Description
Module/Solution Overview
The City4Age activity recognition is able to recognise activities from Low Elementary Actions executed by a user. Activities can be defined by geriatricians or health carers using the Expert Activity Models, where concepts like actions, locations, duration and starting time have to be provided. Once Expert Activity Models are defined, the activity recognition module will detect the occurrence of such models in the data produced by a user.
Innovation
The City4Age activity recognition is a hybrid approach, where knowledge-based models and data-driven learning algorithms are combined. Although there are some similar approaches in the literature, the City4Age activity recognition requires less modelling effort, considers idle activities and performs comparably to supervised learning systems.
Business Impact
Organisations that provide services depending on the activities performed by users can easily use the City4Age activity recognition module.
Interoperability
The activity recognition module is written in Python and integrated with the shared repository of City4Age. In order to use it in other apps or systems the Python classes should be integrated manually.
Stakeholders profile
Health and Sports related apps and organisations that need to offer services depending on the activities performed by users.
Competitors
No similar commercial solution is known.
Future availability
Open Source
Contact info
Details
| Categories: | Models and Algorithms |
UDeusto
Universidad de la Iglesia de Deusto
The University of Deusto, recently recognized as an International Excellence Campus, was founded in 1886 and comprises 6 Faculties: Psychology and Education, Human and Social Sciences, Engineering, Law, Business and Economic Sciences and Theology. The Deutotech - MORElab (http://www.morelab.deusto.es/) research group is one of the largest and most successful research groups in the University and belongs to the Internet unit within DeustoTech – Deusto Institute of Technology, affiliated to the Faculty of Engineering of the University of Deusto. The group has a strong background in the application of Artificial Intelligence techniques to middleware for embedded and mobile system in order to foster context-aware reactivity and activity modelling and reaction. In addition, the group is currently focusing its research on the area of Smart Cities by leveraging its expertise on Ubiquitous Computing, Linked Open Data management and recommendation and social data mining (Big Data Analytics) to extract structured data from social networks and thus enable urban apps and services assisting the daily activities of citizens or visitors.
