Applying pattern recognition techniques based on hidden Markov models for vehicular position location in cellular networks

In this paper, field m easurem ents from the GSM and UMTS netw orks are analysed in a road traffic inform ation context. The m easurem ents ind icate a p otentially large im provem ent using UMTS signalling d ata com pared to GSM regard ing hand over location accuracy. These im provem ents can be used to generate real-tim e traffic inform ation w ith higher quality and extend the geographic usage area for cellular based travel tim e estim ation system s. The r esults confirm previous reports ind icating that he technology has a large p otential in GSM and they also show that the potential m ight be even larger u sing UMTS. Assum ing that non vehicle term inals can be filtered out, that veh icles are tracked to the correct route and that hand overs can be pred icted co rrectly, a conclusion from the experim ents is that the hand ov er location accuracy in both GSM and UMTS w ill be sufficient to estim ate useful travel tim es, also in urban environm ents. If there is a scalable w ay of d oing this filtering, tracking and pred iction in urban environm ents is not clear to the authors t od ay.58

show abstract

“…This problem is d iscussed in d etail in e.g. [6,7]. Figure 6 show s an exam ple of estim ated and actual hand over locations d uring a test run.…”

Section: Potential Travel Time Accuracymentioning

confidence: 99%

“…The route d eterm ination problem is d iscu ssed in e.g. [7,8]. A survey and a detailed d escription about the d ifferences in location d ata for generating road traffic inform ation from the GSM and UMTS netw orks can be found in [9].…”

Section: Introductionmentioning

confidence: 99%

Handover location accuracy for travel time estimation in GSM and UMTS

Gundlegård

Karlsson

2009

IET Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…Recently three extensive reports have been published summarizing the different projects and field trials that have been performed within the field of estimating road traffic information from cellular networks [6][7][8]. The conclusions from these reports are quite similar; the technology has large potential although more research is needed in order to use it as efficiently as possible.…”

Section: Introductionmentioning

confidence: 99%

Route classification in travel time estimation based on cellular network signaling

Gundlegård

Karlsson

2009

2009 12th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Abstract-Travel time estimation based on cellular networksignaling is a promising technology for delivery of wide area travel times in real-time. The technology has received much attention recently, but few academic research reports has so far been published in the area, which together with uncertain location estimates and environmental dependent performance makes it difficult to assess the potential of the technology. This paper aims to investigate the route classification task in a cellular travel time estimation context in detail. In order to estimate the magnitude of the problem, two classification algorithms are developed, one based on nearest neighbor classification and one based on Bayesian classification. These are then evaluated using field measurements from the GSM network. A conclusion from the results is that the route classification problem is not trivial even in a highway environment, due to effects of multipath propagation and changing radio environment. In a highway environment the classification problem can be solved rather efficiently using e.g., one of the methods described in this paper, keeping the effect on travel time accuracy low. However, in order to solve the route classification task in urban environments more research is required.

show abstract

“…Metrics can be measured and processed on the network entity or on the mobile. There are several handoff decision algorithms that employ tools of artificial intelligence like fuzzy logic systems [8][9][10][11], neural networks [8,12], and pattern recognition algorithms [8,[13][14][15] to process the collected metrics.…”

Section: Introductionmentioning

confidence: 99%

“…For multicriteria handoff, different pattern recognition based handoff decision algorithms have been proposed in the literature [8,[13][14][15]. Fuzzy logic systems and neural network classifiers are good candidates for pattern classifiers due to their non-linearity and generalization capability.…”

Section: Introductionmentioning

confidence: 99%