 Accenture
449, Route des Cretes
06902 Sophia Antipolis
FRANCE
Research Interests - Vision and image-based recognition.
- The propagation of information (i.e., data, viruses, beliefs, ideas) in networks due to their structures, butterfly effects or the network effect.
- Models and technologies that capture, predict, and improve our daily lives and business processes.
- Data fusion (i.e., how to take into account information coming in from different sensors at the same time, especially when they contradict one another).
Related fields: Computer vision, applied mathematics, stochastic processes, hidden Markov models, Bayesian networks, mobility models, social networks, small worlds, scale-free networks, data fusion, sensor networks, WiFi, RFID.Recent Project   Visual Shelf Monitoring (project leader): The presence, misplacement, and in particular, the lack of products on supermarket shelves are monitored in real-time through in-store cameras and visual object recognition algorithms. This allows retailers to avoid stock-outs of the products, which otherwise incur revenue losses and cause customer dissatisfaction. In addition, consumer goods companies can monitor that their products are displayed according to agreements. The use of cameras allows for tag-less monitoring of products and requires no modification to the shelf infrastructure other than the deployment of a camera network. Current research focuses on practical deployment issues and algorithmic improvements to boost performance.
 Automated Visual Repository Building: With the advent of powerful state-of-the-art object recognition algorithms, new capabilities arise for any image capturing device. For example, imagine pointing your phone at an object—small or big—and retrieving real-time information on this item, such as reviews, price comparisons, vendor and content information, installation instructions, and what model it is. In addition, this automatic recognition of objects in images can be applied to any image and therefore also has applications in content filtering and automated image labelling. In order to build such a powerful system there is a need for (automatically creating) databases of images, independent of the application or the object recognition algorithm used.
These databases need to contain in vitro images (i.e., containing no background/clutter around the object in the image) under a variety of angles and lighting conditions and ideally need to be created with a couple of keywords and a simple push of a button. We are developing methods and algorithms in order to build such systems—using images from the Web—as well as investigating the strengths and limitations of the technologies (can all objects be recognized? How scalable is it? How well does it perform?). Education
Ph.D., computer science, INRIA, France;
Master's in mathematics, Vrije Universiteit, Amsterdam;
Master's in business mathematics and computer science, Vrije Universiteit, Amsterdam. Personal Interests
Activities that challenge, sports, releasing energy, photography, discovering the world, salsa. Making the world a better place to live in. Testimonial/Personal Quote
Live each day as if it were your last, because some day you're bound to be right. Publications Papers in Conferences
Impact of Mobility on the Performance of Relaying in Ad Hoc Networks
A. Al-Hanbali, A.A. Kherani, R. Groenevelt, P. Nain, and E. Altman
IEEE Infocom 2006, Barcelona, April 2006
[Paper (PDF, 974K)]
PDF Help Message Delay in Mobile Ad Hoc Networks
R. Groenevelt, G. Koole, and P. Nain
Performance, Juan-les-Pins, October 2005
[Paper (PDF, 363K)]
PDF Help Message Delay in MANET
R. Groenevelt, G. Koole, and P. Nain
ACM SIGMETRICS, June 2005 (extended abstract)
[Paper (PDF, 125K)]
PDF Help Analysis of Alternating-priority Queueing Models with (Cross) Correlated Switchover Times
R. Groenevelt and E. Altman
IEEE INFOCOM2005, Miami, March 2005 (a full version is available in Queueing Systems, vol. 51, 2005)
[Paper (PDF, 284K)]
PDF Help Papers in Journals
Relaying in Mobile Ad Hoc Networks: The Brownian Motion Mobility Model
R. Groenevelt, E. Altman, and P. Nain
ACM Kluwer - Springer Journal of Wireless Networks (WINET), 2005
[Paper (PDF, 235K)]
PDF Help Analysis of Alternating-priority Queueing Models with (Cross) Correlated Switchover Times
R. Groenevelt and E. Altman
Queueing Systems, vol. 51, special issue on Stochastic Networks, 2005
(a short version is available in the proceedings of IEEE INFOCOM 2005)
[Paper (PDF, 456K)]
PDF Help On the Bias Vector of a Two-class Preemptive Priority Queue
R. Groenevelt, G. Koole, and P. Nain
Mathematical Methods in Operations Research, 2002
[Paper (PDF, 163K)]
PDF Help Papers in workshops
Towards Understanding & Modeling Individual Behavior & Group Dynamics
M. Bezzi and R. Groenevelt
Pervasive (Workshop), Dublin, May 2006
[Paper (PDF, 150K)]
PDF Help Thesis
Stochastic Models in Mobile Ad Hoc Networks
University of Nice—Sophia Antipolis, INRIA
[Presentation][Paper (PDF, 4.5MB)]
PDF Help
Estimated download time using 56.6K modem for 1MB file = 3 min.
Reports
On the value function of a two-class single server preemptive priority queue
Master's thesis Mathematics
Amsterdam, August 2000.
The classification of potential customers applying for a personal loan
Master's thesis Business Mathematics and Computer Science
ABSA Bank, Johannesburg, South Africa, July 1998.
BWI Business case: Optimal inventory control Bijenkorf
July 1997
Data Mining Techniques: Rough Sets, Decision Trees, and Rough Data Models
Joint work with S.v. Westerop To Top |