Neural Networks and Principal Components Analysis for Strain-Based Vehicle Classification

Yan, Linjun; Fraser, Michael; Elgamal, Ahmed; Fountain, Tony; Oliver, Kendra H.

doi:10.1061/(asce)0887-3801(2008)22:2(123)

Cited by 18 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they yield a black-box representation with no physical meaning. Data-based techniques applied to WIM sensing include the use of neural networks [44] and principal component analysis [45] to classify vehicles from strain time histories, and decision trees and k-means clustering [46] or neural networks [47,48] to conduct WIM from inductive signature data [49].…”

Section: Introductionmentioning

confidence: 99%

A Weigh-in-Motion Characterization Algorithm for Smart Pavements Based on Conductive Cementitious Materials

Birgin

Laflamme

D’Alessandro

et al. 2020

Sensors

View full text Add to dashboard Cite

Smart materials are promising technologies for reducing the instrumentation cost required to continuously monitor road infrastructures, by transforming roadways into multifunctional elements capable of self-sensing. This study investigates a novel algorithm empowering smart pavements with weigh-in-motion (WIM) characterization capabilities. The application domain of interest is a cementitious-based smart pavement installed on a bridge over separate sections. Each section transduces axial strain provoked by the passage of a vehicle into a measurable change in electrical resistance arising from the piezoresistive effect of the smart material. The WIM characterization algorithm is as follows. First, basis signals from axles are generated from a finite element model of the structure equipped with the smart pavement and subjected to given vehicle loads. Second, the measured signal is matched by finding the number and weights of appropriate basis signals that would minimize the error between the numerical and measured signals, yielding information on the vehicle’s number of axles and weight per axle, therefore enabling vehicle classification capabilities. Third, the temporal correlation of the measured signals are compared across smart pavement sections to determine the vehicle weight. The proposed algorithm is validated numerically using three types of trucks defined by the Eurocodes. Results demonstrate the capability of the algorithm at conducting WIM characterization, even when two different trucks are driving in different directions across the same pavement sections. Then, a noise study is conducted, and the results conclude that a given smart pavement section operating with less than 5% noise on measurements could yield good WIM characterization results.

show abstract

Section: Introductionmentioning

confidence: 99%

A Weigh-in-Motion Characterization Algorithm for Smart Pavements Based on Conductive Cementitious Materials

Birgin

Laflamme

D’Alessandro

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…A support vector machine (SVM) is applied for the classification tasks utilising the number of axes and the speed function as input features. Yan et al (2008) exploits a principal component analysis (PCA) on strain time-series data. A bridgedeck in the USA has been equipped with 16 gauges at both the top and the bottom side of the panel.…”

Section: Related Workmentioning

confidence: 99%

Detection and Classification of Bridge Crossing Events With Ground-Based Interferometric Radar Data and Machine Learning Approaches

Arnold¹,

Keller²

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this paper, we investigate the potential of detecting and classifying vehicle crossings (events) on bridges with ground-based interferometric radar (GBR) data and machine learning (ML) approaches. The GBR data and image data recorded by a unmanned aerial vehicle, used as ground truth, have been measured during field campaigns at three bridges in Germany non-invasively. Since traffic load of the bridges has taken place during the measurement, we have been able to monitor the bridge dynamics in terms of a vertical displacement. We introduce a methodological approach with three steps including preprocessing of the GBR data, feature extraction and well-chosen ML models. The impact of the preprocessing approaches as well as of the selected features on the classification results is evaluated. In case of the distinction between event and no event, adaptive boosting with low-pass filtering achieves the best classification results. Regarding the distinction between different class types of vehicles, random forest performs best utilising low-pass filtered GBR data. Our results reveal the potential of the GBR data combined with the respective methodological approach to detect and to classify events under real-world conditions. In conclusion, the preliminary results of this paper provide a basis for further improvements such as advanced preprocessing of the GBR data to extracted additional features which then can be used as input for the ML models.

show abstract

“…Furthermore, a vehicle classification system was developed for field road experiments in which a support vector machine (SVM) algorithm was reliable to classify small, medium and combined vehicles [ 22 ]. Besides, for axle number-based classification, an artificial neural network (ANN) was designed based on a dataset consisting of 9000 records [ 23 ]. After extracting essential features by principal components analysis technique, the model was capable of classifying five types of predetermined vehicles.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Vehicle Detection and Classification Methodology Using Strain Sensors under Bridge Deck

Zhang

Dong

et al. 2020

Sensors

View full text Add to dashboard Cite

Vehicle detection and classification have become important tasks for traffic monitoring, transportation management and pavement evaluation. Nowadays there are sensors to detect and classify the vehicles on road. However, on one hand, most sensors rely on direct contact measurement to detect the vehicles, which have to interrupt the traffic. On the other hand, complex road scenes produce much noise to consider when to process the signals. In this paper, a data-driven methodology for the detection and classification of vehicles using strain data is proposed. The sensors are well arranged under the bridge deck without traffic interruption. Next, a cascade pre-processing method is applied for vehicle detection to eliminate in-situ noise. Then, a neural network model is trained to identify the close-range following vehicles and separate them by Non-Maximum Suppression. Finally, a deep convolutional neural network is designed and trained to identify the vehicle types based on the axle group. The methodology was applied in a long-span bridge. Three strain sensors were installed beneath the bridge deck for a week. High robustness and accuracy were obtained by these algorithms. The methodology proposed in this paper is an adaptive and promising method for vehicle detection and classification under complex noise. It would serve as a supplement to current transportation systems and provide reliable data for management and decision-making.

show abstract

Neural Networks and Principal Components Analysis for Strain-Based Vehicle Classification

Cited by 18 publications

References 16 publications

A Weigh-in-Motion Characterization Algorithm for Smart Pavements Based on Conductive Cementitious Materials

A Weigh-in-Motion Characterization Algorithm for Smart Pavements Based on Conductive Cementitious Materials

Detection and Classification of Bridge Crossing Events With Ground-Based Interferometric Radar Data and Machine Learning Approaches

Deep Learning Based Vehicle Detection and Classification Methodology Using Strain Sensors under Bridge Deck

Contact Info

Product

Resources

About