Dr Sebastian Stein

Sebastian left the BESiDE team in October 2016 to join the School of Computing at the University of Glasgow.


My background is in activity recognition, sensor fusion, computer vision and machine learning. For my PhD, I investigated methods for recognizing manipulation activities, which involve complex interactions between hands, tools and other objects, combining information from accelerometers and video. My goal is to take methods for activity recognition and machine learning out of the academic sandpit and apply them to real problems of socially and technologically excluded people. In order to reach this goal, I believe that it is absolutely necessary to assess needs and design solutions in a user-centric approach. Within the BESiDE project, I am interested in developing methods for automatic physical activity assessment and indoor tracking from body-worn sensors, providing the link between medical researchers and cloud computing experts.

Skills: Activity Recognition, Sensor Fusion, Machine Learning

sstein's picture
Contact Details
  • BESiDE Method for Sensor-Based Analysis of Building Use in Care Homes


    The BESiDE team have developed a system for capturing quantitative data about how older adults utilise the indoor spaces in residential care homes. The system uses sensors and smart devices to collect data about residents’ movement and activities, and was successfully used in multiple studies in a number of homes.

  • CENSIS 3rd Technology Summit and Conference
    SENSING IN THE CONNECTED WORLD - Sensor-based analysis of building use in elderly residential care

    Professional/Trade Conference

    CENSIS, the Innovation Centre for Sensor and Imaging Systems was described as a game changer for Scotland when it launched in April 2013. It is a catalyst to an already rapidly growing technology market and there are endless opportunities within this emerging global market to develop fundamental changes to benefit society and commercialise sensor lead products over wide market areas.

  • Baseline Measure of Physical Activity among Care-Home Residents Captured

    19 Residents from 8 Care Homes wore the GENEActiv accelerometer (a wrist-worn watch like device) for periods of up to 7 days in the daytime. Together they provided valuable information on their levels of physical activity over 124 days, giving 1300 hours of recorded data.

  • SICSA Community Challenge
    Scoping the challenges - large-scale activity data collection from care home environments

    A Workshop

    As part of the , we ran a workshop at the University of Dundee on the 27th May. This one-day workshop was for the community to meet and explore the main challenges, requirements and best practices regarding large-scale activity data collection from care home environments, and to identify relevant questions such a dataset could and should answer.


    10:00 – 10:30 Registration

  • SiDE User Pool
    Celebration of Contributions to Research

    An Open day

    Around 90 older adults from across Scotland visited the School of Computing at the University of Dundee for a special event to celebrate their work helping researchers to develop more inclusive technologies.

    The Social Inclusion through the Digital Economy (SiDE) User Pool, based in Dundee and including members across Scotland supported 30 academics to complete 50 research activities over the last five years. The User Pool is comprised of individuals who volunteered to help research into the digital exclusion of older adults and people with disabilities. 

  • SICSA HCI All Hands Meeting

    A Scientific Meeting (conference, seminar etc.)

    BESiDE researchers Dr Sebastian Stein and Dr Kyle Montague helped identify common research challenges faced by Human-Computer Interaction (HCI)  research projects across Scotland and brainstormed ideas for potential solutions at the on January 19th at the University of Strathclyde in Glasgow.

  • SiDE Showcase
    Introducing BESiDE and our early findings on activity analysis of care home residents

    An Open day

    BESiDE was represented with a demo and information booth at the SiDE Showcase on the 15th of January in the Banqueting Hall of the Newcastle Civics Centre. Sebastian Stein introduced the project to members of the user pool, industry representatives and fellow academics, and received very encouraging feedback. He also presented our latest findings on activity analysis of care home residents.

  • Platform for data analysis within BESiDE

    Within BESiDE, researchers are using a workflow based approach to analyse the data collected from the sensing devices deployed in the care homes. Accelerometers are being used to measure the physical activity of individual participants within multiple care homes. The participants from the care homes are provided with accelerometers and data is being collected from registered participants across various care homes.

  • Automated Activity Recognition.

    One of the goals of the BESiDE project is to identify enabling and disabling elements of the built environment. In order to understand, for example, how the built environment impacts on residents' physical activity we need methods and tools to analyze resident movement and behavior in the context of the building they live in.

  • SICSA Meetings
    Talk at the SICSA Sensors Meeting

    A Talk

    Mr Sebastian Stein gave a talk at the first SICSA Sensors meeting in a session on user-centric applications for sensors. His talk was on "Multi-modal Recognition of Food Preparation Activities".