Abstract: Inductive Loop Detectors (ILD) are the most commonly used sensors in traffic management systems. Using the acquired inductive signatures, most proposed systems classify the vehicles using a criterion based on the estimation of the vehicle length, which requires to have a good a-priori estimate of its speed. Contrary to such standard proposals, in this paper we present a method for vehicle classification based on the criterion of the Fourier Transform (FT), which shows several interesting properties: firstly, robustness against variations in vehicle speed or constant acceleration, and secondly, only one inductive signature is required. Our method will be evaluated using real inductive signatures captured with a hardware prototype also developed by us.

• Publication Date: 11-Oct-2015
• DOI: 10.15224/978-1-63248-064-4-09
• Views: 0
• Downloads: 0

Abstract: In general, there are two types of feedback documents: positive feedback documents and negative feedback documents. These types share some knowledge because they retrieved using the same query. It is clear that all feedback documents contain some noise knowledge that affects the quality of the extracted features. The amount of noise is different from document to another. Therefore, the number of feedback documents affects the amount of extracting noise features. Then, using all feedback documents can increase the number of extracted noise features. However, we believe that negative feedback documents contain more noise than positive feedback documents. In this paper, we introduce a methodology to select some negative feedback documents to extract high-quality features and to reduce the amount of noises features.

• Publication Date: 11-Oct-2015
• DOI: 10.15224/978-1-63248-064-4-10
• Views: 0
• Downloads: 0