Archives

Probabilistic Input

Leave a comment

Increasingly natural, sensed, and touch-based input is being integrated into devices. Along the way, both custom and more general solutions have been developed for dealing with the uncertainty that is associated with these forms of input. However, it is difficult to provide dynamic, flexible, and continuous feedback about uncertainty using traditional interactive infrastructure. Our contribution is a general architecture with the goal of providing support for continual feedback about uncertainty.

Our architecture tracks multiple interfaces – one for each plausible and differentiable sequence of input that the user may have intended. This paper presents a method for reducing the number of alternative interfaces and fusing possible interfaces into a single interface that both communicates uncertainty and allows for disambiguation.

Rather than tracking a single interface state (as is currently done in most UI toolkits), we keep track of several possible interfaces. Each possible interface represents a state that the interface might be in. The likelihood of each possible interface is updated based on user inputs and our knowledge of user behavior. Feedback to the user is rendered by first reducing the set of possible interfaces to a representative set, then fusing interface alternatives into a single interface, which is then rendered.


Julia Schwarz, Jennifer Mankoff, Scott E. Hudson:
An Architecture for Generating Interactive Feedback in Probabilistic User Interfaces. CHI 2015: 2545-2554

Julia Schwarz, Jennifer Mankoff, Scott E. Hudson:
Monte carlo methods for managing interactive state, action and feedback under uncertainty. UIST 2011: 235-244

Julia Schwarz, Scott E. Hudson, Jennifer Mankoff, Andrew D. Wilson:
A framework for robust and flexible handling of inputs with uncertainty. UIST 2010: 47-56

Christian Koehler

Leave a comment

Christian Koehler is a Principal UX Data Scientist at Oracle Design. He is passionate about the intersection where Artificial Intelligence (AI) and Human Computer Interaction (HCI) meet and interested in how insights derived from users and users’ data can empower the development of AI to build human-centric technology.

He has experience in a number of different areas from Data Science, over Applied Machine learning to Survey design and interview studies. He develops deep learning algorithms and analyzes large scale data to derive descriptive and inferential statistics. He is familiar with both quantitative and qualitative methods and believes the best technology is being build with the user in mind from the ground up.

His thesis was titled “Indoor Location Prediction through Modeling of Human Spatiotemporal Behavior”

He received his PhD from Carnegie Mellon, where he was advised by Jennifer Mankoff and Anind Dey.

www.christiankoehler.org/resume

Sign showing: Sustainability -- Next Exit

Automatically Tracking and Executing Green Actions

Tawanna Dillahunt

Leave a comment

Tawanna Dillahunt is an Associate Professor at the University of Michigan’s School of Information (UMSI) and holds a courtesy appointment with the Electrical Engineering and Computer Science (EECS) department. Before starting as an Assistant Professor, she was a Presidential Postdoctoral Fellow in UMSI from January 2013 – July 2014. She also leads the Social Innovations Group at UMSI and her research interests are in the areas of human-computer interaction, ubiquitous computing, and social computing. She is primarily interested in identifying needs and opportunities to further explore how theories from the social sciences can be used to design technologies that have a positive impact on group and individual behavior. With the narrowing of the digital divide, the ubiquity of smart devices and mobile hotspots in common places in the U.S. (e.g., libraries, community centers, and even McDonald’s) she sees an urgent need to explore the use of these technologies for those that stand the most to gain from these resources. Therefore, she designs, builds, enhances and deploys innovative technologies that solve real-world problems, particularly in underserved communities.

Tawanna holds a M.S. and Ph.D. in Human-Computer Interaction from Carnegie Mellon University, a M.S. in Computer Science from the Oregon Graduate Institute School of Science and Engineering (now a part of the Oregon Health and Science University in Portland, OR), and a B.S. in Computer Engineering from North Carolina State University. She was also a software engineer at Intel Corporation for several years

Sign showing: Sustainability -- Next Exit

Automatically Tracking and Executing Green Actions

Severity of Chronic Lyme Disease

Leave a comment

Johnson, L., Wilcox, S., Mankoff, J., & Stricker, R. B. (2014). Severity of chronic Lyme disease compared to other chronic conditions: a quality of life survey. PeerJ, 2, e322.

The Centers for Disease Control and Prevention (CDC) health-related quality of life (HRQoL) indicators are widely used in the general population to determine the burden of disease, identify health needs, and direct public health policy. These indicators also allow the burden of illness to be compared across different diseases. Although Lyme disease has recently been acknowledged as a major health threat in the USA with more than 300,000 new cases per year, no comprehensive assessment of the health burden of this tickborne disease is available. This study assesses the HRQoL of patients with chronic Lyme disease (CLD) and compares the severity of CLD to other chronic conditions.

fig-2-1x

Sunyoung Kim

Leave a comment

Website

Sunyoung Kim is interested in improving the quality of everyday life through the use of technology. Leveraging mobile and ubiquitous computing technologies, she explores novel technical solutions that empower people to better understand the world around them and make informed choices for quality of life. She is also an affiliate faculty member in the Department of Computer Science.

Sunyoung Kim, an HCI researcher, designs, builds, and evaluates ubiquitous computing technologies that can promote positive changes towards everyday health, wellbeing, and environmental sustainability. Before joining the Rutgers SC&I faculty, she was a postdoctoral fellow at Harvard University’s Center for Research on Computation and Society (CRCS). She was a member of Aware Home Research Initiative and the Ubiquitous Computing Research Group at Georgia Institute of Technology. Previously, she worked as a user interaction designer and project manager in the field of internet media, user interface for mobile device and Ubiquitous Appliance for Apartment Complex.

Here thesis was titled “Democratizing Mobile Technology in Support of Volunteer Activities in Data Collection.”

Replacing ‘Wave to Engage’ with ‘Intent to Interact’

Leave a comment

Schwarz, J., Marais, C., Leyvand, T., Hudson, S., Mankoff, J. Combining Body Pose, Gaze and Motion to Determine Intention to Interact in Vision-Based Interfaces. In Proceedings of the 32nd Annual SIGCHI Conference on Human Factors in Computing Systems (Toronto, Canada, April 26 – May 1, 2014). CHI ’14. ACM, New York, NY.

 paper  | video summary  | slides

Vision-based interfaces, such as those made popular by the
Microsoft Kinect, suffer from the Midas Touch problem:
every user motion can be interpreted as an interaction. In
response, we developed an algorithm that combines facial
features, body pose and motion to approximate a user’s
intention to interact with the system. We show how this can
be used to determine when to pay attention to a user’s actions and when to ignore them. To demonstrate the value of
our approach, we present results from a 30-person lab study
conducted to compare four engagement algorithms in single
and multi-user scenarios. We found that combining intention to interact with a “raise an open hand in front of you”
gesture yielded the best results. The latter approach offers a
12% improvement in accuracy and a 20% reduction in time
to engage over a baseline “wave to engage” gesture currently used on the Xbox 360

Julia Schwarz

Leave a comment

Julia Schwarz builds software that leverages probabilistic modeling, signal processing, and machine learning to improve user interfaces.

She received a BS from University of Washington, and a PhD from Carnegie Mellon University, advised by Jennifer Mankoff and Scott Hudson. Here thesis was titled: “Monte Carlo Methods for Managing Uncertain User Interfaces”

While at Carnegie Mellon she co-founded Qeexo, where she led the team that developed FingerSense, currently shipping on over 300 million Huawei devices.

In 2015 she moved back home to work on the HoloLens team at Microsoft. At Microsoft, she brings instinctual interactions to HoloLens 2, allowing users to directly interact with holograms using their hands.

For more information, please see her résumé and website.

You can find her on GitHub, Twitter, StackOverflow, and LinkedIn.

Probabilistic Input

Replacing ‘Wave to Engage’ with ‘Intent to Interact’

Stepgreen.org

Stepgreen.org

Leave a comment

The goal of the Stepgreen project is to leverage Internet scale technologies to create opportunities for reduced energy consumption. The original vision of the project was to leverage existing online social networks to encourage individual change. Since then the project has broadened to include a number of other ideas. We have explored the impact of demographics on energy use practices; studied the value of empathetic figures such as a polar bear for motivation and explored organizational-level planning. We have also developed mobile technologies that can provide feedback about green actions on the go.

StepGreen.org Website

StepGreen.org Website

Try StepGreen.org out: The Stepgreen.org website provides a mechanism for allowing individuals to report on and track their environmental impact. It includes a visualization that can be displayed on an individual’s social networking web page. Go to Stepgreen.organd see for yourself how we leverage social networks to engage individuals in green behaviors.

Learn about our software products. Stepgreen  is a service that we are hoping to share with non-profits that are encouraging behavior change,  such as an open API you can use to build your own clients for encouraging green behavior. Please contact us at stepgreen@cs.cmu.edu if you are interested in collaborating with us. 

Learn about our research and our publications

Keep in touch with us through our Facebook page  and Twitter account.

Sample Publications

JOURNAL PAPERS & MAGAZINE ARTICLES

  1. J. Mankoff. “HCI and Sustainability: A Tale of Two Motivations,” Interactions.
  2. Dillahunt, T. & Mankoff, J. (2011) In the dark, out in the cold. ACM Crossroads 17(4):39-41
  3. Jennifer Mankoff, Robin Kravets, Eli Blevis, Some Computer Science Issues in Creating a Sustainable World, IEEE Computer 41(8):102-105. (pdf)
    1. Reprinted as: Jennifer Mankoff, Robin Kravets and Eli Blevis, Some Computer Science Issues in Creating a Sustainable World. Posted on November 17th, 2008 in Articles, Climate, OpEd, Technology http://www.earthzine.org/2008/11/17/some-computer-science-issues-in-creating-a-sustainable-world/

CONFERENCE PAPERS

  1. Tawanna Dillahunt, Jennifer Mankoff, Eric Paulos. Understanding Conflict Between Landlords and Tenants: Implications for Energy Sensing and Feedback. Ubicomp ’10.  (full paper)(pdf)
  2. Jennifer Mankoff, Susan R. Fussell, Tawanna Dillahunt, Rachel Glaves, Catherine Grevet, Michael Johnson, Deanna Matthews, H. Scott Matthews, Robert McGuire, Robert Thompson. StepGreen.org: Increasing Energy Saving Behaviors via Social Networks. ICWSM’10.  (full paper) (pdf, video of talk)
  3. C. Grevet, J. Mankoff, S. D. Anderson Design and Evaluation of a Social Visualization aimed at Encouraging Sustainable Behavior. In Proceedings of HICSS 2010.  (full paper) (pdf)
  4. T. Dillahunt, J. Mankoff, E. Paulos, S. Fussell It’s Not All About “Green”: Energy Use in Low-Income Communities. In Proceedings of Ubicomp 2009. (Full paper) (pdf)
  5. J. Froehlich, T. Dillahunt, P. Klasnja, J. Mankoff, S. Consolvo, B. Harrison, J. A. Landay, UbiGreen: Investigating a Mobile Tool for Tracking and Supporting Green Transportation Habits. In Proceedings of CHI 2009. (Full paper) (pdf)
  6. J. Schwartz, J. Mankoff, H. Scott Matthews. Reflections of everyday activity in spending data. In Proceedings of CHI 2009.  (Note). (pdf)
  7. Jennifer Mankoff, Deanna Matthews, Susan R. Fussell and Michael Johnson. Leveraging Social Networks to Motivate Individuals to Reduce their Ecological Footprints. HICSS 2007. (pdf)

OTHER

  1. Rachael Nealer, Christopher Weber, H. Scott Matthews and Chris Hendrickson. Energy and Environmental Impacts of Consumer Purchases: A Case Study on Grocery Purchases. ISSST 2010
  2. Dillahunt, T., Becker, G., Mankoff, J. and Kraut, R. Motivating Environmentally Sustainable Behavior Changes with a Virtual Polar Bear.” Pervasive 2008 workshop on Pervasive Persuasive Technology and Environmental Sustainability. (pdf)
  3. Johnson, M., Fussell, S. Mankoff, J., Matthwes, D., and Setlock, L. “When Users Pledge to Take Green Actions, Are They Solving a Decision Problem?” INFORMS Fall 2008 Conference. (ppt)
  4. Johnson, M., Fussell, S. Mankoff, J. and Matthwes, D. “How Does Problem Representation Influence Decision Performance and Attitudes?” INFORMS Fall 2007 Conference. Abstract
  5.  Johnson, M.P. 2006. “Public Participation and Decision Support Systems: Theory, Requirements, and Applications.” For presentation at Association of Public Policy Analysis and Management Fall Conference, Madison, WI, November 3, 2006. (pdf)

Automatically tracking green actions

Leave a comment

We believe that self-reporting is a limiting factor in the original vision of StepGreen.org, and this component of our research has begun to explore alternatives. For example, we showed that financial data can be used to extract footprint information [1], and in collaboration with researchers at Intel and University of Washington, we used a mobile device to track and visualize green transportation behavior in the Ubigreen project [2].

More details on Ubigreen and a video are available at http://dub.washington.edu/projects/ubigreen and published at CHI 2009 [1]. We are currently in the process of implementing an updated version of Ubigreen which can connect to the Stepgreen.org website and can track more than just transportation behaviors.

[1] J. Schwartz, J. Mankoff, H. Scott Matthews. Reflections of everyday activity in spending data. In Proceedings of CHI 2009.  (Note). (pdf)

[2] J. Froehlich, T. Dillahunt, P. Klasnja, J. Mankoff, S. Consolvo, B. Harrison, J. A. Landay, UbiGreen: Investigating a Mobile Tool for Tracking and Supporting Green Transportation Habits. In Proceedings of CHI 2009. (Full paper) (pdf)

Competing Online Viewpoints and Models of Chronic Illness

Leave a comment

People with chronic health problems use online resources to understand and manage their condition, but many such resources can present competing and confusing viewpoints. We surveyed and interviewed with people experiencing prolonged symptoms after a Lyme disease diagnosis. We explore how competing viewpoints in online content affect participants’ understanding of their disease. Our results illustrate how chronically ill people search for information and support, and work to help others over time. Participant identity and beliefs about their illness evolved, and this led many to take on new roles, creating content and advising others who were sick. What we learned about online content creation suggests a need for designs that support this journey and engage with complex issues surrounding online health resources.

Jennifer Mankoff, Kit Kuksenok, Sara B. Kiesler, Jennifer A. Rode, Kelly Waldman:
Competing online viewpoints and models of chronic illness.CHI 2011: 589-598