Towards Proactive Context-aware Computing and Systems

A primary goal of context-aware systems is delivering the right information at the right place and right time to users in order to enable them to make effective decisions and improve their quality of life. There are three key requirements for achieving this goal: determining what information is relevant, personalizing it based on the users’ context (location, preferences, behavioral history etc.), and delivering it to them in a timely manner without an explicit request from them. These requirements create a paradigm that we term as “Proactive Context-aware Computing”. Most of the existing context-aware systems fulfill only a subset of these requirements. Many of these systems focus only on personalization of the requested information based on users’ current context. Moreover, they are often designed for specific domains. In addition, most of the existing systems are reactive - the users request for some information and the system delivers it to them. These systems are not proactive i.e. they cannot anticipate users’ intent and behavior and act proactively without an explicit request from them. In order to overcome these limitations, we need to conduct a deeper analysis and enhance our understanding of context-aware systems that are generic, universal, proactive and applicable to a wide variety of domains. To support this dissertation, we explore several directions. Clearly the most significant sources of information about users today are smartphones. A large amount of users’ context can be acquired through them and they can be used as an effective means to deliver information to users. In addition, social media such as Facebook, Flickr and Foursquare provide a rich and powerful platform to mine users’ interests, preferences and behavioral history. We employ the ubiquity of smartphones and the wealth of information available from social media to address the challenge of building proactive context-aware systems. We have implemented and evaluated a few approaches, including some as part of the Rover framework, to achieve the paradigm of Proactive Context-aware Computing. Rover is a context-aware research platform which has been evolving for the last 6 years. Since location is one of the most important context for users, we have developed ‘Locus’, an indoor localization, tracking and navigation system for multi-story buildings. Other important dimensions of users’ context include the activities that they are engaged in. To this end, we have developed ‘SenseMe’, a system that leverages the smartphone and its multiple sensors in order to perform multidimensional context and activity recognition for users. As part of the ‘SenseMe’ project, we also conducted an exploratory study of privacy, trust, risks and other concerns of users with smart phone based personal sensing systems and applications. To determine what information would be relevant to users’ situations, we have developed ‘TellMe’ - a system that employs a new, flexible and scalable approach based on Natural Language Processing techniques to perform bootstrapped discovery and ranking of relevant information in context-aware systems. In order to personalize the relevant information, we have also developed an algorithm and system for mining a broad range of users’ preferences from their social network profiles and activities. For recommending new information to the users based on their past behavior and context history (such as visited locations, activities and time), we have developed a recommender system and approach for performing multi-dimensional collaborative recommendations using tensor factorization. For timely delivery of personalized and relevant information, it is essential to anticipate and predict users’ behavior. To this end, we have developed a unified infrastructure, within the Rover framework, and implemented several novel approaches and algorithms that employ various contextual features and state of the art machine learning techniques for building diverse behavioral models of users. Examples of generated models include classifying users’ semantic places and mobility states, predicting their availability for accepting calls on smartphones and inferring their device charging behavior. Finally, to enable proactivity in context-aware systems, we have also developed a planning framework based on HTN planning. Together, these works provide a major push in the direction of proactive context-aware computing.

FOLLOWING THE TRAIL OF THE SNAKE: A LIFE HISTORY OF COBRA MANSA "COBRINHA" MESTRE OF CAPOEIRA

This dissertation is a cultural biography of Mestre Cobra Mansa, a mestre of the Afro-Brazilian martial art of capoeira angola. The intention of this work is to track Mestre Cobrinha's life history and accomplishments from his beginning as an impoverished child in Rio to becoming a mestre of the tradition-its movements, music, history, ritual and philosophy. A highly skilled performer and researcher, he has become a cultural ambassador of the tradition in Brazil and abroad. Following the Trail of the Snake is an interdisciplinary work that integrates the research methods of ethnomusicology (oral history, interview, participant observation, musical and performance analysis and transcription) with a revised life history methodology to uncover the multiple cultures that inform the life of a mestre of capoeira. A reflexive auto-ethnography of the author opens a dialog between the experiences and developmental steps of both research partners' lives. Written in the intersection of ethnomusicology, studies of capoeira, social studies and music education, the academic dissertation format is performed as a roda of capoeira aiming to be respectful of the original context of performance. The result is a provocative ethnographic narrative that includes visual texts from the performative aspects of the tradition (music and movement), aural transcriptions of Mestre Cobra Mansa's storytelling and a myriad of writing techniques to accompany the reader in a multi-dimensional journey of multicultural understanding. The study follows Cinezio Feliciano Pe anha in his childhood struggle for survival as a street performer in Rio de Janeiro. Several key moves provided him with the opportunity to rebuild his life and to grow into a recognized mestre of the capoeira angola martial art as Mestre Cobra Mansa ("Tame Snake" in Portuguese). His dedicated work enabled him to contribute to the revival of the capoeira angola tradition during the 1980's in Bahia. After his move to the United States in the early 1990's, Mestre Cobrinha founded the International Capoeira Angola Foundation, which today has expanded to 28 groups around the world. Mestre Cobra returned home to Brazil to initiate projects that seek to develop a new sense of community from all that he has learned and been able to accomplish in his life through the performance and study of capoeira angola.

The Many Faces of Paul Hindemith

The purpose of this project is to present selected violin pieces by Paul Hindemith (1895-1963) against a backdrop of the diverse styles and traditions that he integrated in his music. For this dissertation project, selected violin sonatas by Hindemith were performed in three recitals alongside pieces by other German and Austro-German composers. These recitals were also recorded for archival purposes. The first recital, performed with pianist David Ballena on December 10, 2005, in Gildenhorn Recital Hall at the University of Maryland, College Park, included Violin Sonata Op.11, No. 1 (1918) by Paul Hindemith, Sonatina in D Major, Op. 137 (1816) by Franz Schubert, and Sonata in E-flat Major, Op.18 (1887) by Richard Strauss. The second recital, performed with pianist David Ballena on May 9, 2006, in Gildenhorn Recital Hall at the University of Maryland, included Sonata in E Minor, KV 304 (1778) by Wolfgang Amadeus Mozart, Sonata in E (1935) by Paul Hindemith, Romance for Violin and Orchestra No.1 in G Major (1800-1802) by Ludwig Van Beethoven, and Sonata for Violin and Piano in A minor, Op. 105 (1851) by Robert Schumann. The third recital, performed with David Ballena and Kai-Ching Chang on November 10, 2006 in Ulrich Recital Hall at the University of Maryland, included Violin Sonata Op.12 No.1 in D Major (1798) by Ludwig Van Beethoven, Sonata for Violin and Harpsichord No.4 in C Minor BWV 1017 (1720) by J.S. Bach, and Violin Sonata Op.11 No.2 (1918) by Paul Hindemith. For each of my dissertation recitals, I picked a piece by Hindemith as the core of the program then picked pieces by other composers that have similar key, similar texture, same number of movements or similar feeling to complete my program. Although his pieces used some classical methods of composition, he added his own distinct style: extension of chromaticism; his prominent use of interval of the fourth; his chromatic alteration of diatonic scale degrees; and his non-traditional cadences. Hindemith left behind a legacy of multi-dimensional, and innovative music capable of expressing both the old and the new aesthetics.