NCKU-USC Research Collaboration Forum

Monday, 28 May 2012 17:00

Cyrus Shahabi and Seon Ho Kim participated in the NCKU-USC Research Collaboration Forum on May 29th, 2012, which was held at the National Cheng Kung University in Taiwan. The theme of the forum was "Cloud-based Immersion Services for Smart Campus and Smart City". This effort was a joint research collaboration between IMSC at USC and Touch Center at NCKU.


ADMS Project

Friday, 11 October 2013 18:27

Archived Database Management System (ADMS): This project was developed for LA Metro to collect and store data from traffic loop detectors in LA County. This system is to measure and monitor the performance/operation of  Los Angeles highways and arterial streets.                                                                                                                                                                          

[Read More]



Friday, 11 October 2013 18:23

TransDec (short for Transportation Decision-Making) is a real-world end-to-end system  which enables real-time traffic sensor and moving vechile data collection, analysis and visualization of dynamic transportation systems.                                                 

[Read More]


MediaQ Demo

Friday, 11 October 2013 17:04

MediaQ is a novel online media management framework that includes functions to collect, organize, share, search, and trade user-generated mobile images and videos using automatically tagged geospatial metadata.                                                           

[Read More]



Friday, 11 October 2013 17:01

This video by Voice of America shows how the novel navigation app, called ClearPath, developed by IMSC can help people on the roads. ClearPath offers next generation navigation solution that calculates optimal routes based on existing and predicted traffic patterns while taking weather, travel time and accident delays into consideration.

[Read More]

MediaQ NATO Summit 2012 Coverage

Friday, 11 October 2013 16:57

The goal of this experiment was to test mobile video data collection in a large scale. More than 20 journalism students covered the streets in Chicago during the Nato Summit 2012  using iPhones, iPads, and Android phones as video collecting devices. For three day period, more than 250 video clips were collected.


MediaQ PBS Newshour

Friday, 11 October 2013 16:53

The goal of this experiment was to test the generation of panoramic images from user-generated mobile videos using MediaQ. Working with PBS College Reporting Team, more than 15 journalism students recorded and uploaded videos on the Washington DC streets during 2013 US Presidential Inauguration. 

[Read More]

Traffic Flow Data Extraction

Friday, 11 October 2013 16:40

This project is to extract traffic flow data such as the number of passing cars and their speed using Viewmont board and its SDK, video analytics coprocessor developed by Intel.                                                                                                                                                           

[Read More]

IMSC Sponsored Projects 2013-2014

Thursday, 10 October 2013 18:22

Task Allocation in Dynamic Environments

  • Faculty lead: Prof. Ketan Savla
  • Description: Design and development of algorithms for task allocation strategies for groups of  autonomous or human supervised mobile agents. The approach will enable agents to complete tasks in uncertain and dynamically changing environments, where new task requests are generated in real-time over a geographically dispersed region. The applications of this research include crowd sourcing, pickup(/delivery) tasks in transportation networks, as well as surveillance and monitoring missions.

Facial Expression Recognition

  • Faculty lead: Prof. Gerard Medioni
  • Description: This project develops key algorithms for a realtime facial expression recognition of consumers as a part of the customer feedback analysis framework in B2C (Business to Consumer).

Study of Congested Corridors in Los Angeles

  • Faculty lead: Prof. James Elliott Moore, II
  • Description: Study the most congested corridors of Los Angeles County using historical traffic sensor data, and make before and after analysis of Carmegedons.

Analysis of Mobility Data Using Spatiotemporal Graph-based Techniques

  • Faculty lead: Prof. Antonio Ortega (Electrical Engineering)
  • We consider the scenario where multiple body-attached sensors are used and assume that the data provided by these sensors will be noisy. We will start by analyzing the data captured by real sensors in order to develop a better understanding of noise sources and characteristics. We will then study several de-noising approaches. The first one will be purely time based and will seek to develop techniques (e.g., based on Wavelets) to smooth the temporal trajectories of data at each sensor without removing information that will be important for evaluation and diagnostic. Then, we will also consider graph-based techniques to improve data quality by taking into consideration constraints on the sensor position due to the fact that they are attached to the body. As an example, two sensors attached to an individual's arm will be limited in the extent of their relative motions. We will develop methods were the system is initially calibrated under controlled circumstances, and then data acquired regarding relative sensor positions is used for de-noising. We further plan to explore the potential benefits of recently introduced graph wavelets which can capture all relevant information about body movement as either vertex data (sensor information) or edge data (distance between sensors). In addition to considering the de-noising problem, we will also study lossless and lossy techniques to compress the information generated by the sensors in order to make it easier to store complete records of sensor motion during extended periods of time. The compression techniques will be application-specific, with the goal of preserving key information for signal analysis.

IMSC Research

Tuesday, 08 October 2013 19:16

IMSC’s current research focus is on studying data-driven solutions for real-world applications by taking a geo-informatic approach in blending large amounts of data collected from real and virtual worlds.  In particular, we exploit the common coordinates of time and space in order to fuse heterogeneous real-time and historical data into actionable knowledge and bring them to the end-user for higher situational awareness. Consequently, our research activities can be categorized under the auspices of “Big Data”. 

Big Data is conventionally characterized by “V-starting” words such as: Volume, Velocity, Variety, Veracity, Verification, Value, etc. Volume is sometimes considered as the most challenging aspect of BigData due to the misinterpretation of the word “Big” in BigData.  However, what makes the problem challenging is the combination of large dataset with its other characteristics such as the real-time data processing requirement (Velocity) and/or multi-modality of the data (Variety).

IMSC’s research encompasses all the above aspects of BigData:
  • Storage: how to store and index a large amount of data, e.g., on Cloud
  • Queries: how to find data items effectively and efficiently
  • Machine learning and data mining: how to extract useful information from data
  • Distributed computing: end-to-end architectures for big data management
IMSC has a proven record in geo-informatics and digital media technologies, working with major IT industries. A sample of our research activities with recent selected papers is as follows:
Data Acquistion:
  • Spatial Crowdsourcing [ACM GIS 12][ACM GIS 13-2][ACM GIS 13-3]
  • Traffic Flow Data Extraction from Video [DNIS 13]
  • User-Generated Mobile Videos [MediaQ 13]
Data Storage & Access:
  • Cloud [CloudCom 10]
  • Spatio-temporal Indexing: [VLDB 12]
Data Analytics:
  • Traffic Data Pricing [DATA 14]
  • Location and Social Network [SIGMOD 13][ACM GIS 13-1]
  • Traffic Prediction [ICDM 12][ICDM 13]
  • Text Analysis [JNGC 12]
  • Visual Analytics

The above research is conducted in the context of the following BigData applications: 

Big Data in Transportation: TransDec



Big Data in Social Media: MediaQ



Big Data in Security: Janus Big Data in Health: GeoMed



[DATA 14] Negin Golrezaei and Hamid Nazerzadeh, Pricing Schemes for Metropolitan Traffic Data Markets,  International Conference on Data Management Technologies and Applications, Vienna Austria, August 2014

[ACM GIS 13-1] Bei Pan, Yu Zheng, David Wilkie, and Cyrus Shahabi, Crowd Sensing of Traffic Anomalies based on Human Mobility and Social Media, ACM SIGSPATIAL GIS'13, Orlando, Florida, USA, November 5-8, 2013
[ACM GIS 13-2] Leyla Kazemi, Cyrus Shahabi, and Lei Chen, GeoTruCrowd: Trustworthy Query Answering with Spatial Crowdsourcing, International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2013), Orlando, Florida , November 5-8, 2013
[ACM GIS 13-3] Dingxiong Deng, Cyrus Shahabi, and Ugur Demiryurek, Maximizing the Number of Worker's Self-Selected Tasks in Spatial Crowdsourcing, ACM SIGSPATIAL GIS '13, Orlando, Florida, USA, November 5-8, 2013

[DNIS 13] Seon Ho Kim, Junyuan Shi, Abdullah Alfarrarjeh, Daru Xu, Yuwei Tan , and Cyrus Shahabi, Real-Time Traffic Video Analysis Using Intel Viewmont Coprocessor, DNIS 2013: 150-160, 2013
[SIGMOD 13] Huy Pham, Cyrus Shahabi, and Yan Liu, EBM - An Entropy-Based Model to Infer Social Strength from Spatiotemporal Data, SIGMOD, New York, USA, June 2013
[ACM GIS 12] Leyla Kazemi and Cyrus Shahabi, GeoCrowd: Enabling Query Answering with Spatial Crowdsourcing, ACM SIGSPATIAL GIS, Redondo Beach, CA, November 2012
[ICDM 12] Bei Pan, Ugur Demiryurek, and Cyrus Shahabi, Utilizing Real-World Transportation Data for Accurate Traffic Prediction, IEEE International Conference on Data Mining (ICDM), Brussels, Belgium, December 2012
[VLDB 12] Houtan Shirani-Mehr, Farnoush Banaei-Kashani, and Cyrus Shahabi, Efficient Reachability Query Evaluation in Large Spatiotemporal Contact Datasets, 38th International Conference on Very Large Databases (VLDB), Istanbul, Turkey , August 2012
[IWGS 11] Farnoush Banaei-Kashani, Cyrus Shahabi, and Bei Pan, Discovering Traffic Patterns in Traffic Sensor Data, IWGS, ACMGIS 2011, Chicago, IL, November 2011

[CloudCom 10] Afsin Akdogan, Ugur Demiryurek, Farnoush Banaei-Kashani , and Cyrus Shahabi, Voronoi-based Geospatial Query Processing with MapReduce, IEEE Cloud Computing Technology and Science (CloudCom), Best Paper Award, Indianapolis, IN, November 2010

[MediaQ 13] Seon Ho Kim, Ying Lu, Giorgos Constantinou, Cyrus Shahabi, Guanfeng Wang, Roger Zimmermann, MediaQ: Online Mobile Media Management Framework, Submitted for publication.