Browsing by Author "Marsland S"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Exploring The Responsibilities Of Single-Inhabitant Smart Homes With Use Cases
    (IOS Press, 2010) Lyons P; Tran CA; Steinhauer HJ; Marsland S; Dietrich J; Guesgen HW
    This paper makes a number of contributions to the field of requirements analysis for Smart Homes. It introduces Use Cases as a tool for exploring the responsibilities of Smart Homes and it proposes a modification of the conventional Use Case structure to suit the particular requirements of Smart Homes. It presents a taxonomy of Smart-Home-related Use Cases with seven categories. It draws on those Use Cases as raw material for developing questions and conclusions about the design of Smart Homes for single elderly inhabitants, and it introduces the SHMUC repository, a web-based repository of Use Cases related to Smart Homes that anyone can exploit and to which anyone may contribute.
  • Thumbnail Image
    Item
    Incremental Learning of Human Activities in Smart Homes
    (MDPI (Basel, Switzerland), 2022-11-03) Chua S-L; Foo LK; Guesgen HW; Marsland S; Mobilio M; Micucci D
    Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.