Egocentric Interaction Research Articles

A Framework for the Analysis of Personal Learning Networks

This paper reports on research undertaken to map and analyse Personal Learning Networks (PLNs). PLNs are the total preferred connections to the different people, technological devices, services, and information resources an individual uses for learning activities and learning goals in all learning contexts. Drawing from Education, Web Science, Digital Sociology and Network Science, a Framework was developed which conceptualises PLNs as egocentric interaction networks involving a mode, purpose and endpoint. The Framework introduces the idea of measuring the frequency of interaction along paths consisting of pre-determined, generalised nodes (and node sets). This eliminate network differences at the micro level and allows meaningful comparison and aggregation of individual PLNs into groups or whole samples. Quantitative survey data was collected as part of a FutureLearn MOOC and in real-time converted by a bespoke mapping and visualisation tool into an online PLN map. Analysis indicates that regardless of any contextual factors, individuals interact nearly three quarters of the time via digital devices, and just a quarter of the time face-to-face or non-digitally. One third of those interactions are with smartphones, most often for the purpose of gathering information from web searches. Individuals also interact more frequently with non-humans than they do with humans. Chi-square significance testing to examine the effect of a range of external shaping factors found that the PLNs of apparently diverse groups display a considerable homogeneity. Gender, country of residence and position on the Digital Resident-Digital Visitor spectrum have no effect on the size and use of a PLN. Age and being a UK HE student have the most effect. There may also be evidence of a Network Lifecycle, with a critical period of PLN growth occurring during the age of 18-25. This means that universities are ideally placed, indeed may even have a duty of care, to foster PLN development in educationally and personally productive ways. If HE institutions are to respond to the networked student, living, working and learning in a network age, then no longer can the learner be considered separately from the network of people, devices, services and information resources they use for daily life. Transitioning towards a PLN-centred, networked learning HE pedagogy and learning design may arguably be the most suitable response to a study body which is increasingly and inextricably embedded in a sociotechnical reality.

Coarse-to-fine online learning for hand segmentation in egocentric video

Hand segmentation is one of the most fundamental and crucial steps for egocentric human-computer interaction. The special egocentric view brings new challenges to hand segmentation tasks, such as the unpredictable environmental conditions. The performance of traditional hand segmentation methods depend on abundant manually labeled training data. However, these approaches do not appropriately capture the whole properties of egocentric human-computer interaction for neglecting the user-specific context. It is only necessary to build a personalized hand model of the active user. Based on this observation, we propose an online-learning hand segmentation approach without using manually labeled data for training. Our approach consists of top-down classifications and bottom-up optimizations. More specifically, we divide the segmentation task into three parts, a frame-level hand detection which detects the presence of the interactive hand using motion saliency and initializes hand masks for online learning, a superpixel-level hand classification which coarsely segments hand regions from which stable samples are selected for next level, and a pixel-level hand classification which produces a fine-grained hand segmentation. Based on the pixel-level classification result, we update the hand appearance model and optimize the upper layer classifier and detector. This online-learning strategy makes our approach robust to varying illumination conditions and hand appearances. Experimental results demonstrate the robustness of our approach.

A Wrist-Worn Thermohaptic Device for Graceful Interruption

Thermal haptics is a potential system output modality for wearable devices that promises to function at the periphery of human attention. When adequately combined with existing attention-governing mechanisms of the human mind, it could be used for interrupting the human agent at a time when the negative influence on the ongoing activity is minimal. In this article we present our self-mitigated interruption concept (essentially a symbiosis of artificial external stimuli tuned to existing human attention management mechanisms) and perform a pilot study laying the ground for using a wrist-worn thermohaptic actuator for self-mitigating interruption. We then develope a prototype and perform an insightful pilot study. We frame our empirical thermohaptic experimental work in terms of Peripheral Interaction concepts and show how this new approach to Human-Computer Interaction relates to the Context-Aware-systems-inspired approach “Egocentric Interaction” aimed at supporting the design of envisioned Wearable Personal Assistants intended to, among other things, help human perception and cognition with the management of interruptions.

Egocentric interaction as a tool for designing ambient ecologies—The case of the easy ADL ecology

The visions of ambient intelligence demand novel interaction paradigms that enable designers and system developers to frame and manage the dynamic and complex interaction between humans and environments populated with physical (real) and virtual (digital) objects of interest. So far, many proposed approaches have adhered to a device-centric stance when including virtual objects into the ambient ecology; a stance inherited from existing interaction paradigms for mobile and stationary interactive devices. In this article, we introduce egocentric interaction as an alternative approach, taking the human agent’s body and mind as the center of reference. We show how this interaction paradigm has influenced both the conception and implementation of the easy ADL ecology, comprising of smart objects, a personal activity-centric middleware attempting to simplify interaction given available resources, ambient intelligence applications aimed at everyday activity support, and a human agent literally in the middle of it all.

The Fairness of Decision Rules

Prior work on resource allocation has generally considered only a small number of allocation rules, usually reflecting equity or equality. We use a scenario study to examine the effect of eight different allocation rules (past performance, future performance, rank, random draw, chance meetings, business need, personal need, and political reasons) on recipient reactions to the gain or loss of three different kinds of resources in an organizational setting. We find evidence that allocations based on past performance and random draw rules lead to the highest fairness perceptions and the lowest expectations that the decisions made will lead to intragroup conflict. However, fairness judgments are also influenced by a variety of other factors, such as the type of resource being allocated and whether the recipient is advantaged or disadvantaged relative to others in the workgroup (what we term the “egocentric interaction”). We discuss how our results might influence managers’ allocation decisions.