Research‎ > ‎

Mobile and Ubiquitous Computing and Systems

Projects:

1. Locus: An indoor localization, tracking and navigation system for multi-story buildings


Abstract:

The holy grail in indoor location technology is to achieve the milestone of combining minimal cost with accuracy, for general consumer applications. A low-cost system should be inexpensive both to install and maintain, requiring only available consumer hardware to operate and its accuracy should be room-level or better. To achieve this, current systems require either extensive calibration or expensive hardware. Moreover, very few systems built so far have addressed localization in multi-story buildings. We explain a heuristics based indoor localization, tracking and navigation system for multi-story buildings called Locus that determines  floor and location by using the locations of infrastructure points, and without the need for radio maps or calibration. It is an inexpensive solution with minimum setup and maintenance expenses. Initial experimental results in an indoor space spanning 175,000 square feet, show that it can determine the  floor with 99.97% accuracy and the location with an average location error of 7m.

Related publications:

a. Preeti Bhargava, Shivsubramani Krishnamoorthy, Aditya Karkada Nakshathri, Matthew Mah, Ashok Agrawala, Locus: An indoor localization, tracking and navigation system for multi-story buildings using heuristics derived from Wi-Fi signal strength, Proceedings of the 9th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2012) [PDF]
b. Preeti Bhargava, Shivsubramani Krishnamoorthy, Anilesh Shrivastava, Aditya Karkada Nakshathri,  Matthew Mah, Ashok Agrawala, Locus: Robust and Calibration-free Indoor Localization, Tracking and Navigation for Multi-story Buildings, Journal of Location based Services, 2015 [PDF]

2. Rover II - An intelligent context-aware middleware

Abstract:

The importance of information for the appropriate handling of any situation is well recognized. We, as human beings, use context not only to interpret available information but also to seek additional relevant, missing information. Most information systems to support human decision-making inadequately process context, and when some context is considered, the structure is often so rigid that, but for very restricted applications, such systems are not usable. In order to integrate context handling capabilities with an information system, we need a framework for representing context that can e.efficiently acquire, maintain,
and integrate contextual information and make it available to applications on demand. In this paper we present such a framework and describe design of Rover II, a situation handling platform which supports integration of context-aware applications. The system manages context based on four primitives - entities, relationships, events, and activities by constructing a situation graph which dynamically reflects the relevant situation information. To illustrate the use of Rover II, we present the M-Urgency system, a public safety application providing audio and video support for emergency help. This system is being deployed for the University of Maryland campus community of 44,000 students, faculty and sta.ff.

Related publications:

a. Preeti Bhargava, Shivsubramani KrishnamoorthyAshok Agrawala, An ontological context model for representing a situation and the design of an intelligent context-aware middleware, Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp 2012) [PDF]

b. Preeti Bhargava, Shivsubramani KrishnamoorthyAshok Agrawala, RoCoMO: A generic ontology for context  modeling, representation and reasoning, Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp 2012) [PDF]

c. Shivsubramani KrishnamoorthyPreeti Bhargava, Matthew Mah, Ashok Agrawala, Representing and Managing the Context of a SituationThe Computer Journal, 2012 [PDF]

3. TellMe – Bootstrapped Discovery and Ranking of Relevant Services and Information in Context-aware Systems


Abstract:

A context-aware system uses context to provide relevant information and services to the user, where relevancy depends on the user's situation. This relevant information could include a wide range of heterogeneous content. Many existing context-aware systems determine this information based on pre-defined ontologies or rules. In addition, they rely on users' context history to filter it. Moreover, they often provide domain-specific information. Such systems are not applicable to a large and varied set of user situations and information needs, and may suffer from cold start for new users. In this paper, we address these limitations and propose a novel, general and flexible approach for bootstrapped discovery and ranking of heterogeneous relevant services and information in context-aware systems. We design and implement four variations of a base algorithm that ranks candidate relevant services, and the information to be retrieved from them, based on the semantic relatedness between the information provided by the services and the user's situation description. We  conduct a live deployment with 14 subjects to evaluate the efficacy of our algorithms. We demonstrate that they have strong positive correlation with human supplied relevance rankings and can be used as an effective means to discover and rank relevant services and information. We also show that our approach is applicable to a wide set of users' situations and to new users without requiring any user interaction history.

Related publications:

a. Preeti Bhargava, James Lampton, Ashok Agrawala, Bootstrapped Discovery and Ranking of Relevant Services and Information in Context-aware Systems, Proceedings of the 12th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2015) [PDF]

4. Enabling Proactivity in Context-aware Middleware Systems by means of a Planning Framework based on HTN Planning


Abstract:

Today’s context-aware systems tend to be reactive or ‘pull’ based - the user requests or queries for some information and the system responds with the requested information. However, none of the systems anticipate the user’s intent and behavior, or take into account his current events and activities to pro-actively ‘push’ relevant information
to the user. On the other hand, Proactive context-aware systems can predict and anticipate user intent and behavior, and act proactively on the users’ behalf without explicit requests from them. Two fundamental capabilities of such systems are: prediction and autonomy. In this paper, we address the second capability required by a context-aware system to act proactively i.e. acting autonomously without an explicit user request. To address it, we present a new paradigm for enabling proactivity in context-aware middleware systems by means of a Planning Framework based on HTN planning. We present the design of a Planning Framework within the infrastructure of our intelligent context-aware middleware called Rover II. We also implement this framework and evaluate its utility with several use cases. We also highlight the benefits of using such a framework in dynamic ubiquitous systems.

Related publications:

a. Preeti Bhargava, Ashok Agrawala, Enabling Proactivity in Context-aware Middleware Systems
by means of a Planning Framework based on HTN Planning, Adjunct Proceedings of the 12th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2015) [PDF]


Ċ
IWWISS.pdf
(539k)
Preeti Bhargava,
Jul 27, 2015, 6:25 PM
Ċ
Preeti Bhargava,
Jul 27, 2015, 6:25 PM