Clustering is one of the most common data mining tasks, used frequently for data organization and analysis in various application domains. Traditional machine learning approaches to clustering are fully automated and unsupervised where class labels are unknown a priori. In real application domains, however, some "weak" form of side…

Large quantities of redundant clinical data are usually transferred from one clinical document to another, making the review of such documents cognitively burdensome and potentially error-prone. Inadequate designs of electronic health record (EHR) clinical document user interfaces probably contribute to the difficulties clinicians experience while…

While many studies have demonstrated that conversational tutoring systems have a positive effect on learning, the amount of manual effort required to author, design, and tune dialogue behaviors remains a major barrier to widespread deployment and adoption of these systems. Such dialogue systems must not only understand student speech, but must…

The project of ubiquitous computing aims to embed computation into everyday spaces. As a practice that is heavily concerned with space and place, its stance towards mobility is sometimes conflicted--treating mobility by turns as a disruption or as an opportunity--and almost always conceiving of it as free and empowered. Conducted in industrial and…

The development of telerobotic systems has evolved from Single Operator Single Robot (SOSR) systems to Multiple Operator Multiple Robot (MOMR) systems. The relationship between human operators and robots follows the master-slave control architecture and the requests for controlling robot actuation are completely generated by human operators. …

Organizing refers to methods of distributing physical and symbolic tasks among multiple agents in order to achieve goals. My dissertation investigates the dynamics of organizing in hybrid information processing systems that incorporate both humans and computers. To explain the behavior of these hybrid systems, I develop and partially test a theory…

A basic and classical assumption in the machine learning research area is "randomness assumption" (also known as i.i.d assumption), which states that data are assumed to be independent and identically generated by some known or unknown distribution. This assumption, which is the foundation of most existing approaches in the literature, simplifies…

Commenting source code has long been a common practice in software development. This thesis, consisting of three pieces of work, made novel use of the code comments written in natural language to improve software reliability. Our solution combines Natural Language Processing (NLP), Machine Learning, Statistics, and Program Analysis techniques to…

Visions of future computing in residential settings often come with assumptions of seamless, well-functioning, properly configured devices and network connectivity. In the near term, however, processes of setup, maintenance, and troubleshooting are fraught with difficulties; householders regularly report these tasks as confusing, frustrating, and…