School of Interactive Computing faculty and alumni were among a group of five recognized for the 10-Year Impact Award at the ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp 2017) for their paper titled At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line.
The paper, which presented an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home, earned Best Paper and Best Presentation honors at Ubicomp 2007. This year, the paper was one of three awarded at Ubicomp 2017 for having outstanding influence over the past 10 years.
Co-authors on the paper included current Georgia Tech Professor Gregory Abowd, former Georgia Tech postdoctoral student and Research Scientist Matt Reynolds, alumni Shwetak Patel and Julie Kientz, and Tom Robertson, who worked in Abowd’s lab for two years around the time of publication.
Reynolds, Patel, and Kientz now each hold faculty positions at the University of Washington.
To achieve desired results, the researchers applied machine learning techniques to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. They tested their system in one home for several weeks and in five homes for one week each to evaluate the system performance over time in different types of houses. Results indicated that it is possible to learn and classify various electrical events with accuracies ranging from 85-90 percent.
The method has become known as Infrastructural Mediated Sensing, a concept developed and commercialized in a variety of subsequent ways by Patel and Reynolds.
Ubicomp 2017 took place earlier this month in conjunction with the ACM International Symposium on Wearable Computing in Maui, Hawaii.
Georgia Tech received another notable accolade at the co-located ISWC 2017 conference, which shares a technical program with Ubicomp. The Jury Prize for Best Paper and Entry in the aesthetics category of the Design Exhibition was awarded to Le Monstré, an interactive participatory performance costume developed by Ph.D. HCC student and research scientist Clint Zeagler. The team also included IMTC research scientists Scott Gilliland and Laura Levy.
Associate Professor Thomas Ploetz also provided organization assistance at the conference, spearheading Deep Learning for Ubiquitous Computing, a one-day tutorial held prior to the main Ubicomp conference. The full-day experience provided lectures and discussions on the theoretical foundations of Deep Learning, grounded into the Ubicomp domain.
This year, Georgia Tech had 11 paper accepted at the conference. Titles, authors, and available links for each can be found below.
- Passive Haptic Training to Improve Speed and Performance on a Keypad (Caitlyn Seim, Nick Doering, Yang Zhang, Wolfgang Stuerzlinger, Thad Starner)
- FingerSound: Recognizing Unistroke Thumb Gestures Using a Ring (Cheng Zhang, Anandghan Waghmare, Pranav Kundra, Yiming Pu, Scott Gilliland, Thomas Ploetz, Thad Starner, Omer Inan, Gregory Abowd)
- FiDO: A Community-based Web Browsing Agent and CDN for Challenged Network Environments (Morgan Vigil-Hayes, Elizabeth Belding, Ellen Zegura)
- FingOrbits: Interaction With Wearables Using Synchronized Thumb Movements (Cheng Zhang, Xiaoxuan Wang, Anandghan Waghmare, Sumeet Jain, Thomas Ploetz, Omer Inan, Thad Starner, Gregory Abowd)
- Itchy Nose: Discreet Gesture Interaction Using EOG Sensors in Smart Eye-Wear (Juyoung Lee, Hui-Shyong Yeo, Murtaza Dhuliawala, Jedidiah Akano, Junichi Shimizu, Thad Starner, Aaron Quigley, Woontack Woo, Kai Kunze)
- Detecting Gaze Towards Eyes in Natural Social Interactions and Its Use in Child Assessment (Eunji Chong, Katha Chanda, Zhefan Ye, Audrey Southerland, Nataniel Ruiz, Rebecca Jones, Agata Rozga, Jim Rehg)
- EarBit: Using Wearable Sensors to Detect Eating Episodes in Unconstrained Environments (Abdelkareem Bedri, Richard Li, Malcolm Haynes, Raj Prateek Kosaraju, Ishaan Grover, Temiloluwa Prioleau, Min Yan Beh, Mayank Goel, Thad Starner, Gregory Abowd)
- Where to Wear It: Functional, Technical, and Social Considerations in On-Body Location for Wearable Technology, 20 Years of Designing for Wearability (Clint Zeagler)
- SoundTrak: Continuous 3D Tracking of a Finger Using Active Acoustics (Cheng Zhang, Qiuyue Xue, Anandghan Waghmare, Sumeet Jain, Yiming Pu, Jordan Conant, Sinan Hersek, Kent Lyons, Kenneth A. Cunefare, Omer T. Inan, Gregory Abowd)
- Inferring Mood Instability on Social Media by Leveraging Ecological Momentary Assessments (Koustuv Saha, Larry Chan, Kaya de Barbaro, Gregory Abowd, Munmun De Choudhury)
- Activity Recognition for Quality Assessment of Batting Shots in Cricket using a Hierarchical Representation (Aftab Khan, James Nicholson, Thomas Ploetz)
- Ensembles of Deep LSTM Learners for Activity Recognition using Wearables (Yu Guan, Thomas Ploetz)