Projects

Peer assessment is a popular approach for grading assignments that cannot be simplified to multiple choice questions in Massive Open Online Courses (MOOCs).
Food plays a huge role in shaping our identity. We engage in food practices daily, and through these engagements, we associate meaning with these specific acts. Our research explored this theme by deconstructing cultural identity through food narratives. How can we use narrative to make sense of and frame our identities around food within cultures and across different cultures? From this research, we gathered multiple stories around a single fruit - the persimmon.
Augmented reality (AR) has long been explored as a tool for education, from textbooks that come to life, to plant identification training via the augmentation of actual flora, and a tangible molecular modeling tool. The power of AR (overlaying virtual content on the physical world) is that it can be used to show the "unseen" and the "hidden" information in the world.
During our research, we found out that only one-third of people finish their physical therapy due to reasons such as money and commute issues. Our team will be creating an accessible and affordable way to help people with chronic pain by exploring a physiotherapy intervention that users could access within the comfort of their homes. Our solution will engage people in a fun and innovative way. The aim is to also motivate users to continue their exercises, even after they feel better.
Pipping aims to explore how players interact with physical objects while in Virtual Reality. The experience has been created for the HTC Vive utilizing the Vive Trackers to aid in the tracking of physical objects. In the experience, a player must return a fallen egg to its nest to begin hatching. The player then takes on a caretaker role building a bond while interacting with a variety of digital and physical objects.
A tool used for the subversion of algorithmic analysis and surveillance by central network authorities like Facebook and Google.
Professional esports athletes compete under tremendous pressure that has significant impacts on their physical, cognitive, emotional, and mental health. However, little is known for how to support this specific kind of demographic, which trends young and where its players often find themselves far from home working in a language they might not be comfortable with. Students in this team study how mobile health tools can mitigate these impacts and empower users through a co-design process with players and the staff that support them.
People often rank and order data items as a vital part of making decisions. Multi-attribute ranking systems are a common tool used to make such data-driven decisions. These systems are often table-based tools that can produce rankings based on numerical weights that a user assigns to each attribute, where the weight represents how important the user believes an attribute is to their decision. These systems assume that users are able to quantify their conceptual understanding of how important particular attributes are; however, this is not always the case.
CopyCat and PopSign are two games that help deaf children and their parents acquire language skills in American Sign Language. 95% of deaf children are born to hearing parents, and most of those parents never learn enough sign language to teach their children. As short term memory skills are learned from acquiring a language, many deaf children enter school with short term memory of less than 3 items, much less than hearing children of hearing parents or Deaf children of Deaf parents. Our systems address this problem directly.
Crowdfunding sites like Kickstarter‚ where entrepreneurs and artists look to the internet for funding‚ have quickly risen to prominence. However, we know very little about the factors driving the ‚crowd‚Äù to take projects to their funding goal. In this paper we explore the factors which lead to successfully funding a crowdfunding project. We study a corpus of 45K crowdfunded projects, analyzing 9M phrases and 59 other variables commonly present on crowdfunding sites.
Healthcare delivery processes are complex activities that span organizational, spatial, and temporal boundaries. Systemic insights, redesign, and improvements are consequently difficult to achieve. Using existing digital healthcare data, we are developing a data-driven methodology, fusing computational systems modeling, data mining, and interactive visualization, to identify, describe, and visualize healthcare delivery processes. Our system will help providers (e.g. physicians, nurses, etc.) and strategic decision makers (e.g.
Management of supply network risks is a critical competency for today's global enterprises. Current practices and tools, however, have limited capabilities and do not allow for systemic exploration of alternate risk strategies. We develop a computational model of risk diffusion in global supply networks that is grounded in techniques from complex systems, network analysis, and epidemiological risk modeling. We draw on a unique, curated dataset of firms, their supply networks, and financial risk in the global electronics industry.
Computer simulations are effective tools for addressing enterprise transformation in terms of alternative organizational policies, operating procedures, and allocations of resources. We present a multilevel approach to computationally model health delivery enterprises. This approach is illustrated by its application to an employer-based prevention and wellness program. The decision of interest in this application concerns the design of prevention and wellness programs that are self-sustaining and provide a positive return on investment for the overall enterprise.
With the remarkable increase of data, novel tools and metrics are needed for comprehensive and systemic analyses of converging business ecosystems. Knowledge discovery is the computational process of identifying valid, novel, interesting, potentially useful and ultimately understandable patterns in data. The objective of our study is twofold. First, we introduce the emerging domain of "big" business ecosystem data. Second, we describe the success and challenges that we encountered in analyzing this data using state of the art analytics and visualization techniques.

Pages