Saturday, November 9, 2019

Won the First Place at ACM SIGSPATIAL Cup 2019!

The authors of "Distance-Aware Competitive Spatiotemporal Searching Using Spatiotemporal Resource Matrix Factorization" won the first place ($500) at ACM SIGSPATIAL Cup 2019

Dr. Bo Xu, a contest co-chair and a Principal Research Engineer at HERE Technologies, introduced this year challenge in the Contest Session. ACM SIGSPATIAL Cup 2019 was about optimization of agents’ maneuvers based on the ride-hailing simulation provided by the contest organizers. The main challenge was how smartly the agents (or drivers) seeking customers relocate their cars without any communication with other agents while globally minimizing search time of all agents and wait time of all customers. The results of the top three teams (George Mason University, Ludwig-Maximilians-Universität, Eindhoven University of Technology) were very close to each other. I believe tuning parameters to higher the chance to win was the secret. The certificate was awarded at the banquet on November 7, 2019.

From left to right: Prof. Andreas Züfle, Dr. Joon-Seok Kim, Prof. Goce Trajcevski (ACM SIGSPATIAL Vice-Chair), Prof. Cyrus Shahabi (ACM SIGSPATIAL Chair)

For more information, please visit my project web site:

Sunday, October 20, 2019

Special Issue "Geo-Enriched Data Modeling & Mining", IJGI

A Special Issue "Geo-Enriched Data Modeling & Mining" of  ISPRS International Journal of Geo-Information (ISSN 2220-9964)

Deadline for manuscript submissions: 31 August 2020.

Special Issue Information

Dear Colleagues,

Both of the current trends in technology such as smartphones, general mobile devices, stationary sensors and satellites as well as a new user mentality of utilizing this technology to voluntarily share information produce a huge flood of geospatial data. This data is enriched by multiple additional sources or contexts such as social information, text, multimedia data, and scientific measurements, called geo-enriched data. This data flood provides a tremendous potential of discovering new and possibly useful knowledge. The novel research challenge is to model, share, search, and mine this wealth of geo-enriched data. The focus of this Special Issue is to analyze what has been achieved so far and how to further exploit the enormous potential of this data flood. The ultimate goal of this Special Issue is to develop a general framework of methods for modeling, searching and mining enriched geospatial data in order to fuel an advanced analysis of big data applications beyond the current research frontiers. Furthermore, this Special Issue intends to compile an interdisciplinary research collection in the fields of databases, data science, and geoinformation science.

This Special Issue is dedicated to giving an overview of state-of-the-art solutions, techniques and applications on modeling, managing, searching and mining geo‐enriched data, such spatio-textual, spatio-temporal, spatio-social, geo-social network, mobile and wireless data.

We call for original papers from researchers around the world that focus on topics including, but not limited to, the following:

Dr. Andreas Züfle
Dr. Joon-Seok Kim
Guest Editors


  • Big Spatial Data
  • Crowdsourcing Computing Resources
  • Data Extraction Techniques including NLP
  • Data Mining on Geo-Enriched data
  • Geo-Multimedia DataM Geo-Social Data
  • Geo-Textual Data
  • Indexing Geo-Enriched data
  • Location-Based Social Networks
  • Spatial Data Models and Representation
  • Spatial Privacy and Confidentiality
  • Spatial Reasoning and Analysis
  • Spatial Recommendation Systems
  • Temporal Geo-Enriched Data
  • Uncertainty in Spatial and Spatio-Temporal Data
  • Visualization of Geo-Enriched Data

Special Issue Editors

  • Dr. Andreas Züfle (Guest Editor)
  • Dr. Joon-Seok Kim (Co-Guest Editor)

Tuesday, October 8, 2019

Distance-Aware Competitive Spatiotemporal Searching Using Spatiotemporal Resource Matrix Factorization

GIS Cup is an annual contest of SIGSPATIAL. ACM SIGSPATIAL Cup 2019 was about optimization of agents’ maneuvers based on the ride-hailing simulation provided by the contest organizers. The main challenge was how smartly the agents (or drivers) seeking customers relocate their cars without any communication with other agents while globally minimizing search time of all agents and wait time of all customers. My approach is to learn a spatiotemporal resource model using non-negative matrix factorization. Then, our SmartAgents strive to avoid both oversupply and undersupply, considering balance of greed for travel-distance and resource distribution.

Our paper was accepted as one of four finalists who achieved the best results. The final result of the contest will be revealed at ACM SIGSPATIAL'19, November 7, 2019. For more information, please visit my project web site


Congested traffic wastes billions of liters of fuel and is a significant contributor to Green House Gas (GHG) emissions. Although convenient, ride sharing services such as Uber and Lyft are becoming a significant contributor to these emissions not only because of added traffic but by spending time on the road while waiting for passengers. To help improve the impact of ride sharing, we propose an algorithm to optimize the efficiency of drivers searching for customers. In our model, the main goal is to direct drivers represented as idle agents, i.e., not currently assigned a customer or resource, to locations where we predict new resources to appear. Our approach uses non-negative matrix factorization (NMF) to model and predict the spatio-temporal distributions of resources. To choose destinations for idle agents, we employ a greedy heuristic that strikes a balance between distance greed, i.e., to avoid long trips without resources and resource greed, i.e., to move to a location where resources are expected to appear following the NMF model. To ensure that agents do not oversupply areas for which resources are predicted and under supply other areas, we randomize the destinations of agents using the predicted resource distribution within the local neighborhood of an agent. Our experimental evaluation shows that our approach reduces the search time of agents and the wait time of resources using real-world data from Manhattan, New York, USA.

Smart Agent vs. Random Destination

Our contributions:

  • Generalization: Assuming that resources vary between days, the algorithm should adapt to random deviations in resource distributions, rather than overfitting to the resource distribution in the training data set.
  • Balancing Utility and Distance: Agents should find a balance between exploration (moving to more useful locations) and exploitation (remaining in the current location). The algorithm must find a balance between these two aspects.
  • Fairness: Without allowing agents to communicate with each other, the algorithm should evade flocking towards the same destination, to avoid oversupplying some regions while causing starvation in others.
  • Timing: Agents should move towards regions where their is a maximal chance of finding a resource at the time of arrival.

J.-S. Kim, D. Pfoser, and A. Züfle, Distance-Aware Competitive Spatiotemporal Searching Using Spatiotemporal Resource Matrix Factorization (GIS Cup), In Proceedings of ACM SIGSPATIAL GIS ’19, November 5-8, 2019. Chicago, IL, USA (to appear)

Monday, September 16, 2019

Simulating Urban Patterns of Life: A Geo-Social Data Generation Framework

Data generators have been heavily used in creating massive trajectory datasets to address common challenges of real-world datasets, including privacy, cost of data collection, and data quality. However, such generators often overlook social and physiological characteristics of individuals and as such their results are often limited to simple movement patterns. To address these shortcomings, we propose an agent-based simulation framework that facilitates the development of behavioral models in which agents correspond to individuals that act based on personal preferences, goals, and needs within a realistic geographical environment. Researchers can use a drag-and-drop interface to design and control their own world including the geospatial and social (i.e. geo-social) properties. The framework is capable of generating and streaming very large data that captures the basic patterns of life in urban areas. Streaming data from the simulation can be accessed in real time through a dedicated API.

Our framework allows us to define and combine each of these four concepts to create unique simulation and data generators.

  • Trigger is a mechanism that is initiated by a change or event in internal or external factors. Internal factors include one's needs, beliefs, and characteristics, while external factors include the environment or other individuals. For example, a trigger called hunger can be defined as an agent having a food level less than a specified threshold.
  • Behavior is a construct that is directly initiated by a trigger. For instance, we assume that eating is a behavior because it is directly initiated by the trigger of hunger. Inside a behavior, one can define multiple actions that make up the lifetime of the behavior.
  • Action is the process of performing certain step(s) that directly produce an output once it reaches the defined goal. Sticking with the eating behavior example, each process leading towards becoming full is considered an action. For instance, deciding whether eating at home or outside is a one-step action that generates a decision. Similarly, the process of grocery shopping is an action with multiple steps. 
  • Goal is simply the end condition for an action, such as an agent reaching a food level of 100%.

The demo will be presented at ACM SIGSPATIAL'19. For more information (sample data, figures), please visit my demo web site 

J.-S. Kim, H Kavak, U. Manzoor, A. Crooks, D. Pfoser, C. Wenk, and A. Züfle, Simulating Urban Patterns of Life: A Geo-Social Data Generation Framework, In Proceedings of ACM SIGSPATIAL GIS ’19, November 5-8, 2019. Chicago, IL, USA (to appear)

Sunday, August 18, 2019

Call For Papers: SpringSim 2020

MAY 19 - 21, 2020


The 2020 Spring Simulation Conference (SpringSim’20) is an annual conference sponsored by The Society for Modeling and Simulation International (SCS), which covers state-of-the-art developments in Modeling & Simulation (M&S). SpringSim’20 invites original contributions to the theory and practice of modeling and simulation in any scientific or engineering discipline including but are not limited to:

  • AI and Simulation
  • Simulation modeling tools and methods based on AI and ML
  • Communications and Network Simulation
  • Complex, Intelligent, Adaptive and Autonomous Systems
  • Cyber Physical Systems
  • Cyber Security Engineering
  • High Performance Computing
  • Humans, Societies and Artificial Agents
  • Model-driven Approaches for Simulation Engineering
  • M&S in Medicine
  • M&S for Smart Energy Systems
  • Theory and Foundations for Modeling and Simulation

The conference includes keynote speeches presented by technology and industry leaders, technical sessions, professional development tutorials, as well as vendor exhibits. Scientists, engineers, managers, educators, and business professionals who develop or use M&S methodologies and tools are invited to participate and present original contributions.


Tutorial Proposals: December 16, 2019
Paper Submission: December 16, 2019
Author Notification: February 17, 2020
Ext Abstract Submission: February 20, 2020
Demo Proposals: February 20, 2020
Camera-Ready: March 4, 2020


AI and Simulation (AIS)
Joon-Seok Kim and Andreas Züfle

Annual Simulation Symposium (ANSS)
Erika Frydenlund and José Luis Risco Martín

Cyber Physical Systems (CPS)
Akshay Rajhans and Nikos Arechiga

Cyber Security Engineering (CSE)
Sachin Shetty and Danda Rawat

Humans, Societies, and Artificial Agents (HSAA)
Philippe J. Giabbanelli and Andrew T. Crooks

Communications and Networking Simulation (CNS)
Abdolreza Abhari and Ala’a Al-Habashna

High Performance Computing (HPC)
Dongyoon Lee and Shaikh Arifuzzaman

Modeling and Simulation in Medicine (MSM)
Jerzy W. Rozenblit and Johannes Sametinger

M&S for Smart Energy Systems (MSSES)
James Nutaro and Ozgur Ozmen

Theory and Foundations for Modeling and Simulation (TMS)
Joachim Denil and Hessam Sarjoughian

Krzysztof Rechowicz

M&S Demo and Student Colloquium Posters
Salim Chemlal, Youssef Bouanan, Nahom Kidane, and Mohammad Moallemi

For more information, please visit the official web page (

Saturday, May 25, 2019

Call for Papers: GeoSim 2019

The GeoSim 2019 workshop focuses on all aspects of simulation as a general paradigm to model and predict spatial systems and generate spatial data. New simulation methodologies and frameworks, not necessarily coming from the SIGSPATIAL community, are encouraged to participate. Also, this workshop is of interest to everyone who works with spatial data. The simulation methods that will be presented and discussed in the workshop should find a wide application across the community by producing benchmark datasets that can be parameterized and scaled. Simulated data sets will be made available to the community via the website. 
The workshop seeks high-quality full (8 pages) and short (4 pages) papers that will be peer-reviewed. Once accepted, at least one author is required to register for the workshop and the ACM SIGSPATIAL conference, as well as attend the workshop to present the accepted work which will then appear in the ACM Digital Library.
Example topics include, but not limited to:
  • Urban Simulation
  • Agent Based Models for Spatial Simulation
  • Multi-Agent Based Spatial Simulation
  • Big Spatial Data Simulation
  • Spatial Data/Trajectory Generators
  • Road Traffic Simulation
  • Environmental Simulation
  • GIS using Spatial Simulation
  • Interactive Spatial Simulation
  • Spatial Simulation Parallelization and Distribution
  • Geo-Social Simulation and Data Generators
  • Social Unrest and Riot Prediction using Simulation
  • Spatial Analysis based on Simulation
  • Behavioral Simulation
  • Verifying, and Validating Spatial Simulations
  • Applications for Spatial Simulation

For more information, please visit our workshop website: at

Trajectory data editing tool

Trajectory data editing tool

The trajectory data editing tool was one of the deliverables of a project, called Query Processing for moving objects on Road Networks, funded by Electronics and Telecommunications Research Institute, back in 2004. Internally, our team named the primary system as MODB.NET (Moving Object DataBase .NET). The project aimed to develop a database management system for moving objects on road networks. From a development phase to the utilization phase, data acquisition was challenging. For the data acquisition, two approaches were made: synthetic data generation and real data collection.

At that time, open data about moving objects were rare. So, we had to collect all data by ourselves, taking buses and taxis in Busan, South Korea. For the real data collection, I developed a location tracking program in Java on PDAs equipped with GPS. Unlike today, receiving GPS streaming data required serial-port communication. Besides, I had to handle raw GPS messages, learning specification of National Marine Electronics Association (NMEA) messages. One of the challenges was the low accuracy of the data collected by GPS. The error was so severe that we could not use without data preprocessing. I implemented a map-matching algorithm based on the literature [1]. Unfortunately, the quality of the results was not good enough to make use of them. That was the motivation to create the trajectory data editing tool.

The primary goal is to convert raw GPS data to locations on the road network. Its major functions are

  • To browser maps: zoom in/out, panning,
  • To convert coordinates from WGS84 to Korean 1985 Korea Central/East Belt,
  • To select/translate/delete trajectories,
  • To split a trajectory into parts, and
  • To match locations onto maps with different algorithms.
Trajectories, especially taxi data, included multip trips, and we needed to split them for multiple purposes. The tool was supposed to facilitate quality control of data leading to the non-functional requirements including
  • Ease of use, and
  • Efficient visualization.

Compared to data size nowadays, data I handled at that time was not that big though, still computing power wasn't that strong neither. Thus, to efficiently plot all points and lines was the critical non-functional requirement. To accelerate, I introduced a double-buffering technique with multilayers. Rather than updating canvas, I managed layers separately, checking whether an update is needed to reduce the unnecessary overhead from redrawing all segments.

As an undergraduate in computer engineering, it was an exciting project beyond a simple course project. Yet, I was a kid who loves building blocks from scratch.

[1] Quddus, M.A., Ochieng, W.Y., Zhao, L. and Noland, R.B., 2003. A general map matching algorithm for transport telematics applications. GPS solutions, 7(3), pp.157-167.