a phd student at
computer science and artificial intelligence laboratory,
department of aeronautics and astronautics,
exploring somewhere between
mobile computing, ai, and machine learning.

i have graduated! i defended my phd thesis on may 2013.

my phd research theme is people-centric mobile indoor positioning, viewing people as a central model for designing indoor positioning systems with mobile devices.

my phd advisor is prof. seth teller.

here is my resume.

contact me at: jgpark@csail.mit.edu


brief descriptions of some projects i have been involved in so far at MIT, from newer to older...

Motion Compatibility for Indoor Localization

We as humans represent their own movement trajectories only by abstract terms describing unit activities or motions, such as "walking", "turning left", "riding elevator up", or "climbing stairs down", associated with, but not necessarily requiring, coarse metric information, such as "for 3 seconds." We can also reconstitute the path taken from such motion descriptors, provided a map with sufficient details. Assume that you can remember the actions you have taken to arrive at your office from the entrance of the building, then you will be able to find the path you have taken from the series of motions.

We explored this idea of finding user trajectory in indoor environment from a series of discrete motions using mobile devices in this work. The method works in two stages: 1) extracting navigational activities from smartphone sensor data, 2) matching the extracted series of motions onto a map parsed automatically from floorplans and represented as a route network to find user trajectory starting from an unknown location. We also devised classification-based algorithms to infer the user's walking speed and the position of the mobile device releative to the user. Here's a youtube video showing how this works in practice.
Relevant publications: 09,10,11

The MIT Intelligent Wheelchair Project and The Nurse Interface

The MIT Intelligent Wheelchair project develops a smart wheelchair that aids people with limited mobility, due to, for example, progressive neurological diseases (http://rvsn.csail.mit.edu/wheelchair/). One of the key components of the system is to provide location and its related services to caregivers through sensor modules equipped on the patients' wheelchairs. In particular, I have been involved in developing the nurse interface, an end-to-end system informing the patients' whereabouts to nurses in a residential facility with a well-thought UI, deployed and tested at The Boston Home with great success. (Image courtesy of Sachi Hemachandra)
Relevant publications: 07

Molé: a Scalable, User-Generated WiFi Positioning Engine

Molé (Mobile Organic Location Engine) is an organic location system, redesigned and extended from our previous design of the organic indoor location system. Its focus is enhanced flexibility and scalability, by adopting hierarchical space representations and cloud-based fingerprint distribution system, among others. See https://projects.developer.nokia.com/mole (project led by Jonathan Ledlie at Nokia Research)
Relevant publications: 06,08

Organic Indoor Location Discovery

We combine the idea of crowdsourcing with RF-based indoor localization system to overcome its biggest limitation --- the need for calibration, or training data, which are used for mapping from RF signal characteristics to physical locations.

We first show that it is feasible to leverage crowdsourcing of WiFi data required for learning such mappings from end users, making the locationing system organic in a sense that it grows by itself from scratch. We then tackle related algorithmic challenges in growing such a system, e.g., how to present information to users, filter out erroneous inputs, or tackle device diversity problem when users use different types of devices with different RF signal characteristics. See http://rvsn.csail.mit.edu/location/ for the project page.
Relevant publications: 04,05,10

Moving-Baseline Localization

Many algorithms and applications in sensor networks, such as routing or in-network data aggregation, assume the knowledge of sensor locations. The most challenging scenario arises when all nodes are moving in a "GPS-denied" environment, where none of them are aware of their absolute positions. However, most existing work on sensor network localization algorithms assume either that sensors are static or that a fraction of them know their own location. We developed a localization algorithm that is free from such assumptions, which recovers a relative motion configuration, i.e. positions and velocities, of the sensor nodes from pairwise range measurements between them.
Relevant publications: 01,02,03


Motion Compatibility for Indoor Localization 11

Jun-geun Park, Seth Teller
CSAIL Technical Reports, MIT-CSAIL-TR-2014-017, 2014

Indoor Localization using Place and Motion Signatures 10

Jun-geun Park
PhD Thesis, MIT, 2013

Online Pose Classification and Walking Speed Estimation using Handheld Devices 09

Jun-geun Park, Ami Patel, Dorothy Curtis, Jonathan Ledlie, Seth Teller
Proc. 14th International Conference on Ubiquitous Computing (UbiComp 2012), 2012, pp.113-122

Molé: a Scalable, User-Generated WiFi Positioning Engine 08

Jonathan Ledlie, Jun-geun Park, Dorothy Curtis, André Cavalcante, Leonardo Camara, Afonso Costa, Robson Vieira
Journal of Location Based Services (JLBS), vol. 6, no. 2, 2012

Improving Safety and Operational Efficiency in Residential Care Settings with WiFi-based Localization 07

Finale Doshi-Velez, William Li, Yoni Battat, Ben Charrow, Dorothy Curtis, Jun-geun Park, Sachi Hemachandra, Javier Velez, Cynthia Walsh, Don Fredette, Bryan Reimer, Nicholas Roy, Seth Teller
Journal of the American Medical Directors Association (JAMDA), vol. 13, no. 6, 2012, pp.558-563

Molé: a Scalable, User-Generated WiFi Positioning Engine 06

Jonathan Ledlie, Jun-geun Park, Dorothy Curtis, André Cavalcante, Leonardo Camara, Afonso Costa, Robson Vieira
Proc. International Conference on Indoor Positioning and Indoor Navigation (IPIN 2011), 2011 (Best Paper Award)

Implications of Device Diversity for Organic Localization 05

Jun-geun Park, Dorothy Curtis, Seth Teller, Jonathan Ledlie
Proc. 30th IEEE International Conference on Computer Communications (INFOCOM 2011), 2011, pp.3182-3190

Growing an Organic Indoor Location System 04

Jun-geun Park, Ben Charrow, Jonathan Battat, Dorothy Curtis, Einat Minkov, Jamey Hicks, Seth Teller, Jonathan Ledlie
Proc. 8th International Conference on Mobile Systems, Applications, and Services (MobiSys 2010), 2010, pp.271-284

Moving-Baseline Localization for Mobile Wireless Sensor Networks 03

Jun-geun Park
SM Thesis, MIT, 2009

Moving-Baseline Localization 02

Jun-geun Park, Erik Demaine, Seth Teller
Proc. 7th International Conference on Information Processing in Sensor Networks (IPSN 2008), 2008, pp.15-26

Moving-Baseline Navigation 01

Jun-geun Park, Erik Demaine, Seth Teller
Dagstuhl Seminar Proceedings, Dagstuhl Seminar 07151 - Geometry in Sensor Newtorks, 2007