KMi Seminars
Context Computing Based on Wireless Features
This event took place on Wednesday 04 July 2012 at 11:30

 
Dr. Stephan Sigg National Institute of Informatics


We are surrounded by sensing and actuating wireless devices. This environment is characterised by a high number of devices which can be reportedly explored as atypical ubiquitous sensing devices such as the power supply system, light bulbs or electromagnetic noise. A further ubiquitous sensing source,   incorporated by nearly all electronic devices, and presumably present in all devices that will constitute the Internet of Things, is the RF-interface. The RF-interface is a rich communication medium but also a rich sensing device. Its physical layer capabilities for the description of information and as a fingerprint of environmental situation are only partially explored currently. Environmental changes and situations alter the propagation path of electromagnetic waves and therefore channel characteristics at an RF-receiver, which can, in turn, be utilised for ubiquitous applications. Although this rich context source can support applications in a multitude of ways, its potential is seldom fully exploited. We explore the RF-channel for 1/ the detection of actions and environmental situations from RF features 2/ the reduction of computational load in a distributed context computation 3/ spontaneous, unattended secure device interaction.



 
KMi Seminars Event | SSSW 2013, The 10th Summer School on Ontology Engineering and the Semantic Web Journal | 25 years of knowledge acquisition
 

Multimedia and Information Systems is...


Multimedia and Information Systems
Our research is centred around the theme of Multimedia Information Retrieval, ie, Video Search Engines, Image Databases, Spoken Document Retrieval, Music Retrieval, Query Languages and Query Mediation.

We focus on content-based information retrieval over a wide range of data spanning form unstructured text and unlabelled images over spoken documents and music to videos. This encompasses the modelling of human perception of relevance and similarity, the learning from user actions and the up-to-date presentation of information. Currently we are building a research version of an integrated multimedia information retrieval system MIR to be used as a research prototype. We aim for a system that understands the user's information need and successfully links it to the appropriate information sources, be it a report or a TV news clip. This work is guided by the vision that an automated knowledge extraction system ultimately empowers people making efficient use of information sources without the burden of filing data into specialised databases.

Visit the MMIS website