Search

Urban traffic sensing has been investigated extensively by different real-time sensing approaches due to important applications such as navigation and emergency services. Basically, the existing traffic sensing approaches can be classified into two categories, i.e., explicit and implicit sensing. In this paper, we design a measurement framework called EXIMIUS for a large-scale data-driven study to investigate the strengths and weaknesses of these two sensing approaches by using two particular systems for traffic sensing as concrete examples, i.e., a vehicular system as a crowdsourcing-based explicit sensing and a cellular system as an infrastructure-based implicit sensing. In our investigation, we utilize TB-level data from two systems: (i) vehicle GPS data from 3 thousand private cars and 2 thousand commercial vehicles, (ii) cellular signaling data from 3 million cellphone users, from the Chinese city Hefei. Our study adopts a widely-used concept called crowdedness level to rigorously explore the impacts of various spatiotemporal contexts on real-time traffic conditions including population density, region functions, road categories, rush hours, etc. based on a wide range of context data. We quantify the strengths and weaknesses of these two sensing approaches in different scenarios then we explore the possibility of unifying these two sensing approaches for better performance. Our results provide a few valuable insights for urban sensing based on explicit and implicit data from transportation and telecommunication domains.

Mobile devices have become major sources of context-aware data due to their ubiquity and sensing capabilities. However, deploying mobile devices as dynamic, unabridged context data provider either locally or remotely is still challenging due to their limited computing capability. Furthermore, integrating physical sensor data with social context data from online social networks is necessary for rich context data provisioning. In this paper, we present AndroCon, an Android-based context-aware middleware framework that enables mobile devices to acquire, integrate, manage, and provision context data. We have applied AndroCon to manage social and physical context data from various sources and have evaluated its performance in terms of power consumption and CPU utilization.

Monitoring user interaction activities provides the basis for creating a user model that can be used to predict user behaviour and enable user assistant services. The BaranC framework provides components that perform UI monitoring (and collect all associated context data), builds a user model, and supports services that make use of the user model. In this case study, a Next-App prediction service is built to demonstrate the use of the framework and to evaluate the usefulness of such a prediction service. Next-App analyses a user's data, learns patterns, makes a model for a user, and finally predicts based on the user model and current context, what application(s) the user is likely to want to use. The prediction is pro-active and dynamic; it is dynamic both in responding to the current context, and also in that it responds to changes in the user model, as might occur over time as a user's habits change. Initial evaluation of Next-App indicates a high-level of satisfaction with the service.

Undirected advertising generates huge costs for advertisers when they spend large sums on ad spaces that result in being irrelevant to consumers. In recent years Real-time Bidding (RTB) has evolved as a method for selling and buying advertising based on real-time context factors. We propose a real-time bidding platform for Public Display networks that matches publishers and their content with advertisers through an auction mechanism. Thereby we take into account context data sent by the display where the ad is being rendered, such as the number of people in front of the display, their average age, gender and whether they have been spotted before. Based on this information advertisers can dynamically place bids and thus effectively use their marketing budget to reach specific target audiences. Publishers on the other hand are guaranteed to achieve the highest price for their ad space with regards to these context factors. Our platform implements the OpenRTB standard and therefore allows Public Display networks to be integrated into existing ad network economies. We present results from initial system tests for evaluating the scalability and feasibility of our approach.

Ambient (aka pervasive, ubiquitous) media environments offer a plethora of context data as well as opportunities for context-related content production and consumption. They are the perfect environments for providing users with highly contextualized data-driven services and data-driven visual and additive content. To build such ambient media environments, semantics play an essential role to deal with a seamless integration of the context and the digital services to be provided. We aim to bring together communities involved in different semantic applications needed for the creation of ambient media environments.

Health-compromising behaviors are difficult to change since people do not behave in accordance with their intention. This paper aims at studying the extent to which a person's healthy habit forming process can be affected by mobile phone usage. We propose a novel healthy habit forming states predicting framework using mobile phone platform. First we present a definition for the healthy habit forming process consisting of several states. We define the social intervention types and user context data which are extracted from mobile phone sensor data. Then we make use of machine learning methods to study the correlation between these data and healthy habit forming states. Specifically, a predicting model called Habits Factor Graph(HaFG) is proposed to predict the habit forming states. To evaluate our work, an Android based prototype system is implemented. Experimental results show that the healthy habit forming states are predicted possibly from user context information with a fairly good accuracy (around 67%).

In ubiquitous computing systems, heterogeneous applications must be capable of responding to dynamic changes in their environments with minimal human interference and strongly relying on context information. Reasoning is necessary in ubiquitous systems mainly for transforming raw context data into meaningful information and for infering new implicit context information that may be relevant for the applications. Besides that, reasoning is fundamental for triggering actions or adaptations according to specific situations described by rules. These rules typically depend on several context variables, which may originate from different distributed sources. Hence, we propose a strategy for cooperative context reasoning of complex situations involving a reasoner for the user side and a reasoner for the ambient side.

Context datasets are essential not only to design and evaluate context-aware systems but also to help identify important problems. For practical and ethical reasons, collecting real-life context data is not always feasible. In this paper, we investigate the possibility to use context data extracted from screenplays in certain context-aware applications. In the absence of real context data, screenplays are inexpensive, rich and well-structured substitutes. However, narrative art and techniques naturally restrict the range of applications in which they can be used. Some television series have been showing for over ten years. We argue that this substantial source of context data could benefit the community in certain applications. As a case study, we compare a context dataset extracted from a specific screenplay with one of the major publicly available real context datasets collected on mobile phones. Results in social relationship characterization are discussed.

Pervasive computing systems need to be strongly proactive. Context-awareness contributes to this, thus minimizing human-machine interaction. Context-aware systems are greatly enhanced by the utilization of recorded history of the users' situations and interactions. In this paper, an approach is proposed for modelling, storing and exploiting history-of-context, in order to predict or estimate context information. The proposed framework is context-type-independent, requires minimal processing and storage resources, and can be used for data compression. It is based on multiple context prediction rule generation models, demonstrates high prediction success ratio, and has been empirically evaluated via extensive experiments.

This paper reports on how we learned from an alternative practice in order to design engaging interactive technology intended for a more general user group. When investigating new types of digital photography we designed context photography, where real-time context data visually affects digital pictures as they are taken. To understand how to design for a meaningful photographic experience, we took inspiration from an amateur practice involving a particular type of analogue camera --- Lomography. This paper shows how such alternative or marginal practices can help to ground design of interactive technology in existing human interests, while at the same time leading to a novel design outcome.

In everyday life there are low risk situations where resources normally need to be protected and thus access to them controlled, but at the same time the implications of occasional unauthorized access are not severe. In these situations using an authentication technique that is expensive or requires significant effort from the user may not be justified. In this paper, we introduce a question-based authentication scheme appropriate for low risk situations. The scheme utilizes the context data already collected within a smart environment to generate the questions. Despite, the limited capabilities of the smart environment used in this experiment our preliminary study shows that using simple questions based on workplace events it is possible to discriminate between genuine users and impostors.

Context-aware mobile applications and systems have been extensively explored in the last decade and in the last few years we already saw promising products on the market. Most of these applications assume that context data is highly accurate. But in practice this information is often unreliable, especially when gathered from sensors or external sources. Previous research has argued that the system usability can be improved by displaying the uncertainty to the user. The research presented in this paper shows that it is not always an advantage to show the confidence of the context-aware application to the user. We developed a system for automatic form filling on mobile devices which fills in any web form with user data stored on the mobile device. The used algorithm generates rules which indicate with which probability which input field of a form should be filled in with which value. Based on this we developed two versions of our system. One shows the uncertainty of the system and one not. We then conducted a user study which shows that the user needs slightly more time and produces slightly more errors when the confidence of the system is visualized.

Given time and location information about digital photographs we can automatically generate an abundance of related contextual metadata, using off-the-shelf and Web-based data sources. Among these are the local daylight status and weather conditions at the time and place a photo was taken. This metadata has the potential of serving as memory cues and filters when browsing photo collections, especially as these collections grow into the tens of thousands and span dozens of years.We describe the contextual metadata that we automatically assemble for a photograph, given time and location, as well as a browser interface that utilizes that metadata. We then present the results of a user study and a survey that together expose which categories of contextual metadata are most useful for recalling and finding photographs. We identify among still unavailable metadata categories those that are most promising to develop next.