Home Coordinates Research Teaching Links & Biblio
 

Research

Research interests

Interested in machine learning: feature selection, feature transformation, parametric model optimization and model selection. I focused during my PhD on the design and implementation of machine learning techniques for wireless sensor networks, with a particular interest in environmental and industrial monitoring applications.

My PhD thesis is entitled "Learning in Wireless Sensor Networks for Energy-Efficient Environmental Monitoring" and is available here. The slides of my PhD defense are available here (60MB, embedded videos).

Experimental work and real-world deployments with sensor networks are described on the wireless sensor network lab web page.

Main topics of interest:
  • Localization, data prediction and data compression in Wireless Sensor Networks (WSN)
  • Distributed principal component analysis
  • Time series prediction
  • Multidimensional scaling, curvilinear component analysis
  • Bias and variance characterization in prediction model design
  • Local linear modeling, lazy learning
  • Forests of trees
  • Regularized linear model - Ridge regression - Lasso - Elastic nets

Research Group


Publications

  • Book chapter
    • Y. Le Borgne and G. Bontempi. Prediction-based data collection in wireless sensor networks. In Intelligent Sensor Networks: Across Sensing, Signal Processing, and Machine Learning. Taylor and Francis/CRC Press, 2012, To appear.
    • Y. Le Borgne, J.M. Dricot, and G. Bontempi. Principal component aggregation for energy-efficient information extraction in wireless sensor networks. In Knowledge Discovery from Sensor Data, pages 55–80. Taylor and Francis/CRC Press, 2008. [preprint PDF]

  • Journals
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. Decentralised reinforcement learning for energy-efficient scheduling in wireless sensor networks. International Journal of Communication Networks and Distributed Systems, 9:207–224, 2012.
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. Reinforcement learning for self-organizing wake-up scheduling in wireless sensor networks. Communications in Computer and Information Science, 271:382–397, 2012.
    • Y. Le Borgne, S. Raybaud, and G. Bontempi. Distributed Principal Component Analysis for Wireless Sensor Networks. Sensors Journal, MDPI, Volume 8, Issue 8, August 2008, Pages 4821-4850. [Link to Sensors Journal - Open Access]
    • A. A. Miranda, Y. Le Borgne, and G. Bontempi. New Routes from Minimal Approximation Error to Principal Components. Neural Processing Letters, Springer, Volume 27, Issue 3, June 2008, Pages 197-207. [preprint PDF] [Link to springer]
    • Y. Le Borgne, S. Santini and G. Bontempi. Adaptive Model Selection for Time Series Prediction in Wireless Sensor Networks. Journal of Signal Processing, Elsevier, Volume 87, Issue 12, December 2007, Pages 3010-3020. [preprint PDF] [Link to sciencedirect]

  • Conferences
    • Y. Le Borgne and G. Bontempi. Time series prediction for energy- efficient wireless sensors : Applications to environmental monitoring and video games. In Third International Conference on Sensor Systems and Software (S-Cube 2012), June 2012.
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. Decentralized (de)synchronization in wireless sensor networks. In Proceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC 2011), Gent, Belgium, November 2011.
    • M. Devillé, Y. Le Borgne, and A. Nowé. Reinforcement learning for energy efficient routing in wireless sensor networks. In Proceedings of the 23rd Benelux Conference on Artificial Intelligence (BNAIC 2011), Gent, Belgium, November 2011.
    • Y. Le Borgne and A. Campo. Open review in computer science. Elsevier grand challenge on executable papers. In International Conference on Computational Science (ICCS 2011), Procedia Computer Science, volume 4, pages 778–780, May 2011.
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. Self-organizing synchronicity and desynchronicity using reinforcement learning. In Proceedings of the 3rd International Conference on Agents and Artificial Intelligence (ICAART 2011), pages 94–103, Rome, Italy, January 2011.
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. Distributed cooperation in wireless sensor networks. In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), pages 249 – 256, May 2011.
    • M. Mihaylov, Y. Le Borgne, K. Tuyls, and A. Nowé. DESYDE: Decentralized (de)synchronization in wireless sensor networks. In Proceedings of the 20th Annual Belgian-Dutch Conference on Machine Learning (BENELEARN 2011), pages 109–110, The Hague, The Netherlands, 2011.
    • Mihaylov M., Le Borgne Y., Nowe A., and Tuyls K., “Decentralized Reinforcement Learning for Wake-up Scheduling”, 7th European conference on wireless sensor networks (EWSN 2010), pp.49 - 51, 2010.
    • Le Borgne Y., Nowe A., Steenhaut K., and Bontempi G., “Demo Abstract: Demonstrating Principal Component Aggregation for Distributed Spatial Pattern Recognition”, 9th International Conference on Information Processing in Sensor Networks, issue April 12, 2010 Stockholm, Sweden, pp.430 - 431, eds. Tarek Abdelzaher, Thiemo Voigt, Adam Wolisz, published by ACM, 2010.
    • Abughalieh N., Le Borgne Y., Steenhaut K., and Nowé A., “Lifetime Optimization for Wireless Sensor Networks with Correlated Data Gathering”, 8th Intl. Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, pp.252 - 258, eds. Eitan Altman, Tamer Basar, Imrich Chlamtac, 2010.
    • Le Borgne Y., Nowe A., Abughalieh N., and Steenhaut K., “Distributed regression for high-level feature extraction in wireless sensor networks”, 7th International Conference on Networked Sensing Systems, pp.249 - 252, eds. Hartmut Hillmer, Masateru Minami, published by IEEE, 2010.
    • J. M. Dricot, M. Van Der Haegen, Y. Le Borgne and G. Bontempi. A Modular Framework for User Localization and Tracking Using Machine Learning Techniques in Wireless Sensor Networks. Accepted at the 8th IEEE Conference on Sensors, October 2008.
    • J. M. Dricot, M. Van Der Haegen, Y. Le Borgne and G. Bontempi. Performance Evaluation of Machine Learning Technique for the Localization of Users in Wireless Sensor Networks. In L. Wehenkel and P. Geurts and R. Marée, Editors, Proceedings of the BENELEARN Machine Learning Conference, pages 93-94. 2008.
    • Y. Le Borgne and G. Bontempi. Unsupervised and Supervised Compression with Principal Component Analysis in Wireless Sensor Networks. Proceedings of the Workshop on Knowledge Discovery from Data, 13th ACM International Conference on Knowledge Discovery and Data Mining, pages 94-103. ACM Press, New York, NY, 2007. [PDF]
    • Y. Le Borgne, M. Moussaid, and G. Bontempi. Simulation architecture for data processing algorithms in wireless sensor networks. Proceedings of the 20th Conference on Advanced Information Networking and Applications (AINA), pages 383–387. IEEE Press, Piscataway, NJ, 2006. [PDF]
    • Y. Le Borgne, G. Bontempi. Round Robin Cycle for Predictions in Wireless Sensor Networks. Proceedings of the 2nd International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), pages 253-258. IEEE Press, Piscataway, NJ, 2005. [PDF]
    • G. Bontempi, Y. Le Borgne. An adaptive modular approach to the mining of sensor network data. Proceedings of the workshop on Data Mining in Sensor Networks. SIAM SDM, pages 3-9. SIAM Press, Philadelphia, PA, 2005.[PDF]

  • Posters
    • Y. Le Borgne and G. Bontempi. Unsupervised and supervised compression with principal component analysis in wireless sensor networks. Second Computational Intelligence and Learning Contact day, Leuven, August 2007. [PDF]
    • M. Van Der Haegen, Y. Le Borgne and G. Bontempi. Wireless Sensor Networks for Localization. Printemps des Sciences, Bruxelles, March 2007 (in French). [PDF1] [PDF2]
    • Y. Le Borgne, S. Santini, and G. Bontempi. Adaptive Model Selection for Streaming of Wireless Sensor Data. First Computational Intelligence and Learning Contact day, Bruxelles, September 2006. [PDF]

  • Technical report
    • Y. Le Borgne. Bias variance trade-off characterization in a classification. What differences with regression?. Technical Report N°534, ULB, January 2005.

  • Theses
    • Y. Le Borgne, Learning in Wireless Sensor Networks for Energy-Efficient Environmental Monitoring. PhD Thesis, Université Libre de Bruxelles, 2009.
    • Y. Le Borgne. Interactions entre les propriétés globales et locales des scènes naturelles (in French). DEA Thesis, Université Joseph Fourier - INPG, Grenoble, France, 2003. [PDF]
    • Y. Le Borgne. Application du système Bonom à la recherche de CV ou d'offres d'emploi. Master's Thesis, Institut de Recherche en Informatique de Nantes - Nantes, France, 2002.
Competitions