There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

In this work, algorithms are developed and evaluated to de- tect physical activities from data acquired using five small biaxial ac- celerometers worn simultaneously on different parts of the body. Ac- celeration data was collected from 20 subjects without researcher su- pervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. De- cision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers - thigh and wrist - the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves.

/pdf/activity-recognition-from-user-annotated-acceleration-data-lh3b5ajkau.pdf

Activity recognition from user-annotated acceleration data

How we Think

The theory of affordances

Cultivating Communities of Practice: A Guide to Managing Knowledge

Analysis of socio-technical challenges and opportunities around contemporary mobilities suggests new interpretations and visions for intelligent transport systems. Multiple forms of intelligence are required (but not easily compatible), transport is too narrow a term, and innovation results in new socio-technical systems. An exploration of cumulative, collective and collaborative aspects of mobility systems, allows us to sketch challenges and opportunities in relation to practices of collaboration, communication and coordination, literacies for creativity, comfort and control, citizenship and (lack of) a sense of crisis, concluding with a discussion of methodological implications.

/pdf/intelligent-mobility-systems-some-socio-technical-challenges-1s8g8h1izj.pdf

Intelligent Mobility Systems: Some Socio-technical Challenges and Opportunities

Eye tracking is compelling for hands-free interaction with pervasive displays. However, most existing eye tracking systems require specialised hardware and explicit calibrations of equipment and individual users, which inhibit their widespread adoption. In this work, we present a light-weight and calibration-free gaze estimation method that leverages only an off-the-shelf camera to track users' gaze horizontally. We introduce pupil-canthi-ratio (PCR), a novel measure for estimating gaze directions. By using the displacement vector between the inner eye corner and the pupil centre of an eye, PCR is calculated as the ratio of the displacement vectors from both eyes. We establish a mapping between PCR to gaze direction by Gaussian process regression, which inherently infers averted horizontal gaze directions of users. We present a study to identify the characteristics of PCR. The results show that PCR achieved an average accuracy of 3.9 degrees across different people. Finally, we show examples of real-time applications of PCR that allow users to interact with a display by moving only their eyes.

Pupil-canthi-ratio: a calibration-free method for tracking horizontal gaze direction

It can be argued that pervasive access to information and services becomes more valuable when they are related and adapted to the real world situations of their use. We discuss sensor-based approaches to awareness of such situations based on experience from two projects, one investigating context-awareness as add-on technology for mobile devices, and the other exploring the use of everyday things as context suppliers.

/pdf/sensor-based-context-awareness-for-situated-computing-1dknrm7ady.pdf

Sensor-Based Context-Awareness for Situated Computing

Bimanual pen and touch UIs are mainly based on the direct manipulation paradigm. Alternatively we propose partially-indirect bimanual input, where direct pen input is used with the dominant hand, and indirect-touch input with the non-dominant hand. As direct and indirect inputs do not overlap, users can interact in the same space without interference. We investigate two indirect-touch techniques combined with direct pen input: the first redirects touches to the user's gaze position, and the second redirects touches to the pen position. In this paper, we present an empirical user study where we compare both partially-indirect techniques to direct pen and touch input in bimanual pan, zoom, and ink tasks. Our experimental results show that users are comparatively fast with the indirect techniques, but more accurate as users can dynamically change the zoom-target during indirect zoom gestures. Further our studies reveal that direct and indirect zoom gestures have distinct characteristics regarding spatial use, gestural use, and bimanual parallelism.

/pdf/partially-indirect-bimanual-input-with-gaze-pen-and-touch-2humlz3gwv.pdf

Partially-indirect Bimanual Input with Gaze, Pen, and Touch for Pan, Zoom, and Ink Interaction

What new challenges does the combination of games and eye-tracking present? The EyePlay workshop brings together researchers and industry specialists from the fields of eye-tracking and games to address this question. Eye-tracking been investigated extensively in a variety of domains in human-computer Interaction, but little attention has been given to its application for gaming. As eye-tracking technology is now an affordable commodity, its appeal as a sensing technology for games is set to become the driving force for novel methods of player-computer interaction and games evaluation. This workshop presents a forum for eye-based gaming research, with a focus on identifying the opportunities that eye-tracking brings to games design and research, on plotting the landscape of the work in this area, and on formalising a research agenda for EyePlay as a field. Possible topics are, but not limited to, novel interaction techniques and game mechanics, usability and evaluation, accessibility, learning, and serious games contexts.

/pdf/eyeplay-applications-for-gaze-in-games-3xdkwrc6yh.pdf

Hans Gellersen

Papers

Intelligent Mobility Systems: Some Socio-technical Challenges and Opportunities

Pupil-canthi-ratio: a calibration-free method for tracking horizontal gaze direction

Sensor-Based Context-Awareness for Situated Computing

Partially-indirect Bimanual Input with Gaze, Pen, and Touch for Pan, Zoom, and Ink Interaction

EyePlay: applications for gaze in games