BendID: Flexible Interface for Localized Deformation Recognition

by | Sep 15, 2014

Authors: Vinh Nguyen, Sang Ho Yoon, Ansh Verma, Karthik Ramani
Proceedings of the ACM international Joint Conference on Pervasive and Ubiquitous Computing, Sep 13-17, Seattle, USA. pp 553-557, 2014
Paper
Video

We present BendID, a bendable input device that recognizes the location, magnitude and direction of its deformation. We use BendID to provide users with a tactile metaphor for pressure based input. The device is constructed by layering an array of indium tin oxide (ITO)-coated PET film electrodes on a Polymethylsiloxane (PDMS) sheet, which is sandwiched between conductive foams. The pressure values that are interpreted from the ITO electrodes are classified using a Support Vector Machine (SVM) algorithm via the Weka library to identify the direction and location of bending. A polynomial regression model is also employed to estimate the overall magnitude of the pressure from the device. A model then maps these variables to a GUI to perform tasks. In this preliminary paper, we demonstrate this device by implementing it as an interface for 3D shape bending and a game controller.

 BendID

Sang Ho Yoon

Sang Ho Yoon

Sang Ho Yoon is currently working at Microsoft, Seattle, WA. He received his PhD at Purdue University and his B.S & M.S degrees from Carnegie Mellon University in 2008 with major in Mechanical Engineering and minor in Robotics. He worked at Research Department in LG Display & LG Electronics for 5 years. There, he involved in product development for consumer electronics as well as the futuristic products including 'Transparent & Public Display', 'Assistive/Rehabilitation Robot', and 'Smart Car User Interface'. He is particularly interested in applying novel sensing techniques to bring the new forms of input metaphor for Human-computer interaction. Areas of interest include wearable/tangible interface, sensing techniques & fabrication, and novel input device. Currently, his research aims at combining the state-of-art machine learning approaches with novel sensing technique to better support natural human-computer interaction. [Personal Website][LinkedIn]