Pedestrian flow prediction in extensive road networks using biased observational data

In this paper, we discuss an application of spatial data mining to predict pedestrian flow in extensive road networks using a large biased sample. Existing out-of-the-box techniques are not able to appropriately deal with its challenges and constraints, in particular with sample selection bias. For this purpose, we introduce s-knnapriori, an efficient nearest neighbor based spatial mining algorithm that allows prior knowledge and deductive models to be included in a straightforward and easy way. Categories and Subject Descriptors I.2.6 [Learning]: Induction, Knowledge acquisition; I.5.1 [Models]; I.5.2 [Design Methodology] General Terms Algorithms, Economics, Reliability, Human Factors, Verification Keywords Spatial data mining, pedestrian flow prediction, sample selection bias, prior knowledge, extensive road networks, large scale data

• Type: Conference
• Year: 2008
• Where: GIS
• Authors: Michael May, Simon Scheider, Roberto Rösler, Daniel Schulz, Dirk Hecker
• Keywords: Database, GIS 2008, Sample Selection Bias, Spatial Data Mining, Spatial Mining Algorithm