Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Milan Marković is active.

Publication


Featured researches published by Milan Marković.


IEEE Transactions on Speech and Audio Processing | 1996

A statistical pattern recognition approach to robust recursive identification of nonstationary AR model of speech production system

Milan Marković; Branko Kovačević; Milan Milosavljević

We propose a new robust recursive procedure based on the weighted recursive least squares (WRLS) algorithm with variable forgetting factor (VFF) and frame-based quadratic classifier for identification of nonstationary AR model of speech. Two versions of the frame-based quadratic classifier design procedure are elaborated upon. Experimental results are obtained in analyzing speech signal on voiced and mixed excitation frames.


Archive | 2004

Development of Secure Web Financial Services in Serbia

Zoran Savić; Milan Marković

Abstract Text — Recently, a boom of trusted electronic banking services has happened in Serbia. A lot of broker companies, and other legal persons (approximately more than 20000 from the begining of this year), use a trusted electronic financial services through Serbian commercial banks and National Bank of Serbia. All of them perform the remote electronic payment service through the web banking service secured with digital signature and envelope technology based on PKI digital certificate and asymmetrical keys stored on PKI smart cards. Digital certificates are issued mostly by banks themselves or throuh some of the outsourcing Certification Authority schemes. As an example of the secure electronic banking system, a trusted web financial portal which is now dominant technical solution in Serbia is described in this paper. The system provides the highest level of security and large functional and cryptographic customization capabilities.


International Journal of Pattern Recognition and Artificial Intelligence | 2001

SHAPE CLASSIFICATION BY MOMENT AND AUTOREGRESSIVE INVARIANTS

Predrag Pejnovic; Milan Marković; Srdjan Stankovic

An experimental analysis of shape classification methods based on moment and autoregressive (AR) invariants is presented. Various types of translation, scale and rotation invariants are used to construct feature vectors for classification. The performance is evaluated using five different objects picked up from real scenes with a TV camera. Silhouettes and contours are extracted from nonoccluded two-dimensional (2D) objects rotated, scaled and translated in 3D space. The feature extraction methods are implemented and systematically tested using several parametric and nonparametric classifiers. The results clearly show the advantage of the method based on the moment invariants.


Innovations in Systems and Software Engineering | 2013

Secure Mobile Government and Mobile Banking Systems Based on Android Clients

Milan Marković; Goran Đorđević

In this paper, we consider an overview of a possible secure model for m-government and m-banking systems. The proposed model is based on secure mobile application and SOA-Based central platform. The model additionally consists of external entities/servers, such as: PKI, XKMS, Authentication and Time Stamping server. The proposed model could be used in different local and/or cross-border m-government scenarios, as well as in different kind of m-banking systems. As a possible example of described secure mobile application we considered and experimentally evaluated a possible usage of secure Android based Web services application in the proposed model.


Innovations in Systems and Software Engineering | 2006

PKi Consolidation Project and Multiapplicative Smart Payment Cards

Milan Marković; Miloš Kilibarda; Aleksandar Milošević

In this paper, main characteristics of the consolidated PKI system in Banca Intesa ad Beograd are described. This PKI system is used for electronic banking services for external users (home banking for physical persons and e-banking for legal persons), as well as a part of the identity management system (windows logon, single sign-on) and other security services for Bank’s internal users (secure e-mail, SSL client authentication). One of the main features of this project is an introduction of the EMV DDA MasterCards in Banca Intesa ad Beograd. These are PKI Multos cards which will have three applications on them: MIChip Select 4 and CAP payment applications, as well as PKI application. This way, our Maestro users could make payment through POS and ATMs by using the M/Chip payment applications, via Internet in unconnected mode by using external CAP reader and CAP application on the card and, in connected mode, via Bank’s web portal by using the connected smart card reader and PKI application on the card with X.509 digital certificate issued by the consolidated PKI system of Banca Intesa ad Beograd. The PKI consolidated system of Banca Intesa ad Beograd is based on the fully customized domestic PKI solution.


Innovations in Systems and Software Engineering | 2004

Recent PKI Experiences in Serbia

Milan Marković

This is a survey paper about recent PKI experiences in Serbia. These PKI projects are briefly described in the paper and include PKI systems for: National Bank of Serbia, commercial banks — especially sophisticated PKI system in Delta bank, Serbian ID smart card project, Serbian Academic Institution network — NIOnet, etc. Also, the activities on these projects are followed by activities in preparing the Electronic signature Law and SubLaw acts, as well as for preparing the Data Protection Law in Electronic Communications. Besides, there were some educational activities in domain of electronic business security and computer network security in which the author is included.


Circuits Systems and Signal Processing | 2000

On evaluating A class of frame-based nonstationary pattern recognition methods using bhattacharyya distance

Milan Marković; Milan Milosavljević; Branko Kovačević

We consider a possible evaluation of frame-based nonstationary pattern recognition methods by using the upper bound trajectories of the Bayes error based on the Bhattacharrya distance. The experimental part of the work is based on natural speech processing, using isolated spoken Serbian vowels and digits as examples of nonstationary signals. The results obtained justify the use of the upper bound trajectories of the Bayes error expressed by the Bhattacharyya distance as a possible evaluation tool for the class of frame-based nonstationary pattern recognition systems.


european signal processing conference | 2002

RSA algorithm optimization on assembler of TI TMS320C54x signal processors

Milan Marković; Tomislav Unkasevic; Goran Dordevic


Archive | 2006

Secure Mobile Health Systems: Principles and Solutions

Milan Marković; Zoran Savić; Branko Kovačević


european signal processing conference | 2000

Robust recursive AR speech analysis based on quadratic classifier with sliding training data set and a heuristic decision threshold

Milan Marković

Collaboration


Dive into the Milan Marković's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Goran Dordevic

Military Technical Academy

View shared research outputs
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge