AI for the Ambient Assisted Living and personal safety/security at home
Conceptualising the non-energy services for personal safety/security and AAL based on the deployed sensor infrastructure and aggregated data from elderly care house.
What is the challenge that is being addressed?
The fields of ambient assisted living (AAL) and smart living are reaching a crossroads, with advanced technology and methods required to realise the potential of improving the quality of life. As an example, the Advanced Metering Infrastructure (AMI) is being widely rolled out to bring improvements to the energy system in terms of accurate billing, dynamic tariffs, greater efficiency, and better network management. However, with the smart meters (SM) deployed exactly at the intersection of power network and end customers, the benefits of AMI could be extended way beyond these primary objectives. This pilot focuses on the potential of SM to contribute to one of the most important domains to both individuals and the state – i.e. the provision of health and care. SM allow to provide insights into activities within the home in terms of behaviour profiles, signatures extraction, events classification, and anomalies detection. Central to their regular use is the ability to transmit data automatically and hence support the digitisation and personalisation of care providers’ services. The ambition of pilot is to complement the P2P energy trading platform of SONCE with non-energy services for AAL virtual communities.
What is the AI solution the project plans to implement?
The goal of the pilot is to conceptualise the non-energy services for personal safety/security and AAL based on the deployed sensor infrastructure and aggregated data from elderly care house. The electricity fingerprinting methods will be applied to be behaviour modelling of specific devices, individuals and activities. The instantiated analytics platform will ingest data through adapters developed on purpose for a given input data. The data will be modelled by a pre-specified schema, indexed, and queried using a no-SQL query language. The data exploration will be enabled through unsupervised clustering and ranking grouping according to a range of similarity measures. Specifically, the solution is aimed to support care givers by triggering alerts in case of anomalous events as well as provide monitoring of living conditions, habits, and behaviour changes.
Who will help implement this solution?
This pilot is implemented within the framework of the “I-NΕRGΥ: Artificial Intelligence for Next Generation Energy” Project. The I-NERGY Project has received funding from the European Union's Horizon 2020 Research and Innovation programme under grant agreement No. 101016508.
The responsible partner for this Use Case is SONCE (https://sonce.com/).