A Scalable Distributed Stream Mining System for Highway Traffic Data

Liu, Ying; Choudhary, Alok; Zhou, Jianhong; Khokhar, Ashfaq

doi:10.1007/11871637_31

Cited by 20 publications

(10 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, Liu et al (2006) presents a distributed traffic stream mining system. The core of the system consists of a training and pattern learning module based on historical data that communicates with a network of light-weight sensors of limited computational power.…”

Section: Related Work For Stream Data Labellingmentioning

confidence: 97%

See 1 more Smart Citation

Real time movement labelling of mobile event data

Kõivumägi

Vait

Hadachi

et al. 2015

Journal of Location Based Services

View full text Add to dashboard Cite

In this paper we introduce an advanced platform to label mobile event data with significant subscriber locations in real time. The presented platform is divided into two sections -the learning section and the real-time processing section. During the real-time processing step, we enrich live event streams with significant locations calculated in the learning step using stream and call detail record data. We validate our system by comparing a sample of subscribers' calculated locations with actual locations and give state benchmarks for minimum event counts. The validation confirms that the platform works within desired deviation levels from real locations. The accuracy strongly depends on the event count that we can take into account. Finally, we simulate a real-world scenario and measure the real-time labelling performance of our system. The results of this simulation confirm that our event labelling platform performs sufficiently well to process real event streams for millions of subscribers in real time.

show abstract

Section: Related Work For Stream Data Labellingmentioning

confidence: 97%

“…Moreover, interesting stream data mining applications are coming from the traffic area (Kargupta et al 2004;Liu et al 2006). Kargupta et al (2004) presents a stream mining system called VEDAS for real-time vehicle monitoring and driver characterisation.…”

Section: Related Work For Stream Data Labellingmentioning

confidence: 99%

Real time movement labelling of mobile event data

Kõivumägi

Vait

Hadachi

et al. 2015

Journal of Location Based Services

View full text Add to dashboard Cite

show abstract

“…In Reference [2], a scheme base on Fast Fourier Transform (FFT) and Wavelet Transform is proposed, but the authors didn't give exactly performance of their scheme. Ying Liu [3] propose a distributed congestion prediction scheme base on stream mining, but the accuracy was quite low. Although 27% of the sensors acquire 100% accurate prediction, the average accuracy is only 25%.…”

Section: A Data Reduction In Sensor Networkmentioning

confidence: 99%

Data reduction in urban traffic sensor network

et al. 2009

2009 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

In a large scale sensor network for traffic surveillance, the data to be transmitted is huge, which leads to high cost of communication. When sensor nodes are connected wirelessly, the situation will be worse. So it's necessary to reduce the data amount before data packets are transmitted. In this paper, we propose a distributed algorithm base on FCM (Fuzzy C-Means Clustering). Parameters in the algorithm are also discussed. With a set of relative optimal parameters, we perform an experiment. In our experiment based on a traffic flow volume data set, the algorithm shows high-performance with a really high reconstruction precise. The data is compressed evidently before it's transmitted, saving 46% approximately transmitted.

show abstract

“…Another approach detecting driver behavior is presented by Horovitz et al [11], which use a combined approach of unsupervised data stream clustering and fuzzy logic to detect drunken driver behavior. Liu et al [16] propose a distributed traffic stream mining system for determination of congestion level using Frequent Episode Mining. On a central server frequent patterns are determined based on historical data and are then distributed to stationary detectors, which use the pattern to classify data from the sensors.…”

Section: Related Workmentioning

confidence: 99%

A data stream-based evaluation framework for traffic information systems

Geisler

Quix

Schiffer

2010

Proceedings of the ACM SIGSPATIAL International Workshop on GeoStreaming

View full text Add to dashboard Cite

Traffic information systems based on mobile, in-car sensor technology are a challenge for data management systems as a huge amount of data has to be processed in real-time. Data mining methods must be adapted to cope with these challenges in handling streaming data. Although several data stream mining methods have been proposed, an evaluation of such methods in the context of traffic applications is yet missing. In this paper, we present an evaluation framework for data stream mining for traffic applications. We apply a traffic simulation software to emulate the generation of traffic data by mobile probes. The framework is evaluated in a first case study, namely queue-end detection. We show first results of the evaluation of a data stream mining method, varying multiple parameters for the traffic simulation. The goal of our work is to identify parameter settings for which the data stream mining methods produce useful results for the traffic application at hand.

show abstract

A Scalable Distributed Stream Mining System for Highway Traffic Data

Cited by 20 publications

References 12 publications

Real time movement labelling of mobile event data

Real time movement labelling of mobile event data

Data reduction in urban traffic sensor network

A data stream-based evaluation framework for traffic information systems

Contact Info

Product

Resources

About