Alireza Kashian

[vc_row][vc_column width=”1/3″ css=”.vc_custom_1453342300079{padding-top: 15px !important;}”][vc_column_text]Alireza Kashian[/vc_column_text][/vc_column][vc_column width=”2/3″][vc_column_text]

Research@Locate Presentation:
Mining the Co-existence of POIs in OpenStreetMap for Faulty Entry Detection

Alireza Kashian, PhD candidate from the University of Melbourne


[/vc_column_text][/vc_column][/vc_row][vc_row css=”.vc_custom_1453341977865{border-top-width: 1px !important;border-top-color: #28b7ff !important;border-top-style: solid !important;}”][vc_column][vc_column_text]

5 Things You Will Learn

  1. Application of spatial data mining can help us to understand the relationship between objects in our real world
  2. Through the proposed platform in this short paper, we can analyze any newly registered POI in OpenStreetMap project and discover if an object has potentially inaccurate positon on the map
  3. Current mechanisms for automatic processing of volunteered information in OSM is not sufficient and they are mainly based on credit and reputation of users in the system
  4. It is highly possible that many POI objects are wrongly places in OSM project and by using the proposed platform, we can quickly discover such items and send them to chief editors for revision
  5. More advanced analytical tools are needed to develop for OSM project in future

Target Audience

Anyone in the domain of Volunteer Geographic information, Fraud detection and Spatial data analysis. Especially researchers interested in OpenStreetMap projects and spatial data mining.

Presentation Overview

In recent years, more amateur volunteers join crowdsourcing activities for collecting geodata which in turn might result in higher rate of man-made mistakes in open geo-spatial databases such as OpenStreetMap (OSM). While there are some methods and routines to monitor the accuracy and consistency of the created data, there is still lack of advanced predicting systems to automatically discover misplaced objects on the map. One main feature which is contributed daily in OSM is Point of Interest. When a new POI is added to the map, it is interesting to explore what would be the probability of existence of such POI in that specific position. To answer this question, this paper reports a work in progress which is about a newly designed and developed platform to analyse POI objects in OSM database in order to find co-existing patterns among features in close metric distance to each other. These patterns could potentially improve current tracking and verifying systems and thus enhances positional accuracy of registered POIs in OSM.


Alireza Kashian is PhD candidate at University of Melbourne and works at Centre for Disaster Management and Public Safety. Alireza has Masters in Computer Science from Nanyang Technological University in Singapore. He has more than 10 years of industry experience working on online digital maps and created the map of Tehran in 2008 at which currently has more than 4 million users per year. Alireza has also developed a mobile application called RoadPlex to collect POI attributes through the crowd in 2013. Alireza is interested in crowd-sourcing geographic information and specially studies features and challenges in OSM project for enhancing data quality.