Customer Experience Data Strategy

Machine learning for safer independent living in old age

Zühlke is supporting Siima Solution GmbH (created from an innovation project by ewb) in developing a solution that detects patterns in the energy consumption data of elderly people in their homes and automatically alerts relatives if it detects any irregularities.

two elderly people looking at a laptop while cooking and eating

  • Comprehensive support provided by an interdisciplinary team from Zühlke

  • Development of a customised machine learning algorithm

  • Machine learning solution developed and put into operation in just three months

Safety in independent living in old age

Based on energy consumption data, Siima Solution GmbH wants to develop a system that allows elderly people to live independently in their own homes, and offers safety in the event of an emergency. The Siima application is intended to work in the background without any involvement of residents, automatically detect emergencies and notify relatives or an emergency call centre when necessary.

Dominik Hanisch, CEO and Co-Founder Siima Solutions GmbH
' Thanks to Zühlke, not only did we manage to develop a marketable and reliable assistance system, but we also laid the foundation for our start-up. '
Dominik Hanisch
CEO and Co-Founder, Siima Solution GmbH

Interdisciplinary team

Zühlke is supporting Siima along the entire innovation process: Starting with the initial vision, through the stages of develop-ing and evaluating a suitable machine learning algorithm, right up to the technical implementation of the final application. With an interdisciplinary team consisting of data scientists, data engineers, software developers and UX designers, a custom-ised solution is being created based on agile methodology and in close cooperation with the customer. The developed algo-rithm automatically detects time frames with recurring patterns of behaviour and determines suitable threshold values for these patterns. During operation, these threshold values must be exceeded in the respective time frames to indicate that an expected pattern of behaviour has occurred. Otherwise, an alarm will be triggered.

Example of energy consumption thresholds Example of energy consumption thresholds

Short time to market and scalability

The partnership with Zühlke allows the application to be developed on a cooperative and iterative basis, while also being continuously adapted to the needs and requirements of Siima. And so after a short amount of time, the result is a marketable prototype that will gradually evolve into an automated, scalable and productive application.

Philipp Morf
Contact person for Switzerland

Philipp Morf

Head AI & Data Practice

Dr. Philipp Morf holds a doctorate in engineering from the Swiss Federal Institute of Technology (ETH) and holds the position head of the Artificial Intelligence (AI) and Machine Learning (ML) Solutions division at Zühlke since 2015. As Director of the AI Solutions Centre, he designs effective AI/ML applications and is a sought-after speaker on AI topics in the area of applications and application trends. With his many years of experience as a consultant in innovation management, he bridges the gap between business, technology and the people who use AI.

Thank you for your message.