Keywords
Decision-theoretic optimization is becoming a popular tool in the user interface community, but creating accurate cost (or utility) functions has become a bottleneck --- in most cases the numerous parameters of these functions are chosen manually, which is a tedious and error-prone process. This paper describes ARNAULD, a general interactive tool for eliciting user preferences concerning concrete outcomes and using this feedback to automatically learn a factored cost function. We empirically evaluate our machine learning algorithm and two automatic query generation approaches and report on an informal user study.
Creating high-quality label layouts in a particular visual style is a time-consuming process. Although automated labeling algorithms can aid the layout process, expert design knowledge is required to tune these algorithms so that they produce layouts which meet the designer's expectations. We propose a system which can learn a labellayout style from a single example layout and then apply this style to new labeling problems. Because designers find it much easier to create example layouts than tune algorithmic parameters, our system provides a more natural workflow for graphic designers. We demonstrate that our system is capable of learning a variety of label layout styles from examples.
Cameras are a useful source of input for many interactive applications, but computer vision programming is difficult and requires specialized knowledge that is out of reach for many HCI practitioners. In an effort to learn what makes a useful computer vision design tool, we created Eyepatch, a tool for designing camera-based interactions, and evaluated the Eyepatch prototype through deployment to students in an HCI course. This paper describes the lessons we learned about making computer vision more accessible, while retaining enough power and flexibility to be useful in a wide variety of interaction scenarios.
In this paper, we present a methodology for recognizing seatedpostures using data from pressure sensors installed on a chair.Information about seated postures could be used to help avoidadverse effects of sitting for long periods of time or to predictseated activities for a human-computer interface. Our system designdisplays accurate near-real-time classification performance on datafrom subjects on which the posture recognition system was nottrained by using a set of carefully designed, subject-invariantsignal features. By using a near-optimal sensor placement strategy,we keep the number of required sensors low thereby reducing costand computational complexity. We evaluated the performance of ourtechnology using a series of empirical methods including (1)cross-validation (classification accuracy of 87% for ten posturesusing data from 31 sensors), and (2) a physical deployment of oursystem (78% classification accuracy using data from 19sensors).
When users handle large amounts of data, errors are hard to notice. Outlier finding is a new way to reduce errors by directing the user's attention to inconsistent data which may indicate errors. We have implemented an outlier finder for text, which can detect both unusual matches and unusual mismatches to a text pattern. When integrated into the user interface of a PBD text editor and tested in a user study, outlier finding substantially reduced errors.
