oo

Post conference update: Poster and demo papers are available online.



Keynotes

Computing for Human Experience: Semantics empowered Sensors, Services, and Social Computing on ubiquitous Web

Amit Sheth, Kno.e.sis Center, Wright State University

Today, systems, devices, sensors and human participation enable something more than a “human instructs machine” paradigm. In the past, we had to artificially simplify the complexity and richness of the real world to constrained computer models and languages for more efficient computation. Now, sensing, semantics, and social computing work in concert to enrich the Web based interactions; multisensory devices, computing, and ubiquitous connectivity involving multimodal information engage transparency in human activities to enrich them in ways not possible before.  Citizen sensors and citizen journalism are early examples of these. Increasingly intelligent systems and participatory sensing capture observations that can be contextually integrated and enhanced to create awareness of events and situations— they not only deal with simple objects such as documents or entities but also support situational awareness by incorporating relationships between objects and the temporal (“when”), thematic (“what”) and spatial (”where”) aspects of objects and events. This positions us for what we call an era of “computing for human experience” that supports a seamless interaction between the physical world and the virtual or cyber world with advanced integrated capabilities in sensing, perceiving and recognizing the physical world (e.g., in extending sensory engagement with environments and narrowing the gaps between the real world and computing). It also uses “humans as sensors” of intensions and emotions, and historical facts or background knowledge and community generated knowledge or collective intelligence while integrating online and offline interactions, all the while making computing disappear in the background.

This vision builds upon applications and infrastructures embodying the principles of computing for richer human experiences that include Internet of Things, Intelligence@Interfaces, multisensory interactions, MyLifeBits, Linked Data, Open Social, Semantic Web, Semantics-empowered Social Computing, and Semantic Sensor Web. It also borrows aspects from other exciting visions such as The Computer for 21st Century, Humanist Computing, Relationship Web, PeopleWeb, EventWeb, and Experiential Computing.


Amit Sheth is the LexisNexis Ohio Eminent Scholar at the Wright State University, Dayton OH. He directs the Kno.e.sis Center (http://knoesis.org) which performs leading research in Semantic, Social, Sensor and Services computing over Web. Prof. Sheth is an IEEE fellow and is well cited (h-index = 58) for his work in semantic information integration, workflow management, semantic web, and semantic web services. He is EIC of ISI indexed Intl. Journal of Semantic Web &Information Systems (http://ijswis.org), is joint-EIC of Distributed & Parallel Databases, is series co-editor of two Springer book series, and serves on several editorial boards. By licensing his funded university research, he has also founded and managed two successful companies. Several commercial products and many operationally deployed applications have resulted from his R&D.



Large Scale Sensor Networks Deployment: Research Challenges and Opportunities

Marimuthu Palaniswami,  ARC Research Network on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), The University of Melbourne

Sensor networks offer the great potential providing unique access to critical data at a scale not previously realizable. The subsequent information extracted from this sensor data can become a vital tool for scientists in understanding natural phenomena and also service providers in translating field data to meeting community needs. Numerous challenges are still being faced in deploying such systems. This talk describes some of the research challenges and opportunities in deploying large scale sensor networks – making the transition from the lab to the real world – through case studies in environmental monitoring and healthcare.

The Great Barrier Reef (GBR) in Australia consists of 3200 coral reefs extended over 280,000 km2. Coral reef ecosystems are areas greatly susceptible to impact of global climate change as well as other man-made influences. This creates an urgent demand for the sensor network technologies to be deployed in order to perform essential environmental monitoring and information collection based on reliable data. One such deployment is the Great Barrier Reef Ocean Observing System (GBROOS), consisting of a 3-tier sensor network, spanning seven sites throughout the GBR. GBROOS provides the physical and chemical data required to measure and understand short term variability and long term change; infrastructure and logistics to support and facilitate the next generation of observational science and the issues driving this; and data for real-time observing information from the Great Barrier Reef. The Smart Environmental Monitoring and Analysis Technologies (SEMAT) project fills specific knowledge and technical gaps so that a cost effective, robust, and easily installed monitoring system is available for real-time monitoring in marine and other aquatic ecosystems. It is taking a working proof-of-concept next generation wireless marine sensor network to a commercial prototype to enable real time monitoring of the marine environment. The system utilises an integrated, sensor network solution using underwater radio-frequency communication. The central aim of the SEMAT project is to build a “smart” wireless sensor architecture that will allow users to apply both their existing hardware and emerging technologies within a multi-scale monitoring system that allows them to interrogate and task aspects of the sensor network according to need and monitoring outcomes.

In the healthcare domain, we look at projects incorporating sensor networks technology to provide critical diagnostic services in third world countries exploring the low cost potential of this technology. A number of deployment scenarios delivering pulse oximetry capabilities are being explored integrating networking functionality to provide real time low-cost diagnostic services.  Research has shown that people with sleep disordered breathing (SDB) are at least 4 times as likely to have a traffic accident, while early diagnosis and treatment of SDB could prevent adverse consequences. This project provides a simple scheme for screening SDB and sleep quality based on pulse oximetry signals with the consequences could be substantial, potentially saving billions of dollars in healthcare costs and million of lives worldwide. Another related project involves cell phone applications for clinical diagnostic, therapeutic and public health use by front-line health workers in Mozambique incorporating sensing capabilities and reference material in a distributed sensor network framework. With the national drug formulary in a searchable form and a collection of sensors, the technology delivers point-of-care diagnosis, as well as monitoring of treatment, of respiratory diseases.


Palaniswami received his MEngSc from the University of Melbourne and PhD from the University of Newcastle, Australia before rejoining the University of Melbourne.  He has published over 300 refereed research papers, a majority of which have appeared in the prestigious IEEE Journals and Conferences. He was given a Foreign Specialist Award by the Ministry of Education, Japan in recognition of his contributions to the field of Machine Learning. He currently leads one of the largest funded ARC Research Network on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP) programme –that is structured it run as a network centre of excellence with complementary funding for fundamental research, test beds, international linkages and industry linkages. The areas of application include healthcare, security and environment. Sustained knowledge transfer has been achieved through a large number of Industrial Linkages, International Linkages, several large Scale Test beds (NCRIS GBROOS, SEMAT, ARC-LIEF BigNet) with competitive funding over $20 million along with other national and international investigators in the last five years. His leadership includes as an external reviewer to an international research centre, a selection panel member for senior appointments/promotions, grants panel member for NSF, Advisory board member for European FP6 grant centre, steering committee member for NCRIS GBROOS and SEMAT, and board member for IT and SCADA companies.  He has the distinction of receiving UoM Knowledge Transfer Excellence Award for 2008 and Knowledge Transfer Commendation Award for 2007. His research interests include SVMs, Sensors and Sensor Networks, Machine Learning, Neural Network, Pattern Recognition, Signal Processing and Control. He has 6 keynote talks, 6 plenary talks and 3 invited talks in international conferences and workshops. He initiated the ISSNIP conference series and ICISIP conference series which are the flagship events of the Research Network that draws over 250 international delegates and renowned plenary speakers; the fifth ISSNIP (www.issnip.org/2009) in the series scheduled in 2009 at Melbourne.


Conference Program

The final program can be downloaded from here.

 

Wednesday, September 16, 2009

Thursday, September 17, 2009

Friday, September 18, 2009

9:00-10:30

 

Second keynote

Technical session 5

10:30-11:00 

Coffee break

Coffee break

11:00-12:30

Technical Session 2

Technical session 6


Discussion Paenl &
Concluding remarks

12:30-14:00 

Registration

Lunch break

Lunch

14:00-15:30

Welcome message, and First keynote

Technical session 3

 

15:30-16:00 

Coffee break

Coffee break

16:00-17:30

Technical Session 1

Technical session 4

 

 

17:30-19:00

Reception and Poster session

Social dinner

19:00-



Technical Session 1: Activity Recognition

  • Episode Segmentation Using Recursive Multiple Eigenspaces,  Aziah Ali, Guang-Zhong Yang, Surapa Thiemjarus.

  • Keep on Moving! Activity Monitoring and Stimulation using Wireless Sensor Networks, Stephan Bosch, Hermie Hermens, Paul Havinga, Raluca Marin-Perianu, Mihai Marin-Perianu.

  • Time-lag as Limiting Factor for Indoor Walking Navigation,  Andreas Riener, Markus Straub, Alois Ferscha. 

Technical Session 2:
Information aspects of context-aware sensor and actuator systems

  • A Query Service for Raw Sensor Data,  Dónall McCann, Mark Roantree.

  • A Context Lifecycle For Web-Based Context Management Services, Gearoid Hynes,  Manfred Hauswirth, Vinny Reynolds.

  • Semantic Annotation and Reasoning for Sensor Data, Wei Wang, Payam Barnaghi. 

Technical Session 3:
Context-aware service platforms

  • Semantic Rules for Context-Aware Geographical Information Retrieval, Carsten Keßler, Christoph Wosniok, Martin Raubal.

  • A Context Provisioning Framework to Support Pervasive & Ubiquitous Applications, Michael Knappmeyer, Ralf Tönjes, Saad Liaquat, Nigel Baker.

  • Context-aware Recommendations on Mobile Services: The m:Ciudad Approach,    Andreas Emrich, Alexandra Chapko, Dirk Werth.

Technical Session 4:
Context processing, reasoning, and fusion

  • Context Cells: Towards Lifelong Learning in Activity Recognition Systems, Alberto Calatroni, Gerhard Tröster, Daniel Roggen, Claudia Villalonga.


  • Automatic Event Based Synchronization of Multi Modal Data Streams from Wearable and Ambient Sensors, David Bannach, Paul Lukowicz, Oliver Amft.

  • Using Dempster-Shafer Theory of Evidence for Situation Inference, Susan Mckeever, Simon    Dobson, Lorcan Coyle, Juan Ye.

Technical Session 5: Real-world experiences with deployed systems

  • Recognizing the Use-Mode of Kitchen Appliances from their Current Consumption, Gerald Bauer,  Karl Stockinger and Paul Lukowicz.

  • Wireless Sensor Networks to enable the Passive House - Deployment Experiences, Tessa Daniel, Elena Gaura, James Brusey.

Technical Session 6:
Context-aware frameworks  in mobile environments

  • Mobile Context Toolbox an extensible context framework for S60 mobile phones, Jakob Eg Larsen and Kristian Jensen.

  • Statistic-based Context Recognition in Smart Car, Jie Sun, Kejia He.