodologies and technical solutions elaborated in the LEXNET project. Part-A details the developed EMF measurement tools and their characterization. Different methods for the Exposure Index (EI) assessment are implemented and demonstrated in various environments. In Part-B, a set...

In NLOS propagation conditions power of direct component can be attenuated significantly. Therefore detection of direct component is aggravated which can degrades accuracy of Time of Arrival mobile positioning. The goal of this paper is to determine possibilities to improve estimation of direct component time delay by reducing detection threshold....

The long-term variability of electric field strength, obtained by band selective measurements for GSM 900MHz, DCS 1800MHz and UMTS 2100MHz downlink band in realistic mobile network environment, is considered in this paper. Intensive measurements were carried out for 7 days at each of 7 different locations in an urban area of Belgrade. The measureme...

In NLOS propagation conditions power of direct component can be attenuated significantly. Therefore detection of direct component is aggravated which can degrades accuracy of Time of Arrival mobile positioning. The goal of this paper is to determine possibilities to improve estimation of direct component time delay by reducing detection threshold....

To determine the level of radiofrequency radiation generated by base stations of Global System for Mobile Communications and Universal Mobile Telecommunication System, extensive electromagnetic field strength measurements were carried out in the vicinity of 664 base station locations. These were classified into three categories: indoor, masts, and...

One of the main goals of this paper is to improve the existing routing metrics in such a way to track fast changes that occur in the link state. Three new metrics are proposed by introducing a parameter based on the received signal level into three known metrics. The results have shown that proposed metrics significantly outperform original metrics...

This paper investigates a novel method for mobile user indoor positioning based on k Nearest Neighbours (kNN) algorithm, but with possibility of determining optimal number of neighbours dynamically in execution phase and for each positioning request separately. Proposed dynamic kNN (DkNN) model for indoor positioning is implemented using infrastruc...

Duty Factor (DF) of Wireless Local Area Network (WLAN) user devices is one of important factors for Electromagnetic Field (EMF) exposure level evaluation in modern human environment. In this paper DF measurements were conducted in three representative radio conditions (good, medium, bad), for eight most commonly used services (web browsing, VoIP ca...

This paper presents a novel method for fingerprint ROI (region of interest) segmentation using Fourier coefficients computed over non-overlapping image segments and used to train a neural network. Experimental results, obtained using a publicly available test database of 200 fingerprint image, demonstrate that this method outperforms a pixel-based...

As a result of dense deployment of public mobile base stations, additional electromagnetic (EM) radiation occurs in the modern human environment. At the same time, public concern about the exposure to EM radiation emitted by such sources has increased. In order to determine the level of radio frequency radiation generated by base stations, extensiv...

This paper proposes a way to assess total electric field strength by using mono-axial probe (instead of isotropic, tri-axial probe). When mono-axial probe is used, additional conversion factor should be applied. Consequently, the usage of mono-axial probe causes additional uncertainty in measurement results that should be taken into account. Measur...

In order to compare cellular technologies and services with respect to EMF exposure, the methodology for comparing user equipment transmit power levels averaged in time is proposed. Focusing on data that can be retrieved from the network and drive-test measurements, the paper identifies the main challenges: different reporting in different technolo...

The long-term variability of electric field strength, obtained by band selective measurements for GSM 900 MHz DL band in real mobile network environment, is considered in this paper. Intensive measurements were carried out for 7 days at each of 7 different locations in urban area of Belgrade. The measurement results show that each day can be divide...

This work introduces joint power amplifier (PA) and I/Q modulator modelling and compensation for Long Term Evolution (LTE) transmitters using artificial neural networks (ANNs). The proposed solution utilizes a powerful nonlinear autoregressive with exogenous inputs (NARX) ANN architecture, which yields noticeable results for high peak to average po...

A large interest in developing commercial Location-Based Services (LBS) and the necessity of implementing emergency call services, have led to the intensive development of techniques for mobile users' localisation. In this paper, a Public Land Mobile Networks (PLMN) -based technique for initial position determination is proposed as an alternative t...

A new link layer protocol, quality of service hybrid multi channel protocol (QoS–HMCP), that takes into account the need for QoS support in multi-channel multi-interface wireless mesh networks (MCMI–WMNs) is proposed in this paper. QoS–HMCP protocol retains most properties of enhanced distributed channel access (EDCA) mechanism, defined by the 802....

As a result of dense installations of public mobile base station, additional electromagnetic radiation occurs in the living environment. Research group of accredited Radio-communications Laboratory, has been involved in human exposure assessments of GSM/UMTS base stations for over 15 years. Within these activities over 2200 base station locations (...

This paper presents a novel method for simulation of two correlated short-term fading envelopes in mobile radio channel. Proposed method is enabled by artificial neural network principles. The main idea was to base the simulation approach solely on the measurement results. In order to obtain an adequate measured data set, extensive electric field s...

A new microcell prediction model for mobile radio environment is presented in this paper. The popular support vector machine algorithm is used as an optimizing tool to build a model. In order to validate the model quality, extensive electric field strength measurements were carried out in the city of Belgrade, for two different test transmitter loc...

In this paper the problem of selecting optimal paths in a MCMI (Multi-Channel Multi-Interface) WMN (Wireless Mesh Network) is considered. The WMNs are characterized by high dynamic range of the received signal level, especially in the indoor environment. To improve the existing routing metrics and track fast changes that occur in the link state, a...

As a result of dense installations of public mobile base station, additional electromagnetic radiation occurs in the living environment. In order to determine the level of radio-frequency radiation generated by base stations, extensive electromagnetic field strength measurements were carried out for 664 base station locations. Base station location...

A big interest in developing commercial LBS (Location Based Services), and also the obligation of mobile network operators to implement emergency call service, have led to the intensive development of techniques for mobile users localization in the last few years. In this paper, three different types of positioning models, based upon utilization of...

Procuring location information for intelligent transportation systems is a popular topic among researchers. This paper investigates the vehicle location algorithm based on the received signal strength (RSS) from available Global System for Mobile Communications (GSM) networks. The performances of positioning models, which consisted of cascade-conne...

The obligation of mobile operators to implement emergency call services, as well as the big interest in developing commercial LBS (Location Based Services), have led to the intensive development of techniques for determination of mobile user's position in the last few years. The main goal of these researches is to achieve the highest possible accur...

This paper presents an algorithm for estimating a location of the base station in GSM system. The algorithm uses received signal strength measurements to detect and emphasize less reflected signal rays originating from the base station. The position estimate is obtained by averaging the intersection points of such rays. The performances of the algo...

This paper provides results regarding the maximal number of TETRA packet data service users which can be served by one TETRA cell. The analyzed scenario assumes that users are using web based applications and generate HTTP/IP packet data traffic. The paper considers single-slot packet-data TETRA system mode. A range of simulations and measurements...

This paper deals with the compression of fingerprints and the impact of compression on matching (recognition) performance. PCA method with the compression ratio 2.18:1 is proposed for fingerprints compression. Fingerprints compressed in this manner and the original (uncompressed) fingerprints were matched (1:n identification) with the fingerprints...

Positioning in public land mobile networks has become increasingly popular over the past years with the development of more sophisticated mobile equipment and standards. New services which rely on location information have been developed, such as emergency call localization, navigation, location sensitive commercials/ billing, etc. This paper inves...

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 cros...

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 str...

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-co...

In this paper a new approach to the electroencephalogram (EEG) signal simulation based on the artificial neural networks (ANN) is proposed. The aim was to simulate the spontaneous human EEG background activity based solely on the experimentally acquired EEG data. Therefore, an EEG measurement campaign was conducted on a healthy awake adult in order...

Providing the localization algorithm for context-aware services is the focus of many studies. This paper explores the properties of positioning models based on received signal strength (RSS) in PLMN (Public Land Mobile Network) networks. The effects of using the RSS at a mobile terminal from various systems, such as GSM and UMTS, as well as from mu...

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores models based on Artificial Neural Networks (ANNs): single ANN positioning models using RSSI, SNR and N values as in...

In order to make comparative quality analysis of UMTS signal of mobile operators, measuring procedure realized with specialized ROMES (Rohde&Schwarz) measurement system is introduced and represented in this paper. The measurement campaign and the essentials for evaluating and interpreting the measurement results are shown. In order to make quality...

In this paper different ways of planning the radio resources within an LTE network are analyzed. All simulations were carried out by 3GPP recommendations. SFR, SFFR and HFFR radio resource management are compared to R1 and R3 radio resource management. An optimum way of planning radio resources in LTE network is proposed at the end of the paper.

In this paper the application of M-step 4-state Markov multipath channel model for outdoor-to-outdoor and outdoor-to-indoor Tx/Rx scenarios is discussed. The above-mentioned Markov model was initially proposed for the indoor-to-indoor scenario and for the receiver in motion, while in this paper the case of the stationary receiver is considered. In...

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...

Standards stipulate 6-min time interval of averaging for measurements of radio-frequency electromagnetic fields to assess human exposure to non-ionising radiation. Having in mind the base stations of public land mobile systems, the time interval defined in such a way noticeably limits the number of measuring points in practical applications. In thi...

A novel method for short-term fading simulation is presented in this paper. Proposed solution is based on artificial neural network principles. In order to obtain an adequate training data set, extensive measurements of the received electric field strength were carried out in an indoor environment, in a nonline-of-sight scenario. As quality assessm...

Experimental evaluation of QoS mechanism defined in IEEE 802.11e standard is presented in this paper. Measurements were carried out in controlled laboratory conditions, with and without configured QoS. Mean and maximum delay, jitter and packet loss are measured in voice communications between two clients, competing with other voice clients. The res...

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures...

Digital Video Broadcasting - Terrestrial (DVB-T), European standard for Digital Terrestrial Television, even designed for fixed and portable reception, offers various trade-offs between bit rate, robustness and mobile performances. Consequently, reception of DVB-T signal by moving vehicles becomes feasible under specific requirements on receiver's...

1

Short range wireless technologies such as wireless local area network (WLAN), Bluetooth, radio frequency identification, ultrasound and Infrared Data Association can be used to supply position information in indoor environments where their infrastructure is deployed. Due to the ubiquitous presence of WLAN networks, positioning techniques in these e...

Various radio systems can be used to obtain the position information in indoor environments. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores the properties of cascade-connected Artificial Neural Networks (ANNs) structures. Several cascade-connected...

In this paper, a novel technique for simulation of the short-term fading is presented and analyzed. A proposed solution is based on a trained artificial neural network (in further text ANN) and an oscillator for regulating the simulation process. In order to obtain adequate input data for training, cross-validation and testing, extensive measuremen...

In this paper, the extensive experimental analysis of RSSI, SNR and noise level parameters usefulness for WLAN positioning purposes was conducted. Four positioning models, based on artificial neural networks, with RSSI, SNR, noise level and both RSSI and SNR as network's inputs, were created, trained and verified. The obtained results have shown th...

This paper presents one feature based method for automatic classification and recognition of 7 digital modulations for software defined radio. After reviewing some spectral based features, new statistical based ones are proposed. The classification is conducted with artificial neural networks (ANN). Three architectures are investigated: Multilayer...

Short range wireless technologies such as WLAN, Bluetooth, RFID, ultrasound and IrDA can be used to supply location information in indoor areas in which their coverage is assured. With respect to outdoor techniques, these technologies are more accurate but with smaller covering areas. In this paper, we present the comparison of the existing locatio...

The majority of existing GSM positioning techniques can be described as either costly or with limited performance. Basic GSM positioning techniques cell-ID and cell-ID+TA can be upgraded to decrease positioning error. We introduce a new location technique E-CIDTA that requires no additional infrastructure. A probabilistic approach is used to model...

In this article a review of popular propagation models for wireless communication channels is given. Macrocell, microcell, and indoor prediction methods are considered separately. Advantages and disadvantages of these models are discussed. Also, some practical improvements of the existing models as well as some new models are given.

Osnovni parametri jednog radio-sistema u pogledu pokrivenosti teritorije, utvrđuju se u fazi planiranja sistema na osnovu različitih metoda predikcije nivoa električnog polja. Proračunate vrednosti, a time i same metode predikcije, najčešće je potrebno proveriti merenjem na terenu. Merni sistemi koji omogućavaju proveru pokrivenosti teritorije sign...