LiLoLe—A Framework for Lifelong Learning from Sensor Data Streams for Predictive User Modelling

Abstract

Abstract. Adaptation in context-aware ubiquitous environments and adaptive systems is becoming more and more complex. Adaptations need to take into account information from a plethora of heterogeneous sensors, while the adaptation decisions often imply personalised aspects and individual preferences, which are likely to change over time. We present a novel concept for lifelong learning from sensor data streams for predictive user modelling that is applicable in scenarios where simpler mechanisms that rely on pre-trained general models fall short. With the LILOLE-Framework, we pursue an approach that allows ubiquitous systems to continuously learn from their users and adapt the system at the same time through stream-based active learning. This Framework can guide the development of context-aware or adaptive systems in form of an overall architecture.

Textual evaluation vs. User testing: a comparative analysis

“…The textual evaluation method is: (a) frequently applied [Fetter and Gross 2014, Hedegaard and Simonsen 2013, Mendes 2015, da Silva et al 2017, Freitas et al 2016; (b) covers many user texts; and (c) considers spontaneous reports. Some studies have suggested that this method may: (a) require a lot of time or effort [Freitas et al 2016, da Silva et al 2017 if no methods are used to analyze the texts automatically; (b) does not precisely describe the use problems because it is limited to what has been reported by users about the system [Hedegaard and Simonsen 2013]; and, (c) may have influence of very satisfied or very dissatisfied users (who are more prone to express themselves) [Hedegaard and Simonsen 2014].…”