Marcus Ständer

Towards interactionflows for smart products

Nowadays, the interaction between a product and the user is described using different methods than for product to product communication. This makes it difficult to replace users and products mutually to create really dynamical environments, capable of reducing the amount of interactions, if possible. To advance the design of interactive smart environments, we introduce a concept for describing productinitiated interaction with users and demonstrate, how they can be applied in practice. This allows to combine both, automated procedures and interaction with the user, to a new concept called interactionflows.

A Smart Kitchen Infrastructure

In the future our homes will be more and more equipped with sensing and interaction devices that will make new multimedia experiences possible. These experiences will not necessarily be bound to the TV, tabletop, smart phone, tablet or desktop computer but will be embedded in our everyday surroundings. In order to enable new forms of interaction, we equipped an ordinary kitchen with a large variety of sensors according to best practices. An innovation in comparison to related work is our Information Acquisition System that allows monitoring and controlling kitchen appliances remotely. This paper presents our sensing infrastructure and novel interactions in the kitchen that are enabled by the Information Acquisition System.

Bridging the gap between users and smart products

The increasing number of interactive products in our environment leads to an accession of interaction between products and users. Nowadays, this interaction is described with different concepts than the interaction between the products. This makes it difficult to mutually replace users and products to create smart environments that are able to automatically perform tasks for the user, if suitable products are available. To advance the design of interactive smart environments and to bridge this gap, we introduce a concept for describing product-initiated interaction with users.

Prediction of interface preferences with a classifier selection approach

Interaction in smart environments should be adapted to the users’ preferences, e.g., utilising modalities appropriate for the situation. While manual customisation of a single application could be feasible, this approach would require too much user effort in the future, when a user interacts with numerous applications with different interfaces, such as e.g. a smart car, a smart fridge, a smart shopping assistant etc. Supporting user groups, jointly interacting with the same application, poses additional challenges: humans tend to respect the preferences of their friends and family members, and thus the preferred interface settings may depend on all group members. This work proposes to decrease the manual customisation effort by addressing the cold-start adaptation problem, i.e., predicting interface preferences of individuals and groups for new (unseen) combinations of applications, tasks and devices, based on knowledge regarding preferences of other users. For predictions we suggest several reasoning strategies and employ a classifier selection approach for automatically choosing the most appropriate strategy for each interface feature in each new situation. The proposed approach is suitable for cases where long interaction histories are not yet available, and it is not restricted to similar interfaces and application domains, as we demonstrate by experiments on predicting preferences of individuals and groups for three different application prototypes: recipe recommender, cooking assistant and car servicing assistant. The results show that the proposed method handles the cold-start problem in various types of unseen situations fairly well: it achieved an average prediction accuracy of

Adapting Workflows to Intelligent Environments

72 \pm 1\,\%

El método Mundo - Un enfoque ascendente mejorado de ingeniería informática de sistemas ubicuos

72±1%. Further studies on user acceptance of predictions with two different user communities have shown that this is a desirable feature for applications in smart environments, even when predictions are not so accurate and when users do not perceive manual customisation as very time-consuming.