Top > GLO-DAAD > Alumni > Projects > Project-Streibel

Global Liaison Office (GLO) - DAAD


Trend Mining for Situation Recognition

Project by Dr. Olga Streibel between March 2014 and August 2015.


Trend mining is the extraction of implicit, previously unknown and potentially useful information from time-ordered texts or data. Basically, a trend template as a knowledge-based approach for trend mining assumes that mining trends with knowledge will help us in understanding a trend. In general, trend mining techniques can be used for capturing a trend in order to support users in providing previously unknown information and knowledge about the general or specific development in users’ field of interests in a given time frame. The dimensions of time and knowledge are important for the analysis of many kinds of data with a temporal aspect (and whenever a trend in the data progresses over time is relevant). Developing more research on trend mining could bring more interesting insights into the possibilities and novel solutions that trend mining methods bring for different use cases. One of the possible use cases in which a trend mining approach can be applied is the FM-radio or WiFi signal based situation recognition.

The goal of the Trend Mining for Situation Recognition project is to create intelligent, context-aware methods for situation recognition. In particular, we are focusing on sensor-free technology that aims in assisting elderly people in their comfortable living, despite the handicaps that one experiences being elderly. Hereby the trend mining is being applied into the context of wireless networks.

More information is available on my web site.