|
Quality Evaluation of Volunteered Geographic Information (VGI) by assessing user’s reliability, using Artificial Neural Networks (ANN)
|
Elahe Azari Asgari *   , Farhad Hosseinali |
| South Tehran Branch, Islamic Azad University |
|
|
Abstract: (1316 Views) |
| Nowadays Volunteered Geographic Information (VGI) is an important source of geographic information. Unlike formal data, precision and accuracy of VGI is not known at the time of data gathering. Thus, several methods have been developed to evaluate the VGI quality. One of these methods is assessing the VGI quality by evaluating the reliability (trustworthiness) of VGI participants. In this study, using background information of VGI participants and Artificial Neural Networks (ANN), user’s reliability in producing spatial information is estimated. To collect user’s background information, a mobile application was designed under the Android operating system. In this program, the map of Tehran was used and changes were applied to some of its parts. When using this program, the users must answer questions such as gender, age, education, familiarity with GPS or GIS, etc. Then users should answer the questions about the changes made to the map. All of the answers are compared with the correct ones. Then the percentage of user’s correct answers is calculated. Each user should answer the questions of at least three regions. Finally, this information was collected for 1102 regions. The data was used to train the ANN as well as validating. ANN which is a feed forward back propagation multilayer perceptron network was trained by various number of neurons and hidden layers. The best network with mean squared error value 0.19988 was selected. Using the trained ANN, it is possible that in a VGI system, a new user enters his/her background information and the percentage of predicted correct user’s responses is estimated. This percentage may be assumed as one of the criteria of user's reliability in VGI |
|
| Keywords: Volunteered Geographic Information (VGI), Geospatial Information System (GIS), Artificial Neural Network (ANN) |
|
|
Full-Text [PDF 1162 kb]
(400 Downloads)
|
Type of Study: Research |
Subject:
GIS
Received: 2022/05/22 | Accepted: 2023/09/18 | ePublished ahead of print: 2023/10/10 | Published: 2023/10/10
|
|
|
|
|
|
|
| Send email to the article author |
|
|
