Dragan Obradovic

Short CV

Dragan Obradovic received his B.E. and M.E. degrees in Mechanical Engineering in 1980 and 1985 from the University of Belgrade, Serbia, the latter parallel to holding a Research Engineer position in the Institute Mihailo Pupin. In 1990 he received the Ph.D. degree in Mechanical Engineering from the Massachusetts Institute of Technology, Cambridge, USA. After finishing his PhD, he stayed at MIT until the end of 1991 in the position of a Postdoctoral Fellow at the Laboratory for Information and Decision Systems (LIDS). Since 1992, Obradovic has been with Siemens Corporate Technology, Information and Communications, in Munich, Germany where he currently holds a position of Principal Research Scientist. In addition, since 2001 Obradovic has been teaching as an Industrial Lecturer in the international “Masters of Science in Communication Engineering (MSCE)” program within the EE Department at Technical University Munich.

Selected Awards

• 1997, SIEMENS INNOVATION PRIZE’97
• 1985, FULBRIGHT SCHOLARSHIP FOR GRADUATE STUDIES, Awarded by the USA-Yugoslav Commission for Cultural Exchange

Research Interests

Obradovic’ research interests involve, among others, machine learning applications to signal processing, networked control systems, clock synchronization in automation systems, and control of wind turbines and of smart grid.

Selected Publications

• Na, Chongning; Obradovic, Dragan; Szabo, Andrei: EM based channel estimation method for MIMO-OFDM systems. Eur. Trans. Telecomm. 19 (8), 2008, 907-916.

• Lenz, Henning; Parodi, Bruno Betoni; Wang, Hui; Szabo, Andrei; Bamberger, Joachim; Obradovic, Dragan; Horn, Joachim; Hanebeck, Uwe D.: Adaptive Localization in Wireless Networks. In: Signal Processing Techniques for Knowledge Extraction and Information Fusion. Springer Science + Business Media, 2008.

• Obradovic, Dragan; Lenz, Henning; Schupfner, Markus: Fusion of Sensor Data in Siemens Car Navigation System. IEEE Trans. Veh. Technol. 56 (1), 2007, 43-50.

• Obradovic, D.; H. Lenz, H.: Stabilizing higher periodic orbits of chaotic discrete-time maps. International Journal of Bifurcation and Chaos 09 (01), 1999, 251-266.

• Obradovic, D.; Deco, G.: Information Maximization and Independent Component Analysis: Is There a Difference? Neural Computation 10 (8), 1998, 2085-2101.

• Obradovic, Dragan; Lenz, Henning: When is OGY Control More Than Just Pole Placement. International Journal of Bifurcation and Chaos 07 (03), 1997, 691-699.

• Deco, Gustavo; Obradovic, Dragan: An Information-Theoretic Approach to Neural Computing. Springer New York, 1996.

• Obradovic, D.: On-line training of recurrent neural networks with continuous topology adaptation. IEEE Trans. Neural Netw. 7 (1), 1996, 222-228.

• Obradovic, Dragan; Valavani, Lena: Stability and performance in the presence of magnitude bounded real uncertainty: Riccati equation based state space approaches. Automatica 28 (4), 1992, 827-830.