KMi Seminars
What is happening in a meeting?
This event took place on Wednesday 12 December 2007 at 11:30

 
Dr. Nailah Abdullah Honiden Laboratory, Intelligent Research System Division, National Institute of Informatics, Japan

This is an introduction to a proposed collaboration between National Institute of Informatics, Japan and KMi on developing method of analysis and tools for understanding what is happening in a meeting. The long-term goal is to capitalize FlashMeeting for the field of requirement engineering. The rapidly increasing globalization of software industry creates a strong demand to achieve a better understanding of the challenges faced by multi-site software development and to study advanced technologies that successfully support collaborative activities in global software engineering. Software engineers have adopted every mainstream communication technology

such as telephone, teleconferences, email, voice mail, discussion lists, Web, instant messaging, text messaging, video conferences, voice over IP, useful at every stage of a project?s lifecycle. Their main concern during these Web meetings is for analysts to understand ?what is happening in the meeting (for example during videoconferencing meetings)?

FlashMeeting currently provides data analysis of meeting footprints. As a first step towards achieving our goal, we propose further: linking a micro-level analysis to the current data analysis provided by Flashmeeting. We retrieved two different types of naturalistic meetings as benchmark data. We focus firstly on analyzing animation meeting, closely resembling a working/design meeting.

This talk will be divided into two parts. The first part briefly introduces the problems faced by requirement engineers in Japan. The second part concerns the ongoing research with collaborating teams at KMi on analyzing animeetings highlighting the developing method and some results.

 
KMi Seminars
 

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