Links zu weiteren Portalen

Seiteninterne Suche

Knowledge Extraction

CDH

Our research concentrates on behaviour and context information extraction and knowledge mining algorithms, often within a Bayesian framework. Typical examples are pattern spotting, rule mining, and data-expert fusion methods. Algorithms are developed and empirically validated for resource-constrained systems, e.g. exploiting sparse sampling.

Problem A main obstacle to deploy body-worn sensor-based wearable systems in free-living settings is the limited battery life. Runtime of devices such miniature accessories and garment can barely cover the time of a daily activity. A continuous long-term behavioural monitoring system requires energy...

In data mining, the relationship between variables is extracted from the association of events in a record. For example,  consider a shopping receipt as a record of acquired items and each item as an event. Therefore, data mining looks for the association of products that are usually purchased toget...

Swallowing appears more accessible than chewing since it involves the neck (pharyngeal) region, rather than the head. Our early investigations were focused on EMG and strain sensing collars. EMG sensors at submental and hyoid positions showed sufficient signal quality for detection of swallows due t...

As people move through the building, they generate paths seen as activations of different sensors and actuators. Individually, a path can be described a sequence of events; each event corresponds to a significant change in the state or value of a sensor or actuator. As paths repeat and overlap, a...

ACTLab Activities Office buildings take up to a year to be fully commissioned, and usually, only a subset of the installed capacities are deployed. The main goal of the project is to aid in the commissioning and management of smart office building with a high density of pervasive devices. We...