Machine Learning
Start Date: 
Tuesday, December 20, 2011 - 09:00 to 17:00
Amritapuri Campus

Tutorial Speaker:  (1) Venu Govindaraju, Professor of Computer Science and Engineering, University at Buffalo, State University of New York, USA (2) Anurag Bharadwaj, Senior Research Scientist, eBay Research Labs, USA, (3) Utkarsh Porwal, PhD Student, University at Buffalo, State University of New York,USA 
Title:  Machine Learning Algorithms and its Applications in Distributed Wireless Sensor Networks 


Wireless  Sensor  Networks  (WSNs)  has  been  applied  in  various  domains  such  as  environment monitoring,  industry  and  healthcare  for  various  purposes.  WSNs  are  used  to  interact  with  the environment and send useful information across the network. These sensors need to keep track of states of other nodes, perform adaptive information extraction, and predict location of mobile nodes for optimum utilization of resources. However, sensors often suffer from problems such as physical constraints, low bandwidth and ineffective communication between different nodes which leads to error  and  inefficiency  in  the  network.  Hence,  WSNs  have  inspired  research  on  machine  learning techniques  to address these  limitations  with  more  generic  ways  of  extracting  information  and discovering relations. Machine learning has already been used to address problems such as to make 
inference from the  data  by  extracting  useful features,  building similarity matrices, mapping  vector spaces  of signals  given  by sensors  with  physical spaces  and  dealing  with large  amount  of  online unlabeled  data.  Different  learning  paradigms such  as supervised,  unsupervised  and reinforcement learning  has  been  used  to  address  these  issues.  Moreover,  classification,  regression  and  kernel techniques have been used to solve several problems pertaining to WSNs. On the other hand Machine learning and Artificial Intelligence community has taken great interest in distributed wireless sensor networks.  Applications such as robotics and context aware computing have used WSNs extensively for more  intelligent  and  automated  learning  process.  This tutorial  intends to  give the  comprehensive overview of fundamental working and limitations of such machine learning algorithms and highlight the scope of future research in this area using Machine Learning.