Qualification of traffic data by Bayesian network data fusion

Junghans, Marek; Jentschel, H.-J.

doi:10.1109/icif.2007.4407966

Cited by 9 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification quality can be evaluated by two different errors [5]. The relative Class Related Error CRE(x) of vehicle class x is given by: …”

Section: Resultsmentioning

confidence: 99%

“…Our current work is characterised by the application of the adaptive learning method to biased traffic data to correct the inherent selection bias, obeying the Bayesian Network Data Fusion concept, which was successfully tested in [5].…”

Section: Discussionmentioning

confidence: 99%

“…Although the methods are powerful, the results of the fusion process are only as good as the sensors are; as good as the a-priori knowledge about the sensors is; as good as the a-priori knowledge about the underlying process is; and as good as the knowledge about the inherent selection bias affecting the performance of the sensors and thus, the quality of the measured data is [5]. This paper addresses the problem of adaptive learning of the a-priori probability of the unknown traffic process in Bayesian Networks (BNs) for data fusion.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive learning of Bayesian Networks for the qualification of traffic data by Contaminated Dirichlet Density Functions

Junghans¹,

Jentschel²

2008

2008 1st International Conference on Information Technology

Self Cite

View full text Add to dashboard Cite

The concept of Bayesian Networks (BNs) is an established method to model data fusion in sensor networks of several equal or different sensors. Although the method is powerful, there is a particular need for accurate sensors, the consideration of the affecting external, e.g. environmental conditions, and internal influences, e.g. the physical life of the sensor, in the sensor model and an accurate a-priori knowledge about the underlying process. In this paper an adaptive algorithm for learning BNs is introduced, which is applied to update the time-variant a-priori probabilities in sensor networks. This algorithm makes use of Contaminated Dirichlet Density Functions (CDDFs). The effectiveness of adaptive learning is demonstrated for vehicle classification in traffic surveillance.

show abstract

“…The classification quality can be evaluated by two different errors [5]. The relative Class Related Error CRE(x) of vehicle class x is given by: …”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive learning of Bayesian Networks for the qualification of traffic data by Contaminated Dirichlet Density Functions

Junghans¹,

Jentschel²

2008

2008 1st International Conference on Information Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the last 30 years, pattern recognition has been used with increasing success in a number of areas such as medicine, weather forecasting, automated industrial inspection and transportation. Vehicle classification is a type of pattern recognition, so many effective pattern recognition methods and combinations of multiple sensors have been used for classification and identification of vehicles in a particular vehicle classification system which have achieved satisfactory results, such as artificial neural networks [1, 4, 6, 11], Bayesian network data fusion [12], fuzzy data fusion [13], etc.…”

Section: Introductionmentioning

confidence: 99%

A Novel Vehicle Classification Using Embedded Strain Gauge Sensors

Zhang

Wang

Suo

2008

Sensors

View full text Add to dashboard Cite

This paper presents a new vehicle classification and develops a traffic monitoring detector to provide reliable vehicle classification to aid traffic management systems. The basic principle of this approach is based on measuring the dynamic strain caused by vehicles across pavement to obtain the corresponding vehicle parameters – wheelbase and number of axles – to then accurately classify the vehicle. A system prototype with five embedded strain sensors was developed to validate the accuracy and effectiveness of the classification method. According to the special arrangement of the sensors and the different time a vehicle arrived at the sensors one can estimate the vehicle's speed accurately, corresponding to the estimated vehicle wheelbase and number of axles. Because of measurement errors and vehicle characteristics, there is a lot of overlap between vehicle wheelbase patterns. Therefore, directly setting up a fixed threshold for vehicle classification often leads to low-accuracy results. Using the machine learning pattern recognition method to deal with this problem is believed as one of the most effective tools. In this study, support vector machines (SVMs) were used to integrate the classification features extracted from the strain sensors to automatically classify vehicles into five types, ranging from small vehicles to combination trucks, along the lines of the Federal Highway Administration vehicle classification guide. Test bench and field experiments will be introduced in this paper. Two support vector machines classification algorithms (one-against-all, one-against-one) are used to classify single sensor data and multiple sensor combination data. Comparison of the two classification method results shows that the classification accuracy is very close using single data or multiple data. Our results indicate that using multiclass SVM-based fusion multiple sensor data significantly improves the results of a single sensor data, which is trained on the whole multisensor data set.

show abstract

“…The class variable corresponds to that phenomenon, and feature variable F i to the input from sensor i. For example, one may be interested in the type of vehicles (car, truck, bus, motorcycle) passing at a certain point of a highway [37]. This is sensed using two different sensors: an induction loop and a video camera.…”

Section: Naive Bayes Classifiers For Sensor Datamentioning

confidence: 99%

Sensor data management with probabilistic models

Evers

View full text Add to dashboard Cite

Qualification of traffic data by Bayesian network data fusion

Cited by 9 publications

References 4 publications

Adaptive learning of Bayesian Networks for the qualification of traffic data by Contaminated Dirichlet Density Functions

Adaptive learning of Bayesian Networks for the qualification of traffic data by Contaminated Dirichlet Density Functions

A Novel Vehicle Classification Using Embedded Strain Gauge Sensors

Sensor data management with probabilistic models

Contact Info

Product

Resources

About